Intelligent Matching Method and System for Judicial Provisions Based on Natural Language Processing

Abstract

The present invention relates to the technical field of data processing. More specifically, the present invention relates to an intelligent matching method and system for judicial provisions based on natural language processing, including: extracting effective sentences in any judgment text, calculating the relevance between each effective sentence and a crime name according to the frequency of occurrence of the effective sentence in the judgment text, and constructing a text library, where the text library includes judgment texts, effective sentences, and crime names. The present invention can timely delete outdated judgment texts and construct the latest text library by calculating an update coefficient and determining an update node, can adapt to legal changes (such as the promulgation of an amended law or the emergence of new case precedents), avoid the problem of inaccurate crime name recommendations caused by changes in legal bases, thereby ensuring the timeliness of the recommendation results, and obtaining the crime name recommendation index of all crime names in the judgment text according to the latest text library, adapt to the rapidly changing legal environment, and achieve accurate matching between the factual content in the judgment document and the corresponding crime names.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing. More specifically, the present invention relates to an intelligent matching method and system for judicial provisions based on natural language processing. Background Art

[0002] With the development of society and the continuous improvement of the legal system, the complexity and quantity of judicial provisions have increased significantly. The fields covered by the law are becoming increasingly extensive, involving multiple aspects such as civil, criminal, and administrative, and the content of the provisions is gradually refined and intertwined. At the same time, the continuous introduction of case laws, judicial interpretations, and amended laws has further enriched the connotation of the legal system. In this context, judicial staff face greater challenges in case handling and need to quickly and accurately match applicable legal bases from a vast number of provisions to support the legality and rationality of judgments. Traditional matching methods are no longer fully able to meet the requirements of such complexity and dynamics. To improve judicial efficiency and ensure the quality of judgments, intelligent matching methods based on natural language processing technology have gradually attracted attention. Such methods can more efficiently assist judicial staff in completing the provision matching task by deeply analyzing text semantics and combining the professional characteristics of the legal field, promoting the modernization and intelligent development of judicial work.

[0003] As the legal provisions and case laws are updated, the relevance between words and charges changes, and existing methods lack the ability to adjust dynamically. With the promulgation of new laws, amendments, or judicial interpretations, the definitions and applicable conditions of charges will be continuously adjusted. For example, after a certain provision is updated, "malice" may be added as a new element of the "crime of fraud", but matching methods based on historical data or fixed dictionaries cannot reflect this change in a timely manner. This may cause the recommended provisions to be out of touch with current judicial practice, reducing the timeliness and reliability of the matching results. Summary of the Invention

[0004] The present invention provides an intelligent matching method and system for judicial provisions based on natural language processing, aiming to solve the problem that matching methods based on historical data or fixed dictionaries in related technologies cannot reflect this change in a timely manner. This may cause the recommended provisions to be out of touch with current judicial practice, reducing the timeliness and reliability of the matching results.

[0005] In a first aspect, the present invention provides an intelligent matching method for judicial provisions based on natural language processing, including: extracting valid words and sentences from any judgment text, calculating the relevance between each valid word and sentence and the crime name according to the frequency of occurrence of the valid word and sentence in the judgment text, and constructing a text library, where the text library includes judgment texts, valid words and sentences, and crime names; sorting in descending order according to the level of relevance between each valid word and sentence and the crime name to obtain a sequence of words and sentences for the crime name, dichotomizing the relevance between all valid words and sentences and the crime name in the sequence of words and sentences for the crime name, and taking the category with a larger average relevance as the sequence of valid words and sentences for the crime name; calculating an update coefficient for the sequence of valid words and sentences for the crime name, where the update coefficient is positively correlated with the difference value between the sequence of valid words and sentences for the current node crime name and the sequences of valid words and sentences for the crime names of each historical node; if the update coefficient is greater than the update threshold, determining an update node, deleting the judgment text corresponding to the crime name before the update node in the text library, and constructing a latest text library; calculating a recommendation index for each crime name corresponding to the judgment text based on the latest text library to complete the intelligent matching of the judgment text and the crime name, where the recommendation index is positively correlated with the relevance between all valid words and sentences in the judgment text and the crime name. Through this method, the relevant degree between words and sentences and the crime name can be accurately captured, and the interference of irrelevant words and sentences can be avoided, thereby significantly improving the accuracy of crime name recommendation. In addition, through a dynamic update mechanism, an update coefficient is calculated to monitor the change of the sequence of valid words and sentences, and the outdated judgment text is deleted when the update coefficient exceeds the threshold, ensuring that the recommendation model is always based on the latest legal basis and sentencing criteria, and further reducing the possibility of misjudgment.

