CN117951260A - Decision simulation execution method and device - Google Patents
Decision simulation execution method and device Download PDFInfo
- Publication number
- CN117951260A CN117951260A CN202311628827.2A CN202311628827A CN117951260A CN 117951260 A CN117951260 A CN 117951260A CN 202311628827 A CN202311628827 A CN 202311628827A CN 117951260 A CN117951260 A CN 117951260A
- Authority
- CN
- China
- Prior art keywords
- data
- early warning
- model
- execution
- case
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000004088 simulation Methods 0.000 title claims abstract description 29
- 230000007246 mechanism Effects 0.000 claims abstract description 20
- 230000002159 abnormal effect Effects 0.000 claims abstract description 19
- 238000007781 pre-processing Methods 0.000 claims abstract description 18
- 230000008569 process Effects 0.000 claims abstract description 17
- 230000006870 function Effects 0.000 claims abstract description 4
- 238000003058 natural language processing Methods 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 15
- 238000007670 refining Methods 0.000 claims description 13
- 230000005856 abnormality Effects 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000005516 engineering process Methods 0.000 claims description 7
- 230000004927 fusion Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 238000010801 machine learning Methods 0.000 claims description 5
- 238000003860 storage Methods 0.000 claims description 3
- 239000013598 vector Substances 0.000 claims description 3
- 238000011161 development Methods 0.000 claims description 2
- 239000000284 extract Substances 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 11
- 230000008520 organization Effects 0.000 abstract 1
- 230000004044 response Effects 0.000 abstract 1
- 238000005457 optimization Methods 0.000 description 5
- 230000003993 interaction Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000013136 deep learning model Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
- G06F40/35—Discourse or dialogue representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a decision simulation execution method and a device, wherein the decision simulation execution method comprises the following steps: s1, acquiring business and case data to be analyzed, and carrying out query preprocessing to form a query database; s2, establishing a problem keyword index between the query database and the problem keyword index, and simultaneously establishing a predictive early warning information active pushing mechanism; and S3, a one-dimensional virtual digital execution model is established, answers to the questions are obtained according to the question keyword indexes, and abnormal information is subjected to abnormal early warning according to the prediction early warning information pushing mechanism. The decision simulation execution method is used for simulating the behavior of manually processing the problem and the decision making process so as to improve the decision making efficiency and accuracy, and by integrating the intelligent, automatic and early warning functions, the prediction capability of a decision maker on future events is enhanced, and the overall decision making capability and response speed of an organization are improved.
Description
Technical Field
The invention belongs to the technical field of computers, and particularly relates to a decision simulation execution method and device.
Background
In most industries and fields, the decision making process is complex and variable, often requiring manual work. Traditional decision making methods often rely on experience and intuition of the practitioner to process the information and make selections. For example, when a court staff is handling various index problems and emergency events, the data needs to be checked and analyzed by a plurality of systems respectively, and the method is time-consuming and labor-consuming, and can cause unstable decision efficiency and quality due to limited information processing capability of individuals. In modern decision making environments, the explosive growth of data volume makes manual processing more difficult.
In addition, conventional decision methods often lack real-time intelligent question-answering and risk early warning mechanisms, so that decision makers cannot respond quickly when facing emergency situations, or it is difficult to foresee potential problems and opportunities in the decision process. Thus, traditional decision methods appear to be increasingly outdated in modern business and technical environments and insufficient to meet modern business needs.
In view of this, the present invention has been made.
Disclosure of Invention
In view of the above, the invention discloses a decision simulation execution method and a device, which are used for simulating the behavior of a manual processing problem and the decision making process so as to improve the decision making efficiency and accuracy.
Specifically, the invention is realized by the following technical scheme:
In a first aspect, the invention discloses a decision simulation execution method, which comprises the following steps:
S1, acquiring business and case data to be analyzed, and carrying out query preprocessing to form a query database;
S2, establishing a problem keyword index between the query database and the problem keyword index, and simultaneously establishing a predictive early warning information active pushing mechanism;
and S3, a one-dimensional virtual digital execution model is established, answers to the questions are obtained according to the question keyword indexes, and abnormal information is subjected to abnormal early warning according to the prediction early warning information pushing mechanism.
