A method and device for evaluating the impact of judicial technology application in judicial institutions

Abstract

This specification relates to a method and device for evaluating the impact of judicial technology applications in judicial institutions. It includes obtaining text data of a target judicial institution; calculating the correlation score between the text data and multiple first predetermined indicators to obtain the first score of each first predetermined indicator; calculating the second score of the second predetermined indicator according to the correspondence between the multiple first predetermined indicators and the second predetermined indicators and the first score of each first predetermined indicator in the multiple first predetermined indicators; calculating the final score according to the second score of each second predetermined indicator and the first weight of each second predetermined indicator in a pre-trained fuzzy cognitive map. The final score is used to evaluate the impact of judicial technology applications in the target judicial institution, and the nodes in the fuzzy cognitive map correspond to the corresponding second predetermined indicators. Through the embodiments of this specification, using the embodiments of this specification, not only the objectivity and consistency of the evaluation are improved, but also the dynamic adaptability and coverage of the evaluation are enhanced.

Description

Technical Field

[0001] The embodiments of this specification relate to the field of artificial intelligence technology, and more particularly to a method and device for evaluating the impact of judicial technology applications in judicial institutions. Background Art

[0002] Impact assessment of judicial technology applications involves quantitative analysis and evaluation of their role in improving judicial efficiency and fairness. In current judicial technology applications, the establishment of evaluation and oversight mechanisms is crucial for improving judicial efficiency and fairness. Traditionally, these evaluation systems rely on manual data collection and subjective judgment, which is not only time-consuming and labor-intensive, but also difficult to achieve highly accurate and comprehensive evaluation results.

[0003] How to reduce the workload of impact assessment of judicial technology applications and improve the assessment accuracy is a technical problem that needs to be solved urgently. Summary of the Invention

[0004] To address the problems existing in the prior art, the embodiments of this specification provide a method and device for evaluating the impact of judicial technology applications in judicial institutions. These methods utilize natural language processing technology to improve the ability to understand legal texts, while also combining multimodal data (including text, tables, images, etc.) for comprehensive analysis to enhance the depth and accuracy of information extraction. The application of fuzzy cognitive maps (FCMs) enables the model to dynamically reflect the complex relationships between evaluation indicators and adjust the model based on real-time data and feedback. Furthermore, by introducing the analytic hierarchy process (AHP), the embodiments of this specification achieve an organic combination of subjective evaluation and objective data. By comparing subjective and objective indicators and optimizing weights, a comprehensive, dynamic, and adaptive judicial technology evaluation system is formed.

[0005] The specific technical solutions of the embodiments of this specification are as follows:

[0006] On the one hand, embodiments of this specification provide a method for evaluating the impact of judicial technology applications in judicial institutions, the method comprising:

[0007] Obtain text data related to the target judicial institution and judicial technology applications;

[0008] Calculating correlation scores between the text data and a plurality of first predetermined indicators to obtain a first score for each of the first predetermined indicators;

[0009] Calculating a second score of the second predetermined indicator according to a correspondence between the plurality of first predetermined indicators and the second predetermined indicator and a first score of each first predetermined indicator in the plurality of first predetermined indicators;

[0010] The final score is calculated based on the second score of each second predetermined indicator and the first weight of each second predetermined indicator in the pre-trained fuzzy cognitive map. The final score is used to evaluate the influence of judicial technology application of the target judicial institution. The nodes in the fuzzy cognitive map correspond to the corresponding second predetermined indicators.

[0011] Furthermore, obtaining text data related to the target judicial institution and judicial technology applications further includes:

[0012] Obtaining judicial text data related to the target judicial institution and the judicial technology application;

[0013] Distributing a questionnaire related to the judicial technology application to staff of the target judicial institution and obtaining text data of the feedback results of the questionnaire;

[0014] The judicial text data and the feedback result text data are used as the text data.

[0015] Furthermore, the first predetermined indicator includes a category of indicators;

[0016] Calculating the correlation scores between the text data and a plurality of first predetermined indicators to obtain a first score for each of the first predetermined indicators further includes:

[0017] Extracting at least one keyword corresponding to each category of indicators in the text data;

[0018] The matching degree between the keyword and the indicator of the first category is calculated to obtain a first score of the indicator of the first category.

[0019] Furthermore, calculating the matching degree between the keyword and the one type of indicator to obtain a first score of the one type of indicator further includes:

[0020] According to the formula Calculate the inverse document frequency of the keyword, where IDF ( k , D ) indicates keywords k In the documentation D Inverse document frequency in , N Represents the total number of documents in the text data;

[0021] According to the formula Calculate the second weight of the first type of indicators, where: Weight ( I ) represents a type of indicator I The second weight, f ( k , D ) indicates keywords k In the documentationD The frequency of occurrence in

[0022] According to the formula Calculate the first score corresponding to the type of indicator, where: EmotionScore ( I ) represents a type of indicator I The first score, E ( k ) indicates keywords k The semantic embedding vector of .

