A method and system for predicting civil judgment results based on thought chain

Abstract

This invention discloses a method and system for predicting civil adjudication outcomes based on thought chaining, belonging to the field of natural language processing technology. This invention aims to utilize thought chaining technology to fully utilize the information between case facts and the plaintiff's claims and defendant's defenses. Starting from the claim of rights and using the analysis of the constituent elements of substantive legal norms as the basic means, this method disassembles the legal logic of civil trials. Through a series of logically related thinking, a complete civil case trial process is formed. This method effectively addresses the challenges posed by the diversity and complexity of civil cases, ensuring that the prediction of civil adjudication outcomes achieves a higher level of accuracy and logical rigor.

Description

Technical Field

[0001] The present invention relates to the field of natural language processing technology, and more specifically, to a method and system for predicting civil judgment results based on thought chains. Background Art

[0002] The core goal of applying artificial intelligence and big data technologies in the judicial field is to comprehensively improve the efficiency and transparency of judicial work with the help of advanced intelligent technologies.

[0003] In the legal field, delivering professional legal decisions is a crucial component of legal practice. Civil cases often involve a variety of legal relationships, such as contracts, torts, and property rights. Each relationship has its own unique legal provisions and adjudication rules, making the automated prediction of legal decisions more complex. Currently, there are two main approaches for predicting civil adjudication outcomes: one is based on mathematical, statistical algorithms, and machine learning. These methods construct tailored legal models based on legal knowledge and case characteristics. These methods require high data accuracy and completeness and are often only applicable to specific legal scenarios. When faced with new and complex cases, these methods lack the legal logic and reasoning mechanisms to generalize. The other is based on historical case prediction. This method analyzes the outcomes of similar cases to predict the likely outcome of the current case. This method relies on the collection, organization, and analysis of a large number of historical cases to identify similarities and patterns between cases. However, civil adjudication cannot rely solely on empirical data, and its legitimacy should not be based solely on the patterns of past cases. Summary of the Invention

[0004] To overcome these issues, the present invention provides a method for predicting civil adjudication outcomes based on thought chaining. This method aims to utilize thought chaining technology, fully utilizing the facts of the case and the information between the plaintiff's claims and the defendant's defenses. Starting from the claim of rights and using the analysis of the constituent elements of substantive legal norms as the fundamental means, this method deconstructs the legal logic of civil trials. Through a series of logically related considerations, a complete civil case trial process is formed. This method effectively addresses the challenges posed by the diversity and complexity of civil cases, ensuring that the prediction of civil adjudication outcomes achieves a higher level of accuracy and logical rigor.

[0005] To achieve the above objectives, the technical solution of the present invention includes the following contents.

[0006] A method for predicting civil judgment results based on thought chain, the method comprising:

[0007] Obtaining input information and extracting case elements from the input information; wherein the input information includes: claims, defenses, and case facts;

[0008] Search the knowledge base based on the input information and case elements to obtain historical cases and relevant laws and regulations similar to the input information;

[0009] Combine the claim and case elements to build the first chain of thought for the purpose of fixing the claim and specifying the rights, call the big model, and obtain the rights;

[0010] Combining the claims, defenses, case elements, rights requests, historical cases similar to the input information, and relevant laws and regulations, a second thinking chain is constructed to screen the basic norms for rights requests and defense rights. The large model is then invoked to obtain the basic norms for rights requests, defense rights, and defense claims and reasons.

[0011] Combining the basic norms of rights claims and the basic norms of defense rights, a third thinking chain is constructed with the purpose of decomposing the constituent elements of the basic norms. The large model is called to obtain the constituent elements of the basic norms of rights claims and the constituent elements of the basic norms of defense rights;

[0012] Combining the claims, defense claims and reasons, the basic normative elements of the claims and the basic normative elements of the defense, a fourth chain of thought is constructed to generate the controversial focus of the case, and the grand model is used to obtain the controversial focus of the case.

[0013] Combining the case elements, historical cases similar to the input information, rights claims, defense claims and reasons, basic norms for rights claims, basic norms for right of defense, constituent elements of basic norms for rights claims and constituent elements of basic norms for right of defense, and the controversial focus of the case, a fifth thinking chain is constructed for the purpose of classifying the elements and generating the judgment results, and the big model is called to obtain the civil judgment prediction results of the input information; wherein, the civil judgment prediction results include: the content of the judgment reasoning and the content of the judgment conclusion.

[0014] Furthermore, extracting case elements from the input information includes:

[0015] Extract litigation requests based on the claims;

[0016] Extract defense opinions based on the arguments;

[0017] Extract events based on claims, defenses, and case facts;

[0018] Extract key information based on claims, defenses and case facts.

[0019] Furthermore, the key information includes: civil behavior, right holder, liability holder, payment type, amount, quantity, performance subject, performance content and performance method.

[0020] Furthermore, the knowledge base includes: a civil case cognition knowledge base, the civil case cognition knowledge base consisting of a first plaintext portion and a first vector portion, the first plaintext portion including a historical civil case and a summary, case characteristics, and legal content of the historical civil case, and the first vector portion generated based on semantic information of the historical civil case;

[0021] Based on the input information and case elements, a civil case cognition knowledge base is searched to obtain historical cases similar to the input information, including:

[0022] Based on the input information, generate a vector representation of the input information, and obtain a first matching result based on the input information and its vector representation, and combining the first plaintext portion and the first vector portion;

[0023] Based on the case elements, a vector representation of the case elements is generated, and based on the case elements and the vector representation, a second matching result is obtained by combining the first plaintext portion and the first vector portion;

[0024] Based on the first matching result and the second matching result, historical cases similar to the input information are obtained.

