Optimization of Judicial Text Evaluation System, Judicial Text Evaluation Method, Device and System

Abstract

This specification relates to the technical field of text data, and provides an optimization of a judicial text evaluation system, a judicial text evaluation method, device, and system. The optimization method includes: determining the initial weights of the evaluation parameters of the judicial text evaluation system; identifying the first minority sample class in the first judicial text dataset; performing multi-dimensional synthetic minority over-sampling processing on the first minority sample class to fill the sample quantity of the first minority sample class and form a second judicial text dataset; identifying the second minority sample class in the second judicial text dataset; determining the influence probability value of the weights affected by the second minority sample class among the evaluation parameters; and adjusting the weights corresponding to the influence probability values greater than the probability threshold. The embodiments of this specification can improve the accuracy of judicial text evaluation.

Description

Technical Field

[0001] This specification relates to the technical field of text data processing, and in particular, to an optimization of a judicial text evaluation system, a judicial text evaluation method, device, and system. Background Art

[0002] In many industries (such as industrial informatization, judicial administration informatization, etc.), the evaluation of the results of business processing based on text information is often involved to comprehensively and systematically evaluate whether the business processing meets the expected requirements.

[0003] However, existing business evaluation systems have some limitations. These systems usually rely on evaluation parameters. However, the weights of the evaluation parameters are generally set manually or determined based on general weight calculation methods (such as principal component analysis method, entropy method, etc.). Compared with setting the weights of evaluation parameters manually, the method of determining the weights of evaluation parameters based on general weight calculation methods has obvious advantages in terms of efficiency and accuracy. However, this application's research finds that: in the scenario of data imbalance, the accuracy of weight assignment by methods such as principal component analysis method and entropy method is poor, thus affecting the accuracy of business evaluation. Summary of the Invention

[0004] The purpose of the embodiments of this specification is to provide an optimization of a judicial text evaluation system, a judicial text evaluation method, device, and equipment to improve the accuracy of judicial text evaluation.

[0005] To achieve the above object, on the one hand, the embodiments of this specification provide an optimization method for a judicial text evaluation system, including:

[0006] Determine the initial weights of the evaluation parameters of the judicial text evaluation system;

[0007] Identify the first minority sample class in the first judicial text dataset;

[0008] Perform multi-dimensional synthetic minority over-sampling processing on the first minority sample class to fill the sample quantity of the first minority sample class and form a second judicial text dataset;

[0009] Identify the second minority sample class in the second judicial text dataset;

[0010] Determine the influence probability value of the weights affected by the second minority sample class among the evaluation parameters;

[0011] Adjust the weights corresponding to the influence probability values greater than the probability threshold.

[0012] In the optimization method for the judicial text evaluation system of the embodiments of this specification, the identification of the first minority sample class in the first judicial text dataset includes:

[0013] Cluster the first judicial text dataset to obtain multiple judicial text classes;

[0014] Calculate the number of samples in each of the judicial text classes;

[0015] Identify the judicial text classes with the number of samples lower than the first target threshold as the first minority sample classes.

[0016] In the method for optimizing the judicial text evaluation system according to the embodiments of this specification, performing multi-dimensional synthetic minority over-sampling processing on the first minority sample classes includes:

[0017] Select a judicial text sample from the first minority sample classes as the target sample;

[0018] Determine the neighbors of the target sample in the three-dimensional space dimension, where the neighbors are judicial text samples in the first minority sample classes;

[0019] Use a random function to add judicial texts between the target sample and its neighbors as new samples of the first minority sample classes.

[0020] In the method for optimizing the judicial text evaluation system according to the embodiments of this specification, the use of a random function to add judicial texts between the target sample and its neighbors includes:

[0021]

[0022] where X i is the text feature of the i-th newly added judicial text, N is the number of neighbors, X j is the text feature of the j-th neighbor, rand(0, 1) is the random function, and X' is the text feature of the target sample selected from the first minority sample classes.

[0023] In the method for optimizing the judicial text evaluation system according to the embodiments of this specification, identifying the second minority sample classes in the second judicial text dataset includes:

[0024] Cluster the second judicial text dataset to obtain multiple judicial text classes;

[0025] Calculate the number of samples in each of the judicial text classes;

[0026] Identify the judicial text classes with the number of samples lower than the second target threshold as the first minority sample classes; the second target threshold is greater than the first target threshold.