[0023] Furthermore, the first predetermined indicator includes two types of indicators;

[0024] Calculating the correlation scores between the text data and a plurality of first predetermined indicators to obtain a first score for each of the first predetermined indicators further includes:

[0025] Analyze the text data using a pre-trained natural language processing model to obtain a key information vector;

[0026] According to the key information vector and the third weight of the second category of indicators, according to the formula Calculate the first score corresponding to the second type of indicators, where: S ( D , I ) represents a document in text data D and the second category indicators I The corresponding first score, LLM ( D ) indicates a document D The corresponding key information vector, W I Represents the second category index I The third weight.

[0027] Furthermore, according to the correspondence between the plurality of first predetermined indicators and the second predetermined indicators and the first score of each first predetermined indicator in the plurality of first predetermined indicators, calculating the second score of the second predetermined indicator further includes:

[0028] The first scores of the plurality of first predetermined indicators under a second predetermined indicator are summed to obtain a second score of the second predetermined indicator.

[0029] Furthermore, calculating the final score according to the second score of each second predetermined indicator and the first weight of each second predetermined indicator in the pre-trained fuzzy cognitive map further includes:

[0030] According to the formula The final score is calculated, where S all Indicates the final score,n represents the total number of the second predetermined index, w i Represents the second predetermined index in the trained fuzzy cognitive map i The corresponding first weight, S 2( I i ) represents the second predetermined index i 's second score.

[0031] On the other hand, the embodiments of this specification also provide a device for evaluating the impact of judicial technology applications in a judicial institution, the device comprising:

[0032] A text data acquisition unit, used to acquire text data related to the target judicial institution and judicial technology applications;

[0033] a first score calculation unit, configured to calculate a correlation score between the text data and a plurality of first predetermined indicators, and obtain a first score for each of the first predetermined indicators;

[0034] a second score calculation unit, configured to calculate a second score of the second predetermined indicator based on a correspondence between the plurality of first predetermined indicators and the second predetermined indicators and a first score of each first predetermined indicator in the plurality of first predetermined indicators;

[0035] A final score calculation unit is used to calculate the final score based on the second score of each second predetermined indicator and the first weight of each second predetermined indicator in a pre-trained fuzzy cognitive map. The final score is used to evaluate the influence of judicial technology application of the target judicial institution. The nodes in the fuzzy cognitive map correspond to the corresponding second predetermined indicators.

[0036] On the other hand, an embodiment of this specification further provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor implements the above method when executing the computer program.

[0037] On the other hand, an embodiment of this specification further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0038] The use of the embodiments of this specification not only improves the objectivity and consistency of the evaluation, but also enhances the dynamic adaptability and coverage of the evaluation. In particular, the embodiments of this specification greatly improve the evaluation efficiency through automation technology and multimodal data processing, adapt to the evaluation needs of large-scale and complex systems, and form a comprehensive, dynamic and adaptive judicial institution evaluation system, providing judicial institutions with a scientific and comprehensive evaluation tool. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0040] Figure 1 The figure shows a schematic diagram of an implementation system of a method for evaluating the impact of judicial technology applications in a judicial institution in an embodiment of this specification;

[0041] Figure 2 The figure shows a flow chart of a method for evaluating the impact of judicial technology applications in a judicial institution in an embodiment of this specification;

[0042] Figure 3 The figure shows the structure of FCM in the embodiment of this specification;

[0043] Figure 4 Shown is a flowchart of the process of obtaining text data related to the target judicial institution and judicial technology applications in this specification;

[0044] Figure 5 FIG2 is a flow chart of calculating the correlation scores between the text data and a plurality of first predetermined indicators and obtaining a first score for each of the first predetermined indicators according to an embodiment of the present specification;

[0045] Figure 6 The figure shows a schematic diagram of the structure of a judicial science and technology application impact assessment device of a judicial institution in an embodiment of this specification;

[0046] Figure 7 The figure shows a schematic diagram of the structure of a computer device in an embodiment of this specification.

[0047]

Description of the accompanying drawings

[0048] 101. Terminal;

[0049] 102. Server;

[0050] 601, text data acquisition unit;

[0051] 602. A first score calculation unit;

[0052] 603. Second score calculation unit;

[0053] 604. Final score calculation unit;

[0054] 702. Computer equipment;

[0055] 704. Processing equipment;

[0056] 706. Storage resources;

[0057] 708, drive system;

[0058] 710, input / output module;

[0059] 712. Input devices;

[0060] 714. Output device;

[0061] 716. Presentation equipment;

[0062] 718. Graphical User Interface;

[0063] 720, network interface;

[0064] 722, communication link;

[0065] 724. Communication bus. DETAILED DESCRIPTION

[0066] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the embodiments described are only part of the embodiments of this specification, not all of them. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the embodiments of this specification.

