Judicial evidence association relationship construction method and device and storage medium

Abstract

The invention relates to a judicial evidence association relationship construction method and device and a storage medium, and is applied to the technical field of judicial big data intelligent processing, and the method comprises the steps: obtaining a to-be-authenticated fact and event element entities in evidence, and carrying out the statistics of an event set of each event element entity; according to the event set of each event element entity, obtaining frequent item sets of facts to be verified and evidences; establishing an association rule of the facts to be authenticated and the evidence according to the frequent item set, and obtaining an association relation set of the facts to be authenticated and an association relation set of the evidence through the association rule; finally, obtaining an evidence-to-be-certified fact association relationship set according to the to-be-certified fact association relationship set and the evidence association relationship set; according to the invention, starting from the core element-event element relationship of the case evidence and the to-be-certified facts, the strategy is constructed by adopting the division-and-treatment association relationship, and the reliability of the association relationship between the evidence and the to-be-certified facts is improved without depending on the subjective experience of case handling personnel.

Description

Technical Field

[0001] The present invention relates to the technical field of judicial big data intelligent processing, and in particular to a method and device for constructing a judicial evidence association relationship. Background Art

[0002] Judicial evidence is the material that proves the facts to be proved in a judicial case. It comes from many aspects, including the defendant's statement, the victim's confession and defense, witness testimony, physical evidence, documentary evidence, inspection records, audio-visual materials and electronic data. How to find evidence related to the facts to be proved from a large number of different evidences and find the mutual corroboration relationship between the evidences, that is, how to analyze the correlation between evidences to provide a basis for judicial conviction and sentencing, is the core content of case investigation and trial.

[0003] Currently, evidence correlation analysis is mainly based on the experience of case handlers, with the help of electronic file cataloging, file reading excerpts and other auxiliary tools. According to the facts to be proved in the case described in the indictment, public prosecution, evidence, etc., fact-based evidence search, evidence comparison, hypothesis verification and review are used to construct the correlation between evidence and case facts and the corroborative relationship between evidence. This method is mainly based on empirical and intuitive subjective judgment, and the judgment results are accidental and uncertain. The effectiveness of case handling depends to a large extent on the experience and ability of case handlers, especially for large or difficult cases, where the relationship between case elements is complex and there is a lot of evidence. They often face problems such as difficulty in corroborating each other and unclear evidence of the facts to be proved. Summary of the invention

[0004] In order to solve the technical problems existing in the prior art of evidence correlation analysis, such as the complex relationship between case elements, the large amount of evidence, the difficulty in corroborating each other, and the unclear direction of the evidence to be proved, the embodiment of the present invention provides a method and device for constructing a judicial evidence correlation relationship. The technical solution is as follows: On the one hand, a method for constructing a judicial evidence association relationship is provided, which is implemented by a judicial evidence association relationship construction device, and the method includes: S1. Extract the facts to be proved in any case and the event element entities in the evidence respectively; S2. According to the event element entities in the facts to be proved and the evidence, count the event sets in which each event element entity in the facts to be proved and the evidence appears respectively; S3, according to the event set in which each event element entity appears and the preset support threshold, respectively obtain the frequent item set of the fact to be proved and the frequent item set of the evidence; S4, taking any one or more event element entities in any frequent item set of the fact to be proved as antecedents, taking the remaining event element entities in the frequent item set as consequents, obtaining all association rules of the frequent item set, and then obtaining all association rules of the fact to be proved; S5, taking any one or more event element entities in any frequent item set of the evidence as antecedents, taking the remaining event element entities in the frequent item set as consequents, obtaining all association rules of the frequent item set, and then obtaining all association rules of the evidence; S6. Filter all association rules of the facts to be proved by using a preset screening rule to obtain an association relationship set of the facts to be proved, and filter all association rules of the evidence by using a preset screening rule to obtain an evidence association relationship set; S7. Construct an evidence-fact-to-be-proved association relationship set based on the association relationship set of the facts to be proved and the evidence association relationship set.

[0005] On the other hand, a judicial evidence association relationship construction device is provided, which is applied to a judicial evidence association relationship construction method, and the device includes: The element entity extraction module is used to extract the facts to be proved in any case and the event element entities in the evidence respectively; An event set acquisition module is used to count the event sets in which each event element entity in the facts to be proved and the evidence appears, according to the event element entities in the facts to be proved and the evidence; A frequent item set acquisition module is used to acquire the frequent item sets of the facts to be proved and the frequent item sets of the evidence respectively according to the event set in which each event element entity appears and the preset support threshold; A first association rule acquisition module is used to take any one or more event element entities in any frequent item set of the fact to be proved as antecedents, take the remaining event element entities in the frequent item set as consequents, acquire all association rules of the frequent item set, and further obtain all association rules of the fact to be proved; The second association rule acquisition module is used to take any one or more event element entities in any frequent item set of the evidence as antecedents, take the remaining event element entities in the frequent item set as consequents, acquire all association rules of the frequent item set, and thus obtain all association rules of the evidence; A first association relationship acquisition module is used to filter all association rules of the facts to be proved by using a preset filtering rule to obtain an association relationship set of the facts to be proved, and to filter all association rules of the evidence by using a preset filtering rule to obtain an evidence association relationship set; The second association relationship acquisition module is used to construct an evidence-fact-to-be-proved association relationship set based on the association relationship set of the facts to be proved and the evidence association relationship set.

[0006] On the other hand, a judicial evidence association relationship construction device is provided, which includes: a processor; a memory, wherein computer-readable instructions are stored in the memory, and when the computer-readable instructions are executed by the processor, any one of the above-mentioned judicial evidence association relationship construction methods is implemented.

[0007] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction is stored in the storage medium, and the at least one instruction is loaded and executed by a processor to implement any one of the above-mentioned methods for constructing judicial evidence association relationships.