Further, in the step S3, the one-dimensional virtual digital execution model includes: an NLP model and an early warning model;
The pre-training method comprises the following steps:
For the NLP model, acquiring required data from the query database according to the natural language processing model, performing preprocessing on the text data of the execution cases, converting the preprocessed execution case data into vector representation by adopting a word embedding technology, performing deep analysis on the execution case data, determining case relevance, outputting an analysis result, and generating decision information;
And for the early warning model, collecting the illegal case data ascertained in a tag library, extracting key features of the illegal case data, training the key features by using a machine learning algorithm, and learning the distinction between the ascertained illegal case and a normal case to obtain features with prediction capability, and predicting the illegal possibility of the case according to the feature data of the case.
Further, in the step S3, the method for obtaining the answer to the question includes: and the one-dimensional virtual digital execution model extracts key instructions in natural language through a voice recognition function and the NLP model, and matches the key instructions with the question key word index to obtain a question answer.
Specifically, a judge puts forward a query or statistical instruction, an NLP model automatically converts the instruction into an SQL query statement, and corresponding data is retrieved from a query database;
after the query is finished, the NLP model converts the query result into natural language and feeds the query result back to the client.
Further, in the step S3, the method for early warning of abnormality includes: and the early warning model automatically patrols and examines abnormal conditions which occur or are expected to occur in the service development process according to the label rule, and early warning is carried out in an active broadcasting mode.
Specifically, the executive judge model utilizes NLP technology and machine learning method to summarize the characteristics of the illegal cases from the historical case data, generates a prediction algorithm, further predicts the possible illegal request of the illegal cases executed by the court across the country, automatically alarms the case with the illegal risk exceeding the threshold value to the center only, and informs relevant personnel to pay attention to and intervene in the case;
and meanwhile, the case data flow is monitored, and an alarm is triggered according to the detected potential violation condition.
Further, in the step S1, the service and case data includes a service query case, a data statistics case, a data prediction case, and a system operation case.
Further, in the step S1, the query preprocessing method includes:
refining the business query cases to form an execution business question-answer database;
refining the data query cases to form an execution business entity fusion library and a dictionary library;
refining the data statistics cases to form a statistics index caliber rule base;
Refining the data prediction cases to form a tag rule base;
And refining the system operation cases to form an operation instruction library.
In a second aspect, the present invention discloses a decision simulation execution device, comprising:
and a data preprocessing module: acquiring business and case data to be analyzed, and carrying out query preprocessing to form a query database;
and an index and mechanism establishment module: establishing a problem keyword index between the query database and the query database, and simultaneously establishing a predictive early warning information active pushing mechanism;
Question-answering and early warning module: and establishing a one-dimensional virtual digital execution model, acquiring a question answer according to the question keyword index, and carrying out abnormality early warning on the abnormality information according to the prediction early warning information pushing mechanism.
In a third aspect, the present invention discloses a computer readable storage medium having stored thereon a computer program which when executed by a processor implements the steps of the decision simulation execution method according to the first aspect.
In a fourth aspect, the present invention discloses a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, said processor implementing the steps of the decision simulation execution method according to the first aspect when said program is executed.
Compared with the prior art, the invention has the beneficial effects that:
(1) The decision simulation execution method can acquire information from different data sources, comprehensively cover information in all aspects required by work, reduce information islands and ensure comprehensive decisions;
(2) The system can timely detect and predict potential illegal cases for the illegal cases, and can mark the potential illegal cases in real time in the case process by filling the ascertained illegal case data, so that the risk is reduced;
(3) According to the invention, through combining machine learning and autonomous learning and adopting an artificial intelligence technology, a one-dimensional virtual digital execution model is allowed to perform autonomous learning and optimization, and the accuracy and adaptability of the model can be continuously improved according to new data and cases, so that the decision execution capacity is improved.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
FIG. 1 is a flowchart of a decision simulation execution method according to an embodiment of the present invention;
FIG. 2 is a flow chart of data processing of a decision simulation execution method applied to a court according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a decision simulation executing device according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a computer device according to an embodiment of the present invention.
Detailed Description
The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings and detailed description, but it will be understood by those skilled in the art that the examples described below are some, but not all, examples of the present invention, and are intended to be illustrative of the present invention only and should not be construed as limiting the scope of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In order to more clearly illustrate the technical scheme of the invention, the following description is given by way of specific examples.
Examples
Referring to fig. 1, the invention discloses a decision simulation execution method, which comprises the following steps:
S1, acquiring business and case data to be analyzed, and carrying out query preprocessing to form a query database;
S2, establishing a problem keyword index between the query database and the problem keyword index, and simultaneously establishing a predictive early warning information active pushing mechanism;
and S3, a one-dimensional virtual digital execution model is established, answers to the questions are obtained according to the question keyword indexes, and abnormal information is subjected to abnormal early warning according to the prediction early warning information pushing mechanism.