[0027] In the method for optimizing the judicial text evaluation system according to the embodiments of this specification, determining the influence probability value of the weight affected by the second minority sample classes in the evaluation parameters includes:

[0028] According to the formula calculate the influence probability value of the weight affected by the second minority sample class in the evaluation parameters;

[0029] wherein, P(R i =k|x i ) is the influence probability value of the output R i corresponding to the input x i for the k-th weight, R i is the output feature of the i-th group of judicial texts, x i is the input feature of the i-th group of judicial texts, exp is the exponential function, is the transpose of the i-th weight vector affected by the second minority sample class.

[0030] In the method for optimizing the judicial text evaluation system according to the embodiments of the present specification, adjusting the weight corresponding to the influence probability value greater than the probability threshold includes:

[0031] Calculate the conditional entropy gain of the weight corresponding to the influence probability value greater than the probability threshold according to the formula Gain(Y,K)=H(Y)-H(Y|K);

[0032] Determine whether the conditional entropy gain converges;

[0033] When the conditional entropy gain does not converge, adjust the weight corresponding to the influence probability value greater than the probability threshold until the currently obtained conditional entropy gain converges;

[0034] wherein, Gain(Y,K) is the conditional entropy gain of the evaluation value Y under the influence of the K-th weight, H(Y) is the entropy value of the evaluation value Y, and H(Y|K) is the conditional entropy of the evaluation value Y under the influence of the K-th weight.

[0035] On the other hand, the embodiments of the present specification also provide a method for evaluating judicial texts, including:

[0036] Obtain the evaluation parameter data of the to-be-evaluated judicial text;

[0037] Input the evaluation parameter data into the judicial text evaluation system to obtain the evaluation value corresponding to the to-be-evaluated judicial text; wherein, the judicial text evaluation system is the judicial text evaluation system optimized according to the above optimization method.

[0038] On the other hand, the embodiments of the present specification also provide an apparatus for optimizing a judicial text evaluation system, including:

[0039] A first determination module, configured to determine the initial weight of the evaluation parameters of the judicial text evaluation system;

[0040] The first recognition module is used to recognize the first minority sample class in the first judicial text dataset;

[0041] The sample filling module is used to perform multi-dimensional synthetic minority over-sampling processing on the first minority sample class to fill the sample quantity of the first minority sample class and form a second judicial text dataset;

[0042] The second recognition module is used to recognize the second minority sample class in the second judicial text dataset;

[0043] The second determination module is used to determine the influence probability value of the weight affected by the second minority sample class in the evaluation parameters;

[0044] The weight adjustment module is used to adjust the weight corresponding to the influence probability value greater than the probability threshold.

[0045] On the other hand, an embodiment of this specification further provides a judicial text evaluation system, including:

[0046] An acquisition module is used to acquire the evaluation parameter data of the to-be-judicial text;

[0047] An evaluation module is used to generate an evaluation value corresponding to the to-be-judicial text according to the evaluation parameter data; wherein, the judicial text evaluation system is a judicial text evaluation system optimized according to the above optimization method.

[0048] On the other hand, an embodiment of this specification further provides a computer device, including a memory, a processor, and a computer program stored on the memory. When the computer program is run by the processor, it executes the instructions of the above method.

[0049] On the other hand, an embodiment of this specification further provides a computer storage medium, on which a computer program is stored. When the computer program is run by the processor of a computer device, it executes the instructions of the above method.

[0050] On the other hand, an embodiment of this specification further provides a computer program product, the computer program product includes a computer program. When the computer program is run by the processor of a computer device, it executes the instructions of the above method.

[0051] As can be seen from the technical solutions provided in the embodiments of this specification above, in the embodiments of this specification, by performing multi-dimensional synthetic minority over-sampling processing on a small number of sample classes in the judicial text dataset, the sample learning of the small number of sample classes is realized, thereby reducing or avoiding the influence of the data imbalance problem on the weight adjustment of evaluation parameters. On this basis, the influence probability value of the weight affected by the newly added small number of sample classes is identified and quantitatively calculated, and the weight corresponding to the influence probability value greater than the probability threshold is adjusted; in this way, through small sample learning and automatic weight adjustment, the judicial text evaluation system can more accurately capture the key features of judicial texts, reduce the errors caused by data imbalance or improper parameter settings in judicial texts, and thus improve the accuracy of judicial text evaluation of the judicial text evaluation system. Description of the Drawings

[0052] In order to more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in this specification. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings. In the drawings:

[0053] Figure 1 Shows a schematic diagram of the application environment of judicial text evaluation in some embodiments of this specification;

[0054] Figure 2 Shows a flowchart of the method for optimizing the judicial text evaluation system in some embodiments of this specification;