[0008] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: The present application obtains event element entities in the facts to be proved and evidence and counts the event sets in which each event element entity appears; obtains frequent item sets of the facts to be proved and evidence respectively according to the event sets in which each event element entity appears; establishes association rules for the facts to be proved and evidence according to the frequent item sets, obtains the association relationship set of the facts to be proved and the association relationship set of the evidence through the association rules; finally, obtains the evidence-fact association relationship set according to the association relationship set of the facts to be proved and the evidence association relationship set; the present application starts from the core element of case evidence and facts to be proved - the event element relationship, adopts a divide-and-conquer association relationship construction strategy, and proposes an efficient and reliable method for discovering evidence associations and the association relationship between evidence and facts to be proved in a case, which effectively assists judicial case handlers in case reasoning and evidence chain construction, improves judicial case handling efficiency and judicial fairness, and is particularly suitable for large and complex cases. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 This is a flow chart of a method for constructing judicial evidence association relationships provided by an embodiment of the present invention; Figure 2 It is a sample diagram of a horizontal evidence event table provided by an embodiment of the present invention; Figure 3 It is a sample diagram of a vertical evidence event table provided by an embodiment of the present invention; Figure 4 It is a schematic diagram of an evidence association relationship map provided by an embodiment of the present invention; Figure 5 It is a block diagram of a judicial evidence association relationship construction device provided by an embodiment of the present invention; Figure 6 It is a structural schematic diagram of a judicial evidence association relationship building device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0011] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0012] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0013] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0014] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0015] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0016] An embodiment of the present invention provides a method for constructing a judicial evidence association relationship. The method can be implemented by a judicial evidence association relationship construction device, and the judicial evidence association relationship construction device can be a terminal or a server.

[0017] In order to facilitate understanding of the solution of the present application, this embodiment first briefly describes some concepts appearing in the text: Association analysis is an important means to bring out the value of big data. Diverse data sources and massive amounts of data provide us with rich data resources for management, analysis and decision-making. However, it also makes it difficult to find the relationship between data on the surface. Through association analysis, we can find the rules and patterns behind these data. For example, in the classic shopping basket analysis, by analyzing the combination relationship of goods in the customer's shopping list, we can find out which goods are often purchased by customers at the same time. Based on this relationship, we can formulate corresponding marketing strategies. Association analysis is to find relationships in large-scale data sets. These relationships generally have the following two forms: frequent item sets and association rules. Frequent item sets are sets of things that often appear together, and association rules imply that there may be a strong relationship between two things.

[0018] The basic concepts of association analysis are explained below.

[0019] (1) Itemset A set of zero or more items is called an itemset; (2) k-itemset An itemset containing k items is called a k-itemset; (3) Support count The number of transactions that contain an itemset is the support count of the itemset; (4) Support Used to determine the frequency of itemsets.

[0020] The quotient of the support count divided by the total number of transactions is the support. (5) Frequent itemsets Item sets whose support is greater than or equal to a certain threshold are called frequent item sets; (6) Association rules Association rules are of the form The implied expression of , where X and Y are disjoint item sets, X is called the antecedent, and Y is called the consequent; The ultimate goal of association analysis is to find strong association rules and frequent item sets. The association analysis algorithm is the process of identifying frequent item sets and strong association rules. The most complex part is the identification of frequent item sets, which is also the key to the efficiency of association analysis. After understanding the above basic concepts, Figure 1 The flowchart of the method for constructing judicial evidence association relationship is shown in FIG. The processing flow of the method may include the following steps: S1. Extract the facts to be proved in any case and the event element entities in the evidence respectively.

[0021] In a feasible implementation, the events in the evidence and facts to be proved reflect the case facts. Natural language processing tools such as HanNLP and StanfordNLP, or multimodal pre-trained large models (such as GLM, etc.) Promt engineering and other methods are used to extract the case event element entities in the facts to be proved and evidence, and perform entity fusion to ensure the uniqueness of the entity name of the same case element. For example, Zhang San is called "Zhang San" in some documents and "defendant" in others. After entity fusion, the entity name is unified as "Zhang San"; The extracted event entities mainly include the following elements: Time of occurrence: the specific date and time when the event occurred, or any time point related to the event (such as start time, end time); Location: The specific geographical location where the incident occurred, including country, city, specific place, etc.; Participants: individuals, groups or organizations involved in the incident, including witnesses, actors, etc.; Behavior: The specific actions or activities that occur during an event, such as transactions, communications, etc. Behavior object: the direct target of the behavior, which can be a person, object, information, etc. Behavior mode: the specific method or means of implementing the behavior, such as using tools, adopting strategies, etc. Cause of behavior: The motivation, purpose, or trigger that causes the behavior to occur; Behavior results: direct or indirect consequences of the behavior, including impact, loss, benefit, etc.; It should be noted that the facts and evidence event elements of large-scale cases are numerous and complex. In order to simplify the process and improve efficiency, a horizontal table of facts to be proved and a table of evidence events are constructed for all extracted events. Each event element is called an "item", such as Figure 2 shown. Figure 2 In , the first column is the item, and the second column is the event set in which the item appears. The number of elements in each event set is the support count of the item (i.e., event element). The support count of the 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.

[0022] In order to improve the efficiency of discovering the relationship between items, Figure 2 The horizontal evidence event table is converted to an appendix Figure 3 In the vertical evidence event table shown, each row is an item and the columns are a collection of event numbers in which the item appears.

[0023] S2. According to the event element entities in the facts to be proved and the evidence, count the event sets in which each event element entity in the facts to be proved and the evidence appears.

[0024] S3. According to the event set in which each event element entity appears and the preset support threshold, the frequent item sets of the facts to be proved and the frequent item sets of the evidence are obtained respectively.