[0006] Further, calculating the recommendation index for each crime name corresponding to the judgment text includes: the recommendation index is also positively correlated with the probability that the judgment text is the crime name when all valid words and sentences of the crime name appear. Through this method, the actual application frequency of the crime name in similar situations is reflected. The higher the probability, the more frequently the crime name is adopted, and the higher the recommendation index of the crime name.

[0007] Further, obtaining the sequence of valid words and sentences for the crime name includes: dichotomizing the relevance between all valid words and sentences and the crime name in the sequence of words and sentences for the crime name, taking the group with a larger average relevance as the valid related words, and taking the group with a smaller average relevance as the invalid related words; deleting the invalid related words, retaining the valid related words, and constructing the sequence of words and sentences corresponding to the valid related words as the sequence of valid words and sentences for the crime name. By dichotomizing the sequence of words and sentences and distinguishing valid related words and invalid related words based on the average value, this method can screen out the words and sentences with stronger relevance to the crime name.

[0008] Further, calculating the update coefficient of the effective phrase sequence of the charge includes: determining the weight coefficient corresponding to each historical node, and weighting the difference value between the effective phrase sequence of the charge at the current node and the effective phrase sequence of the charge at each historical node by using the weight coefficient corresponding to each historical node, so as to obtain the update coefficient of the effective phrase sequence of the charge. The calculation of the update coefficient comprehensively considers the differences between the current node and multiple historical nodes, and performs weighted adjustment through the weight coefficient, so that the update coefficient can more accurately reflect the change degree of the effective phrase sequence of the charge.

[0009] Further, the determination method of each historical node includes: setting the current day as the current node, and taking each month before the current node as a historical node to obtain multiple historical nodes.

[0010] Further, determining the update node, where the update node is the Nth day before the current node.

[0011] Further, determining the weight coefficient corresponding to each historical node includes: calculating the weight coefficient corresponding to each historical node based on the time distance between the current node and each historical node, where the weight coefficient is inversely correlated with the time distance of the historical node. The inverse correlation between the weight coefficient and the time distance means that the weight of the farther historical node is smaller, thereby reducing the interference of outdated data on the overall calculation.

[0012] Further, binary-classifying the phrase sequence of the charge includes: using the Otsu threshold method to perform binary classification on the relevance between all effective phrases in the phrase sequence of the charge and the charge.

[0013] Further, the empirical value of the update threshold is 0.7.

[0014] In the second aspect of the present invention, there is also provided an intelligent matching system for judicial provisions based on natural language processing, including a processor and a memory, where the memory stores a computer program, and the processor executes the computer program to implement the intelligent matching method for judicial provisions based on natural language processing described in any one of the above.

[0015] Beneficial effects: By calculating the update coefficient and determining the update node, outdated judgment texts are deleted in a timely manner and the latest text library is constructed, which can adapt to legal changes (such as the promulgation of amended laws or the emergence of new precedents), avoid inaccurate charge recommendations caused by changes in legal bases, thereby ensuring the timeliness of the recommendation results, and obtaining the charge recommendation index of all charges in the judgment text according to the latest text library, adapting to the rapidly changing legal environment, and realizing the accurate matching of the factual content in the judgment document with the corresponding charges. Description of the Drawings

[0016] Figure 1It is a flowchart schematically showing the calculation of the recommended index of crime names according to an embodiment of the present invention. Detailed implementation manners

[0017] The following will describe in detail the specific implementation manners of the present invention in conjunction with the accompanying drawings.