[0067] It should be noted that the terms "first", "second", etc. in the description and claims of the embodiments of this specification and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the embodiments of this specification described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0068] It should be noted that the acquisition, storage, use, and processing of data in the technical solutions of the embodiments of this specification comply with the relevant provisions of national laws and regulations.

[0069] It should be noted that in the embodiments of this specification, certain software, components, models and other existing solutions in the industry may be mentioned. They should be regarded as exemplary and their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0070] like Figure 1 The figure shows a schematic diagram of a system for implementing a method for evaluating the impact of judicial technology applications in a judicial institution according to an embodiment of the present specification, including a terminal 101 and a server 102. The terminal 101 and the server 102 can communicate with each other via a network, which can include a local area network (LAN), a wide area network (WAN), the Internet, or a combination thereof, and is connected to a website, a user device (e.g., a computing device), and a back-end system.

[0071] The staff can input text data related to the judicial institution and judicial technology applications into the server 102 through the terminal 101. The server 102 analyzes and processes the text data, calculates the final evaluation score, and provides the final score to the staff through the terminal 101 so that the staff can evaluate the influence of the judicial technology applications of the target judicial institution based on the final score.

[0072] Alternatively, the server 102 may be a node of a cloud computing system (not shown), or each server may be a separate cloud computing system including multiple computers interconnected by a network and operating as a distributed processing system.

[0073] In addition, it should be noted that Figure 1 What is shown is only one application environment provided by the embodiment of this specification. In actual application, other application environments may also be included, and this specification does not limit them.

[0074] In response to the problems in the prior art, this specification provides a method for evaluating the impact of judicial technology applications in judicial institutions. Figure 2 The figure shows a flow chart of a method for assessing the impact of judicial technology applications in judicial institutions, as described in an embodiment of this specification. This figure describes the process of assessing the impact of technology applications in judicial institutions. The order of steps listed in the embodiment is only one of many possible execution sequences and does not represent the only execution sequence. When implemented in a real system or device product, the methods shown in the embodiment or the accompanying drawings may be executed sequentially or in parallel.

[0075] Specific examples Figure 2 As shown, the method may include:

[0076] Step 201: Acquire text data related to the target judicial institution and judicial technology applications;

[0077] Step 202: Calculating correlation scores between the text data and a plurality of first predetermined indicators to obtain a first score for each of the first predetermined indicators;

[0078] Step 203: Calculating a second score of the second predetermined indicator based on the correspondence between the plurality of first predetermined indicators and the second predetermined indicator and the first score of each first predetermined indicator in the plurality of first predetermined indicators;

[0079] Step 204: Calculate a final score based on the second score of each second predetermined indicator and the first weight of each second predetermined indicator in the pre-trained fuzzy cognitive map. The final score is used to evaluate the influence of judicial technology application of the target judicial institution. The nodes in the fuzzy cognitive map correspond to the corresponding second predetermined indicators.

[0080] The use of the embodiments of this specification not only improves the objectivity and consistency of the evaluation, but also enhances the dynamic adaptability and coverage of the evaluation. In particular, the embodiments of this specification greatly improve the evaluation efficiency through automation technology and multimodal data processing, adapt to the evaluation needs of large-scale and complex systems, and form a comprehensive, dynamic and adaptive judicial institution evaluation system, providing judicial institutions with a scientific and comprehensive evaluation tool.

[0081] In the embodiments of this specification, the application of the final score is mainly reflected in providing data support for the optimization and improvement of judicial technology applications. The high or low final score can help judicial institutions identify deficiencies in the application of judicial technology, thereby optimizing the resource allocation of judicial institutions and promoting technological improvements in judicial technology. For example, if the final score is lower than the predetermined threshold value, it means that the judicial technology application of the judicial institution is insufficient and staff need to make improvements and optimizations.

[0082] At the same time, the final score can be self-optimized through continuous monitoring and feedback mechanisms, ensuring that it always adapts to the dynamic and changing judicial environment. Furthermore, the openness and transparency of the final score will enhance users' trust in judicial technology and the judicial system, thereby enhancing the credibility and transparency of the judiciary.

[0083] In the embodiments of this specification, the second predetermined indicator is a predefined indicator by staff that directly reflects the impact of judicial technology applications. The specific indicator can be set or adjusted by staff based on experience and is not limited in this embodiment. For example, the second predetermined indicator may include social conflict resolution, judicial fairness and justice, and social risk monitoring and early warning.

[0084] The staff then further decomposes the second predetermined indicator to obtain its corresponding multiple first predetermined indicators, ensuring that each first predetermined indicator can specifically and accurately measure the evaluation content it represents, while facilitating effective tracking and monitoring through data.