[0025] Optionally, the specific operations of S3 may include: Obtain each event element entity in the facts to be proved and the evidence respectively, and use each event element entity to form a set with only one element as the 1-item set of the facts to be proved and the evidence respectively; All 1-item sets are screened by a preset support threshold, and 1-item sets with a support greater than the preset threshold are regarded as frequent 1-item sets; Merge the frequent 1-itemsets of the facts and evidence to be proved in pairs, and obtain the 2-itemsets of the facts and evidence to be proved respectively. The event set in the 2-itemsets is the common event of the two merged frequent 1-itemsets; obtain the support of each 2-itemset of the facts and evidence to be proved respectively, and filter all 2-itemsets by a preset support threshold, and take the 2-itemsets with a support greater than the preset threshold as frequent 2-itemsets; Repeat the merging process of frequent item sets, and add 1 to the number of event element entity items of the new item set generated by each merging, until no new frequent item sets can be generated. All frequent k-itemsets generated by the merging process of the facts and evidence to be proved are used as the frequent item sets of the facts and evidence to be proved; The acquisition of support includes: dividing the number of events in the event set corresponding to any item set in the facts or evidence to be proved by the total number of events of the facts or evidence to be proved, and obtaining the support of the item set of the facts or evidence to be proved.

[0026] In a feasible implementation, the case handler sets the minimum support threshold of the event frequent item set according to the case situation. For the facts to be proved in the case, in order to ensure that the facts are not missed, the minimum support threshold is set as small as possible. For evidence, in order to screen out irrelevant facts and evidence, the minimum support threshold is set to be greater than 0.2. The specific setting value of the threshold can also be set by the case handler according to the actual situation of the case. The larger the threshold, the fewer the associated sets of event items and the faster the execution efficiency, but important associated relationships may be missed.

[0027] According to the attached Figure 3 The evidence event table shown uses the following steps to construct the evidence event item association set. For the sake of illustration, the minimum support of the frequent item set is set to 0.2.

[0028] Keep attached Figure 3 Items whose support is greater than or equal to the minimum support threshold form frequent 1-item sets: {{A1}, {A2}, {B1}, {C1}, {C2}, {D1}, {D2}, {E1}, {E2}, {F1}, {F2}, {G1}, {G2}, {H1}, {H2}}.

[0029] Frequent k-item sets (k greater than or equal to 1) are constructed recursively according to the attached Figure 3 In the vertical event table of the example, frequent k-itemsets are merged in pairs to find all possible frequent (k+1)-itemsets. The event set of the merged itemsets is the events contained in both merged itemsets. For example, Figure 3In the example, the event set intersection of frequent 1-item sets {B1} and {H1} is {T01,T02,T05,T06} {T01,T02,T06}={T01,T02,T06}, the intersection support is 3 / 6=0.5, which is greater than 0.2, so {B1,H1} is a frequent 2-item set.

[0030] Next, all the frequent 2-item sets are merged. It is worth emphasizing that each time the merge occurs, the event element entity is increased by 1. That is to say, the merger of two frequent 2-item sets results in a 3-item set, not a 4-item set. For example, the two frequent 2-item sets are {B1, H1} and {A1, C1}, then the 3-item sets can be {B1, H1, A1}, {B1, H1, C1}, {A1, C1, B1}, {A1, C1, H1}; select the frequent 3-item sets from all the 3-item sets; then merge the frequent 3-item sets into 4-item sets; The merging process is repeated until no new frequent itemsets can be generated.

[0031] All frequent k-item sets (k greater than or equal to 1) generated are frequent item sets of evidence or facts to be proved.

[0032] S4. Take any one or more event element entities in any frequent item set of the fact to be proved 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 then obtain all association rules of the fact to be proved.

[0033] S5. Take any one or more event element entities in any frequent item set of the evidence as antecedents, take the remaining event element entities in the frequent item set as consequents, obtain all association rules of the frequent item set, and then obtain all association rules of the evidence.

[0034] In a feasible implementation, all possible association rules are generated for each frequent item set of evidence and facts to be proved. The evidence association rules are used to represent the association relationship between the elements of the evidence event items, reflecting the mutual corroboration relationship between the evidence; the case facts to be proved association rules are used to represent the association relationship between the case facts to be proved event items; the association rules are expressed as: X Y, where X and Y are a frequent itemset, X is the antecedent and Y is the consequent.

[0035] S6. Filter all association rules of the facts to be proved by using preset screening rules to obtain a set of association relationships of the facts to be proved, and filter all association rules of the evidence by using preset screening rules to obtain a set of association relationships of the evidence.

[0036] Optionally, the specific operation process of S6 may include: S61, obtaining the confidence, certainty, lift and leverage of each association rule of the fact to be proved, screening each association rule according to the confidence, certainty, lift and leverage of each association rule of the fact to be proved, and using the screened association rules as the association relationship set of the fact to be proved.

[0037] Optionally, the specific operation process of S61 may include: Respectively set a first confidence threshold, a first certainty threshold, a first lift threshold, and a first leverage threshold of the fact to be proved; Acquire a first association rule whose confidence is greater than a first confidence threshold and whose certainty is greater than the first certainty threshold; In the first association rule, a second association rule whose lift is greater than the first lift threshold is obtained; In the second association rule, a third association rule is obtained in which the leverage ratio is greater than the first leverage ratio threshold; The third association rule of the facts to be proved is used as the association relationship set of the facts to be proved; S62, obtaining the confidence, certainty, lift and leverage of each association rule of the evidence, screening each association rule according to the confidence, certainty, lift and leverage of each association rule of the evidence, and using the screened association rules as the evidence association relationship set.

[0038] Optionally, the specific operation process of S62 may include: respectively setting a second confidence threshold, a second certainty threshold, a second lift threshold, and a second leverage threshold of the evidence; Acquire a fourth association rule of evidence whose confidence is greater than a second confidence threshold of the evidence and whose certainty is greater than the second certainty threshold; In the fourth association rule, a fifth association rule whose lift is greater than the second lift threshold is obtained; In the fifth association rule, a sixth association rule is obtained in which the leverage ratio is greater than the second leverage ratio threshold; The sixth association rule of evidence is taken as the evidence association relationship set.