The decision simulation execution method is applied to the execution bureau of the court, is integrated in the interaction between the internal and external networks of the court service, is shown with reference to fig. 2, and is specifically expressed as follows:
acquiring court executive office business and case data, and inquiring and preprocessing the business and case data; specifically, the business query cases for executing relevant laws and regulations are refined to form an execution business question-answer database;
Filling data query data of 3500 national court 2016 so far, and refining to form an execution business entity fusion library and a dictionary library;
filling data statistics data such as composite index calculation standards including old storage, new collection, already-formed, final cost, application target amount, execution in-place amount and the like, wherein the data statistics data comprises a legal limit internal implement and conclude rate, final cost qualification rate, execution case implement and conclude rate, actual implement and conclude rate, execution finishing rate, final cost rate, actual execution in-place rate, target in-place rate, final case average time and the like, and a statistics index caliber rule base is refined and formed.
And filling data prediction class data, and refining to form a tag rule base.
And (3) filling system operation class data of operation paths of nine major execution core system main body functions such as an execution case management system, a network check and control system, a price inquiry evaluation system, a network judicial auction system, a trust loss limit elimination system, an execution command management platform, an execution information disclosure network, a mobile execution platform, an emergency command scheduling system and the like, and refining to form an operation instruction library.
The specific query preprocessing method comprises the steps of collecting data, and collecting multi-source data related to case execution, wherein the multi-source data comprises guide files, case execution handling information, punishment information, property treatment information, interview supervision information, court management data, index caliber data, case execution flow node data, principal information and the like. These data sources include local databases, court intranet systems; preprocessing the collected data, cleaning, classifying and marking the collected execution case data, standardizing the data format, processing missing data, detecting abnormal values, dividing the data, standardizing and standardizing the data, storing and managing the data, and processing the data by a subsequent algorithm. And extracting features related to the execution case according to the characteristics of the case and the requirements of the digital execution model. The method is characterized in that the method is used for data query, data statistics and data prediction based on clear execution service requirements, can solve the problems that the existing execution service adopts manual data processing, consumes time and labor and is easy to make mistakes, and simultaneously solves the problem that the current court service system cannot perform early warning on an execution model.
And establishing a problem keyword index between the user and each database, and establishing an active pushing mechanism of predictive early warning information to construct a business communication bridge for natural language interaction between the user and the one-dimensional virtual digital execution model.
Establishing a one-dimensional virtual digital execution model, wherein the one-dimensional virtual digital execution model comprises a behavior rule and a decision basis of the execution model; and obtaining answers to the questions according to the keyword indexes, and carrying out abnormal early warning on the abnormal information according to a prediction early warning information pushing mechanism. Specifically, for a one-dimensional virtual digital execution model of a court executive office, two modes of passive question answering and active early warning are provided, the passive answer supports a user station to ask questions in the virtual digital execution model of an executive command center hall, key instructions in natural language are extracted through voice recognition and an NLP model, and answers of questions are obtained by matching with question keyword indexes in preprocessing; the active early warning support virtual digital execution model automatically patrols and examines abnormal situations which are happened or expected to happen in the process of carrying out business in national court according to the label rules, early warning is carried out on duty business personnel of the execution command center in an active broadcasting mode, meanwhile, the virtual digital execution model is pre-trained according to instructions of five dimensions of business question-answering, data query, data statistics, data prediction and system operation, accuracy of the virtual digital execution model in supporting the execution business is improved, accuracy of natural language interaction is improved, and further the virtual digital execution model is more suitable for executing business scenes.
Wherein, the service questions and answers, the data inquiry, the data statistics and the system operation are used as a passive answer mode, and in the specific operation process, the service questions and answers inquiry' which are specific measures after the executed person is limited high? "data queries such as query" what are the execution cases nationally related to by the executed person three? The system operates as a query such as please open the execution command management platform quality and effect check page. According to keywords in natural language query, automatically matching the most matched keyword index, and calling matched answer content aiming at service question and answer; the method comprises the steps of calling and acquiring entity fusion data of a matched execution 'personnel and cases' aiming at data query; aiming at the data statistics, the matched caliber rule is acquired, SQL is automatically generated and executed in an entity fusion library, and the statistics result value feedback is automatically calculated; and aiming at the system operation, calling the matched operation instruction, executing the RPA automatic generation operation flow, and opening the required system page layer by layer.