[0025] Furthermore, the knowledge base includes: a civil laws and regulations knowledge base, the civil laws and regulations knowledge base consisting of a second plaintext portion and a second vector portion, the second plaintext portion including: the plaintext portion including civil laws and regulations, judicial interpretations, and feature tags and topics of the civil laws and regulations and judicial interpretations, and the second vector portion generated based on semantic information of the civil laws and regulations and the judicial interpretations;

[0026] Search the civil laws and regulations knowledge base based on the input information and case elements to obtain the legal and regulatory provisions related to the input information, including:

[0027] Based on the input information, generate a vector representation of the input information, and obtain a third matching result based on the input information and its vector representation, and in combination with the second plaintext portion and the second vector portion;

[0028] Based on the case elements, a vector representation of the case elements is generated, and based on the case elements and their vector representations, a fourth matching result is obtained by combining the second plaintext portion and the second vector portion;

[0029] Based on the third matching result and the fourth matching result, legal and regulatory provisions related to the input information are obtained.

[0030] Furthermore, the first chain of thought, the second chain of thought, the third chain of thought, the fourth chain of thought and the fifth chain of thought also include: detailed reference content that is helpful in completing the corresponding task objectives.

[0031] Furthermore, the training process of the large model includes:

[0032] Construct training datasets based on data from general and judicial fields;

[0033] The LoRA fine-tuning method is used to fine-tune the large model on the training data.

[0034] A civil judgment result prediction system based on thought chain, the system comprising:

[0035] An information acquisition module is used to acquire input information and extract case elements from the input information; wherein the input information includes: claims, defenses and case facts;

[0036] The knowledge retrieval module is used to search the knowledge base based on the input information and case elements to obtain historical cases and relevant laws and regulations similar to the input information;

[0037] The rights claim generation module is used to combine the claim and case elements to construct the first thought chain for the purpose of fixing the claim and specifying the rights claim, and then call the large model to obtain the rights claim;

[0038] The basic norms generation module is used to combine the claims, defenses, case elements, rights requests, historical cases similar to the input information, and relevant laws and regulations to construct a second thinking chain for the purpose of screening the basic norms of rights requests and defense rights. It then calls the large model to obtain the basic norms of rights requests, defense rights, and defense claims and reasons.

[0039] The basic norms constituent elements generation module is used to combine the basic norms of the claim and the basic norms of the defense, build a third thinking chain for the purpose of decomposing the basic norms constituent elements, call the large model, and obtain the basic norms constituent elements of the claim and the basic norms constituent elements of the defense;

[0040] The module for generating the focus of dispute in a case is used to combine the claim, the claims and reasons for the defense, the constituent elements of the basic rules of the claim, and the constituent elements of the basic rules of the defense to construct a fourth chain of thought for the purpose of generating the focus of dispute in the case, and then call the large model to obtain the focus of dispute in the case;

[0041] The judgment result prediction module is used to combine the case elements, historical cases similar to the input information, rights claims, defense claims and reasons, basic norms for rights claims, basic norms for rights defenses, constituent elements of basic norms for rights claims and constituent elements of basic norms for rights defenses, and the focus of the case, to construct a fifth thinking chain for the purpose of classifying elements and generating judgment results, call the big model, and obtain the civil judgment prediction results of the input information; wherein, the civil judgment prediction results include: the content of the judgment reasoning and the content of the judgment conclusion.

[0042] An electronic device comprising: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, it implements any of the above-mentioned methods for predicting civil judgment results based on thought chains.

[0043] A computer-readable storage medium, characterized in that computer program instructions are stored on the computer-readable storage medium, and when the computer program instructions are executed by a processor, any of the above-mentioned civil judgment result prediction methods based on thought chain is implemented.

[0044] Compared with the prior art, the present invention has at least the following beneficial effects.

[0045] This invention utilizes thought chaining technology to break down and reorganize complex legal logic into a series of interconnected thought steps, making the entire prediction process more consistent with the essential characteristics of legal reasoning and enhancing the logic and rationality of the prediction results. Furthermore, compared to traditional methods that rely on specific scenarios or a large number of historical cases, this invention starts from the case itself and constructs a reasonable logical chain for analysis and prediction. This allows it to better handle emerging complex case types and demonstrates stronger generalization capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is the overall flow chart of the present invention.

[0047] Figure 2 This is a schematic diagram of the technical route of the present invention. DETAILED DESCRIPTION

[0048] The technical solutions in the embodiments of the present invention will be fully described below in conjunction with the accompanying drawings in the implementation of the present invention.

[0049] The overall process of the present invention is shown in Figure 1 , technical route see Figure 2 , including the following steps:

[0050] S1. Input the claim, defense and case facts;

[0051] S2. Call the big model to extract case elements from the input information.

[0052] Case elements include litigation request extraction, defense opinion extraction, event extraction, and key information extraction. Litigation request extraction and defense opinion extraction include the extraction of specific requirements or claims raised by the plaintiff and defendant in the case; event extraction includes the extraction of events in three parts: claims, defenses, and case facts; key information extraction includes civil acts, right holders, liability holders, types of payment, amounts, quantities, performing entities, content of performance, and methods of performance.

[0053] S3. Based on the input claims and defenses, case facts, and case elements, a hybrid retrieval method using text similarity matching based on BM25 (Best Matching) and semantic similarity matching based on SIMCES (Similarity Contrastive Estimation) is used to search the civil case cognition knowledge base and the civil laws and regulations knowledge base to obtain historical cases and relevant legal and regulatory provisions similar to the input information.

[0054] The civil case cognition knowledge base consists of a plaintext portion and a vector storage portion. Specifically, the plaintext portion includes historical civil cases (cases whose causes of action are those issued by the Supreme People's Court, but do not include special procedures, non-litigation procedures, or undisclosed case causes, and are civil cases that occurred after the promulgation of the Civil Code of the People's Republic of China) and the portion after knowledge enhancement processing. These historical civil cases are subjected to large-scale model-based knowledge enhancement processing, including summary generation, case feature extraction, and legal content recognition, forming an index with the historical civil cases. SIMCES-based vector representation technology is used to construct a vector library to store semantic information, forming the final civil case cognition knowledge base.

