A judicial evidence association relationship construction method and device and a storage medium

Abstract

The application relates to a judicial evidence association relationship construction method and device and a storage medium, which are applied to the technical field of judicial big data intelligent processing and include the following steps: acquiring event element entities in a to-be-proved fact and evidence and counting event sets in which each event element entity appears; acquiring a frequent item set of the to-be-proved fact and the evidence according to the event sets in which each event element entity appears; establishing an association rule of the to-be-proved fact and the evidence according to the frequent item set, acquiring a to-be-proved fact association relationship set and an evidence association relationship set through the association rule; and finally acquiring an evidence-to-be-proved fact association relationship set according to the to-be-proved fact association relationship set and the evidence association relationship set. The application starts from the event element relationship of the core elements of the case evidence and the to-be-proved fact, adopts a divide-and-conquer association relationship construction strategy, does not depend on the subjective experience of case handling personnel, and improves the reliability of the association relationship between the evidence and the to-be-proved fact.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent processing of big data in the judicial system, and in particular to a method and device for constructing a correlation between judicial evidence. BACKGROUND

[0002] Judicial evidence is material that proves the facts to be proven in a judicial case, and is derived from various sources, including statements by defendants, confessions and defenses by victims, witness testimonies, physical evidence, documentary evidence, investigation and inspection notes, audio-visual materials and electronic data, etc. How to find evidence related to the facts to be proven and the mutual corroboration relationship between the evidence from a large number of different evidence, i.e. how to analyze the correlation between the evidence, provides a basis for judicial conviction and sentencing, and is the core content of case investigation and trial.

[0003] Evidence correlation analysis currently mainly relies on the experience of case handlers, and uses file cataloging, document reading and copying and other reading aids to construct the correlation between evidence and case facts and the corroboration relationship between evidence based on the case facts described in the case indictment, prosecution and evidence, etc. This method is mainly based on subjective experience and intuition, and the judgment result is accidental and uncertain. The effectiveness of the case largely depends on the experience and ability of the case handlers. In particular, for large cases or difficult cases, the relationship between the case elements is complex, and there are many evidences, often facing the problems of difficulty in mutual corroboration of evidence, unclear evidence pointing to the facts to be proven, etc. SUMMARY

[0004] In order to solve the technical problems of complex relationship between case elements, too many evidences, difficulty in mutual corroboration of evidence and unclear evidence pointing to the facts to be proven in the prior art, the present application provides a method and device for constructing a correlation between judicial evidence. The technical solution is as follows:

[0005] On the one hand, a method for constructing a correlation between judicial evidence is provided, which is realized by a device for constructing a correlation between judicial evidence. The method comprises the following steps:

[0006] S1, extracting event element entities in the facts to be proven and the evidence of any case, respectively;

[0007] S2, according to the event element entities in the facts to be proven and the evidence, respectively, counting the event sets in which each event element entity appears in the facts to be proven and the evidence;

[0008] S3, according to the event sets in which each event element entity appears and a preset support threshold, respectively, obtaining a frequent item set of the facts to be proven and a frequent item set of the evidence;

[0009] S4, obtaining all association rules of the frequent item set, by taking any one or more event element entities in any frequent item set of the to-be-proved fact as antecedent and taking the remaining event element entities in the frequent item set as consequent, thereby obtaining all association rules of the to-be-proved fact;

[0010] S5, obtaining all association rules of the evidence, by taking any one or more event element entities in any frequent item set of the evidence as antecedent and taking the remaining event element entities in the frequent item set as consequent;

[0011] S6, obtaining a to-be-proved fact association relationship set by screening all association rules of the to-be-proved fact according to a preset screening rule and obtaining an evidence association relationship set by screening all association rules of the evidence according to the preset screening rule;

[0012] S7, constructing an evidence-to-be-proved fact association relationship set according to the to-be-proved fact association relationship set and the evidence association relationship set.

[0013] In another aspect, a judicial evidence association relationship construction device is provided, which is applied to a judicial evidence association relationship construction method, and the device comprises:

[0014] An element entity extraction module is configured to extract event element entities in a to-be-proved fact and evidence of any case respectively.

[0015] An event set acquisition module is configured to respectively count event sets in which each event element entity in the to-be-proved fact and the evidence appears, according to the event element entities in the to-be-proved fact and the evidence.

[0016] A frequent item set acquisition module is configured to respectively acquire frequent item sets of the to-be-proved fact and the evidence, according to the event sets in which each event element entity appears and a preset support threshold.

[0017] A first association rule acquisition module is configured to obtain all association rules of the frequent item set, by taking any one or more event element entities in any frequent item set of the to-be-proved fact as antecedent and taking the remaining event element entities in the frequent item set as consequent, thereby obtaining all association rules of the to-be-proved fact.

[0018] A second association rule acquisition module is configured to obtain all association rules of the frequent item set, by taking any one or more event element entities in any frequent item set of the evidence as antecedent and taking the remaining event element entities in the frequent item set as consequent, thereby obtaining all association rules of the evidence.

[0019] The first association relationship obtaining module is configured to screen all association rules of the to-be-proved fact through a preset screening rule to obtain a to-be-proved fact association relationship set, and screen all association rules of the evidence through the preset screening rule to obtain an evidence association relationship set.

[0020] The second association relationship obtaining module is configured to construct an evidence-to-be-proved fact association relationship set according to the to-be-proved fact association relationship set and the evidence association relationship set.

[0021] In another aspect, a judicial evidence association relationship construction device is provided, which comprises a processor and a memory having computer readable instructions stored thereon, the computer readable instructions being executed by the processor to implement any of the above judicial evidence association relationship construction methods.

[0022] In another aspect, a computer readable storage medium is provided, which stores at least one instruction, the at least one instruction being loaded and executed by a processor to implement any of the above judicial evidence association relationship construction methods.