The data prediction is an active early warning mode, and provides closed-loop and guided type prediction early warning and judgment for four execution core business fields of property checking and controlling, credit loss limit elimination, property auction and execution supervision, wherein a closed-loop guiding link comprises: risk monitoring, risk studying and judging, case-like supervision, case-full monitoring, one-key supervision and progress tracking. If the detection risk exceeding the standard is found, in the risk monitoring link, the virtual number executes the background automatic inspection fit prediction and early warning data of the judge, and abnormal active voice broadcasting is found. In the risk research and judgment link, the user is guided to develop and research and judge the focusing problem, for example, 2 judgment bases of the case having the overstandard seal risk are provided, firstly, the related sealed asset is real property, and the court is widely understood in judging the overstandard seal problem due to fluctuation of the real property value and difficulty in accurate calculation, so that the judgment standard of the overstandard seal is properly relaxed; secondly, mortgage rights exist on the checked assets, the factor of the priority compensation of the mortgage rights needs to be considered, the factor can be comprehensively considered by the court when the check with the standard exceeding is judged, and all the bases are automatically extracted by the artificial intelligence model. In the case-like supervision link, the user is guided to extend to monitor similar cases. The one-key supervision link guides the user to issue supervision and urge to implement to the court where the abnormal problem belongs after the front cause and the back cause of the abnormal problem are determined through the deep analysis. The progress tracking link is to continuously track the subsequent processing progress of the abnormal problem, for example, if the court to which the abnormal problem belongs is not consulted 3 days after receiving supervision, and the virtual number executes the voice broadcast reminding of the court officer after 7 days of unprocessed.
Specifically, the one-dimensional virtual digital execution model includes: an NLP model and an early warning model; training the extracted features by using AIGC algorithm, constructing a virtual digital execution model, optimizing parameters and structures of the model by genetic algorithm in the training process, and improving the accuracy and generalization capability of the model;
The specific NLP model training steps comprise:
Text embedding, in which text is typically represented in the form of embedded vectors, which are mathematical representations, allows the model to convert the text into a computable form, can be applied to pre-trained embedded models such as Word2Vec, gloVe, or generated using deep learning models such as Word Embeddings, BERT, etc.
Model selection, in selecting NLP models, conventional natural language processing techniques such as cyclic neural networks (RNNs) or Convolutional Neural Networks (CNNs) are used, or pre-trained deep learning models such as BERT, GPT, etc. are selected. The selection of the appropriate model architecture depends on the nature of the task and the complexity of the data.
Model training, which requires the use of clean and labeled text data sets, involves forward propagation, back propagation and parameter optimization of the model to enable the model to adapt to the text data and learn language patterns. This process requires a significant amount of computing resources and time, typically accelerated using a GPU or TPU.
And (3) super-parameter adjustment, wherein in the training process, the best performance is found by adjusting the super-parameter of the model. Wherein the super parameters include learning rate, batch size, number of layers and number of hidden units. Specifically, an iterative process of optimal superparameter combining is obtained.
And (3) evaluating the model after training, and evaluating the model to ensure that the performance meets the requirements, specifically, performing performance measurement by using a verification data set, wherein the performance measurement comprises accuracy, precision, recall and F1 score.
And the deployment model is used for deploying the NLP model into a production environment on the premise of detecting that the NLP model has good training performance so as to provide answers and suggestions according to actual questions.
Continuous learning and optimization, the NPL model is continuously updated and retrained according to new regulations, cases and the occurrence of legal practices, and the accuracy and the practicability of the NPL model are maintained.
Training of the early warning model comprises the following steps:
and selecting a model, namely selecting a proper machine learning model and a deep learning model according to the nature of specific case data and the complexity of the problem, and predicting the illegal case, wherein the model comprises a decision tree, a random deep forest, a support vector machine and a neural network.
Training the early warning model by using case data in an execution business entity fusion library, a dictionary library and a label rule library, wherein the specific training process comprises forward propagation, reverse propagation and parameter optimization, and the accuracy and performance of the model are improved to the greatest extent by continuously iterating and adjusting model parameters.
And (3) evaluating the model, and evaluating the model after training is finished to ensure that the performance of the model meets the requirements. Specific evaluation comprises the steps of calculating performance indexes such as accuracy, precision, recall rate, F1 fraction, area under ROC curve and the like of a prediction model.