[0055] The civil laws and regulations knowledge base consists of a plaintext portion and a vector storage portion. Specifically, the plaintext portion includes civil law provisions, judicial interpretations, and knowledge-enhanced portions of these civil law provisions and judicial interpretations. Civil law provisions include the Civil Code of the People's Republic of China, the Arbitration Law of the People's Republic of China, the Civil Procedure Law of the People's Republic of China, the Partnership Enterprise Law, the Company Law, the Labor Law, the Labor Contract Law, and the Consumer Protection Law. Judicial interpretations include the Interpretation of the Supreme People's Court on the Application of the Tort Liability Section of the Civil Code of the People's Republic of China (I), the Interpretation of the Supreme People's Court on Several Issues Concerning the Application of the General Provisions of the Contract Section of the Civil Code of the People's Republic of China, and the Provisions of the Supreme People's Court on Several Issues Concerning the Application of Law in the Trial of Private Lending Cases, which are currently in effect (as of October 2024). The overall structure of legal and regulatory texts is analyzed, and hierarchical entries are split. These legal provisions are then subjected to knowledge enhancement processing based on large models, including feature label extraction and topic extraction, and indexed with the legal and regulatory provisions. A vector storage portion is constructed using SIMCES-based vector representation technology to store semantic information, forming the final civil laws and regulations knowledge base.

[0056] S4. Combine the claim and case elements to construct a thinking chain with the purpose of fixing the claim and concretizing the rights request, call the big model, and finally obtain the rights request.

[0057] The reference template for the thinking chain is as follows:

[0058] Input part:

[0059] “Role: Civil judge;

[0060] Task: [Specific task description and requirements for securing the rights claim, including but not limited to analysis, reasoning, decision-making, etc.]

[0061] Known information:

[0062] (1) Allegation:

[0063] (2) Case elements:

[0064] Reference Information:

[0065] (1) Related reference information 1: [Detailed reference content that helps to complete the task objectives];

[0066] (2) Related reference information 2: [Detailed reference content that helps to complete the task objectives];

[0067] Analytical reasoning: [This step requires careful consideration of known information, combined with reference information, and thinking according to the legal trial logic of civil cases, ultimately reasoning to arrive at the rights claim;]

[0068] Final fixed rights request:

[0069] Summary and confirmation: [Finally fix the plaintiff's claim and clarify the specific content and composition of the plaintiff's claim.]"

[0070] Output section:

[0071] "Rights Requested:\n{}"

[0072] Here, {} represents the input claim information and the case elements obtained in step S2. The reference information includes legal logic knowledge related to fixing the plaintiff's claim and clarifying the plaintiff's specific claim, aiming to provide support for fixing the claim.

[0073] In one embodiment, a specific example of a thought chain is as follows:

[0074] Input part:

[0075] “Role: Civil judge;

[0076] Task: Fully analyze known information such as the claim and case elements, fully draw on and reference information to determine the plaintiff's claim rights, clarify the plaintiff's specific claims, etc., and ultimately determine the plaintiff's claim rights and clarify the plaintiff's rights (the specific content and composition of the claims). Note that the rights claims must not contain contradictions, ambiguities, or other flaws;

[0077] Known information:

[0078] (1) Allegation:

[0079] (2) Case elements:

[0080] Reference information includes:

[0081] (1) Reference information on the plaintiff's claim: The claim is the right to request others to act or not act, including the right to claim for debt, the right to claim for return, the right to damages, the right to claim compensation and reimbursement, the right to claim for reimbursement of expenses, the right to claim for inaction, the right to claim personal rights, and other claims; clarify the right to form, which is the right to establish, change or eliminate legal relations, including the right to request changes due to major misunderstandings or obvious unfairness, the right to change due to fraud or coercion, the right of set-off under contract law, the right to revoke under contract law, the right to revoke company resolutions, the right of first refusal under company law, the right of first refusal under contract law, the right of first refusal under property law, the right of first refusal under co-ownership ... Limited purchase rights, contract rescission rights, termination rights, etc.; clarify the adversarial and complementary relationships of rights, and when fixing rights claims, pay special attention to the fact that different types of lawsuits and different claims may form adversarial or complementary relationships; clarify the conflict of rights, and pay attention to whether the same fact meets the requirements of different legal norms at the same time, including conflict of laws (the same event meets the constituent elements of two or more legal norms at the same time, but only one of the legal norms can be applied according to the rules of law application), selective conflict (when the same event meets two or more rights-based norms at the same time, the right holder can only choose one right between the right to claim and the right to form), aggregation of claims, and conflict of claims;

[0082] (2) Reference information for clarifying the plaintiff's specific litigation request: ① When the plaintiff requests confirmation of the validity of a civil act, it should be clarified whether it is valid, invalid, ineffective, or revoked; ② When the plaintiff requests confirmation of the ownership of rights, it should be clarified as to the subject, nature, and content of the rights; ③ When the plaintiff requests payment of money or in-kind goods, it should be clarified as to the subject, type, amount, and quantity of the payment; ④ When the plaintiff requests the performance of a certain act, it should be clarified as to the subject, content, and method of performance;

[0083] Analytical reasoning: This step requires careful consideration of the plaintiff's statement of opinion (i.e., the claim, known information item 1), combined with the specific circumstances of the case (known information item 2) and reference information, and the following aspects of thinking in a logical order to ultimately deduce the rights claim;

[0084] (1) Determine the type of claim: Based on the aforementioned preparatory work and the part of the plaintiff's claim in the reference information (reference information item 1), determine which type of claim the plaintiff's claim belongs to, or whether it involves the issue of formative rights. If there is a conflict of rights, the conflict of rights must also be clarified. Finally, determine the type of claim.

[0085] (2) Specify the claim: Based on the above preparations and the reference information on clarifying the plaintiff's specific claim (reference information item 2), all the above analysis results are finally converted into a specific statement of the claim, and finally the claim is obtained. For example: if the validity / invalidity of a civil act is requested, the status of the act must be clarified; if the ownership of a specific property right is sought, the object of the right ownership and relevant details must be specified; when the other party is required to pay money or other forms of compensation, the required amount and list of items must be listed in detail; if a specific action is desired to be enforced, it must be clearly stated who the executor is, what action should be taken, and how it should be implemented.

[0086] Final fixed rights request:

[0087] Summary and Confirmation: Based on the above analysis, the plaintiff's claim is finally confirmed, and the specific content and composition of the plaintiff's claim are clarified.