[0023] The technical scheme provided by the embodiments of the present application has at least the following beneficial effects:

[0024] The present application obtains event element entities in the to-be-proved fact and the evidence, and counts event sets in which each event element entity appears; the frequent item sets of the to-be-proved fact and the evidence are obtained according to the event sets in which each event element entity appears; the association rules of the to-be-proved fact and the evidence are established according to the frequent item sets, the to-be-proved fact association relationship set and the evidence association relationship set are obtained through the association rules; finally, the evidence-to-be-proved fact association relationship set is obtained according to the to-be-proved fact association relationship set and the evidence association relationship set; the present application starts from the event element relationship which is the core element of the case evidence and the to-be-proved fact, adopts the association relationship construction strategy of divide and conquer, proposes an efficient and high-reliability evidence association and evidence-to-be-proved fact association relationship discovery method, effectively assists the case reasoning and evidence chain construction of the judicial case handling personnel, improves the judicial case handling efficiency and judicial fairness, and is especially suitable for large and complex cases. BRIEF DESCRIPTION OF DRAWINGS

[0025] In order to more clearly illustrate the technical scheme in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0026] Figure 1 is a judicial evidence association relationship construction method flowchart provided by the embodiments of the present application;

[0027] Figure 2 is a horizontal type evidence event table sample diagram provided by an embodiment of the present application;

[0028] Figure 3 is a vertical type evidence event table sample diagram provided by an embodiment of the present application;

[0029] Figure 4 is a judicial evidence association relationship graph diagram provided by an embodiment of the present application;

[0030] Figure 5 is a judicial evidence association relationship construction device block diagram provided by an embodiment of the present application;

[0031] Figure 6 is a structure diagram of a judicial evidence association relationship construction device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0032] The technical solutions in the present application will be described below with reference to the drawings.

[0033] In the embodiments of the present application, the words such as "example", "for example" are used to represent an example, illustration or description. Any embodiment or design scheme described as "example" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the word "example" is intended to present the concept in a specific manner. In addition, in the embodiments of the present application, the meaning expressed by "and / or" can be both, or can be one of the two.

[0034] In the embodiments of the present application, "image" and "picture" can be used interchangeably at times, and it should be pointed out that the meanings expressed are consistent when the distinction is not emphasized. "Of", "corresponding" and "corresponding" can be used interchangeably at times, and it should be pointed out that the meanings expressed are consistent when the distinction is not emphasized.

[0035] In the embodiments of the present application, sometimes the subscript such as W1 can be written in the form of non-subscript such as W1, and the meanings expressed are consistent when the distinction is not emphasized.

[0036] In order to make the technical problems, technical solutions and advantages of the present application clearer, specific embodiments will be described in detail below with reference to the drawings.

[0037] The embodiments of the present application provide a judicial evidence association relationship construction method, which can be realized by a judicial evidence association relationship construction device, and the judicial evidence association relationship construction device can be a terminal or a server.

[0038] For the convenience of understanding the scheme of the present application, the present embodiment first briefly describes some concepts appearing in the present application:

[0039] Correlation analysis is an important means to realize the value of big data. Various data sources and massive data of various types provide rich data resources for management, analysis and decision-making, but at the same time, the connection between data is not easy to discover through the surface. Through correlation analysis, the rules and patterns hidden behind the data can be discovered, for example, in the classic market basket analysis, by analyzing the combination relationship of the goods in the customer purchase list, it can be found that which goods are often purchased by customers at the same time, and through this relationship, corresponding marketing strategies can be developed.

[0040] Correlation analysis is to find relationships in large-scale data sets. These relationships generally have the following two forms: frequent item set and association rule. Among them, the frequent item set is a set of things that often appear together, and the association rule implies that there may be a strong relationship between two things.

[0041] The basic concepts of correlation analysis are described below.

[0042] (1) Item set

[0043] A set containing zero or more items is called an item set.

[0044] (2) k-item set

[0045] An item set containing k items is called a k-item set.

[0046] (3) Support count

[0047] The number of transactions containing an item set is the support count of the item set.

[0048] (4) Support

[0049] Used to determine the frequency of an item set.

[0050] The quotient of the support count divided by the total number of transactions is the support,

[0051] (5) Frequent item set

[0052] An item set with a support greater than or equal to a certain threshold is called a frequent item set.

[0053] (6) Association rule

[0054] An association rule is an implication expression of the form X , where X and Y are disjoint item sets,

[0055] X is called the antecedent, and Y is called the consequent.

[0056] The ultimate goal of association analysis is to find strong association rules and frequent itemsets, and the association analysis algorithm is the process of identifying frequent itemsets and strong association rules, among which the identification of frequent itemsets is the most complex and is the key to affecting the efficiency of association analysis.

[0057] After understanding the above basic concepts, as shown in the judicial evidence association relationship construction method flow chart, the processing flow of the method can include the following steps: Figure 1

[0058] S1, extract the event element entities in the evidence and the fact to be proved of any case respectively.

[0059] In a feasible implementation manner, the events in the evidence and the fact to be proved embody the case facts of the case, and the natural language processing tools such as HanNLP and StanfordNLP, or the multi-modal pre-training large model (such as GLM) Promt engineering method is used to extract the case event element entities in the evidence and the fact to be proved, to perform entity fusion, and ensure the uniqueness of the same case element entity name, for example, in the document, some are called “Zhang San”, and some are called “defendant”, after entity fusion, the entity name is unified as “Zhang San”;

[0060] The extracted event entities mainly include the following elements:

[0061] Time of occurrence: the specific date and time of the event occurrence, or any time point related to the event (such as start time, end time);

[0062] Place of occurrence: the specific geographical location of the event occurrence, including country, city, specific place, etc.;

[0063] Participants: individuals, groups or organizations involved in the event, including witnesses, behavior subjects, etc.;

[0064] Action: specific actions or activities in the event, such as transactions, communications, etc.;

[0065] Action object: the direct target of the action, which can be a person, an article, information, etc.;

[0066] Behavior method: the specific method or means of implementing the behavior, such as using tools, adopting strategies, etc.;

[0067] Behavior reason: the motivation, purpose or trigger factor leading to the behavior;

[0068] Behavior result: the direct or indirect consequences produced after the behavior implementation, including influence, loss, benefit, etc.;

[0069] ​It should be noted that large-scale cases involve numerous and complex factual and evidentiary events. To simplify the process and improve efficiency, horizontal tables of facts to be proven and tables of evidentiary events are constructed for all extracted events. Each event element is referred to as an "item," such as... Figure 2 As shown. Figure 2 In the table, the first column is the item, and the second column is the set of events in which the item appears. The number of elements in each event set is the support count of the item (i.e., the event element). The support count of an item is divided by the total number of events to get the support of the item. For example, the event set of item A1 (event element) is {T01, T03, T04}, the total number of events is 6, the support count of item A1 is 3, and the support is 3 / 6 = 0.5.

[0070] To improve the efficiency of discovering relationships between items, Figure 2 Horizontal evidence event table converted to appendix Figure 3 The vertical evidence event table shown has each row as an item and each column as a set of event numbers that occurred in that item.