[0085] It can be understood that the first predetermined indicator is the scoring point of the second predetermined indicator to which it belongs. The first score between the first predetermined indicator and the text data related to judicial technology application is the score of the judicial institution's judicial technology application at the corresponding scoring point. The second score of the second predetermined indicator is the sum of the first scores of all the first predetermined indicators decomposed from the second predetermined indicator.

[0086] Specifically, based on the correspondence between multiple first predetermined indicators and second predetermined indicators and the first score of each first predetermined indicator in the multiple first predetermined indicators, calculating the second score of the second predetermined indicator further includes: summing the first scores of multiple first predetermined indicators under one second predetermined indicator to obtain the second score of the second predetermined indicator.

[0087] In the embodiments of this specification, the second predetermined indicator is a predefined indicator by staff that directly reflects the impact of judicial technology applications. However, each second predetermined indicator has slightly different weights for determining the impact of judicial technology applications. To improve the accuracy of the assessment of the impact of judicial technology applications, this embodiment uses a fuzzy cognitive map (FCM) to train the first weights of each second predetermined indicator. Thus, after calculating the second score of each second predetermined indicator, the final score is calculated based on the second score of each second predetermined indicator and the first weights of each second predetermined indicator in the pre-trained fuzzy cognitive map.

[0088] Specifically, an FCM is constructed in advance based on the existing text data, in which the nodes represent a second predetermined indicator in the assessment of the impact of judicial technology, and the edges represent the relationship between the corresponding second predetermined indicators. Each node and edge has specific attributes and weights, reflecting their importance in the assessment of the impact of judicial technology applications. These nodes and edges will be designed in combination with the specific detailed indicators in the second predetermined indicator system to ensure that each node can accurately represent a specific dimension of the impact of judicial technology applications. In actual implementation, the FCM structure diagram can be referred to Figure 3 .

[0089] Then, node feature aggregation is performed. For each node in FCM, the feature information of its neighboring nodes is aggregated to enhance the node's representation ability. The aggregation function in FCM is used to dynamically adjust the weight according to the importance of neighboring nodes. The basic model of FCM can be expressed as formula (1):

[0090] (1)

[0091] in, C i ( t ) represents a node i In time t The conceptual value of W ij Represents a slave node i To Node j The weight of f is the activation function (usually a Sigmoid function).

[0092] Weight Assignment and Optimization: The initial weight of each node in FCM is determined by preliminary judgment by domain experts. Edges represent the mutual influence between secondary predetermined indicators, and their initial weights are typically derived through correlation analysis of literature and historical data. Each piece of evidence (text data) related to a secondary predetermined indicator constitutes a dataset, and the subjective ratings for that secondary predetermined indicator serve as data labels for model training.

[0093] In the embodiments of this specification, domain experts can use the analytic hierarchy process (AHP) to obtain the initial value of the FCM, so that there is a good start in the training process of the FCM. The model is fine-tuned and iteratively optimized during the scoring process, and finally the training is completed to obtain the weight of each node in the FCM.

[0094] Through FCM and AHP, dynamic modeling and weighting of evaluation indicators are achieved. By constructing a graph model of complex relationships through FCM and training it within a graph neural network, the evaluation model is dynamically adjusted to reflect the changes and impacts of judicial technology applications in real time. This dynamic evaluation method enhances the timeliness and adaptability of the evaluation, ensuring timely updates and optimization of the results.

[0095] By integrating subjective evaluation factors through AHP, constructing a discriminant matrix and conducting consistency tests, and rationally allocating subjective weights, we achieved an organic combination of subjective evaluation and objective data. By designing and implementing a subjective questionnaire and collecting opinions from experts and judicial personnel, we further refined and adjusted the model's weights, making the evaluation results more comprehensive, fair, and scientific.

[0096] According to one embodiment of this specification, Figure 4 As shown, obtaining text data related to the target judicial institution and judicial technology applications further includes:

[0097] Step 401: Obtaining judicial text data related to the target judicial institution and the judicial technology application;

[0098] Step 402: Distribute a questionnaire related to the judicial technology application to the staff of the target judicial institution, and obtain text data of the feedback results of the questionnaire;

[0099] Step 403: The judicial text data and the feedback result text data are used as the text data.

[0100] In the embodiments of this specification, the text data related to judicial institutions and judicial technology applications include judicial text data and feedback result text data.

[0101] Judicial text data can be obtained from multiple sources, including judicial databases, electronic files, and legal documents, to obtain data and information related to the impact of judicial technology applications. This data can then be preliminarily screened and categorized to eliminate irrelevant information and retain valuable text data for subsequent analysis.

[0102] For missing values ​​in the dataset, use interpolation techniques, including but not limited to mean interpolation, median interpolation, or interpolation methods based on predictive models. For features with extremely high missing rates, consider removing these features from the feature set to reduce the impact of noise on the analysis results.

[0103] Staff can pre-design a questionnaire based on judicial technology applications, distribute it to staff at target judicial institutions, and obtain text data on the questionnaire's feedback. Finally, the obtained judicial text data and feedback text data are used as the text data required for evaluation.