[0088] Output section:

[0089] "Rights Requested:\n{}"

[0090] S5. Combine the claims, defenses, case elements, the rights request obtained in step S4, historical cases similar to the input information obtained in step S3, and relevant legal and regulatory provisions to construct a thinking chain for the purpose of screening the basic norms for rights requests and the basic norms for defenses (rights), call the big model, and obtain the basic norms for rights requests, the basic norms for defenses, and the defense claims and reasons.

[0091] The reference template for the thinking chain is as follows:

[0092] Input part:

[0093] “Role: Civil judge;

[0094] Task: [A specific description of the task and specific requirements, with the goal of clarifying the defense claims and reasons, and screening the basic norms for the claim and the defense (right), including but not limited to analysis, reasoning, decision-making, etc.]

[0095] Known information:

[0096] (1) Allegation:

[0097] (2) Argument:

[0098] (3) Case elements:

[0099] (4) Rights claim:

[0100] Reference Information:

[0101] (1) Similar historical cases:

[0102] (2) Relevant laws and regulations:

[0103] (3) Related reference information 1: [Detailed reference content that helps to complete the task objectives];

[0104] (4) Related reference information 2: [Detailed reference content that helps to complete the task objectives];

[0105] Analytical reasoning: [This step requires careful consideration of known information, combined with reference information, and thinking according to the legal trial logic of civil cases. Ultimately, reasoning is used to obtain the defense claims and reasons, and to screen out the basic norms for the rights claim and the basic norms for the defense (right);]

[0106] Finally, the basic specifications were selected:

[0107] Summary and confirmation: [Finally, the reasoning resulted in the defense claims and reasons, and the screening resulted in the basic norms for the rights claim and the basic norms for the defense (right).]”

[0108] Output section:

[0109] "Claim Base Specification:\n{}\n;

[0110] Defense claims and reasons:\n{}\n;

[0111] Basic norms for defense (right):\n{}”

[0112] Where {} represents the input claim and defense information, the case elements obtained in step S2, and the rights claim obtained in step S4. Reference information includes historical cases and relevant laws and regulations similar to the input information obtained in step S3, as well as legal logic related to clarifying the basic norms for rights claims and defenses. This information is intended to provide support for obtaining the basic norms for rights claims, defenses, and the defense claims and reasons.

[0113] In one embodiment, a specific example of a thought chain is as follows:

[0114] Input part:

[0115] “Role: Civil judge;

[0116] Task: Fully analyze known information such as the claim, defense, case elements, and rights requests, and fully draw on and refer to similar historical cases, similar legal and regulatory provisions, reference information that clarifies the basic norms for rights requests, and reference information that clarifies the basic norms for defenses (rights), etc., ultimately clarifying the claims and reasons of the parties' defenses, and clarifying the substantive law norms corresponding to the defenses, i.e., the basic norms for defenses (rights); focusing on the rights requests, ultimately enumerate the laws and regulations that support the plaintiff's litigation requests, i.e., the basic norms for rights requests;

[0117] Known information:

[0118] (1) Allegation:

[0119] (2) Argument:

[0120] (3) Case elements:

[0121] (4) Rights claim:

[0122] Reference information includes:

[0123] (1) Similar historical cases:

[0124] (2) Relevant laws and regulations:

[0125] (3) Clarify the reference information of the basic norms of the rights request: refers to the legal norms that support the plaintiff's litigation request. The purpose is to list in detail the laws and regulations that support the plaintiff's litigation request based on the rights request. For example: if the rights request involves requesting the confirmation of property rights (including ownership, usufruct rights, security rights and other property rights), the corresponding basic norm is Article 234 of the Civil Code: If there is a dispute over the ownership and content of property rights, the interested party may request confirmation of the rights. If the request is to confirm the mortgage right, the provisions of Article 402 and Article 403 of the Civil Code should also be included.

[0126] (4) Clarify the reference information of the basic norms of defense (right): The right of defense is the right to oppose the claim, and is the defendant's right to refuse to pay when the plaintiff requests the exercise of the right. Check whether the defendant has raised a defense or exercised the right of defense. If the defendant has raised a defense or exercised the right of defense, the right of defense should be clarified. According to the time and scope of effect, the right of defense includes permanent defense (permanently preventing the claim from taking effect, that is, the claimant's lawsuit for payment will be deemed unreasonable and dismissed), temporary defense (temporarily preventing the court from enforcing the claim, that is, the claimant's lawsuit for payment will be temporarily dismissed as unreasonable, and can only temporarily exclude the other party's claim within a certain period of time), and restrictive defense (which cannot prevent the court from enforcing the claim, but can lead to a judgment of payment that gradually accepts that the claimant should pay, and limitedly supports the claimant's claim). On the basis of clarifying the right of defense, further clarify the basic norms of defense (right). The basic norms of defense (right) are the legal norms on which the defendant raises the defense (right). First, clarify whether the defendant's defense claims or reasons are clear. Second, identify whether the defendant has raised a defense (right) in his defense or whether he intends to defend. Third, based on the right of defense, list in detail the laws and regulations to which the right of defense refers.

[0127] Analytical reasoning: This step requires careful consideration of the specific circumstances of the claims, defenses, case elements, and rights requests (known information), and combined with similar historical cases and relevant laws and regulations (reference information items 1 and 2), the following aspects should be considered in a logical order, and the final reasoning should be used to obtain the content and composition of the party's defense, the basic norms of rights requests, and the basic norms of defense rights.

[0128] (1) Reference to similar historical cases: Based on the claims, defenses, case elements, rights claims, etc. (known information), refer to the legal provisions mentioned in similar historical cases (reference information item 1), especially the provisions directly related to the core issues of the case, and retain the most relevant legal provisions.

[0129] (2) Refer to relevant laws and regulations: Based on the content of the claim, defense, rights request, and right basis (known information), refer to relevant laws and regulations (reference information item 2), and retain the most relevant laws and regulations.