[0071] S2. Based on the facts to be proven and the event element entities in the evidence, respectively count the set of events in which each event element entity in the facts to be proven and the evidence appears.

[0072] S3. Based on the event set in which each event element entity appears and the preset support threshold, obtain the frequent itemset of the fact to be proven and the frequent itemset of the evidence, respectively.

[0073] Optionally, the specific operations of S3 may include:

[0074] Obtain each event element entity from the fact to be proven and the evidence, and use each event element entity to form a set with only one element, which are respectively used as the 1-itemset of the fact to be proven and the evidence.

[0075] All 1-itemsets are filtered by a preset support threshold, and 1-itemsets with a support value greater than the preset support threshold are identified as frequent 1-itemsets.

[0076] The frequent 1-itemsets of the facts to be proven and the evidence are merged pairwise to obtain 2-itemsets of the facts to be proven and the evidence, respectively. The event set in the 2-itemsets is the common event of the two frequent 1-itemsets merged. The support of each 2-itemset of the facts to be proven and the evidence is obtained respectively. All 2-itemsets are filtered by a preset support threshold. 2-itemsets with a support greater than the preset support threshold are regarded as frequent 2-itemsets.

[0077] The process of merging frequent itemsets is repeated, and the number of event element entity items in the new itemset generated by each merge is increased by 1, until no new frequent itemsets can be generated. All frequent k-itemsets generated during the merging process of the facts to be proven and the evidence are taken as frequent itemsets of the facts to be proven and the evidence.

[0078] The support is obtained by dividing the number of events in the event set corresponding to any itemset of the fact or evidence to be proved by the total number of events of the fact or evidence to be proved.

[0079] In one feasible implementation, the investigators set a minimum support threshold for the frequent itemsets of events based on the case circumstances. To ensure that no facts are missed, the minimum support threshold is set to be as small as possible for the facts to be proven in the case. For evidence, the minimum support threshold is set to be greater than 0.2 in order to filter out irrelevant facts and evidence. The specific value of the threshold can also be set by the investigators based on the actual situation of the case. The larger the threshold, the fewer the association sets of event items, and the faster the execution efficiency, but important associations may be missed.

[0080] According to the appendix Figure 3 The evidence event table shown is constructed using the following steps to create an association set of evidence event items. For ease of illustration, the minimum support of the frequent itemset is set to 0.2.

[0081] Keep attached Figure 3 Items with support greater than or equal to the minimum support threshold are grouped into frequent 1-itemsets.

[0082] {{A1}, {A2}, {B1}, {C1}, {C2}, {D1}, {D2}, {E1}, {E2}, {F1}, {F2}, {G1}, {G2}, {H1}, {H2}}.

[0083] Construct frequent k-itemsets (k ≥ 1) recursively, according to the appendix. Figure 3 The example vertical event table merges frequent k-itemsets pairwise, finding all possible frequent (k+1)-itemsets. The event set of the merged itemset is the set of events shared by the two merged itemsets. For example, see Appendix Figure 3 In the frequent 1-itemsets {B1} and {H1}, the intersection of the event sets is {T01,T02,T05,T06}. The intersection support of {T01,T02,T06}={T01,T02,T06} is 3 / 6=0.5, which is greater than 0.2. Therefore, {B1,H1} is a frequent 2-itemset.

[0084] Next, all the frequent 2-item sets are combined, and it is worth emphasizing that each time the combination is performed, the event element entity is only added by 1, that is, two frequent 2-item sets are combined to obtain a 3-item set, rather than a 4-item set, for example, two frequent 2-item sets are {B1, H1} and {A1, C1}, and the 3-item set can be {B1, H1, A1}, {B1, H1, C1}, {A1, C1, B1}, {A1, C1, H1}; the frequent 3-item sets are screened from all the 3-item sets; and the frequent 3-item sets are combined into 4-item sets;

[0085] The combination process is repeated until no new frequent item set can be generated.

[0086] All the generated frequent k-item sets (k is greater than or equal to 1) are the frequent item sets of the evidence or the fact to be proved.

[0087] S4, any one or more event element entities in any frequent item set of the fact to be proved are taken as antecedents, and the remaining event element entities in the frequent item set are taken as consequents, all the association rules of the frequent item set are obtained, and then all the association rules of the fact to be proved are obtained.

[0088] S5, any one or more event element entities in any frequent item set of the evidence are taken as antecedents, and the remaining event element entities in the frequent item set are taken as consequents, all the association rules of the frequent item set are obtained, and then all the association rules of the evidence are obtained.

[0089] In a feasible implementation, for each frequent item set of the evidence and the fact to be proved, all the possible association rules are generated, the association rules of the evidence are used to represent the association relationship between the event item elements of the evidence, and the mutual corroboration relationship between the evidence is embodied; the association rules of the case fact to be proved are used to represent the association relationship between the event item elements of the case fact to be proved; and the association rule is represented as: X Y, wherein X and Y are a frequent item set, X is an antecedent, and Y is a consequent.

[0090] S6, the all association rules of the fact to be proved are screened through preset screening rules to obtain a fact-to-be-proved association relationship set, and the all association rules of the evidence are screened through preset screening rules to obtain an evidence association relationship set.

[0091] Optionally, the specific operation process of S6 can include:

[0092] S61, the confidence, the certainty, the lift, and the leverage of each association rule of the fact to be proved are obtained, each association rule is screened through the confidence, the certainty, the lift, and the leverage of each association rule of the fact to be proved, and the screened association rule is taken as the fact-to-be-proved association relationship set.

[0093] Optionally, the specific operation process of S61 can include:

[0094] respectively set the first confidence threshold, the first certainty threshold, the first lift threshold and the first leverage ratio threshold of the to-be-proved fact;

[0095] obtain the first association rule with the confidence greater than the first confidence threshold and the certainty greater than the first certainty threshold;

[0096] In the first association rule, obtain the second association rule with the lift greater than the first lift threshold;

[0097] In the second association rule, obtain the third association rule with the leverage ratio greater than the first leverage ratio threshold;

[0098] take the third association rule of the to-be-proved fact as the to-be-proved fact association rule set;

[0099] S62, obtain the confidence, certainty, lift and leverage ratio of each association rule of the evidence, and screen each association rule through the confidence, certainty, lift and leverage ratio of each association rule of the evidence, and take the screened association rule as the evidence association rule set.