[0104] In the embodiment of this specification, the first predetermined indicator is a decomposition of the second predetermined indicator, so the first predetermined indicator includes fuzzy indicators and clear indicators. If the same correlation calculation method is used to calculate the first score of each first predetermined indicator and the text data, there will be a certain deviation.

[0105] Among them, a semantic recognition model can be pre-trained, and the semantic recognition model is used to determine whether the indicator is fuzzy or clear. The first predetermined indicator is input into the trained semantic recognition model to obtain semantic classification. The classification results include fuzzy classes and cleaned classes, thereby determining whether the first predetermined indicator is a fuzzy indicator or a clear indicator.

[0106] For example, if the first predetermined indicator is "whether there are provisions for accountability methods," and the semantic recognition model finds "accountability methods" to be a vague term, the result obtained by the semantic recognition model is a vague indicator. If the first predetermined indicator is "whether the document named xx is disclosed" or "case closure rate," the result obtained by the semantic recognition model is a clear indicator.

[0107] Therefore, the embodiment of this specification takes the clear indicators as a category of indicators and uses the keyword matching method to calculate the first score between the category of indicators and the text data.

[0108] Specifically, if Figure 5 As shown, calculating the correlation scores between the text data and a plurality of first predetermined indicators to obtain a first score of each of the first predetermined indicators further includes:

[0109] Step 501: extracting at least one keyword corresponding to each category of indicators in the text data;

[0110] Step 502: Calculate the matching degree between the keyword and the indicator of the category to obtain a first score of the indicator of the category.

[0111] In an embodiment of the present specification, at least one keyword corresponding to a category of indicators can be extracted from the text data using natural language recognition technology, and then the matching degree between each keyword and a category of indicators is calculated, and the matching degrees are summed to obtain a first score for the category of indicators.

[0112] Calculating the matching degree between the keyword and the one type of indicator to obtain a first score of the one type of indicator further includes:

[0113] The inverse document frequency of the keyword is calculated according to formula (2):

[0114] (2)

[0115] in, IDF ( k , D ) indicates keywords k In the documentation D Inverse document frequency in , N Represents the total number of documents in the text data;

[0116] The second weight of the aforementioned indicator is calculated according to formula (3):

[0117] (3)

[0118] in, Weight ( I ) represents a type of indicator I The second weight, f ( k , D ) indicates keywords k In the documentation D The frequency of occurrence in

[0119] The first score corresponding to the indicator of the above type is calculated according to formula (4):

[0120] (4)

[0121] in, EmotionScore ( I ) represents a type of indicator I The first score, E ( k ) indicates keywords k The semantic embedding vector of .

[0122] The embodiment of this specification regards the fuzzy index as the second-class index, and uses a large model to calculate the first score between the second-class index and the text data.

[0123] Specifically, calculating the correlation scores between the text data and a plurality of first predetermined indicators to obtain a first score of each of the first predetermined indicators further includes:

[0124] Analyze the text data using a pre-trained natural language processing model to obtain a key information vector;

[0125] According to the key information vector and the third weight of the second category indicator, the first score corresponding to the second category indicator is calculated according to formula (5):

[0126] (5)

[0127] in, S ( D , I ) represents a document in text data D and the second category indicators I The corresponding first score, LLM ( D ) indicates a document D The corresponding key information vector, W I Represents the second category index I The third weight of W I It can be set by the staff based on experience, and the embodiments of this specification do not limit it.

[0128] By leveraging the powerful capabilities of large models, we can not only efficiently process and analyze complex text data, but also accurately identify and extract legal concepts and public sentiment, thereby improving the accuracy and depth of information extraction, reducing the need for manual intervention, and improving work efficiency.

[0129] In this embodiment of the present specification, calculating the final score according to the second score of each second predetermined indicator and the first weight of each second predetermined indicator in the pre-trained fuzzy cognitive map further includes:

[0130] The final score is calculated according to formula (6):

[0131] (6)

[0132] in, S all Indicates the final score, n represents the total number of the second predetermined index, w i Represents the second predetermined index in the trained fuzzy cognitive map i The corresponding first weight, S 2( I i ) represents the second predetermined index i 's second score.

[0133] The final score reflects whether the target judicial institution's judicial technology applications meet the requirements. The staff will then improve and optimize the target judicial institution's judicial technology applications based on the final score, thereby improving the judicial institution's efficiency and user experience.