[0130] (3) Determine the basic norms for the claim: Based on the above analysis results, according to the part of the reference information that clarifies the basic norms for the claim (reference information item 3) and the legal provisions retained in (1) and (2), and combined with the applicability of the specific circumstances of the case, finally list the laws and regulations that support the plaintiff's claim, that is, the basic norms for the claim. For example, if the case involves a loan contract dispute, the legal provisions related to borrowing and guarantee may be involved to judge the case;

[0131] (4) Determine the basic norms of defense (right): Based on the above analysis results, analyze the defendant's reply according to the part of the reference information that clarifies the basic norms of defense (right) (reference information item 4) and the legal provisions retained in (1) and (2), and judge whether there are valid reasons for defense or rights of defense. If so, further explore whether the defense complies with the law and find out the specific legal provisions that support its position. The key to this step is to identify all possible conditions that can effectively counter the plaintiff's claims and understand how these conditions interact to form an effective defense strategy. Finally, clarify the claims and reasons of the parties' defense and clarify the substantive law norms corresponding to the defense, that is, the basic norms of defense (right).

[0132] Finally, the basic specifications were selected:

[0133] Summary and Confirmation: Based on the above analysis, the claims and reasons of the parties' defenses are finally clarified, and the substantive law norms corresponding to the defenses, namely the basic norms of the defense (right), are clarified; based on the rights requested, the laws and regulations supporting the plaintiff's litigation request, namely the basic norms of the rights request, are finally listed.

[0134] Output section:

[0135] "Claim basis:\n{}\n;

[0136] Defense claims and reasons:\n{}\n;

[0137] Basic norms for defense (right):\n{}”

[0138] S6. Combined with the basic norms obtained in step S5, a thinking chain is constructed with the purpose of decomposing the constituent elements of the basic norms, and the large model is called to obtain the constituent elements of the basic norms of rights claims and the basic norms of defense (rights).

[0139] The reference template for the thinking chain is as follows:

[0140] Input part:

[0141] “Role: Civil judge;

[0142] Task: [Specific task description and specific requirements with the goal of decomposing the constituent elements of the basic norms for claims and defenses, including but not limited to analysis, reasoning, decision-making, etc.]

[0143] Known information:

[0144] (1) Basic norms for claiming rights:

[0145] (2) Basic norms of defense (right):

[0146] Reference information for decomposing the constituent elements of the basic specification:

[0147] [Detailed reference content that helps complete the task objectives];

[0148] Analytical reasoning: [This step requires careful consideration of known information, combined with reference information, and thinking according to the legal trial logic of civil cases. Ultimately, reasoning will lead to a breakdown of the constituent elements of the basic norms for the claim and the basic norms for the defense (right);]

[0149] Elements of the final output basic specification:

[0150] Summary and confirmation: [The final reasoning resulted in a breakdown of the constituent elements of the basic norms for claiming rights and the basic norms for defense (rights).]”

[0151] Output section:

[0152] "Basic normative elements of the claim:\n{}\n;

[0153] Basic normative elements of defense (right):\n{}”

[0154] Where {} represents the basic norms for the claim and the basic norms for the defense (right) obtained in step 5. The reference information includes legal logic knowledge related to decomposing the constituent elements of the basic norms, and is intended to provide support for obtaining the constituent elements of the basic norms for the claim and the basic norms for the defense (right).

[0155] In one embodiment, a specific example of a thought chain is as follows:

[0156] Input part:

[0157] “Role: Civil judge;

[0158] Task: Fully analyze the basic norms of rights claims and defenses (rights), fully learn from and refer to the reference information on the decomposition of the constituent elements of the basic norms, analyze the constituent elements contained in all relevant legal provisions, and ultimately obtain the constituent elements of the basic norms of rights claims and defenses (rights);

[0159] Known information:

[0160] (1) Basic norms for claiming rights:

[0161] (2) Basic norms of defense (right):

[0162] Reference information for decomposing the constituent elements of the basic specification:

[0163] The basic norms supporting the plaintiff's litigation request and the defendant's defense (right) reasons are analyzed in accordance with the logic of legal norms to analyze the constituent elements of the basic norms. Legal provisions are divided into complete legal provisions and incomplete legal provisions based on whether they can serve as an independent basis for the right to claim. Complete legal provisions are legal provisions that can serve as an independent basis for the right to claim. They are composed of two parts: constituent elements and legal effects. For example, if: one party fails to perform its contractual obligations or performs its contractual obligations inconsistent with the agreement; legal effect: it should bear the liability for breach of contract such as continuing to perform, taking remedial measures or compensating for losses; incomplete legal provisions refer to legal provisions that cannot directly serve as the basis for the right to claim and need to be linked to other legal provisions. Assumptions in legal provisions usually have basic constituent elements, which are constituent elements. There are two basic structural forms of constituent elements:

[0164] Structure 1: M1+M2+M3......=R

[0165] In the above formula, M1, M2, M3, etc. represent different constituent elements. R stands for legal effect.

[0166] For example, Article 34 of the Property Law states: "If a person has no right to occupy real estate or movable property, the right holder may request the return of the original property."

[0167] M1: The possessor has no rights.

[0168] M2: The possessor has taken possession of the immovable property or movable property.

[0169] Legal effect (R): The right holder can request the return of the original property.

[0170] Analyzing the constituent elements of basic regulations is the process of identifying the essential and implicit elements. Only by thoroughly examining all the elements can we accurately apply the legal provisions and render fair judgments.

[0171] Structure 2: M1, M2 or M3......=R

[0172] For example, Article 107 of the Contract Law states that the first requirement is that “one party fails to perform its contractual obligations”; the second requirement is that “or the performance of its contractual obligations does not conform to the agreement.” These two requirements are optional.

[0173] Analytical reasoning: Think about the following aspects in a logical order, and finally deduce the constituent elements of the basic norms of rights claims and the constituent elements of the basic norms of defenses (rights).