[0039] In one feasible implementation, for each frequent item set, such as {A, B, C}, the candidate association rules include the associations between {A, B, C} and all its subsets, such as {A} {B,C}, {B} {A,C}, {C} {A,B}, {A,B} {C}, {A,C} {B}, and {B,C} {A} etc.

[0040] For each candidate association rule, the reliability of the association rule is evaluated using confidence, certainty, lift and leverage: Confidence (X Y)=P(X,Y) / P(X) Confidence (X Y) = (1-P(Y)) / (1-Confidence(X Y)) Lift (X Y)=P(X,Y) / (P(X)P(Y)) Leverage Ratio (X Y)=P(X,Y)-P(X)P(Y) Among them, P(X)=(support of X)=(number of events containing X) / (total number of events), P(X,Y)=(number of events containing both X and Y) / (total number of events).

[0041] Confidence is used to measure when a piece of evidence or condition appears. For example, if the confidence between the rule antecedent and the rule consequent is high, then the value of this evidence may be great.

[0042] 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.

[0043] The degree of certainty is used to measure the probability that the outcome of a case will not occur in the absence of certain evidence. If the degree of certainty is high, it can be considered that the evidence is very important in excluding the possibility of innocence.

[0044] The leverage ratio is used to assess the impact of a piece of evidence on the outcome of a case. If the leverage ratio of a piece of evidence is high, then it may be the key evidence in the case.

[0045] Association rule threshold setting and association rule filtering: The first confidence threshold and the second confidence threshold should be set to be greater than 0. The larger the value, the stronger the direct correlation between X and Y can be found. The first confidence threshold and the second confidence threshold should be set to be greater than 1. The higher the confidence, the more significant the impact of X on Y. The first lift threshold and the second lift threshold should be set to be greater than 1. The higher the lift, the stronger the positive correlation effect of X on Y. The first leverage ratio threshold and the second leverage ratio threshold must be set to be greater than 0. The higher the leverage ratio, the stronger the correlation between X and Y.

[0046] When evaluating rule screening, we first screen out candidate association rules whose confidence and certainty are greater than their respective thresholds to ensure a strong association between the premise and the result; then we calculate the lift of the rule. If the lift is greater than the threshold, it indicates that the association of the rule is not random but truly related; finally, we calculate the leverage ratio. If the leverage ratio is greater than the threshold, the uniqueness and statistical significance of the rule are further confirmed and it will be retained.

[0047] Compare the screening results with the actual case situation to verify the accuracy of the rules, and adjust the combined evaluation method and threshold based on the feedback.

[0048] All the selected association rules constitute the case evidence association relationship set and the case facts to be proved association relationship set respectively.

[0049] S7. Construct an evidence-fact-to-be-proved association relationship set based on the association relationship set of the facts to be proved and the evidence association relationship set.

[0050] In a feasible implementation, the evidence-fact association rule is used to discover the association between evidence and the facts to be proved in the case, and is used for evidence authentication and case reasoning of the facts to be proved in the case. This embodiment provides two methods for constructing candidate evidence-fact association rules, which are described below: The first method is to construct the evidence-fact-to-be-proven candidate association rules using the intersection of the evidence association rule set and the case-fact-to-be-proven association rule set. Optionally, the specifics are as follows: Obtaining association rules contained in both the association relationship set of facts to be proved and the association relationship set of evidence; The association rules contained in both the association relationship set of facts to be proved and the evidence association relationship set are taken as the evidence-association relationship set of facts to be proved.

[0051] In a feasible implementation, for example: Evidence association rule set (evidence) = {(A,B) (C),(D,E,G) (H,G),(B,E) (C),(A,H) (B,C),(A) (B)}; Association rule set of facts to be proved (facts) = {(A,B) (C),(D,E,G) (H,G),(B,G) (C)}; Evidence-fact candidate association rule set = evidence ∩ fact = {(A,B) (C),(D,E,G) (H,G)}.

[0052] The second type is an association rule in which the antecedent and consequent of the association rule of the facts to be proved respectively have intersections with the evidence association rule, which can be selected as follows: If the antecedents of any association rule in the association relationship set of the facts to be proved and any association rule in the evidence association relationship set have an intersection, and the consequents also have an intersection, then any association rule in the association relationship set of the facts to be proved and any association rule in the evidence association relationship set are both used as candidate evidence-fact association rules; The candidate evidence-to-be-proven fact association rules are screened by using preset rules, and the screened candidate evidence-to-be-proven fact association rules are used as the evidence-to-be-proven fact association relationship set.

[0053] Optionally, the candidate evidence-to-be-proven association rules are screened by preset rules, and the screened candidate evidence-to-be-proven association rules are used as the evidence-to-be-proven association relationship set, including: Obtain the confidence, certainty, lift and leverage of each candidate evidence-fact association rule respectively; respectively setting a third confidence threshold, a third certainty threshold, a third lift threshold, and a third leverage ratio threshold; Acquire a first evidence-to-be-proven fact association rule whose confidence level is greater than a third confidence level threshold and whose certainty level is greater than the third certainty level threshold; In the first evidence-to-be-proven fact association rule, obtaining a second evidence-to-be-proven fact association rule whose lift is greater than a third lift threshold; In the second evidence-to-be-proven fact association rule, a fourth evidence-to-be-proven fact association rule is obtained whose leverage ratio is greater than a third leverage ratio threshold; The fourth evidence-fact-to-be-proven association rule is used as the evidence-fact-to-be-proven association relationship set.

[0054] In a feasible implementation, for example: Evidence association rule set (evidence) = {(A,B,D) (C,E),(D,E,G) (H,G),(B,E) (C),(A,H) (B,C),(A) (B)}; Association rule set of facts to be proved (facts) = {(A, B, E) (C),(D,E,G) (H,G),(B,G) (C)}; For any association rule of evidence (A, B, D) (C,E), and any association rule of the facts to be proved (A,B,E) (C), their respective antecedents (A,B,D) and (A,B,E) have an intersection (A,B), and their consequents also have an intersection (C), so (A,B,D) (C,E) and (A,B,E) (C) are all used as candidate association rules.