[0100] Optionally, the specific operation process of S62 can include:

[0101] respectively set the second confidence threshold, the second certainty threshold, the second lift threshold and the second leverage ratio threshold of the evidence;

[0102] obtain the fourth association rule of the evidence with the confidence greater than the second confidence threshold of the evidence and the certainty greater than the second certainty threshold;

[0103] In the fourth association rule, obtain the fifth association rule with the lift greater than the second lift threshold;

[0104] In the fifth association rule, obtain the sixth association rule with the leverage ratio greater than the second leverage ratio threshold;

[0105] take the sixth association rule of the evidence as the evidence association rule set.

[0106] In a feasible implementation, for each frequent item set, for example, {A, B, C}, the candidate association rules include the associations between {A, B, C} and all its subsets, for example, {A} {B, C}, {B} {A, C}, {C} {A, B}, {A, B} {C}, {A, C} {B}, and {B, C} {A}, and so on.

[0107] For each candidate association rule, the reliability of the association rule is evaluated by using the confidence, the certainty, the lift and the leverage:

[0108] The confidence (X Y) = P(X,Y) / P(X)

[0109] The certainty (X Y) = (1-P(Y)) / (1-Confidence (X Y))

[0110] The lift (X Y) = P(X,Y) / (P(X)P(Y))

[0111] The leverage (X Y) = P(X,Y) - P(X)P(Y)

[0112] Where P(X) = (the support of X) = (the number of events containing X) / (the total number of events), P(X,Y) = (the number of events containing both X and Y) / (the total number of events).

[0113] The confidence is used to measure the value of a piece of evidence or condition when it occurs, for example, if the confidence between the rule antecedent and the rule consequent is high, the value of this evidence can be great.

[0114] The lift is used to determine whether two case elements are independent of each other, for example, if the lift between the rule antecedent and the rule consequent is greater than 1, it indicates that there is a positive correlation between the two elements.

[0115] The certainty is used to measure the probability that the case result does not occur without a piece of evidence, if the certainty is high, it can be considered that the evidence is very important to exclude the possibility of innocence.

[0116] The leverage is used to evaluate the degree of influence of a piece of evidence on the case result, if the leverage of a piece of evidence is high, it can be a key evidence of the case.

[0117] Association rule threshold setting and association rule screening:

[0118] The first confidence threshold and the second confidence threshold are set to be greater than 0, the greater the value, the stronger the direct association between X and Y can be found;

[0119] The first certainty threshold and the second certainty threshold are set to be greater than 1, the higher the certainty, the more significant the influence of X on Y;

[0120] The first lift threshold and the second lift threshold are set to be greater than 1, the higher the lift, the stronger the positive correlation of X on Y;

[0121] The first leverage ratio threshold and the second leverage ratio threshold are greater than 0, and the higher the leverage ratio, the stronger the correlation between X and Y.

[0122] In the rule screening evaluation, first, candidate association rules with confidence and certainty greater than the respective thresholds are screened out to ensure strong correlation between the premise and the result; then, the lift of the rule is calculated, and if the lift is greater than the threshold, it indicates that the correlation of the rule is not random and accidental, but truly relevant; finally, the leverage ratio is calculated, and if the leverage ratio is greater than the threshold, the uniqueness and statistical significance of the rule are further confirmed, and the rule is retained.

[0123] The screening results are compared with the actual situation of the case to verify the accuracy of the rules, and the combination evaluation method and the threshold are adjusted according to the feedback.

[0124] All the screened association rules form the case evidence association relationship set and the case to-be-proved fact association relationship set.

[0125] S7, according to the to-be-proved fact association relationship set and the evidence association relationship set, an evidence-to-be-proved fact association relationship set is constructed.

[0126] In a feasible implementation, the evidence-to-be-proved fact association rule is used to find the association between the evidence and the to-be-proved fact of the case, and is used for evidence authentication and case reasoning of the to-be-proved fact of the case. Two methods for constructing evidence-to-be-proved fact candidate association rules are given in this embodiment, which are described as follows:

[0127] The first method is to use the intersection of the evidence association rule set and the case to-be-proved fact association rule set to construct the evidence-to-be-proved fact candidate association rule, and the specific method is as follows:

[0128] The association rules contained in both the to-be-proved fact association relationship set and the evidence association relationship set are obtained.

[0129] The association rules contained in both the to-be-proved fact association relationship set and the evidence association relationship set are obtained.

[0130] In a feasible implementation, for example:

[0131] The evidence association rule set (evidence)={(A,B) (C),(D,E,G) (H,G),(B,E) (C),(A,H) (B,C),(A) (B)};

[0132] The to-be-proved fact association rule set (fact)={(A,B) (C), (D, E, G) (H, G), (B, G) (C)}.

[0133] evidence-to-be-proved-fact candidate association rule set = evidence ∩ fact = {(A, B) (C), (D, E, G) (H, G)}.

[0134] Second, the antecedent and consequent of the association rule to be proved fact have intersections with the evidence association rule, and the association rule can be selected as follows:

[0135] If any association rule in the to-be-proved-fact association rule set has an intersection with the antecedent of any association rule in the evidence association rule set, and the consequent also has an intersection, then any association rule in the to-be-proved-fact association rule set and any association rule in the evidence association rule set are both used as candidate evidence-to-be-proved-fact association rules.

[0136] The candidate evidence-to-be-proved-fact association rules are screened by a preset rule, and the screened candidate evidence-to-be-proved-fact association rules are used as the evidence-to-be-proved-fact association rule set.

[0137] Alternatively, the candidate evidence-to-be-proved-fact association rules are screened by a preset rule, and the screened candidate evidence-to-be-proved-fact association rules are used as the evidence-to-be-proved-fact association rule set, including:

[0138] The confidence, certainty, lift, and leverage of each candidate evidence-to-be-proved-fact association rule are obtained respectively;

[0139] The third confidence threshold, the third certainty threshold, the third lift threshold, and the third leverage threshold are set respectively;

[0140] The first evidence-to-be-proved-fact association rule with a confidence greater than the third confidence threshold and a certainty greater than the third certainty threshold is obtained;

[0141] In the first evidence-to-be-proved-fact association rule, the second evidence-to-be-proved-fact association rule with a lift greater than the third lift threshold is obtained;

[0142] In the second evidence-to-be-proved-fact association rule, the fourth evidence-to-be-proved-fact association rule with a leverage greater than the third leverage threshold is obtained;

[0143] The fourth evidence-to-be-proved-fact association rule is used as the evidence-to-be-proved-fact association rule set.

[0144] In a feasible implementation, for example:

[0145] The set of evidence association rules (evidence) = {(A, B, D) (C, E), (D, E, G) (H, G), (B, E) (C), (A, H) (B, C), (A) (B)}.