[0174] (1) Clarify the constituent elements of the basic norms for the claim: Based on the known basic norms for the claim (known information item 1), fully refer to the reference information for decomposing the constituent elements of the basic norms (reference information item 1) to identify whether the norm is a complete legal provision or an incomplete legal provision. According to the principle of decomposing the constituent elements of the basic norms, if it is a complete legal provision, the constituent elements M1, M2, ... and the legal effect R are directly extracted from it; if it is an incomplete legal provision, it means that as long as one of the conditions is met, the legal effect can be generated. Finally, the constituent elements of the basic norms for the claim are obtained.

[0175] (2) Clarify the constituent elements of the basic norms of the defense (right): Similarly, for the basic norms on which the defendant's defense is based (known information item 2), a similar decomposition of constituent elements is required. Ultimately, the constituent elements of the basic norms of the defense (right) are obtained.

[0176] Elements of the final output basic specification:

[0177] Summary and Confirmation: Based on the above analysis, we finally obtain the constituent elements of the basic norms for rights claims and the basic norms for defenses (rights).

[0178] Output section:

[0179] "Basic elements of the claim:\n{}\n;

[0180] Basic normative elements of defense (right):\n{}”

[0181] S7. Combine the rights claim obtained in step S4, the claims and reasons for the defense obtained in step S5, and the basic regulatory elements of the rights claim and the basic regulatory elements of the defense (right) obtained in step S6, and construct a thinking chain for the purpose of generating the focus of the dispute of the case, call the big model, and obtain the focus of the dispute of the case.

[0182] The reference template for the thinking chain is as follows:

[0183] Input part:

[0184] “Role: Civil judge;

[0185] Task: [Specific task description and requirements for generating litigation arguments, including but not limited to analysis, reasoning, and decision-making]

[0186] Known information:

[0187] (1) Claim:

[0188] (2) Defense claims and reasons:

[0189] (3) Constituent elements of the basic norms of the claim:

[0190] (4) Constituent elements of the basic norms of defense (right):

[0191] Reference information for organizing the focus of litigation disputes:

[0192] [Detailed reference content to help you complete your mission objectives.]

[0193] Analytical reasoning: [This step requires careful consideration of known information, combined with reference information, and thinking according to the legal trial logic of civil cases, ultimately reasoning to determine the controversial point of the case.]

[0194] The final controversial issues in the case:

[0195] Summary and confirmation: [The final reasoning leads to the controversial focus of the case.]"

[0196] Output section:

[0197] "The controversial point of the case:\n{}"

[0198] Here, {} represents the claim obtained in step S4, the assertions and reasons for the defense obtained in step S5, and the basic elements of the claim and defense obtained in step S6. The reference information includes legal logic knowledge related to organizing the focus of the litigation dispute, aiming to provide support for identifying the focus of the case.

[0199] In one embodiment, a specific example of a thought chain is as follows:

[0200] Input part:

[0201] “Role: Civil judge;

[0202] Tasks: Thoroughly analyze the case elements, claims, defenses, and reasons; fully draw upon and reference information on the disputed points; and through judicial actions such as comparing, analyzing, summarizing, and clarifying the claims and defenses of both parties, clarify any conflicts in the underlying norms of their claims. Based on this, ultimately determine the disputed point of the case, ensuring that the disputed point is relevant to the claim.

[0203] Known information:

[0204] (1) Claim:

[0205] (2) Defense claims and reasons:

[0206] (3) Constituent elements of the basic norms of the claim:

[0207] (4) Constituent elements of the basic norms of defense (right):

[0208] Reference information for organizing the focus of litigation disputes:

[0209] Based on the plaintiff and defendant's arguments and their underlying legal framework, the case's disputed points are summarized and the trial is centered around these points. Issues refer to specific matters of dispute between the parties, including both legal and factual matters. The organization of these issues should be based on the constituent elements of the underlying legal framework. Sorting out the focus of the dispute effectively limits the scope of the trial and expedites it. The organization of these issues follows the principle of "one party's claim—whether the other party admits (admits)—the presentation and cross-examination of evidence in the event of a denial—and determination based on the rules for allocating the burden of proof."

[0210] Analytical reasoning: Conduct the following thinking in a logical order, and ultimately deduce the focus of the dispute, the reasoning for the judgment, and the conclusion of the judgment. Based on the plaintiff and defendant's claims and defenses (known information items 1 and 2), the constituent elements of the basic norms of their claims and the constituent elements of the basic norms of their defenses (known information items 3 and 4), fully consult and organize the reference information on the litigation points, identify the differences in the positions of the two parties, and ultimately summarize the focus of the dispute;

[0211] The final controversial issues in the case:

[0212] Summary and Confirmation: Based on the above analysis, we finally arrive at the controversial focus of the case.

[0213] Output section:

[0214] "The controversial point of the case:\n{}"

[0215] S8. Combine the case elements, similar historical cases obtained in step S3, the rights claim obtained in step S4, the claims and reasons of the defense obtained in step S5, the basic norms of the rights claim and the basic norms of the defense (right), the constituent elements of the basic norms of the rights claim and the constituent elements of the basic norms of the defense (right) obtained in step S6, and the focus of the dispute of the case obtained in step S7, and construct a thinking chain for the purpose of classifying the elements and generating the judgment results, call the big model, and obtain the reasoning and civil judgment results of the civil judgment.

[0216] The reference template for the thinking chain is as follows:

[0217] Input part:

[0218] “Role: Civil judge;

[0219] Task: [Specific task description and requirements for classifying elements and generating adjudication results, including but not limited to analysis, reasoning, and decision-making]

[0220] Known information:

[0221] (1) Case elements:

[0222] (2) Rights claim:

[0223] (3) Basic norms for claiming rights:

[0224] (4) Defense claims and reasons:

[0225] (5) Basic norms of defense (right):

[0226] (6) Constituent elements of the basic norms of the claim:

[0227] (7) Constituent elements of the basic norms of defense (right):

[0228] (8) The focus of the dispute:

[0229] Reference information includes:

[0230] (1) Similar historical cases:

[0231] (2) Related reference information 1: [Detailed reference content that helps to complete the task objectives];

[0232] (3) Related reference information 2: [Detailed reference content that helps to complete the task objectives];

[0233] Analytical reasoning to generate the judgment reasoning and conclusion: [This step requires careful consideration of known information, combined with reference information, and thinking according to the legal trial logic of civil cases, ultimately reasoning to obtain the civil judgment reasoning and civil judgment conclusion;]

[0234] The final output is the referee's reasoning and conclusion:

[0235] Summary and confirmation: [The final reasoning resulted in the civil judgment reasoning and civil judgment result.]"