[0055] The candidate association rule set of evidence-fact to be proved = the rules whose precedent and antecedent of evidence and fact have intersection respectively = {(A, B, D) (C,E),(A,B,E) (C),(D,E,G) (H,G),(B,G) (C),(B,E) (C)}.

[0056] For each candidate association rule X Y, recalculate the confidence, certainty, lift and leverage of the rule. It is worth emphasizing that the calculation of confidence, certainty, lift and leverage involves the calculation of support. In the calculation of the relevant support of the above evidence and the facts to be proved, the support count is only for the number of occurrences and the total number of events. For example, in the calculation of the support of the evidence, the number of times an event element appears in the evidence is 3, and the total number of events in the evidence is 6, then the support of the event element is 0.5. Similarly, for the calculation of the support of the facts to be proved, the number of times any event element appears in the facts to be proved is 2, and the total number of events in the facts to be proved is 6. If the number of events is 8, the support of the event element is 0.25; and in the confidence, certainty, lift and leverage calculation process of the evidence-fact candidate association rule, when it comes to support calculation, the support of the antecedent X and the consequent Y in each rule is equal to the number of times X and Y appear in all facts to be proved and evidence events divided by the total number of events, and the total number of events is equal to the sum of the number of facts to be proved and the number of evidence events. In simple terms, if any event element appears twice in the evidence and twice in the facts to be proved, and the total number of evidence events is 6 and the total number of facts to be proved is 8, then the support of the event element is (2+2) / (6+8).

[0057] After calculating the confidence, certainty, lift and leverage of each candidate association rule of evidence-fact to be proved, it is necessary to set a third confidence threshold, a third certainty threshold, a third lift threshold and a third leverage threshold for screening.

[0058] When evaluating rule screening, we first screen out candidate association rules whose confidence and certainty are greater than their respective thresholds to ensure a strong association between the premise and the result; then we calculate the lift of the rule. If the lift is greater than the threshold, it indicates that the association of the rule is not random but truly related; finally, we calculate the leverage ratio. If the leverage ratio is greater than the threshold, the uniqueness and statistical significance of the rule are further confirmed and it will be retained.

[0059] It should be noted that of the two methods mentioned above, the first one is suitable for relatively simple and clear cases, while the second one is suitable for complex cases or cases with great uncertainty in facts and evidence.

[0060] Optionally, after S7, the method may further include: S8. Construct a case correlation map based on the correlation set of facts to be proved, the correlation set of evidence, and the correlation set of evidence-facts to be proved.

[0061] In a feasible implementation, a graph database is used to construct an evidence association relationship graph. The antecedents and consequents of the evidence association rules, the association rules of facts to be proved, and the evidence-facts to be proved association rules mined out above are the vertices of the evidence association relationship graph. The antecedent and consequent of each rule are connected by a directed edge from the antecedent to the consequent. The vertex attribute of the association relationship graph is the element name of the antecedent or consequent set of the rule. For the vertices belonging to the evidence-facts to be proved association rules, the set element names of their vertex attributes are uniformly prefixed with *, such as the attached Figure 4 As shown, the attributes of the graph edges are the evaluation indicators of the rules: confidence, lift, certainty, and leverage, and the edge attribute values ​​are the corresponding evaluation indicator values.

[0062] Judicial personnel can use evidence correlation maps to assist in case reasoning and building evidence chains.

[0063] In an embodiment of the present invention, event element entities in facts to be proved and evidence are obtained and the event set in which each event element entity appears is counted; frequent item sets of facts to be proved and evidence are obtained respectively according to the event set in which each event element entity appears; association rules for facts to be proved and evidence are established according to the frequent item sets, and an association relationship set of facts to be proved and an evidence association relationship set are obtained through the association rules; finally, an evidence-fact association relationship set is obtained according to the association relationship set of facts to be proved and the evidence association relationship set; the present application starts from the core element of case evidence and facts to be proved—the relationship between event elements, and adopts a divide-and-conquer association relationship construction strategy to propose an efficient and reliable method for discovering evidence associations and association relationships between evidence and facts to be proved in a case, which effectively assists judicial case handlers in case reasoning and evidence chain building, improves judicial case handling efficiency and judicial fairness, and is particularly suitable for large and complex cases.

[0064] Figure 5 The invention is a block diagram of a judicial evidence association relationship construction device according to an exemplary embodiment, wherein the device is used in a judicial evidence association relationship construction method. Figure 5 , the device 500 comprises: An element entity extraction module 510 is used to extract the facts to be proved in any case and the event element entities in the evidence respectively; An event set acquisition module 520 is used to count the event sets in which each event element entity in the facts to be proved and the evidence appears, according to the event element entity in the facts to be proved and the evidence; A frequent item set acquisition module 530 is used to acquire the frequent item sets of the facts to be proved and the frequent item sets of the evidence respectively according to the event set in which each event element entity appears and a preset support threshold; A first association rule acquisition module 540 is used to take any one or more event element entities in any frequent item set of the fact to be proved as antecedents, and take the remaining event element entities in the frequent item set as consequents, to acquire all association rules of the frequent item set, and thus obtain all association rules of the fact to be proved; The second association rule acquisition module 550 is used to take any one or more event element entities in any frequent item set of the evidence as antecedents, take the remaining event element entities in the frequent item set as consequents, acquire all association rules of the frequent item set, and further obtain all association rules of the evidence; The first association relationship acquisition module 560 is used to filter all association rules of the facts to be proved by using a preset filtering rule to obtain an association relationship set of the facts to be proved, and to filter all association rules of the evidence by using a preset filtering rule to obtain an evidence association relationship set; The second association relationship acquisition module 570 is used to construct an evidence-fact-to-be-proved association relationship set according to the association relationship set of the facts to be proved and the evidence association relationship set.