[0146] The set of fact association rules (fact) = {(A, B, E) (C), (D, E, G) (H, G), (B, G) (C)}.

[0147] For any association rule (A, B, D) (C, E) of the evidence, and any association rule (A, B, E) (C) of the fact to be proved, the antecedents (A, B, D) and (A, B, E) of each have an intersection (A, B), and the consequents also have an intersection (C), so both (A, B, D) (C, E) and (A, B, E) (C) are candidate association rules.

[0148] The set of evidence-fact candidate association rules = rules whose antecedents and consequents of the rules of the evidence and the fact have intersections = {(A, B, D) (C, E), (A, B, E) (C), (D, E, G) (H, G), (B, G) (C), (B, E) (C)}.

[0149] For each candidate association rule X Y, recalculate the confidence, certainty, lift and leverage of the rules, it is worth emphasizing that in the process of calculating the confidence, certainty, lift and leverage, the calculation of support is involved, in the above-mentioned evidence and the related support calculation process of the fact to be proved, the support count is only for the respective number of occurrences and the total number of events, for example: in the support calculation process of the evidence, the number of times of an event element appearing in the evidence is 3, and the total number of events of the evidence is 6, so the support of the event element is 0.5, and similarly, for the support calculation of the fact to be proved, for any event element, the number of times of the event element appearing in the fact to be proved is 2, and the total number of events of the fact to be proved is 8, so the support of the event element is 0.25; and in the process of calculating the confidence, certainty, lift and leverage of the evidence-fact to be proved candidate association rule, the calculation of support is involved, the support of the antecedent X and the consequent Y in each rule is equal to the number of times of X and Y appearing in all events of the fact to be proved and the evidence, divided by the total number of events, and the total number of events is equal to the sum of the number of events of the fact to be proved and the number of events of the evidence, in simple terms, if any event element appears twice in the evidence and twice in the fact to be proved, and the total number of events of the evidence is 6 and the total number of events of the fact to be proved is 8, then the support of the event element is (2+2) / (6+8).

[0150] After calculating the confidence, certainty, lift and leverage of each candidate association rule of the evidence-fact to be proved, third confidence threshold, third certainty threshold, third lift threshold and third leverage threshold are set for screening.

[0151] In the rule screening evaluation, first, the candidate association rules with confidence and certainty greater than the respective thresholds are screened out to ensure that there is a strong association between the premise and the result; then the lift of the rule is calculated, if the lift is greater than the threshold, it indicates that the association of the rule is not random and accidental, but truly related; finally, the leverage is calculated, if the leverage is greater than the threshold, it further confirms the uniqueness and statistical significance of the rule, and is retained.

[0152] It should be noted that the above two methods, the first method is suitable for cases with relatively simple and clear case facts, and the second method is suitable for cases with complex case facts or large uncertainty of facts and evidence.

[0153] Optionally, after S7, the method can further include:

[0154] S8, constructing a case association relationship graph according to the fact to be proved association relationship set, the evidence association relationship set and the evidence-fact to be proved association relationship set.

[0155] In a feasible implementation, a graph database is used to construct an evidence association graph, and the mined evidence association rules, the to-be-proved fact association rules and the antecedents and consequents of the evidence-to-be-proved fact association rules are vertices of the evidence association graph, and the antecedents and consequents of each rule are connected by a directed edge from the antecedent to the consequent; the vertex attribute of the association graph is the element name of the rule antecedent or consequent set, and for the vertex belonging to the evidence-to-be-proved fact association rule, the element name of the vertex attribute is uniformly prefixed with a * mark, as shown in the accompanying Figure 4 The edge attribute of the graph is the evaluation indexes of the rules, including confidence, lift, certainty and leverage, and the edge attribute values are the corresponding evaluation index values.

[0156] Judicial personnel can use the evidence association graph to assist in case reasoning and evidence chain construction.

[0157] In the embodiment of the application, event element entities in the to-be-proved fact and the evidence are acquired, and the event sets in which each event element entity appears are counted; the frequent item sets of the to-be-proved fact and the evidence are respectively acquired according to the event sets in which each event element entity appears; the association rules of the to-be-proved fact and the evidence are established according to the frequent item sets, the to-be-proved fact association relationship set and the evidence association relationship set are acquired through the association rules; and finally, the evidence-to-be-proved fact association relationship set is acquired according to the to-be-proved fact association relationship set and the evidence association relationship set. The application starts from the core element-event element relationship of the case evidence and the to-be-proved fact, adopts a divide-and-conquer association relationship construction strategy, and proposes an efficient and high-reliability evidence association and evidence-to-be-proved fact association relationship discovery method, which effectively assists judicial personnel in case reasoning and evidence chain construction, improves judicial case handling efficiency and judicial fairness, and is especially suitable for large and complex cases.

[0158] Figure 5 is a block diagram of a judicial evidence association relationship construction device according to an example embodiment, and the device is used for a judicial evidence association relationship construction method. Referring to Figure 5 , the device 500 includes:

[0159] The element entity extraction module 510 is configured to extract event element entities in the to-be-proved fact and the evidence of any case, respectively.

[0160] The event set acquisition module 520 is configured to count the event sets in which each event element entity appears in the to-be-proved fact and the evidence, respectively, according to the event element entities in the to-be-proved fact and the evidence.

[0161] The frequent item set acquisition module 530 is configured to acquire the frequent item sets of the to-be-proved fact and the frequent item sets of the evidence, respectively, according to the event sets in which each event element entity appears and a preset support threshold.

[0162] The first association rule obtaining module 540 is configured to take any one or more event element entities in any frequent item set of the to-be-proved fact as the antecedent, take the remaining event element entities in the frequent item set as the consequent, obtain all association rules of the frequent item set, and further obtain all association rules of the to-be-proved fact;

[0163] The second association rule obtaining module 550 is configured to take any one or more event element entities in any frequent item set of the evidence as the antecedent, take the remaining event element entities in the frequent item set as the consequent, obtain all association rules of the frequent item set, and further obtain all association rules of the evidence;

[0164] The first association relationship obtaining module 560 is configured to filter all association rules of the to-be-proved fact by using a preset filtering rule to obtain a to-be-proved fact association relationship set, and filter all association rules of the evidence by using the preset filtering rule to obtain an evidence association relationship set.

[0165] The second association relationship obtaining module 570 is configured to construct an evidence-to-be-proved fact association relationship set according to the to-be-proved fact association relationship set and the evidence association relationship set.