[0134] Based on the same inventive concept, the embodiment of this specification also provides a device for evaluating the impact of judicial technology applications in judicial institutions. Figure 6 As shown, the device includes:

[0135] A text data acquisition unit 601 is used to acquire text data related to the target judicial institution and judicial technology applications;

[0136] A first score calculation unit 602 is configured to calculate a correlation score between the text data and a plurality of first predetermined indicators to obtain a first score for each of the first predetermined indicators;

[0137] A second score calculation unit 603 is configured to calculate a second score of the second predetermined indicator based on the correspondence between the plurality of first predetermined indicators and the second predetermined indicators and the first score of each first predetermined indicator in the plurality of first predetermined indicators;

[0138] The final score calculation unit 604 is used to calculate the final score based on the second score of each second predetermined indicator and the first weight of each second predetermined indicator in the pre-trained fuzzy cognitive map. The final score is used to evaluate the influence of judicial technology application of the target judicial institution. The nodes in the fuzzy cognitive map correspond to the corresponding second predetermined indicators.

[0139] Furthermore, obtaining text data related to the target judicial institution and judicial technology applications further includes:

[0140] Obtaining judicial text data related to the target judicial institution and the judicial technology application;

[0141] Distributing a questionnaire related to the judicial technology application to staff of the target judicial institution and obtaining text data of the feedback results of the questionnaire;

[0142] The judicial text data and the feedback result text data are used as the text data.

[0143] Furthermore, the first predetermined indicator includes a category of indicators;

[0144] Calculating the correlation scores between the text data and a plurality of first predetermined indicators to obtain a first score for each of the first predetermined indicators further includes:

[0145] Extracting at least one keyword corresponding to each category of indicators in the text data;

[0146] The matching degree between the keyword and the indicator of the first category is calculated to obtain a first score of the indicator of the first category.

[0147] Furthermore, calculating the matching degree between the keyword and the one type of indicator to obtain a first score of the one type of indicator further includes:

[0148] According to the formula Calculate the inverse document frequency of the keyword, where IDF ( k , D ) indicates keywords k In the documentation D Inverse document frequency in , N Represents the total number of documents in the text data;

[0149] According to the formula Calculate the second weight of the first type of indicators, where: Weight ( I ) represents a type of indicator I The second weight, f ( k , D ) indicates keywords k In the documentation D The frequency of occurrence in

[0150] According to the formula Calculate the first score corresponding to the type of indicator, where: EmotionScore ( I ) represents a type of indicator I The first score, E ( k ) indicates keywords k The semantic embedding vector of .

[0151] Furthermore, the first predetermined indicator includes two types of indicators;

[0152] Calculating the correlation scores between the text data and a plurality of first predetermined indicators to obtain a first score for each of the first predetermined indicators further includes:

[0153] Analyze the text data using a pre-trained natural language processing model to obtain a key information vector;

[0154] According to the key information vector and the third weight of the second category of indicators, according to the formula Calculate the first score corresponding to the second type of indicators, where: S ( D , I ) represents a document in text data D and the second category indicators I The corresponding first score, LLM ( D ) indicates a document D The corresponding key information vector, W I Represents the second category index I The third weight.

[0155] Furthermore, according to the correspondence between the plurality of first predetermined indicators and the second predetermined indicators and the first score of each first predetermined indicator in the plurality of first predetermined indicators, calculating the second score of the second predetermined indicator further includes:

[0156] The first scores of the plurality of first predetermined indicators under a second predetermined indicator are summed to obtain a second score of the second predetermined indicator.

[0157] Furthermore, calculating the final score according to the second score of each second predetermined indicator and the first weight of each second predetermined indicator in the pre-trained fuzzy cognitive map further includes:

[0158] According to the formula The final score is calculated, where S all Indicates the final score, n represents the total number of the second predetermined index, w i Represents the second predetermined index in the trained fuzzy cognitive map i The corresponding first weight, S 2( I i ) represents the second predetermined index i 's second score.

[0159] Since the principle of solving the problem by the above device is similar to that of the above method, the implementation of the above system can refer to the implementation of the above method, and the repeated parts will not be repeated.

[0160] like Figure 7 Schematic diagram of the structure of a computer device according to an embodiment of the present specification. The computer device according to this embodiment is capable of executing the methods of the embodiments of the present specification described above. Computer device 702 may include one or more processing devices 704, such as one or more central processing units (CPUs), each of which may implement one or more hardware threads. Computer device 702 may also include any storage resources 706 for storing any type of information, such as code, settings, data, etc. For example, and without limitation, storage resources 706 may include any one or more combinations of the following: any type of RAM, any type of ROM, flash memory devices, hard disks, optical disks, etc. More generally, any storage resource may use any technology to store information. Furthermore, any storage resource may provide volatile or non-volatile retention of information. Furthermore, any storage resource may represent a fixed or removable component of computer device 702. In one embodiment, when processing device 704 executes associated instructions stored in any storage resource or combination of storage resources, computer device 702 may perform any operation of the associated instructions. The computer device 702 also includes one or more drive systems 708 for interacting with any storage resources, such as a hard disk drive system, an optical disk drive system, and the like.