[0065] Optionally, the frequent itemset acquisition module 530 is further configured to: Obtain each event element entity in the facts to be proved and the evidence respectively, and use each event element entity to form a set with only one element as the 1-item set of the facts to be proved and the evidence respectively; All 1-item sets are screened by a preset support threshold, and 1-item sets with a support greater than the preset threshold are regarded as frequent 1-item sets; Merge the frequent 1-itemsets of the facts and evidence to be proved in pairs to obtain the 2-itemsets of the facts and evidence to be proved respectively, wherein the event set in the 2-itemsets is the common event of the two merged frequent 1-itemsets; obtain the support of each 2-itemset of the facts and evidence to be proved respectively, and filter all the 2-itemsets by a preset support threshold, and take the 2-itemsets with a support greater than the preset support threshold as frequent 2-itemsets; Repeat the merging process of frequent item sets, and increase the number of event element entity items of the new item set generated by each merging by 1 until no new frequent item sets can be generated, and take all frequent k-itemsets generated by the facts and evidences to be proved in the merging process as the frequent item sets of the facts and evidences to be proved; The acquisition of the support includes: dividing the number of events in the event set corresponding to any item set in the fact or evidence to be proved by the total number of events of the fact or evidence to be proved, so as to obtain the support of the item set of the fact or evidence to be proved.

[0066] Optionally, the first association relationship acquisition module 560 is further configured to: S61, obtaining the confidence, certainty, lift and leverage of each association rule of the fact to be proved, screening each association rule according to the confidence, certainty, lift and leverage of each association rule of the fact to be proved, and using the screened association rules as the association relationship set of the fact to be proved; S62, obtaining the confidence, certainty, lift and leverage of each association rule of the evidence, screening each association rule according to the confidence, certainty, lift and leverage of each association rule of the evidence, and using the screened association rules as the evidence association relationship set.

[0067] Optionally, the first association relationship acquisition module 560 is further configured to: Respectively set a first confidence threshold, a first certainty threshold, a first lift threshold, and a first leverage threshold of the fact to be proved; Acquire a first association rule whose confidence and certainty are both greater than a first confidence threshold and a first certainty threshold; In the first association rule, a second association rule whose lift is greater than the first lift threshold is obtained; In the second association rule, a third association rule is obtained in which the leverage ratio is greater than the first leverage ratio threshold; The third association rule of the facts to be proved is used as the association relationship set of the facts to be proved; The step S62 of obtaining the confidence, certainty, lift and leverage of each association rule of the evidence, screening each association rule according to the confidence, certainty, lift and leverage of each association rule of the evidence, and using the screened association rules as an evidence association relationship set includes: respectively setting a second confidence threshold, a second certainty threshold, a second lift threshold, and a second leverage threshold of the evidence; Obtaining a fourth association rule of evidence whose confidence and certainty are both greater than a second confidence threshold and a second certainty threshold of the evidence; In the fourth association rule, a fifth association rule whose lift is greater than a second lift threshold is obtained; In the fifth association rule, a sixth association rule is obtained in which the leverage ratio is greater than a second leverage ratio threshold; The sixth association rule of evidence is taken as the evidence association relationship set.

[0068] Optionally, the second association relationship acquisition module 570 is further configured to: Obtaining association rules contained in both the association relationship set of facts to be proved and the association relationship set of evidence; The association rules contained in both the association relationship set of the facts to be proved and the evidence association relationship set are used as the evidence-fact association relationship set.

[0069] Optionally, the second association relationship acquisition module 570 is further configured to: If any association rule in the association relationship set of the facts to be proved and any association rule in the evidence association relationship set have an intersection in their antecedents and an intersection in their consequents, then any association rule in the association relationship set of the facts to be proved and any association rule in the evidence association relationship set are both used as candidate evidence-fact association rules; The candidate evidence-to-be-proven fact association rules are screened by using preset rules, and the screened candidate evidence-to-be-proven fact association rules are used as the evidence-to-be-proven fact association relationship set.

[0070] Optionally, the second association relationship acquisition module 570 is further configured to: Obtain the confidence, certainty, lift and leverage of each candidate evidence-fact association rule respectively; respectively setting a third confidence threshold, a third certainty threshold, a third lift threshold, and a third leverage ratio threshold; Obtaining a first evidence-to-be-proven fact association rule whose confidence and certainty are both greater than a third confidence threshold and a third certainty threshold; In the first evidence-to-be-proven fact association rule, obtaining a second evidence-to-be-proven fact association rule whose lift is greater than a third lift threshold; In the second evidence-to-be-proven fact association rule, a fourth evidence-to-be-proven fact association rule is obtained, in which the leverage ratio is greater than a third leverage ratio threshold; The fourth evidence-fact-to-be-proven association rule is used as the evidence-fact-to-be-proven association relationship set.

[0071] Optionally, the device further comprises a relationship map construction module; The relationship map construction module is used to construct a case relationship map based on the relationship set of facts to be proved, the evidence relationship set and the evidence-facts to be proved relationship set.

[0072] In an embodiment of the present invention, event element entities in facts to be proved and evidence are obtained and the event set in which each event element entity appears is counted; frequent item sets of facts to be proved and evidence are obtained respectively according to the event set in which each event element entity appears; association rules for facts to be proved and evidence are established according to the frequent item sets, and an association relationship set of facts to be proved and an evidence association relationship set are obtained through the association rules; finally, an evidence-fact association relationship set is obtained according to the association relationship set of facts to be proved and the evidence association relationship set; the present application starts from the core element of case evidence and facts to be proved—the relationship between event elements, and adopts a divide-and-conquer association relationship construction strategy to propose an efficient and reliable method for discovering evidence associations and association relationships between evidence and facts to be proved in a case, which effectively assists judicial case handlers in case reasoning and evidence chain building, improves judicial case handling efficiency and judicial fairness, and is particularly suitable for large and complex cases.