[0055] Figure 3 Shows Figure 2 A flowchart of identifying a small number of sample classes in the judicial text dataset in the shown method;

[0056] Figure 4 Shows a flowchart of performing multi-dimensional synthetic minority over-sampling processing on a small number of sample classes in an exemplary embodiment of this specification;

[0057] Figure 5 Shows a schematic diagram of a target sample and its neighbors in an exemplary embodiment of this specification;

[0058] Figure 6 Shows Figure 2 A schematic diagram of adjusting the weight corresponding to the influence probability value greater than the probability threshold in the shown method;

[0059] Figure 7 Shows a flowchart of the judicial text evaluation method in some embodiments of this specification;

[0060] Figure 8The structural block diagram of the judicial text evaluation system optimization device in some embodiments of this specification is shown;

[0061] Figure 9 The structural block diagram of the judicial text evaluation system in some embodiments of this specification is shown;

[0062] Figure 10 The structural block diagram of a computer device in some embodiments of this specification is shown.

[0063]

Explanation of the reference numerals

[0064] 10. Client;

[0065] 20. Server;

[0066] 81. First determination module;

[0067] 82. First recognition module;

[0068] 83. Sample filling module;

[0069] 84. Second recognition module;

[0070] 85. Second determination module;

[0071] 86. Weight adjustment module;

[0072] 91. Acquisition module;

[0073] 92. Evaluation module;

[0074] 1002. Computer device;

[0075] 1004. Processor;

[0076] 1006. Memory;

[0077] 1008. Driving mechanism;

[0078] 1010. Input / output interface;

[0079] 1012. Input device;

[0080] 1014. Output device;

[0081] 1016. Presentation device;

[0082] 1018. Graphical user interface;

[0083] 1020. Network interface;

[0084] 1022. Communication link;

[0085] 1024. Communication bus. Detailed implementation manners

[0086] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this specification, rather than all the embodiments. Based on the embodiments in this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this specification.

[0087] It should be noted that in the embodiments of this specification, the user information involved (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) are all information and data that have been consented to by the user and fully permitted by all parties. That is, the acquisition, transmission, storage, use, processing, etc. of data in the technical solutions of this application all comply with the relevant regulations of relevant laws and regulations.

[0088] It should be noted that in the embodiments of this application, some industry-existing solutions such as certain software, components, models, etc. may be mentioned. They should be regarded as exemplary, and their purpose is only to illustrate the feasibility in the implementation of the technical solutions of this application, but it does not mean that the applicant has already or necessarily used this solution.

[0089] Figure 1 The schematic diagram of the application environment in some embodiments of this specification is shown; the application environment includes a client 10 and a server 20. The server 20 can obtain the evaluation parameter data of the to-be-judicial text from the client 10, input the evaluation parameter data into the judicial text evaluation system, and obtain the evaluation value corresponding to the to-be-judicial text; among them, the judicial text evaluation system is an optimized judicial text evaluation system based on artificially setting the evaluation parameter weights or setting the evaluation parameter weights based on a general weight calculation method, so as to improve the accuracy of judicial text evaluation.

[0090] In some embodiments of this specification, the client 10 can be a self-service terminal device, a mobile terminal (i.e., a smart phone), a display, a desktop computer, a tablet computer, a laptop computer, a digital assistant, or a smart wearable device, etc. Among them, the smart wearable device can include a smart bracelet, a smart watch, smart glasses, or a smart helmet, etc. Of course, the client 10 is not limited to the above-mentioned electronic devices with a certain entity, and it can also be software running on the above-mentioned electronic devices.

[0091] In some embodiments of this specification, the server 20 can be an electronic device with computing and network interaction functions; it can also be software running on the electronic device that provides business logic for data processing and network interaction.

[0092] In addition, it should be noted that Figure 1 The one shown is only an application environment provided in this specification. In actual applications, there can be multiple clients 10 and multiple servers 20, and this specification does not make any restrictions.

[0093] The embodiments of this specification provide an optimization method for a judicial text evaluation system, which can be applied to the server side described above. Referring to Figure 2 As shown, in some embodiments of this specification, the optimization method for the judicial text evaluation system may include the following steps:

[0094] Step 201: Determine the initial weights of the evaluation parameters of the judicial text evaluation system.

[0095] Step 202: Identify the first minority sample class in the first judicial text dataset.

[0096] Step 203: Perform Multidimensional Synthetic Minority Over-sampling Technique (M-SMOTE) on the first minority sample class to fill the sample quantity of the first minority sample class and form a second judicial text dataset.

[0097] Step 204: Identify the second minority sample class in the second judicial text dataset.