[0018] S101: Obtain the judgment text.

[0019] In one embodiment, the judgment text can be obtained from an existing judgment text library, and the text of the factual content and the corresponding crime names in the judgment text are collected, and the text of the factual content and the corresponding crime names in the judgment text will change as the judgment text library is updated.

[0020] S102: Extract the effective words and sentences from the judgment text.

[0021] In one embodiment, for any judgment text, the effective words and sentences in the judgment text need to be extracted. Specifically, for each sentence in the judgment text, auxiliary words, conjunctions, and prepositions need to be deleted. When deleting words and sentences, the stop word list can be referred to or word segmentation can be performed using a special dictionary in the judicial field (THULAC + custom legal dictionary), and the effective words and sentences of all judgment texts are extracted to construct a text library, where the text library contains judgment texts, effective words and sentences, and crime names.

[0022] Exemplarily, the crime name of the judgment text is the crime of violent injury, and the judgment text contains "Defendant Zhang San intentionally used violence to injure another person's body in 2023, resulting in minor injuries to the victim". After removing auxiliary words, conjunctions, and prepositions, the effective words and sentences obtained are: "intentionally, violence, injury, body, minor injuries".

[0023] S103: Calculate the relevance between each effective word and sentence and the crime name.

[0024] In one embodiment, since a judgment text may correspond to multiple crime names, and using a single effective word and sentence in the judgment text cannot accurately determine a single crime name, multiple effective words and sentences are needed to determine a crime name. Therefore, it is necessary to calculate the relevance between each effective word and sentence and the crime name.

[0025] In one embodiment, when calculating the relevance between each effective word and sentence and the crime name, the calculation formula is: , where is the relevance between the th effective word and sentence in the judgment text and the crime name , is the probability that the th effective word and sentence corresponding to the crime name appears in the th judgment text, is the number of judgment texts. is the The overall frequency of occurrence of a valid phrase in all judgment texts, expressing the generalized feature of the valid phrase. The larger this value is, that is, the stronger the independent connection between the valid phrase and the crime name, and the greater the relevance. It should be noted that obtaining the probability of the occurrence of the valid phrase corresponding to the crime name in the judgment text corresponding to the valid phrase , for example, the valid phrases are "violence" and "finance". In a judgment text, for the extracted valid phrases, there can be multiple and some valid phrases will appear repeatedly. For example: for a valid phrase of "violence" and "finance", after extracting the valid phrases from each paragraph in the judgment text, there may be multiple repeated valid phrases of "violence" and "finance". At this time, calculate the probability of the occurrence of the valid phrases of "violence" and "finance" in the judgment text among all the valid phrases. The greater the probability, the stronger the independent connection between the valid phrase and the crime name.

[0026] In another embodiment, another calculation formula for calculating the relevance between each valid phrase and the crime name is provided. This calculation formula not only considers the overall frequency of occurrence of the valid phrase in a single judgment text, but also considers the degree of concentration of the probability of the occurrence of the valid phrase and the crime name in all judgment texts. The greater the degree of concentration, the stronger the relevance. Therefore, the accuracy of calculating the relevance between the valid phrase and the crime name can be further improved. The calculation formula is: . In the formula, is the relevance between the th valid phrase in the judgment text and the crime name , is the probability of the occurrence of the th valid phrase corresponding to the crime name in the th judgment text, is the number of judgment texts, represents the number of valid phrases in the judgment text, represents the median function. is the th valid phrase and the crime name in the th text, and the degree of concentration of the probability. The larger this value is, the stronger the relevance between the th valid phrase and the crime name.

[0027] S104: Obtain the sequence of valid phrases for any crime name.