[0073] Figure 6 is a schematic diagram of the structure of a judicial evidence association relationship building device provided by an embodiment of the present invention, such as Figure 6 As shown, the judicial evidence association relationship building device may include the above Figure 5 Optionally, the judicial evidence association relationship construction device 610 may include a first processor 2001 .

[0074] Optionally, the judicial evidence association relationship construction device 610 may also include a memory 2002 and a transceiver 2003 .

[0075] The first processor 2001, the memory 2002 and the transceiver 2003 may be connected via a communication bus.

[0076] Combine the following Figure 6 The components of the judicial evidence association relationship building device 610 are specifically introduced as follows: The first processor 2001 is the control center of the judicial evidence association relationship construction device 610, which can be a processor or a general term for multiple processing elements. For example, the first processor 2001 is one or more central processing units (CPUs), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (field programmable gate arrays, FPGAs).

[0077] Optionally, the first processor 2001 can perform various functions of the judicial evidence association relationship construction device 610 by running or executing a software program stored in the memory 2002 and calling data stored in the memory 2002.

[0078] In a specific implementation, as an embodiment, the first processor 2001 may include one or more CPUs, such as Figure 6 CPU0 and CPU1 are shown in FIG.

[0079] In a specific implementation, as an embodiment, the judicial evidence association relationship building device 610 may also include multiple processors, such as Figure 6 The first processor 2001 and the second processor 2004 are shown in FIG. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0080] The memory 2002 is used to store the software program for executing the solution of the present invention, and is controlled to be executed by the first processor 2001. The specific implementation method can refer to the above method embodiment, which will not be repeated here.

[0081] Optionally, the memory 2002 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2002 may be integrated with the first processor 2001, or may exist independently, and may be connected to the first processor 2001 through the interface circuit ( Figure 6 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0082] The transceiver 2003 is used to communicate with a network device or a terminal device.

[0083] Optionally, the transceiver 2003 may include a receiver and a transmitter ( Figure 6 The receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0084] Optionally, the transceiver 2003 may be integrated with the first processor 2001, or may exist independently, and construct an interface circuit ( Figure 6 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0085] It should be noted that Figure 6 The structure of the judicial evidence association relationship building device 610 shown in the figure does not constitute a limitation on the router. The actual knowledge structure recognition device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0086] In addition, the technical effects of the judicial evidence association relationship construction device 610 can refer to the technical effects of the judicial evidence association relationship construction method described in the above method embodiment, and will not be repeated here.

[0087] It should be understood that the first processor 2001 in the embodiment of the present invention may be a central processing unit (CPU), and the processor may 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 gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0088] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0089] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part 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 process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). 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 or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0090] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0091] In the present invention, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0092] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0093] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0094] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0095] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0096] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0097] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0098] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0099] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for constructing judicial evidence association relationships, characterized in that: The method comprises: S1. Extract the facts to be proved in any case and the event element entities in the evidence respectively; S2. According to the event element entities in the facts to be proved and the evidence, count the event sets in which each event element entity in the facts to be proved and the evidence appears respectively; S3, according to the event set in which each event element entity appears and the preset support threshold, respectively obtain the frequent item set of the fact to be proved and the frequent item set of the evidence; S4, taking any one or more event element entities in any frequent item set of the fact to be proved as antecedents, taking the remaining event element entities in the frequent item set as consequents, obtaining all association rules of the frequent item set, and further obtaining all association rules of the fact to be proved; S5, taking any one or more event element entities in any frequent item set of the evidence as antecedents, taking the remaining event element entities in the frequent item set as consequents, obtaining all association rules of the frequent item set, and then obtaining all association rules of the evidence; S6. Filter all association rules of the facts to be proved by using a preset screening rule to obtain an association relationship set of the facts to be proved, and filter all association rules of the evidence by using a preset screening rule to obtain an evidence association relationship set; S7. Construct an evidence-fact-to-be-proved association relationship set based on the association relationship set of the facts to be proved and the evidence association relationship set.

2. The method for constructing judicial evidence association relationships according to claim 1, characterized in that: The S3 obtains the frequent item sets of the facts to be proved and the frequent item sets of the evidence respectively according to the event set in which each event element entity appears and the preset support threshold, including: Obtain each event element entity in the facts to be proved and the evidence respectively, and use each event element entity to form a set with only one element as the 1-item set of the facts to be proved and the evidence respectively; All 1-item sets are screened by a preset support threshold, and 1-item sets with a support greater than the preset threshold are regarded as frequent 1-item sets; Merge the frequent 1-itemsets of the facts and evidence to be proved in pairs to obtain the 2-itemsets of the facts and evidence to be proved respectively, wherein the event set in the 2-itemsets is the common event of the two merged frequent 1-itemsets; obtain the support of each 2-itemset of the facts and evidence to be proved respectively, and filter all the 2-itemsets by a preset support threshold, and take the 2-itemsets with a support greater than the preset support threshold as frequent 2-itemsets; Repeat the merging process of frequent item sets, and increase the number of event element entity items of the new item set generated by each merging by 1 until no new frequent item sets can be generated, and take all frequent k-itemsets generated by the facts and evidences to be proved in the merging process as the frequent item sets of the facts and evidences to be proved; The acquisition of the support includes: dividing the number of events in the event set corresponding to any item set in the fact or evidence to be proved by the total number of events of the fact or evidence to be proved, so as to obtain the support of the item set of the fact or evidence to be proved.

3. The method for constructing judicial evidence association relationships according to claim 1, characterized in that: The step S6 filters all association rules of the facts to be proved by using a preset screening rule to obtain an association relationship set of the facts to be proved, and filters all association rules of the evidence by using a preset screening rule to obtain an evidence association relationship set, including: S61, obtaining the confidence, certainty, lift and leverage of each association rule of the fact to be proved, screening each association rule according to the confidence, certainty, lift and leverage of each association rule of the fact to be proved, and using the screened association rules as the association relationship set of the fact to be proved; S62, obtaining the confidence, certainty, lift and leverage of each association rule of the evidence, screening each association rule according to the confidence, certainty, lift and leverage of each association rule of the evidence, and using the screened association rules as the evidence association relationship set.