[0098] Step 205: Determine the influence probability value of the weights affected by the second minority sample class among the evaluation parameters.

[0099] Step 206: Adjust the weights corresponding to the influence probability values greater than the probability threshold.

[0100] In the embodiments of this specification, by performing Multidimensional Synthetic Minority Over-sampling Technique on the minority sample classes in the judicial text dataset, the sample learning of the minority sample classes is realized, thereby reducing or avoiding the influence of the data imbalance problem on the weight adjustment of the evaluation parameters. On this basis, the influence probability value of the weights affected by the newly added minority sample classes is identified and quantitatively calculated, and the weights corresponding to the influence probability values greater than the probability threshold are adjusted; thus, through small sample learning and automatic weight adjustment, the judicial text evaluation system can more accurately capture the key features of the judicial text, reduce the errors caused by the imbalance of judicial text data or improper parameter settings, and further improve the accuracy of the judicial text evaluation of the judicial text evaluation system.

[0101] Moreover, since there is a close correlation among the evaluation parameters of the judicial text evaluation system, and with the passage of time and the change of the external environment, some evaluation parameters may lose their original relevance and importance. By using the optimization method of the embodiments of this specification to optimize the judicial text evaluation system regularly or dynamically, not only can the accuracy of judicial text evaluation of the judicial text evaluation system be improved, but also the performance stability of the judicial text evaluation system can be maintained.

[0102] It should be noted that the general concept of the optimization method of the judicial text evaluation system in the embodiments of this specification can also be applied to the optimization of evaluation systems in other application fields to improve the evaluation accuracy of the corresponding evaluation systems.

[0103] In some embodiments of this specification, an evaluation index system of the judicial text evaluation system can be constructed according to the primary evaluation parameters. For example, in an exemplary embodiment of this specification, a weighted summation judicial text evaluation system can be constructed according to the accuracy of fact-finding, procedural compliance, and fairness of the entity result, and the initial weights of the accuracy of fact-finding, procedural compliance, and fairness of the entity result are set. Among them, the evaluation parameters are the rating indicators, which can also be simply referred to as indicators.

[0104] In other embodiments of this specification, an evaluation index system of the judicial text evaluation system can be constructed according to multi-level evaluation parameters. For example, in an exemplary embodiment of this specification, the accuracy of fact-finding, procedural compliance, and fairness of the entity result can be used as the primary evaluation parameters, and on this basis, secondary evaluation parameters and tertiary evaluation parameters are constructed and the initial weights are set (as shown in Table 1 below).

[0105] Table 1

[0106]

[0107] In some embodiments of this specification, by parsing the pre-constructed judicial text evaluation system, the initial weights of the evaluation parameters of the judicial text evaluation system can be obtained; among them, the initial weights of the evaluation parameters can be the weights set by considering the evaluation parameters or the weights set based on the general weight calculation method; however, no matter which weight assignment method is adopted, there may be an unreasonable weight assignment situation, especially in the data imbalance scenario, this unreasonable weight assignment may be more prominent. Among them, data imbalance refers to a significant difference in the number of samples of different classes in the dataset, usually the number of samples of one class is much more than that of another class; this imbalance may cause the model to be biased towards the majority class, therefore, data imbalance will affect the generalization ability of the model and the recognition ability of the minority class.

[0108] Reference Figure 3As shown, in some embodiments of this specification, identifying the first minority sample class in the first judicial text dataset may include:

[0109] Step 301: Cluster the first judicial text dataset to obtain multiple judicial text classes.

[0110] In some embodiments of this specification, the first judicial text dataset is the judicial text dataset. To distinguish it from the judicial text dataset after multi-dimensional synthetic minority over-sampling processing, it is called the first judicial text dataset, and the judicial text dataset after multi-dimensional synthetic minority over-sampling processing is called the second judicial text dataset.

[0111] In some embodiments of this specification, any suitable clustering algorithm (such as partitioning-based clustering algorithm, hierarchical-based clustering algorithm, model-based clustering algorithm, etc.) can be used to cluster the first judicial text dataset to obtain multiple judicial text classes.

[0112] Step 302: Calculate the number of samples in each of the judicial text classes.

[0113] Step 303: Identify the judicial text classes with the number of samples lower than the first target threshold as the first minority sample class.

[0114] Among them, the first target threshold can be customized as needed.

[0115] In some scenarios, it may occur that small sample data also has a relatively large impact on the overall situation; for example, in the industrial field, normal vibration data represents the stability of the mechanical system, but sudden small sample noise may also indicate some potential fault hazards; therefore, identifying the minority sample class (i.e., the small sample class) is of great significance.