[0161] Computer device 702 may also include an input / output module 710 (I / O) for receiving various inputs (via input devices 712) and providing various outputs (via output devices 714). A specific output mechanism may include a presentation device 716 and an associated graphical user interface (GUI) 718. In other embodiments, input / output module 710 (I / O), input devices 712, and output devices 714 may not be included, and the computer device 702 may simply function as a single computer device on a network. Computer device 702 may also include one or more network interfaces 720 for exchanging data with other devices via one or more communication links 722. One or more communication buses 724 couple the components described above.

[0162] The communication link 722 may be implemented in any manner, for example, via 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 722 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc., governed by any protocol or combination of protocols.

[0163] The embodiments of this specification also provide a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0164] The embodiments of this specification also provide a computer-readable instruction, wherein when a processor executes the instruction, the program therein causes the processor to execute the above method.

[0165] It should be understood that in the various embodiments of the present specification, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present specification.

[0166] It should also be understood that in the embodiments of this specification, the term "and / or" is merely a description of the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent three situations: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, in the embodiments of this specification, the character " / " generally indicates that the associated objects are in an "or" relationship.

[0167] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the embodiments of this specification can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the embodiments of this specification.

[0168] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0169] In the several embodiments provided in the embodiments of this specification, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or can be electrical, mechanical or other forms of connection.

[0170] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of this specification.

[0171] In addition, the functional units in each embodiment of the present specification may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0172] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of this specification is essentially or the part that contributes to the existing technology, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the embodiments of this specification. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

[0173] The embodiments of this specification use specific embodiments to illustrate the principles and implementation methods of the embodiments of this specification. The description of the above embodiments is only used to help understand the methods and core ideas of the embodiments of this specification. At the same time, for those skilled in the art, based on the ideas of the embodiments of this specification, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the embodiments of this specification.

Claims

1. A method for evaluating the impact of judicial technology application in judicial institutions, characterized in that: The method comprises: Obtain text data related to the target judicial institution and judicial technology applications; Calculate the correlation scores between the text data and a plurality of first predetermined indicators to obtain a first score of each of the first predetermined indicators; calculate a second score of the second predetermined indicator according to the correspondence between the plurality of first predetermined indicators and the second predetermined indicators and the first score of each of the plurality of first predetermined indicators, wherein the second predetermined indicator is an indicator pre-defined by the staff that can directly reflect the influence of the application of judicial technology, and the first predetermined indicator is a decomposition of the second predetermined indicator; The first predetermined indicator includes a category of indicators, and the category of indicators is clear indicators; wherein a semantic recognition model is pre-trained, and the semantic recognition model is used to determine whether the indicator is fuzzy or clear, and the first predetermined indicator is input into the trained semantic recognition model to obtain a semantic classification, and the classification result includes a fuzzy class and a clear class. If it is a clear class, the first predetermined indicator is a clear indicator; Calculating the correlation scores between the text data and a plurality of first predetermined indicators to obtain a first score of each of the first predetermined indicators further comprises: Extracting at least one keyword corresponding to each category of indicators in the text data; Calculating the matching degree between the keyword and the one type of indicator to obtain a first score of the one type of indicator; Calculating the matching degree between the keyword and the one type of indicator to obtain a first score of the one type of indicator further includes: According to the formula Calculate the second weight of the first type of indicators, where: Weight ( I ) represents a type of indicator I The second weight, f ( k , D ) indicates a keyword k In the documentation D The frequency of occurrence in IDF ( k , D ) indicates a keyword k In the documentation D Inverse document frequency in ; According to the formula Calculate the first score corresponding to the type of indicator, where: EmotionScore ( I ) represents a type of indicator I The first score, E ( k ) indicates a keyword k The semantic embedding vector of The first predetermined indicator also includes two types of indicators, and the two types of indicators are fuzzy indicators. The first predetermined indicator is input into the semantic recognition model to obtain a semantic classification. If it is a fuzzy class, the first predetermined indicator is a fuzzy indicator; Calculating the correlation scores between the text data and a plurality of first predetermined indicators to obtain a first score of each of the first predetermined indicators further comprises: Analyze the text data using a pre-trained natural language processing model to obtain a key information vector; According to the key information vector and the third weight of the second category of indicators, according to the formula Calculate the first score corresponding to the second type of indicators, where: S ( D , I ) represents a document in text data D With the second category index I The corresponding first score, LLM ( D ) indicates a document D The corresponding key information vector, W I Represents the second category index I The third weight of Calculating the second score of the second predetermined indicator according to the correspondence between the plurality of first predetermined indicators and the second predetermined indicator and the first score of each first predetermined indicator in the plurality of first predetermined indicators further includes: The first scores of multiple first predetermined indicators under a second predetermined indicator are summed to obtain a second score of the second predetermined indicator; a final score is calculated according to the second scores of the second predetermined indicators and the first weights of the respective second predetermined indicators in the pre-trained fuzzy cognitive map, and the final score is used to evaluate the influence of judicial technology application of the target judicial institution, and the nodes in the fuzzy cognitive map correspond to the corresponding second predetermined indicators; Calculating the final score according to the second score of each second predetermined indicator and the first weight of each second predetermined indicator in the pre-trained fuzzy cognitive map further includes: According to the formula The final score is calculated, where S all Indicates the final score, n represents the total number of the second predetermined index, w i Represents the second predetermined index in the trained fuzzy cognitive map i The corresponding first weight is, S 2( I i ) represents the second predetermined index i 's second score.