4. The method for constructing judicial evidence association relationships according to claim 3, characterized in that: The step S61 of obtaining the confidence, certainty, lift and leverage of each association rule of the fact to be proved, screening each association rule according to the confidence, certainty, lift and leverage of each association rule of the fact to be proved, and using the screened association rules as the association relationship set of the fact to be proved includes: Respectively set a first confidence threshold, a first certainty threshold, a first lift threshold, and a first leverage threshold of the fact to be proved; Acquire a first association rule whose confidence is greater than a first confidence threshold and whose certainty is greater than the first certainty threshold; In the first association rule, a second association rule whose lift is greater than the first lift threshold is obtained; In the second association rule, a third association rule is obtained in which the leverage ratio is greater than the first leverage ratio threshold; The third association rule of the facts to be proved is used as the association relationship set of the facts to be proved; The step S62 of obtaining the confidence, certainty, lift and leverage of each association rule of the evidence, screening each association rule according to the confidence, certainty, lift and leverage of each association rule of the evidence, and using the screened association rules as an evidence association relationship set includes: respectively setting a second confidence threshold, a second certainty threshold, a second lift threshold, and a second leverage threshold of the evidence; Acquire a fourth association rule of evidence whose confidence is greater than a second confidence threshold of the evidence and whose certainty is greater than the second certainty threshold; In the fourth association rule, a fifth association rule whose lift is greater than a second lift threshold is obtained; In the fifth association rule, a sixth association rule is obtained in which the leverage ratio is greater than a second leverage ratio threshold; The sixth association rule of evidence is taken as the evidence association relationship set.

5. The method for constructing judicial evidence association relationships according to claim 1, characterized in that: The step S7 constructs an evidence-fact-to-be-proved association relationship set based on the to-be-proved fact association relationship set and the evidence association relationship set, including: Obtaining association rules contained in both the association relationship set of facts to be proved and the association relationship set of evidence; The association rules contained in both the association relationship set of the facts to be proved and the evidence association relationship set are used as the evidence-fact association relationship set.

6. The method for constructing judicial evidence association relationships according to claim 1, characterized in that: The step S7 constructs an evidence-fact-to-be-proved association relationship set based on the to-be-proved fact association relationship set and the evidence association relationship set, including: If any association rule in the association relationship set of the facts to be proved and any association rule in the evidence association relationship set have an intersection in their antecedents and an intersection in their consequents, then any association rule in the association relationship set of the facts to be proved and any association rule in the evidence association relationship set are both used as candidate evidence-fact association rules; The candidate evidence-to-be-proven fact association rules are screened by using preset rules, and the screened candidate evidence-to-be-proven fact association rules are used as the evidence-to-be-proven fact association relationship set.

7. The method for constructing judicial evidence association relationships according to claim 6, characterized in that: The candidate evidence-to-be-proven fact association rules are screened by using preset rules, and the screened candidate evidence-to-be-proven fact association rules are used as the evidence-to-be-proven fact association relationship set, including: Obtain the confidence, certainty, lift and leverage of each candidate evidence-fact association rule respectively; respectively setting a third confidence threshold, a third certainty threshold, a third lift threshold, and a third leverage ratio threshold; Acquire a first evidence-to-be-proven fact association rule whose confidence level is greater than a third confidence level threshold and whose certainty level is greater than the third certainty level threshold; In the first evidence-to-be-proven fact association rule, obtaining a second evidence-to-be-proven fact association rule whose lift is greater than a third lift threshold; In the second evidence-to-be-proven fact association rule, a fourth evidence-to-be-proven fact association rule is obtained, in which the leverage ratio is greater than a third leverage ratio threshold; The fourth evidence-fact-to-be-proven association rule is used as the evidence-fact-to-be-proven association relationship set.

8. The method for constructing judicial evidence association relationships according to claim 1, characterized in that: After constructing the evidence-fact-to-be-proved association relationship set according to the to-be-proved fact association relationship set and the evidence association relationship set in S7, the method further includes: A case association graph is constructed based on the set of association relationships of facts to be proved, the set of association relationships of evidence, and the set of association relationships between evidence and facts to be proved.

9. A judicial evidence association relationship construction device, the judicial evidence association relationship construction device is used to implement the judicial evidence association relationship construction method according to any one of claims 1 to 8, characterized in that: The device comprises: The element entity extraction module is used to extract the facts to be proved in any case and the event element entities in the evidence respectively; An event set acquisition module is used to count the event sets in which each event element entity in the facts to be proved and the evidence appears, according to the event element entities in the facts to be proved and the evidence; A frequent item set acquisition module is used to acquire the frequent item sets of the facts to be proved and the frequent item sets of the evidence respectively according to the event set in which each event element entity appears and the preset support threshold; A first association rule acquisition module is used to take any one or more event element entities in any frequent item set of the fact to be proved as antecedents, take the remaining event element entities in the frequent item set as consequents, acquire all association rules of the frequent item set, and further obtain all association rules of the fact to be proved; The second association rule acquisition module is used to take any one or more event element entities in any frequent item set of the evidence as antecedents, take the remaining event element entities in the frequent item set as consequents, acquire all association rules of the frequent item set, and thus obtain all association rules of the evidence; A first association relationship acquisition module is used to filter all association rules of the facts to be proved by using a preset filtering rule to obtain an association relationship set of the facts to be proved, and to filter all association rules of the evidence by using a preset filtering rule to obtain an evidence association relationship set; The second association relationship acquisition module is used to construct an evidence-fact-to-be-proved association relationship set based on the association relationship set of the facts to be proved 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 called by a processor to execute the method according to any one of claims 1 to 8.

Images