[0116] Reference Figure 4 As shown, in some embodiments of this specification, performing multi-dimensional synthetic minority over-sampling processing on the first minority sample class may include the following steps:

[0117] Step 401: Select a judicial text sample from the first minority sample class as the target sample.

[0118] In some embodiments of this specification, a judicial text sample can be randomly selected from the first minority sample class as the target sample. For example, in Figure 5 the exemplary embodiment shown, node K is the selected target sample.

[0119] Step 402: Determine the neighbors of the target sample in the three-dimensional space dimension, and the neighbors are judicial text samples in the first minority sample class.

[0120] In general, after clustering, the first judicial text dataset will form multiple different clusters (i.e., multiple judicial text classes), and adjacent relationships will be formed between different clusters. Adjacent relationships will also be formed between different nodes (i.e., judicial texts) within the same cluster. Since the cluster is a three-dimensional structure (i.e., a three-dimensional structure), for any node within the same cluster, it has adjacent nodes (i.e., neighbors). For example, in Figure 5 the exemplary embodiment shown, the node K as the target sample has multiple neighbors in three-dimensional space (such as Figure 5 neighbor 1, neighbor 2, neighbor 3, neighbor 4, neighbor 5, neighbor 6, neighbor 7, neighbor n in

[0121] Step 403: Use a random function to add judicial texts between the target sample and its neighbors as new samples of the first minority sample class.

[0122] In some embodiments of this specification, using a random function to add judicial texts between the target sample and its neighbors may include:

[0123]

[0124] where X i is the text feature of the i-th newly added judicial text, N is the number of neighbors, X j is the text feature of the j-th neighbor, rand(0,1) is a random function and its value is 0 or 1, and X' is the text feature of the target sample selected from the first minority sample class.

[0125] In some embodiments of this specification, when there are multiple minority sample classes obtained by clustering, multi-dimensional synthetic minority class oversampling processing can be performed separately for each minority sample class. After multi-dimensional synthetic minority class oversampling processing is completed for each minority sample class, a new judicial text dataset (i.e., the second judicial text dataset) can be formed. By performing multi-dimensional synthetic minority class oversampling processing on the minority sample class, the influence of data imbalance problems on the weight adjustment of evaluation parameters can be reduced or avoided.

[0126] In some embodiments of this specification, the processing logic for identifying the second minority sample class in the second judicial text dataset may include the following steps:

[0127] (1) Cluster the second judicial text dataset to obtain multiple judicial text classes;

[0128] (2) Calculate the number of samples for each of the said judicial text categories;

[0129] (3) Identify the judicial text categories with the number of samples lower than the second target threshold as the first minority sample categories; the second target threshold is greater than the first target threshold.

[0130] After new samples are supplemented, the difference in the number of samples between the minority sample categories and the majority sample categories decreases, but the difference between the minority sample categories may increase, that is, new minority sample categories may be formed due to the relative change in the number of samples. Therefore, the identification of minority sample categories can be performed again; moreover, after new samples are supplemented, the number of samples in the minority sample categories all increases. On this basis, in order to facilitate obtaining more accurate minority sample categories, a larger target threshold can be adopted (that is, the second target threshold is greater than the first target threshold).

[0131] It can be seen that the processing logic for identifying the second minority sample categories in the second judicial text dataset is the same as that for identifying the first minority sample categories in the first judicial text dataset. Therefore, the specific technical details for identifying the second minority sample categories in the second judicial text dataset will not be elaborated here.

[0132] In some embodiments of this specification, to determine the influence probability value of the weight affected by the second minority sample category in the said evaluation parameter, it may include: According to the formula Calculate the influence probability value of the weight affected by the second minority sample category in the said evaluation parameter;

[0133] Wherein, P(R i = k|x i ) is the influence probability value of the output R i corresponding to the input x i on the kth weight, R i is the output feature of the i-th group of judicial texts, x i is the input feature of the i-th group of judicial texts, exp is the exponential function, is the transpose of the i-th weight vector affected by the second minority sample category.

[0134] During the weight assignment process, the large sample categories (i.e., the majority sample categories) and the small sample categories (i.e., the minority sample categories) may simultaneously affect the index weights. Since the large sample categories are not sensitive to the newly added data volume, their influence on the weight assignment is relatively stable; the small sample categories are greatly affected by the newly added data; according to the influence probability value, the influence degree of the already determined small sample categories on the weights of different evaluation parameters can be quantitatively identified, thus providing an objective basis for subsequent selection of which evaluation parameter weights to adjust.