[0236] Output section:

[0237] "Content of the referee's reasoning:\n{}\n;

[0238] Content of the judgement conclusion:\n{}”

[0239] Here, {} represents the case elements, the claim obtained in step S4, the basic norms for the claim obtained in step S5, the assertions and reasons for the defense, and the basic norms for the defense (right), the constituent elements of the basic norms for the claim and the constituent elements of the basic norms for the defense (right) obtained in step S6, the controversial issues of the case obtained in step S7, and the similar historical cases obtained in step S3. Reference information includes historical cases similar to the input information obtained in step S3, as well as legal logic knowledge related to element classification, civil judgments, and logical syllogisms, and is intended to provide support for generating adjudication reasoning and conclusions.

[0240] In one embodiment, a specific example of a thought chain is as follows:

[0241] Input part:

[0242] “Role: Civil judge;

[0243] Task: Fully analyze the case elements, rights claims, defense claims and reasons, focus of dispute, basic norms, and constituent elements of basic norms, etc., fully draw on and refer to similar historical cases and reference information for the classification and judgment of elements, compare and classify the events in the case elements with the constituent elements of the basic norms of the rights claims and the constituent elements of the basic norms of the defense (right), and finally form the content of the judgment reasoning and obtain the judgment result through the classification process of reference logical syllogism;

[0244] Known information:

[0245] (1) Case elements:

[0246] (2) Rights claim:

[0247] (3) Basic norms for claiming rights:

[0248] (4) Defense claims and reasons:

[0249] (5) Basic norms of defense (right):

[0250] (6) Constituent elements of the basic norms of the claim:

[0251] (7) Constituent elements of the basic norms of defense (right):

[0252] (8) The focus of the dispute:

[0253] Reference information includes:

[0254] (1) Similar historical cases:

[0255] (2) Classify the elements and make a judgment: Classify the facts of the case into the constituent elements of legal norms, that is, legal facts and constituent elements facts. There are three requirements for completing the classification: First, the facts of the case must be facts that have been legally recognized, that is, the facts of the case are consistent with the requirements of the basic elements of the constituent elements; second, the facts that are consistent with the constituent elements must not only meet the individual legal constituent elements, but all the elements must be met; third, the other party's defense is not established. In other words, the defense (right) must be invalid before the legal basis norms can be applied to support the plaintiff's litigation request. As long as one element cannot be classified, the legal provision should not be used to support the right request (defense request). The right of defense also needs to be legally classified. The classification method is exactly the same as the classification method of the claim right. All conditions must be met. Compare the constituent elements of the legal norms with the recognized facts. There are several elements in the legal provision. It is necessary to determine whether each element is established and to make a judgment. If each element fact can be recognized, it can be legally classified, that is, the legal provision can be applied to make a judgment. The structural form of the classification of elements: the constituent elements are: M1, M2, M3...; the facts of the case are: A1, A2, A3...; then the case facts A1, A2, A3... can be classified according to the law only if the defense is not established and all the legal constituent elements of M1, M2, M3... are met.

[0256] (3) Logical syllogism: A syllogism consists of three parts: the major premise, the minor premise, and the conclusion. The major premise is the legal provision or legal principle, that is, the legal article or legal interpretation on which the judgment is based. The minor premise is the specific facts of the case. The conclusion is the result derived from the major and minor premises, that is, the judgment result.

[0257] Generate analytical reasoning for the judge's reasoning and conclusion: Think about the following aspects in a logical order, and ultimately deduce the focus of the dispute, the judge's reasoning, and the judge's conclusion.

[0258] First, thoroughly referencing the reference information for categorizing elements and making a judgment (reference information item 2), the case elements and defense claims and reasons (known information items 1 and 4) are mapped one by one to the constituent elements of the underlying norms for the claim and the constituent elements of the underlying norms for the defense (known information items 6 and 7), conducting a comparative analysis. During this comparison, the first priority is to ensure that each constituent element of the underlying norms is met and that the defense is established. Second, combining information such as the case elements, underlying norms, and the focus of the dispute (known information items 1, 6, 7, and 8), the judge makes a reasoning for the application or non-application of the legal provision based on the categorization results. Finally, strictly following the logical syllogism (reference information item 3), the judge ultimately arrives at the case's conclusion. The writing style and approach of the reasoning and conclusion can be referenced to the decisions of similar historical cases (reference information item 1). The final result is the reasoning and conclusion.

[0259] The final output is the referee's reasoning and conclusion:

[0260] Summary and Confirmation: Based on the above analysis, we finally arrive at the content of the judge’s reasoning and the judge’s conclusion.”

[0261] Output section:

[0262] "Content of the referee's reasoning:\n{}\n;

[0263] Content of the judgement conclusion:\n{}”

[0264] Among them, the large model mentioned in steps S2, S3, S4, S5, S6, S7 and S8 is a fine-tuned large model in the legal field. The implementation method includes: combining general field and judicial field data, using hash deduplication, semantic coherence detection and other technologies, constructing case summary, dispute focus generation, reasoning generation and other adjudication task knowledge and legal theory data for 800,000 judicial training corpuses, based on the 14B basic model (Qwen1.5-14B), using the LoRA fine-tuning method to form a fine-tuned large model in the legal field.

[0265] It should be understood that the specific implementation of the present invention and the accompanying drawings disclosed above are intended to facilitate understanding of the present invention and to facilitate implementation thereof. Those skilled in the art will appreciate that various substitutions, changes, and modifications without departing from the principles and spirit of the present invention are within the scope of the present invention, which is defined by the appended claims and their equivalents.