[0166] Optionally, the frequent item set obtaining module 530 is further configured to:

[0167] respectively obtain each event element entity in the to-be-proved fact and the evidence, and form a set with only one element by using each event element entity as the 1-item set of the to-be-proved fact and the evidence respectively;

[0168] filter all 1-item sets by using a preset support threshold, and take the 1-item set greater than the preset support threshold as the frequent 1-item set;

[0169] merge the frequent 1-item sets of the to-be-proved fact and the evidence two by two to obtain 2-item sets of the to-be-proved fact and the evidence respectively, the event set in the 2-item set being the common event of the two merged frequent 1-item sets, obtain the support of each 2-item set of the to-be-proved fact and the evidence respectively, and filter all 2-item sets by using a preset support threshold, and take the 2-item set greater than the preset support threshold as the frequent 2-item set;

[0170] repeat the merging process of the frequent item set, and each time the number of event element entities in the new item set generated by merging is increased by 1, until no new frequent item set can be generated, and all frequent k-item sets generated in the merging process of the to-be-proved fact and the evidence are taken as the frequent item set of the to-be-proved fact and the evidence;

[0171] The support degree acquisition includes: dividing the number of events in the event set corresponding to any one item set in the fact or evidence to be proved by the total number of events in the fact or evidence to be proved, to obtain the support degree of the item set of the fact or evidence to be proved.

[0172] Optionally, the first association relationship acquisition module 560 is further used for:

[0173] S61, acquiring the confidence, certainty, lift and leverage of each association rule of the fact to be proved, screening each association rule through the confidence, certainty, lift and leverage of each association rule of the fact to be proved, and taking the screened association rule as the association relationship set of the fact to be proved.

[0174] S62, acquiring the confidence, certainty, lift and leverage of each association rule of the evidence, screening each association rule through the confidence, certainty, lift and leverage of each association rule of the evidence, and taking the screened association rule as the association relationship set of the evidence.

[0175] Optionally, the first association relationship acquisition module 560 is further used for:

[0176] Respectively setting the first confidence threshold, the first certainty threshold, the first lift threshold and the first leverage threshold of the fact to be proved;

[0177] Acquiring the first association rule with the confidence and the certainty greater than the first confidence threshold and the first certainty threshold;

[0178] In the first association rule, acquiring the second association rule with the lift greater than the first lift threshold;

[0179] In the second association rule, acquiring the third association rule with the leverage greater than the first leverage threshold;

[0180] Taking the third association rule of the fact to be proved as the association relationship set of the fact to be proved;

[0181] The S62 acquiring the confidence, certainty, lift and leverage of each association rule of the evidence, screening each association rule through the confidence, certainty, lift and leverage of each association rule of the evidence, and taking the screened association rule as the association relationship set of the evidence, includes:

[0182] Respectively setting the second confidence threshold, the second certainty threshold, the second lift threshold and the second leverage threshold of the evidence;

[0183] Acquiring the fourth association rule of the evidence with the confidence and the certainty greater than the second confidence threshold and the second certainty threshold of the evidence;

[0184] In the fourth association rule, a fifth association rule with a lift greater than a second lift threshold is obtained;

[0185] In the fifth association rule, a sixth association rule with a leverage greater than a second leverage threshold is obtained;

[0186] The sixth association rule of the evidence is taken as the evidence association relationship set.

[0187] Optionally, the second association relationship obtaining module 570 is further used for:

[0188] An association rule contained in both the to-be-proved fact association relationship set and the evidence association relationship set is obtained;

[0189] The association rule contained in both the to-be-proved fact association relationship set and the evidence association relationship set is taken as an evidence-to-be-proved fact association relationship set.

[0190] Optionally, the second association relationship obtaining module 570 is further used for:

[0191] If an antecedent of any association rule in the to-be-proved fact association relationship set and an antecedent of any association rule in the evidence association relationship set have an intersection, and a consequent also has an intersection, then both the association rule in the to-be-proved fact association relationship set and the association rule in the evidence association relationship set are taken as a candidate evidence-to-be-proved fact association rule;

[0192] The candidate evidence-to-be-proved fact association rule is screened through a preset rule, and the screened candidate evidence-to-be-proved fact association rule is taken as the evidence-to-be-proved fact association relationship set.

[0193] Optionally, the second association relationship obtaining module 570 is further used for:

[0194] The confidence, the certainty, the lift, and the leverage of each candidate evidence-to-be-proved fact association rule are obtained respectively;

[0195] A third confidence threshold, a third certainty threshold, a third lift threshold, and a third leverage threshold are set respectively;

[0196] A first evidence-to-be-proved fact association rule with both the confidence and the certainty greater than the third confidence threshold and the third certainty threshold is obtained;

[0197] In the first evidence-to-be-proved fact association rule, a second evidence-to-be-proved fact association rule with a lift greater than a third lift threshold is obtained;

[0198] In the second evidence-to-be-proved fact association rule, a fourth evidence-to-be-proved fact association rule with a leverage greater than a third leverage threshold is obtained;

[0199] The fourth evidence-to-be-proved fact association rule is taken as the evidence-to-be-proved fact association set.

[0200] Optionally, the device further comprises a relationship graph construction module.

[0201] The relationship graph construction module is configured to construct a case association relationship graph according to the to-be-proved fact association set, the evidence association set and the evidence-to-be-proved fact association set.

[0202] In the embodiment of the application, event element entities in the to-be-proved fact and the evidence are acquired, and event sets in which each event element entity appears are counted; the frequent item sets of the to-be-proved fact and the evidence are acquired according to the event sets in which each event element entity appears; the association rules of the to-be-proved fact and the evidence are established according to the frequent item sets, the to-be-proved fact association set and the evidence association set are acquired through the association rules; and finally, the evidence-to-be-proved fact association set is acquired according to the to-be-proved fact association set and the evidence association set. The application starts from the event element relationship which is the core element of the case evidence and the to-be-proved fact, adopts the association relationship construction strategy of divide and conquer, proposes an efficient and high-reliability evidence association and evidence-to-be-proved fact association relationship discovery method, effectively assists the case reasoning and evidence chain construction of the judicial case handling personnel, improves the judicial case handling efficiency and judicial fairness, and is especially suitable for large and complex cases.

[0203] Figure 6 is a structural schematic diagram of a judicial evidence association relationship construction device provided by the embodiment of the application, as shown in Figure 6 The judicial evidence association relationship construction device can include the judicial evidence association relationship construction device shown in Figure 5 Optionally, the judicial evidence association relationship construction device 610 can include the first processor 2001.