[0135] Since the newly added samples through multi-dimensional synthetic minority oversampling do not have the characteristics of linear distribution or continuous distribution, the above-mentioned multi-class logistic regression formula can be used to calculate the influence probability more efficiently.

[0136] Refer to Figure 6 As shown, in some embodiments of this specification, to adjust the weight corresponding to the influence probability value greater than the probability threshold, the following steps may be included:

[0137] Step 601: Calculate the conditional entropy gain of the weight corresponding to the influence probability value greater than the probability threshold according to the formula Gain(Y,K)=H(Y)-H(Y|K); where Gain(Y,K) is the conditional entropy gain of the evaluation value Y under the influence of the Kth weight, H(Y) is the entropy value of the evaluation value Y, and H(Y|K) is the conditional entropy of the evaluation value Y under the influence of the Kth weight.

[0138] Step 602: Determine whether the conditional entropy gain converges; if the conditional entropy gain does not converge, execute Step 603; otherwise, end the weight adjustment process.

[0139] Step 603: Adjust the weight corresponding to the influence probability value greater than the probability threshold.

[0140] That is, when the conditional entropy gain does not converge, adjust the weight corresponding to the influence probability value greater than the probability threshold until the currently obtained conditional entropy gain converges; when the conditional entropy gain converges (i.e., tends to be stable), it indicates that the current weight value has the least uncertainty under the current conditions, thereby obtaining the desired weight value under the current conditions.

[0141] Some embodiments of this specification also provide a judicial text evaluation method. Refer to Figure 7 As shown, in some embodiments of this specification, the judicial text evaluation method may include the following steps:

[0142] Step 701: Obtain the evaluation parameter data of the to-be-judicial text.

[0143] Step 702: Input the evaluation parameter data into the judicial text evaluation system to obtain the evaluation value corresponding to the to-be-judicial text; where the judicial text evaluation system is the judicial text evaluation system optimized according to the above-mentioned judicial text evaluation system optimization method.

[0144] Since adopting the above-mentioned judicial text evaluation system optimization method can improve the evaluation accuracy of the judicial text evaluation system, evaluating the to-be-judicial text based on the optimized judicial text evaluation system can improve the evaluation accuracy of the judicial text evaluation.

[0145] Although the process flows described above include multiple operations that occur in a specific order, it should be clearly understood that these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel (e.g., using a parallel processor or a multi-threaded environment).

[0146] Corresponding to the above-described method for optimizing a judicial text evaluation system, an embodiment of this specification also provides an apparatus for optimizing a judicial text evaluation system. Refer to Figure 8 As shown, in some embodiments of this specification, the apparatus for optimizing a judicial text evaluation system may include:

[0147] A first determination module 81, configured to determine the initial weights of the evaluation parameters of the judicial text evaluation system;

[0148] A first identification module 82, configured to identify the first minority sample class in the first judicial text dataset;

[0149] A sample filling module 83, configured to perform multi-dimensional synthetic minority over-sampling processing on the first minority sample class to fill the number of samples of the first minority sample class and form a second judicial text dataset;

[0150] A second identification module 84, configured to identify the second minority sample class in the second judicial text dataset;

[0151] A second determination module 85, configured to determine the influence probability value of the weights affected by the second minority sample class among the evaluation parameters;

[0152] A weight adjustment module 86, configured to adjust the weights corresponding to the influence probability values greater than the probability threshold.

[0153] Corresponding to the above-described judicial text evaluation method, an embodiment of this specification also provides a judicial text evaluation system. The judicial text evaluation system is a judicial text evaluation system optimized according to the above-described method for optimizing a judicial text evaluation system, and it can be configured on the above-described server. Refer to Figure 9 As shown, in some embodiments of this specification, the judicial text evaluation system may include:

[0154] An acquisition module 91, configured to acquire the evaluation parameter data of the to-be-judicial text;

[0155] An evaluation module 92, configured to generate an evaluation value corresponding to the to-be-judicial text according to the evaluation parameter data.

[0156] For convenience of description, when describing the above apparatus, various units are described separately according to their functions. Of course, when implementing this specification, the functions of each unit may be implemented in one or more software and / or hardware.