[0028] In one embodiment, a charge corresponds to multiple effective sentences. The relevance between each of the multiple effective sentences and the charge is obtained, and then they are sorted in descending order according to the level of relevance between each effective sentence and the charge, resulting in a sentence sequence for the charge. Binary classification is performed based on the relevance between all the effective sentences and the charge in the sentence sequence of the charge. The group with a larger average relevance is taken as the effective correlation words, and the group with a smaller average relevance is taken as the invalid correlation words. Then, the invalid correlation words are deleted, and the effective correlation words are retained. Finally, the sentence sequence corresponding to the effective correlation words is constructed into the effective sentence sequence for the charge. Among them, the Otsu threshold method is used for the binary classification of the sentence sequence of the charge. Thus, for any charge, the effective sentence sequence for the charge can be obtained.

[0029] S105: Determine whether to update the effective sentence sequence of the charge.

[0030] In one embodiment, as time goes by, the sentencing basis of the law may change. For example, the emergence of new Supreme Court judgments or the promulgation of amended laws will lead to changes in the existing sentencing basis, making the sentence recommendation in previous judgment texts inaccurate and greatly reducing the timeliness. Therefore, it is necessary to update the effective sentence sequence of the charge.

[0031] Specifically, an update coefficient is constructed to delete the previous judgment texts. That is, when there are significant changes in the effective sentence sequence corresponding to a charge in a short period of time, it indicates that there are significant changes between the existing judgment texts and the previous judgment texts. At this time, the original judgment texts for this charge should be deleted and the new texts should be retained to obtain a new effective sentence sequence.

[0032] In one embodiment, the update coefficient of the effective sentence sequence of the charge is calculated. The update coefficient is positively correlated with the difference value between the effective sentence sequence of the current node charge and the effective sentence sequences of the charges at each historical node. The determination method of each historical node includes: setting the current day as the current node, taking each month before the current node as a historical node, obtaining multiple historical nodes, and the number of historical nodes can be set artificially. For example, the number of historical nodes is 4. Then the update coefficient is calculated, and the calculation formula is: , where is the update coefficient, is the relevance between all the effective sentences and the charge in the effective sentence sequence of the current node charge, represents the relevance between all the effective sentences and the charge in the effective sentence sequence of the charge at the mth historical node, represents the number of historical nodes, represents the hyperbolic tangent function, represents the standard deviation function.

[0033] In another embodiment, another method is provided to calculate the update coefficient of the effective phrase sequence of a crime name. Specifically, when calculating the change differences between the effective phrase sequences of the crime names of each historical node and the effective phrase sequence of the current node crime name respectively, since the time distances between each historical node and the current node are different, weight coefficients corresponding to each historical node should be assigned according to the time distance between each historical node and the current node. The farther the historical node is from the current node, the smaller the weight parameter of that historical node, and the sum of the weight coefficients of each historical node is 1. The calculation formula is: , where is the update coefficient, is the relevance between all effective phrases in the effective phrase sequence of the current node crime name and the crime name, represents the relevance between all effective phrases in the effective phrase sequence of the crime name of the m-th historical node and the crime name, represents the number of historical nodes, represents the weight parameter of the m-th historical node, represents the hyperbolic tangent function. It should be noted that determining the weight parameter of the historical node through the distance between the historical node and the current node reflects the characteristics that recent data is more time-sensitive and relevant in judicial practice. For example, the judgment texts of the most recent month may better reflect the current legal trends and sentencing bases and require a larger weight, while the data from a year ago may lose some reference value due to legal amendments or changes in case laws and require a smaller weight. In one embodiment, the number of historical nodes is 4, and the weights of the 4 nodes from the current node in order of proximity are 0.4, 0.3, 0.2, and 0.1. This way of weight allocation ensures that the system pays more attention to the latest data, thereby improving the timeliness and practicality of the analysis results.

[0034] According to the above steps, because the legal environment is dynamic, for example, the introduction of new case laws, amended laws, or judicial interpretations may lead to changes in the phrases related to crime names. In the embodiment, through the weighted calculation of the difference values, these changes can be detected sensitively. For example, if the effective phrases of "crime of intentional injury" change from "injure" "body" to "violence" "minor injury", the difference value will increase significantly, and the update coefficient will increase accordingly, prompting the system to update. This adaptability enables the system to cope with the evolution of legal practice and maintain long-term effectiveness.