[0204] Optionally, the judicial evidence association relationship construction device 610 can further include the memory 2002 and the transceiver 2003.

[0205] The first processor 2001, the memory 2002 and the transceiver 2003 can be connected through a communication bus.

[0206] The following will be specifically introduced to the various constituent parts of the judicial evidence association relationship construction device 610: Figure 6

[0207] ​The first processor 2001 is the control center of the judicial evidence association construction device 610. It can be a single processor or a collective term for multiple processing elements. For example, the first processor 2001 can be one or more central processing units (CPUs), application-specific integrated circuits (ASICs), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).

[0208] Optionally, the first processor 2001 can perform various functions of the judicial evidence association construction device 610 by running or executing software programs stored in the memory 2002 and calling data stored in the memory 2002.

[0209] In a specific implementation, as one example, the first processor 2001 may include one or more CPUs, for example... Figure 6 CPU0 and CPU1 are shown in the diagram.

[0210] In a specific implementation, as one example, the judicial evidence association construction device 610 may also include multiple processors, for example... Figure 6 The first processor 2001 and the second processor 2004 are shown in the diagram. Each of these processors can be a single-core processor or a multi-core processor. Here, a processor can refer to one or more devices, circuits, and / or processing cores used to process data (such as computer program instructions).

[0211] The memory 2002 is used to store the software program that executes the present invention, and is controlled by the first processor 2001 to execute it. The specific implementation method can be referred to the above method embodiment, and will not be repeated here.

[0212] Optionally, the memory 2002 can be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disk storage, a magnetic disk storage or other magnetic storage devices, or any other medium capable of storing desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to this. The memory 2002 can be integrated with the first processor 2001 or exist independently and be coupled with the first processor 2001 through an interface circuit (not shown in the figure) of the device 610, and the embodiments of the present application are not limited in this regard. Figure 6

[0213] The transceiver 2003 is configured to communicate with a network device or a terminal device.

[0214] Optionally, the transceiver 2003 can include a receiver and a transmitter (not shown separately in the figure). The receiver is configured to implement a receiving function, and the transmitter is configured to implement a transmitting function. Figure 6

[0215] Optionally, the transceiver 2003 can be integrated with the first processor 2001 or exist independently and be coupled with the first processor 2001 through an interface circuit (not shown in the figure) of the device 610, and the embodiments of the present application are not limited in this regard. Figure 6

[0216] It should be noted that the structure of the judicial evidence association construction device 610 shown in the figure does not constitute a limitation on the router, and the actual knowledge structure identification device can include more or fewer components than those shown in the figure, or combine certain components, or different component arrangements. Figure 6

[0217] In addition, the technical effects of the judicial evidence association construction device 610 can refer to the technical effects of the judicial evidence association construction method described in the above method embodiments, which will not be described here.

[0218] ​​​​It is to be understood that the first processor 2001 in the embodiments of the present application can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic components, discrete hardware components, etc. The general-purpose processor can be a microprocessor or can also be any conventional processor.

[0219] It is also to be understood that the memory in the embodiments of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memory. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically EPROM (EEPROM) or a flash memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchlink dynamic random access memory (SLDRAM) and direct rambus RAM (DR RAM).

[0220] The above-described embodiments can be implemented in whole or in part by software, hardware (such as a circuit), firmware, or any combination thereof. When implemented in software, the above-described embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center through a wired (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. containing one or more available medium collections. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state disk.

[0221] It should be understood that the term "and / or" herein merely describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent the following three cases: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. In addition, the character " / " herein generally represents that the associated objects before and after it are in an "or" relationship, but it can also represent an "and / or" relationship, which can be understood according to the context before and after it.

[0222] In the present application, "at least one" means one or more, and "multiple" means two or more. "At least one of the following" or the like means any combination of the items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0223] It should be understood that in various embodiments of the present application, the size of the sequence number of the above-described processes does not mean the order of execution, and the execution order of the processes should be determined according to their functions and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0224] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0225] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the devices, apparatuses and units described above can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0226] In several embodiments provided by the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0227] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0228] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit.

[0229] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the parts of the present application that essentially contribute to the prior art or the parts of the technical solutions can be embodied in the form of software products. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0230] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for constructing a judicial evidence association relationship, characterized in that, The method comprises: S1, extracting event element entities in a to-be-proved fact and evidence of any case respectively; S2, according to the event element entities in the to-be-proved fact and evidence, respectively, counting event sets in which each event element entity appears in the to-be-proved fact and evidence; S3, according to the event sets in which each event element entity appears and a preset support threshold, respectively, acquiring frequent item sets of the to-be-proved fact and the evidence; S4, taking any one or more event element entities in any frequent item set of the to-be-proved fact as an antecedent, taking the remaining event element entities in the frequent item set as a consequent, acquiring all association rules of the frequent item set, and then obtaining all association rules of the to-be-proved fact; S5, taking any one or more event element entities in any frequent item set of the evidence as an antecedent, taking the remaining event element entities in the frequent item set as a consequent, acquiring all association rules of the frequent item set, and then obtaining all association rules of the evidence; S6, screening all association rules of the to-be-proved fact by a preset screening rule to obtain a to-be-proved fact association relation set, and screening all association rules of the evidence by the preset screening rule to obtain an evidence association relation set; S7, according to the to-be-proved fact association relation set and the evidence association relation set, constructing an evidence-to-be-proved fact association relation set.

2. The judicial evidence association relationship construction method according to claim 1, characterized in that, The S3 comprises: Respectively, acquiring each event element entity in the to-be-proved fact and the evidence, and using each event element entity to form a set with only one element as a 1-item set of the to-be-proved fact and the evidence; Screening all 1-item sets by a preset support threshold, and taking a 1-item set greater than the preset support threshold as a frequent 1-item set; Merging the frequent 1-item sets of the to-be-proved fact and the evidence two by two to obtain 2-item sets of the to-be-proved fact and the evidence respectively, wherein an event set in the 2-item set is common events of the two merged frequent 1-item sets; acquiring the support of each 2-item set of the to-be-proved fact and the evidence respectively, and screening all 2-item sets by a preset support threshold, and taking a 2-item set greater than the preset support threshold as a frequent 2-item set; Repeating the merging process of the frequent item sets, and each time the number of event element entity items of a new item set generated by merging is increased by 1, until no new frequent item set can be generated, and all frequent k-item sets generated in the merging process of the to-be-proved fact and the evidence are taken as the frequent item sets of the to-be-proved fact and the evidence; The support acquisition comprises: dividing the number of events in an event set corresponding to any one item set in the to-be-proved fact or the evidence by the total number of events in the to-be-proved fact or the evidence to obtain the support of the item set in the to-be-proved fact or the evidence.