[0157] Embodiments of this specification also provide a computer device. As Figure 10 shown, in some embodiments of this specification, the computer device 1002 may include one or more processors 1004, such as one or more central processing units (CPUs) or graphics processing units (GPUs), and each processing unit may implement one or more hardware threads. The computer device 1002 may also include any memory 1006 for storing any kind of information such as code, settings, data, etc. In a specific embodiment, a computer program stored on the memory 1006 and executable on the processor 1004, when run by the processor 1004, may execute the instructions of the judicial text evaluation system optimization method or the judicial text evaluation method described in any of the above embodiments. Non-limiting examples include, for instance, the memory 1006 may include any one or more combinations of the following: any type of RAM, any type of ROM, flash memory devices, hard disks, optical discs, etc. More generally, any memory may use any technology to store information. Further, any memory may provide volatile or non-volatile retention of information. Further, any memory may represent a fixed or removable component of the computer device 1002. In one case, when the processor 1004 executes the associated instructions stored in any memory or combination of memories, the computer device 1002 may perform any operation of the associated instructions. The computer device 1002 also includes one or more drive mechanisms 1008 for interacting with any memory, such as a hard disk drive mechanism, an optical disc drive mechanism, etc.

[0158] The computer device 1002 may also include an input / output interface 1010 (I / O) for receiving various inputs (via the input device 1012) and for providing various outputs (via the output device 1014). A specific output mechanism may include a presentation device 1016 and an associated graphical user interface 1018 (GUI). In other embodiments, the input / output interface 1010 (I / O), the input device 1012, and the output device 1014 may not be included, and it may only be a computer device in a network. The computer device 1002 may also include one or more network interfaces 1020 for exchanging data with other devices via one or more communication links 1022. One or more communication buses 1024 couple the components described above together.

[0159] The communication link 1022 may be implemented in any way, for example, through a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication link 1022 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc. governed by any protocol or combination of protocols.

[0160] The methods, apparatuses (systems), computer-readable storage media, and computer program products of some embodiments of this specification are described with reference to the corresponding flowcharts and / or block diagrams. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processors to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processors generate a device for implementing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 or multiple blocks.

[0161] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processors to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 or multiple blocks.

[0162] These computer program instructions can also be loaded onto a computer or other programmable data processors, so that a series of operation steps are executed on the computer or other programmable devices to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable devices provide steps for implementing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 or multiple blocks.

[0163] In a typical configuration, a computer device includes one or more processors (CPUs), an input / output interface, a network interface, and a memory.

[0164] The memory may include non-permanent memory in the computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.

[0165] A computer-readable medium includes both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile discs (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that can store information accessible by a computing device. As defined in this specification, a computer-readable medium does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0166] Those skilled in the art should understand that the embodiments of this specification can be provided as a method, a system, or a computer program product. Therefore, the embodiments of this specification can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0167] The embodiments of this specification can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The embodiments of this specification can also be practiced in a distributed computing environment where tasks are performed by remote processors connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0168] It should also be understood that in the embodiments of this specification, the term "and / or" is merely a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. Additionally, the character " / " in this article generally represents an "or" relationship between the associated objects before and after.

[0169] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other, and the differences between each embodiment and other embodiments are emphasized. In particular, for system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and reference can be made to the corresponding parts of the method embodiments for relevant details.

[0170] In the description of this specification, the description referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the embodiments of this specification. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0171] The above description is only for the embodiments of this application and is not intended to limit this application. For those skilled in the art, various changes and modifications can be made to this application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included within the scope of the claims of this application.

Claims

1. A judicial text evaluation system optimization method, characterized in that: include: Determine the initial weights of the evaluation parameters of the judicial text evaluation system; Identify the first minority sample class in the first judicial text dataset; The first minority sample class is subjected to multi-dimensional synthetic minority class oversampling processing to fill the number of samples of the first minority sample class to form a second judicial text data set; the multi-dimensional synthetic minority class oversampling processing of the first minority sample class includes: selecting a judicial text sample from the first minority sample class as a target sample; determining the nearest neighbor of the target sample in the three-dimensional space dimension, the nearest neighbor being the judicial text sample in the first minority sample class; adding a judicial text between the target sample and its nearest neighbor using a random function as a newly added sample of the first minority sample class; identifying a second minority sample class in the second judicial text dataset; Determining an influence probability value of a weight in the evaluation parameter that is influenced by the second minority sample class; The weight corresponding to the influence probability value greater than the probability threshold is adjusted; the adjusting the weight corresponding to the influence probability value greater than the probability threshold includes: calculating the conditional entropy gain of the weight corresponding to the influence probability value greater than the probability threshold according to the formula Gain(Y,K)=H(Y)-H(Y|K); judging whether the conditional entropy gain converges; when the conditional entropy gain does not converge, adjusting the weight corresponding to the influence probability value greater than the probability threshold until the currently obtained conditional entropy gain converges; wherein Gain(Y,K) is the conditional entropy gain of the evaluation value Y under the influence of the Kth weight, H(Y) is the entropy value of the evaluation value Y, and H(Y|K) is the conditional entropy of the evaluation value Y under the influence of the Kth weight.