[0035] It should be noted that according to the above two embodiments, the update coefficient of the effective phrase sequence of the crime name can be calculated. Choose any one of the embodiments to calculate the update coefficient of the effective phrase sequence of the crime name. When the update coefficient is greater than the update threshold, it is determined that the effective phrase sequence of the crime name needs to be updated. Among them, the empirical value of the update threshold is 0.6. In other embodiments, the empirical value of the update threshold can be 0.7 or 0.62, etc., and can be adjusted according to the specific implementation situation.

[0036] S106: Determine the update node and construct the latest text library.

[0037] In one embodiment, the update node can be set artificially. For example, when the update coefficient of the effective sentence sequence of the current node's charge is greater than the update threshold, it is determined that the effective sentence sequence of the charge needs to be updated. The Nth day before the current node is used as the update node, and the judgment texts corresponding to this charge before the update node in the text library are deleted, and the latest text library is constructed. Among them, the Nth day can be the day when the amended law is promulgated.

[0038] In one embodiment, after the amended law is promulgated, each region may not fully implement the amended law after promulgation, and the implementation standards of each region are also different. Therefore, it is necessary to obtain the update node more accurately. Specifically, calculate the update degree of each day. Taking the Bth day as an example, first calculate the standard deviation of the difference between the relevance of all effective sentences in the effective sentence sequence of the charge on the Bth day in the text library and the relevance of all effective sentences in the effective sentence sequence of the charge on the (B - 1)th day. The value after normalizing the standard deviation is used as the update degree of the Bth day. Then, traverse the update degree of each day before the current node in chronological order. If there is a day when the update degree is greater than the update threshold, that day is used as the update node, and the judgment texts corresponding to this charge before the update node in the text library are deleted, and the remaining judgment texts are constructed into the latest text library.

[0039] By adopting the above steps, by calculating the update coefficient and determining the update node, the outdated judgment texts are timely deleted and the latest text library is constructed, which can adapt to legal changes (such as the promulgation of the amended law or the emergence of new precedents), avoid the problem of inaccurate charge recommendation caused by the change of legal basis, and thus ensure the timeliness of the recommendation result.

[0040] S107: Calculate the recommendation index of each charge corresponding to the judgment text according to the latest text library.

[0041] In one embodiment, the recommendation index of each charge is positively correlated with the relevance of all effective sentences in the judgment text to this charge. Taking any charge in any judgment text as an example, calculate the recommendation index of this charge. The calculation formula is: , is the relevance of the rd effective sentence in the judgment text to the charge , is the recommendation index of the charge, is the number of effective sentences in the judgment text.

[0042] In another embodiment, a calculation method for calculating the recommendation index of a charge is also provided. The calculation formula is: , For the relevance between the th valid sentence and the charge in the judgment text, the recommended index of the charge, the number of valid sentences in the judgment text, and the probability that other judgment texts are also the same charge when all valid sentences of this charge appear.

[0043] Thus, the charge recommendation coefficient of any charge corresponding to each judgment text can be obtained. By traversing all charges in the judgment text, the charge recommendation coefficients of all charges corresponding to the judgment text can be obtained. Thus, by inputting a text, the charge recommendation coefficient of this text can be obtained, and the charge with the highest charge recommendation coefficient is used as the reference charge for the staff for this text to assist the staff in judicial article matching.

[0044] The present invention also provides a judicial article intelligent matching system based on natural language processing. The system includes a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, it realizes a judicial article intelligent matching method according to the first aspect of the present invention.

[0045] The system also includes other components well-known to those skilled in the art such as a communication bus and a communication interface. Their settings and functions are known in the art, so they will not be described in detail here.