3. The method of claim 1, wherein, The S6 comprises: S61, acquire the confidence, the certainty, the lift and the leverage of each association rule of the to-be-proved fact, filter each association rule through the confidence, the certainty, the lift and the leverage of each association rule of the to-be-proved fact, and take the filtered association rule as the to-be-proved fact association relationship set; S62, acquire the confidence, the certainty, the lift and the leverage of each association rule of the evidence, filter each association rule through the confidence, the certainty, the lift and the leverage of each association rule of the evidence, and take the filtered association rule as the evidence association relationship set.

4. The method of claim 3, wherein, The S61 acquires the confidence, the certainty, the lift and the leverage of each association rule of the to-be-proved fact, filters each association rule through the confidence, the certainty, the lift and the leverage of each association rule of the to-be-proved fact, and takes the filtered association rule as the to-be-proved fact association relationship set, and the method comprises the following steps: firstly confidence threshold value, the first certainty threshold value, the first lift threshold value and the first leverage threshold value of the to-be-proved fact are set respectively; a first association rule with a confidence greater than the first confidence threshold value and a certainty greater than the first certainty threshold value is acquired; in the first association rule, a second association rule with a lift greater than the first lift threshold value is acquired; in the second association rule, a third association rule with a leverage greater than the first leverage threshold value is acquired; the third association rule of the to-be-proved fact is taken as the to-be-proved fact association relationship set; The S62 acquires the confidence, the certainty, the lift and the leverage of each association rule of the evidence, filters each association rule through the confidence, the certainty, the lift and the leverage of each association rule of the evidence, and takes the filtered association rule as the evidence association relationship set, and the method comprises the following steps: secondly confidence threshold value, the second certainty threshold value, the second lift threshold value and the second leverage threshold value of the evidence are set respectively; a fourth association rule of the evidence with a confidence greater than the second confidence threshold value and a certainty greater than the second certainty threshold value is acquired; in the fourth association rule, a fifth association rule with a lift greater than the second lift threshold value is acquired; in the fifth association rule, a sixth association rule with a leverage greater than the second leverage threshold value is acquired; the sixth association rule of the evidence is taken as the evidence association relationship set.

5. The method of claim 1, wherein, The S7 constructs the evidence-to-be-proved fact association relationship set according to the to-be-proved fact association relationship set and the evidence association relationship set, and the method comprises the following steps: acquire the association rule contained in both the to-be-proved fact association relationship set and the evidence association relationship set; take the association rule contained in both the to-be-proved fact association relationship set and the evidence association relationship set as the evidence-to-be-proved fact association relationship set.

6. The method of claim 1, wherein, The S7 constructs the evidence-to-be-proved fact association relationship set according to the to-be-proved fact association relationship set and the evidence association relationship set, and the method comprises the following steps: if there is an intersection between the antecedent of any association rule in the to-be-proved fact association relationship set and the antecedent of any association rule in the evidence association relationship set, and there is also an intersection between the consequent of any association rule in the to-be-proved fact association relationship set and the consequent of any association rule in the evidence association relationship set, then both the association rule in the to-be-proved fact association relationship set and the association rule in the evidence association relationship set are taken as the candidate evidence-to-be-proved fact association rule; Screen the candidate evidence-to-be-proved fact association rules through preset rules, and take the screened candidate evidence-to-be-proved fact association rules as the evidence-to-be-proved fact association relationship set.

7. The method of claim 6, wherein, The screening of the candidate evidence-to-be-proved fact association rules through preset rules, and taking the screened candidate evidence-to-be-proved fact association rules as the evidence-to-be-proved fact association relationship set, comprises: Respectively acquire the confidence, the certainty, the lift and the leverage of each candidate evidence-to-be-proved fact association rule; Respectively set the third confidence threshold, the third certainty threshold, the third lift threshold and the third leverage threshold; Acquire the first evidence-to-be-proved fact association rule with the confidence greater than the third confidence threshold and the certainty greater than the third certainty threshold; In the first evidence-to-be-proved fact association rule, acquire the second evidence-to-be-proved fact association rule with the lift greater than the third lift threshold; In the second evidence-to-be-proved fact association rule, acquire the fourth evidence-to-be-proved fact association rule with the leverage greater than the third leverage threshold; Take the fourth evidence-to-be-proved fact association rule as the evidence-to-be-proved fact association relationship set.

8. The method of claim 1, wherein, After the S7, according to the to-be-proved fact association relationship set and the evidence association relationship set, constructs the evidence-to-be-proved fact association relationship set, the method further comprises: According to the to-be-proved fact association relationship set, the evidence association relationship set and the evidence-to-be-proved fact association relationship set, constructs the case association relationship graph.

9. A judicial evidence association relationship construction device for implementing the judicial evidence association relationship construction method according to any one of claims 1-8, characterized in that, The device comprises: An element entity extraction module is configured to extract event element entities in the to-be-proved fact and the evidence of any case respectively; An event set acquisition module is configured to count event sets in which each event element entity appears in the to-be-proved fact and the evidence respectively according to the event element entities in the to-be-proved fact and the evidence; A frequent item set acquisition module is configured to acquire frequent item sets of the to-be-proved fact and the evidence respectively according to the event sets in which each event element entity appears and a preset support threshold; A first association rule acquisition module is configured to acquire all association rules of any frequent item set of the to-be-proved fact by taking any one or more event element entities in the frequent item set as antecedents and taking the remaining event element entities in the frequent item set as consequents, and to obtain all association rules of the to-be-proved fact; A second association rule acquisition module is configured to acquire all association rules of any frequent item set of the evidence by taking any one or more event element entities in the frequent item set as antecedents and taking the remaining event element entities in the frequent item set as consequents, and to obtain all association rules of the evidence; A first association relationship acquisition module is configured to acquire a to-be-proved fact association relationship set by screening all association rules of the to-be-proved fact through preset screening rules, and to acquire an evidence association relationship set by screening all association rules of the evidence through preset screening rules; A second association relationship acquisition module is configured to construct an evidence-to-be-proved fact association relationship set according to the to-be-proved fact association relationship set and the evidence association relationship set.

10. A computer readable storage medium, characterized in that, The computer readable storage medium stores program codes, which can be invoked by the processor to execute the method of any one of claims 1 to 8.

Images