2. The judicial text evaluation system optimization method according to claim 1, characterized in that: The identifying a first minority sample class in a first judicial text dataset comprises: Clustering the first judicial text data set to obtain multiple judicial text classes; Calculate the number of samples of each of the judicial text categories; The judicial text class whose sample number is lower than the first target threshold is identified as the first minority sample class.

3. The judicial text evaluation system optimization method according to claim 1, characterized in that: The step of adding a judicial text between the target sample and its neighbors by using a random function includes: in, X i For the i The text features of the newly added judicial texts, N is the number of neighbors, X j For the j The text features of the nearest neighbors, rand(0,1) is a random function, X’ is the text feature of the target sample selected from the first minority sample class.

4. The judicial text evaluation system optimization method according to claim 2, characterized in that: The identifying of the second minority sample class in the second judicial text dataset comprises: Clustering the second judicial text data set to obtain multiple judicial text classes; Calculate the number of samples of each of the judicial text categories; A judicial text class whose sample quantity is lower than a second target threshold is identified as a first minority sample class; the second target threshold is greater than the first target threshold.

5. The judicial text evaluation system optimization method according to claim 1, characterized in that: Determining the influence probability value of the weight of the evaluation parameter affected by the second minority sample class includes: According to the formula Calculating an influence probability value of a weight in the evaluation parameter that is influenced by the second minority sample class; in, P ( R i = k | x i ) is the input x i The corresponding output R i For k The influence probability value of the weights is R i For the i Output features of the judicial text group, x i For the i The input features of the judicial text, exp is the exponential function, is the first class affected by the second minority sample class i The transpose of the weight vector.

6. A judicial text evaluation method, characterized in that: include: Obtain evaluation parameter data of the text to be adjudicated; The evaluation parameter data is input into a judicial text evaluation system to obtain an evaluation value corresponding to the judicial text to be processed; wherein the judicial text evaluation system is a judicial text evaluation system optimized according to the method described in any one of claims 1 to 5.

7. A judicial text evaluation system optimization device, characterized in that: include: The first determination module is used to determine the initial weights of the evaluation parameters of the judicial text evaluation system; A first recognition module, used to identify a first minority sample class in a first judicial text dataset; A sample filling module is used to perform multi-dimensional synthetic minority class oversampling processing on the first minority sample class to fill the number of samples of the first minority sample class to form a second judicial text data set; the multi-dimensional synthetic minority class oversampling processing on the first minority sample class includes: selecting a judicial text sample from the first minority sample class as a target sample; determining the nearest neighbor of the target sample in the three-dimensional space dimension, the nearest neighbor is the judicial text sample in the first minority sample class; using a random function to add a judicial text between the target sample and its nearest neighbor as a newly added sample of the first minority sample class; A second recognition module, used for identifying a second minority sample class in the second judicial text dataset; A second determination module, used to determine an influence probability value of a weight in the evaluation parameter that is influenced by the second minority sample class; A weight adjustment module is used to adjust the weight corresponding to the influence probability value greater than the probability threshold; the adjustment of the weight corresponding to the influence probability value greater than the probability threshold includes: calculating the conditional entropy gain of the weight corresponding to the influence probability value greater than the probability threshold according to the formula Gain(Y,K)=H(Y)-H(Y|K); judging whether the conditional entropy gain converges; when the conditional entropy gain does not converge, adjusting the weight corresponding to the influence probability value greater than the probability threshold until the currently obtained conditional entropy gain converges; wherein Gain(Y,K) is the conditional entropy gain of the evaluation value Y under the influence of the Kth weight, H(Y) is the entropy value of the evaluation value Y, and H(Y|K) is the conditional entropy of the evaluation value Y under the influence of the Kth weight.

8. A judicial text evaluation system, characterized in that: include: An acquisition module is used to obtain evaluation parameter data of the text to be adjudicated; An evaluation module generates an evaluation value corresponding to the judicial text according to the evaluation parameter data; wherein the judicial text evaluation system is a judicial text evaluation system optimized according to the method described in any one of claims 1 to 5.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory, characterized in that: When the computer program is executed by the processor, the computer program executes the instructions of the method according to any one of claims 1 to 6.

10. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor of a computer device, the computer program executes instructions of the method according to any one of claims 1 to 6.

11. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor of a computer device, the computer program executes instructions of the method according to any one of claims 1 to 6.

Images