2. The method according to claim 1, characterized in that Acquiring text data related to the target judicial institution and judicial technology applications further includes: Acquire judicial text data related to the target judicial institution and the judicial technology application; Distributing a questionnaire related to the judicial technology application to the staff of the target judicial institution, and obtaining text data of the feedback results of the questionnaire; The judicial text data and the feedback result text data are used as the text data.

3. A judicial institution's judicial technology application impact assessment device, characterized in that: The device comprises: A text data acquisition unit, used to acquire text data related to the target judicial institution and judicial technology applications; A first score calculation unit, used for calculating the correlation scores between the text data and a plurality of first predetermined indicators, and obtaining a first score for each of the first predetermined indicators; A second score calculation unit, configured to calculate a second score of the second predetermined indicator according to a correspondence between the plurality of first predetermined indicators and the second predetermined indicator and a first score of each of the plurality of first predetermined indicators, wherein the second predetermined indicator is an indicator pre-defined by a staff member that can directly reflect the influence of judicial technology application, and the first predetermined indicator is a decomposition of the second predetermined indicator; The first predetermined indicator includes a category of indicators, and the category of indicators is clear indicators; wherein a semantic recognition model is pre-trained, and the semantic recognition model is used to determine whether the indicator is fuzzy or clear, and the first predetermined indicator is input into the trained semantic recognition model to obtain a semantic classification, and the classification result includes a fuzzy class and a clear class. If it is a clear class, the first predetermined indicator is a clear indicator; Calculating the correlation scores between the text data and a plurality of first predetermined indicators to obtain a first score of each of the first predetermined indicators further comprises: Extracting at least one keyword corresponding to each category of indicators in the text data; Calculating the matching degree between the keyword and the one type of indicator to obtain a first score of the one type of indicator; Calculating the matching degree between the keyword and the one type of indicator to obtain a first score of the one type of indicator further includes: According to the formula Calculate the second weight of the first type of indicators, where: Weight ( I ) represents a type of indicator I The second weight, f ( k , D ) indicates a keyword k In the documentation D The frequency of occurrence in IDF ( k , D ) indicates a keyword k In the documentation D Inverse document frequency in ; According to the formula Calculate the first score corresponding to the type of indicator, where: EmotionScore ( I ) represents a type of indicator I The first score, E ( k ) indicates a keyword k The semantic embedding vector of The first predetermined indicator also includes two types of indicators, and the two types of indicators are fuzzy indicators. The first predetermined indicator is input into the semantic recognition model to obtain a semantic classification. If it is a fuzzy class, the first predetermined indicator is a fuzzy indicator; Calculating the correlation scores between the text data and a plurality of first predetermined indicators to obtain a first score of each of the first predetermined indicators further comprises: Analyze the text data using a pre-trained natural language processing model to obtain a key information vector; According to the key information vector and the third weight of the second category of indicators, according to the formula Calculate the first score corresponding to the second type of indicators, where: S ( D , I ) represents a document in text data D With the second category index I The corresponding first score, LLM ( D ) indicates a document D The corresponding key information vector, W I Represents the second category index I The third weight of Calculating the second score of the second predetermined indicator according to the correspondence between the plurality of first predetermined indicators and the second predetermined indicator and the first score of each first predetermined indicator in the plurality of first predetermined indicators further includes: summing the first scores of the plurality of first predetermined indicators under a second predetermined indicator to obtain a second score of the second predetermined indicator; A final score calculation unit, configured to calculate a final score according to the second score of each second predetermined indicator and the first weight of each second predetermined indicator in the pre-trained fuzzy cognitive map, wherein the final score is used to evaluate the influence of judicial technology application of the target judicial institution, and the nodes in the fuzzy cognitive map correspond to the corresponding second predetermined indicators; Calculating the final score according to the second score of each second predetermined indicator and the first weight of each second predetermined indicator in the pre-trained fuzzy cognitive map further includes: According to the formula The final score is calculated, where S all Indicates the final score, n represents the total number of the second predetermined index, w i Represents the second predetermined index in the trained fuzzy cognitive map i The corresponding first weight is, S 2( I i ) represents the second predetermined index i 's second score.

4. A computer device comprising a memory, a processor, and a computer program stored in the memory, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 2 is implemented.

5. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 2 is implemented.

Images