[0046] In the present invention, the aforementioned memory may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, the computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory (RRAM), a dynamic random access memory (DRAM), a static random access memory (SRAM), an enhanced dynamic random access memory (EDRAM), a high-bandwidth memory (HBM), a hybrid memory cube (HMC), etc., or any other medium that can be used to store the required information and can be accessed by an application program, a module, or both. Any such computer storage medium may be part of the device or accessible or connectable to the device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions stored or otherwise held by such a computer-readable medium.

[0047] The above-described embodiments merely represent several implementation manners of the present invention. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all fall within the protection scope of the present invention.

Claims

1. An intelligent matching method for judicial provisions based on natural language processing, characterized in that, Including: Extracting the effective sentences in any judgment text; calculating the relevance between each effective sentence and the crime according to the frequency of the appearance of the effective sentence in the judgment text, and the formula is: , is the relevance between the th valid sentence and the crime ; is the th probability of the crime corresponding to the th occurrence of the valid sentence; is the number of judgment texts, represents the number of valid sentences in the judgment text, represents the median function; Constructing a text library, where the text library includes judgment texts, effective sentences and crimes; Sorting in descending order according to the level of relevance between each effective sentence and the crime to obtain the sentence sequence of the crime, classifying the relevance between all effective sentences and the crime in the sentence sequence of the crime into two categories, and taking the category with a larger average relevance as the effective sentence sequence of the crime; Calculating the update coefficient of the effective sentence sequence of the crime, including: determining the weight coefficient corresponding to each historical node, specifically: based on the time distance between the current node and each historical node, calculating the weight coefficient corresponding to each historical node, and the weight coefficient is inversely related to the time distance of the historical node; using the weight coefficient corresponding to each historical node to weight the difference value between the effective sentence sequence of the crime at the current node and the effective sentence sequence of the crime at each historical node to obtain the update coefficient of the effective sentence sequence of the crime; The update coefficient is positively correlated with the difference value between the effective sentence sequence of the crime at the current node and the effective sentence sequence of the crime at each historical node; if the update coefficient is greater than the update threshold, determining the update node, deleting the judgment text corresponding to the crime before the update node in the text library, and constructing the latest text library; Calculating the recommendation index of each crime corresponding to the judgment text according to the latest text library to complete the intelligent matching of the judgment text and the crime, and the recommendation index is positively correlated with the relevance between all effective sentences in the judgment text and the crime.

2. The intelligent matching method for judicial provisions based on natural language processing according to claim 1, wherein, Calculating the recommendation index of each crime corresponding to the judgment text, including: The recommendation index is also positively correlated with the probability that the judgment text is the crime when all effective sentences of the crime appear.

3. The intelligent matching method of judicial provisions based on natural language processing according to claim 1, characterized in that Obtaining the effective sentence sequence of the crime, including: Classifying the relevance between all effective sentences and the crime in the sentence sequence of the crime into two categories, and taking the group with a larger average relevance as the effective correlation words, and the group with a smaller average relevance as the invalid correlation words; Deleting the invalid correlation words, retaining the effective correlation words, and constructing the sentence sequence corresponding to the effective correlation words into the effective sentence sequence of the crime.

4. The intelligent matching method for judicial provisions based on natural language processing according to claim 2, wherein The determination method of each historical node, including: Setting the current day as the current node, and taking each month before the current node as a historical node to obtain multiple historical nodes.

5. The intelligent matching method for judicial provisions based on natural language processing according to claim 1, wherein Determining the update node, where the update node is the Nth day before the current node.

6. The intelligent matching method for judicial provisions based on natural language processing according to claim 1, characterized in that, Classifying the sentence sequence of the crime, including: Using the Otsu threshold method to classify the relevance between all effective sentences and the crime in the sentence sequence of the crime into two categories.

7. The intelligent matching method of judicial provisions based on natural language processing according to claim 1, characterized in that The empirical value of the update threshold is 0.

7.

8. An intelligent judicial provision matching system based on natural language processing, comprising a processor and a memory, characterized in that, The memory stores a computer program, and the processor executes the computer program to implement the intelligent matching method of judicial provisions based on natural language processing according to any one of claims 1-7.

Images