Claims

1. A method for predicting civil judgment results based on thought chain, characterized in that: The method comprises: Obtaining input information and extracting case elements from the input information; wherein the input information includes: claims, defenses, and case facts; Search the knowledge base based on the input information and case elements to obtain historical cases and relevant laws and regulations similar to the input information; Combine the claim and case elements to build the first chain of thought for the purpose of fixing the claim and specifying the rights, call the big model, and obtain the rights; Combining the claims, defenses, case elements, rights requests, historical cases similar to the input information, and relevant laws and regulations, a second thinking chain is constructed to screen the basic norms for rights requests and defense rights. The large model is then invoked to obtain the basic norms for rights requests, defense rights, and defense claims and reasons. Combining the basic norms of rights claims and the basic norms of defense rights, a third thinking chain is constructed with the purpose of decomposing the constituent elements of the basic norms. The large model is called to obtain the constituent elements of the basic norms of rights claims and the constituent elements of the basic norms of defense rights; Combining the claims, defense claims and reasons, the basic normative elements of the claims and the basic normative elements of the defense, a fourth chain of thought is constructed to generate the controversial focus of the case, and the grand model is used to obtain the controversial focus of the case. Combining the case elements, historical cases similar to the input information, rights claims, defense claims and reasons, basic norms for rights claims, basic norms for right of defense, constituent elements of basic norms for rights claims and constituent elements of basic norms for right of defense, and the controversial focus of the case, a fifth thinking chain is constructed for the purpose of classifying the elements and generating the judgment results, and the big model is called to obtain the civil judgment prediction results of the input information; wherein, the civil judgment prediction results include: the content of the judgment reasoning and the content of the judgment conclusion.

2. The method according to claim 1, characterized in that The extracting of case elements from input information includes: Extract litigation requests based on the claims; Extract defense opinions based on the arguments; Extract events based on claims, defenses, and case facts; Extract key information based on claims, defenses and case facts.

3. The method according to claim 2, characterized in that The key information includes: civil acts, right holders, liability holders, payment types, amounts, quantities, performance holders, performance contents and performance methods.

4. The method according to claim 1, wherein The knowledge base includes: a civil case cognition knowledge base, the civil case cognition knowledge base consisting of a first plaintext portion and a first vector portion, the first plaintext portion including a historical civil case and a summary, case characteristics, and legal content of the historical civil case, and the first vector portion generated based on semantic information of the historical civil case; Based on the input information and case elements, a civil case cognition knowledge base is searched to obtain historical cases similar to the input information, including: Based on the input information, generate a vector representation of the input information, and obtain a first matching result based on the input information and its vector representation, and combining the first plaintext portion and the first vector portion; Based on the case elements, a vector representation of the case elements is generated, and based on the case elements and the vector representation, a second matching result is obtained by combining the first plaintext portion and the first vector portion; Based on the first matching result and the second matching result, historical cases similar to the input information are obtained.

5. The method according to claim 1, wherein The knowledge base includes: a civil laws and regulations knowledge base, the civil laws and regulations knowledge base consisting of a second plaintext portion and a second vector portion, the second plaintext portion including: a plaintext portion including civil law provisions, judicial interpretations, and feature tags and topics of the civil law provisions and judicial interpretations, and the second vector portion is generated based on semantic information of the civil law provisions and the judicial interpretations; Search the civil laws and regulations knowledge base based on the input information and case elements to obtain the legal and regulatory provisions related to the input information, including: Based on the input information, generate a vector representation of the input information, and obtain a third matching result based on the input information and its vector representation, and in combination with the second plaintext portion and the second vector portion; Based on the case elements, a vector representation of the case elements is generated, and based on the case elements and their vector representations, a fourth matching result is obtained by combining the second plaintext portion and the second vector portion; Based on the third matching result and the fourth matching result, legal and regulatory provisions related to the input information are obtained.

6. The method according to claim 1, characterized in that The first chain of thought, the second chain of thought, the third chain of thought, the fourth chain of thought and the fifth chain of thought also include: detailed reference content that is helpful in completing the corresponding task objectives.

7. The method according to claim 1, characterized in that The training process of the large model includes: Construct training datasets based on data from general and judicial fields; The LoRA fine-tuning method is used to fine-tune the large model on the training data.

8. A civil judgment result prediction system based on thought chain, characterized by: The system comprises: An information acquisition module is used to acquire input information and extract case elements from the input information; wherein the input information includes: claims, defenses and case facts; The knowledge retrieval module is used to search the knowledge base based on the input information and case elements to obtain historical cases and relevant laws and regulations similar to the input information; The rights claim generation module is used to combine the claim and case elements to construct the first thought chain for the purpose of fixing the claim and specifying the rights claim, and then call the large model to obtain the rights claim; The basic norms generation module is used to combine the claims, defenses, case elements, rights requests, historical cases similar to the input information, and relevant laws and regulations to construct a second thinking chain for the purpose of screening the basic norms of rights requests and defense rights. It then calls the large model to obtain the basic norms of rights requests, defense rights, and defense claims and reasons. The basic norms constituent elements generation module is used to combine the basic norms of the claim and the basic norms of the defense, build a third thinking chain for the purpose of decomposing the basic norms constituent elements, call the large model, and obtain the basic norms constituent elements of the claim and the basic norms constituent elements of the defense; The module for generating the focus of dispute in a case is used to combine the claim, the claims and reasons for the defense, the constituent elements of the basic rules of the claim, and the constituent elements of the basic rules of the defense to construct a fourth chain of thought for the purpose of generating the focus of dispute in the case, and then call the large model to obtain the focus of dispute in the case; The judgment result prediction module is used to combine the case elements, historical cases similar to the input information, rights claims, defense claims and reasons, basic norms for rights claims, basic norms for rights defenses, constituent elements of basic norms for rights claims and constituent elements of basic norms for rights defenses, and the focus of the case, to construct a fifth thinking chain for the purpose of classifying elements and generating judgment results, call the big model, and obtain the civil judgment prediction results of the input information; wherein, the civil judgment prediction results include: the content of the judgment reasoning and the content of the judgment conclusion.

9. An electronic device, characterized in that: The electronic device includes: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, it implements the civil judgment result prediction method based on thought chain as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the civil judgment result prediction method based on thought chain as described in any one of claims 1 to 7.

Images