And adjusting the super parameters of the model according to the performance condition of the prediction model, and obtaining the optimal super parameter combination to achieve the optimal performance configuration.
And the deployment model is used for deploying the early warning model into the intelligent execution brain system of the court command center so as to be used for predicting and classifying the actual cases. Specifically, the early warning model outputs rule violation probability according to the input case characteristics to judge whether to trigger an alarm, and if the rule violation probability is higher than an early warning threshold, the alarm is triggered.
And continuously learning and optimizing, updating and retraining the early warning model according to new cases and legal requirements, and carrying out regular maintenance and optimization.
After the NLP model and the early warning model are established and deployed, when the problems of the user are input into the system, the NLP model processes the input information, understands the intention of the user and responds to the inquiry and the problems of the user.
The early warning model is applied to a normal case library to screen cases with potential violation characteristics, the violation possibility of the cases is calculated and compared with an early warning threshold, and once the cases exceed the early warning threshold, the cases are immediately early warned to a command center.
The early warning information can be presented in the form of characters, graphics and voice, and the virtual digital execution model can guide a user to view the early warning information and give out the next proposal.
In a specific embodiment, the decision simulation execution method of the present invention may further generate an avatar by using FOM (PaddleGAN) technology according to the virtual face data provided by the user, and display the avatar on a large screen to simulate a real avatar. By setting the avatar, the humanized and user-friendly interaction dimension of the one-dimensional virtual digital execution model can be increased, so that the practicability and the acceptability of the algorithm are improved.
And broadcasting the case data, and generating a corresponding text according to the case analysis result, the early warning result, the research report and the working suggestion. And converting the text into a voice file by using a TTS technology, and generating a broadcasting animation by using PADDLEGAN WAV lip models by combining virtual judges modeling and the voice file. And transmitting the feedback information to the executive officer in a mode of virtual officer broadcasting so that the executive officer can carry out final judgment and executive work.
The decision simulation execution method is applied to the business processing of the court, and can acquire information from different data sources, including executing case handling data, network check and control data, price inquiry evaluation data, judicial auction data, executing command management data, court personnel management data and executing public data. This enables the system to fully cover all aspects of the court's execution work, reducing information islands, ensuring full decisions.
The early warning model can timely detect and predict potential illegal cases, basic characteristics of the detected illegal case data are analyzed through filling, the early warning model is built, the potential illegal cases can be marked in real time in the case process, and risks are reduced.
Various ways are provided for communicating with the execution model, including text, speech, and graphics. Broadcast information aiming at different user demands can be generated, feedback information is transmitted to executive officers in a voice broadcast mode, and the flexibility of information transmission is improved through multi-mode communication.
By adopting AIGC technology, the model is allowed to learn and optimize autonomously, and the model can continuously improve the accuracy and adaptability of the model according to new data and cases and continuously improve the decision support capability.
And the compliance of the execution cases is improved, the compliance of the execution work of the court is ensured, and the cases are analyzed and decided based on laws and regulations and execution related laws and regulations, so that the compliance risk in the execution work is reduced.
The decision simulation execution method not only can analyze details of the cases, but also can carry out overall comprehensive analysis, and provides a comprehensive view angle by finding out the relevance among different cases so as to better support the decision of executing a judge.
The invention also provides a decision simulation executing device, as shown in fig. 3, which specifically comprises:
and a data preprocessing module: acquiring business and case data to be analyzed, and carrying out query preprocessing to form a query database;
and an index and mechanism establishment module: establishing a problem keyword index between the query database and the query database, and simultaneously establishing a predictive early warning information active pushing mechanism;
Question-answering and early warning module: and establishing a one-dimensional virtual digital execution model, acquiring a question answer according to the question keyword index, and carrying out abnormality early warning on the abnormality information according to the prediction early warning information pushing mechanism.
The device mainly comprises the three modules, and the purpose of parallel operation can be realized by well constructing the system and simultaneously mounting the same file system.
In the implementation, each module may be implemented as an independent entity, or may be combined arbitrarily, and implemented as the same entity or several entities, and the implementation of each unit may be referred to the foregoing method embodiment, which is not described herein again.
Fig. 4 is a schematic structural diagram of a computer device according to the present disclosure. Referring to FIG. 4, the computer device 400 includes at least a memory 402 and a processor 401; the memory 402 is connected to the processor through a communication bus 403, and is configured to store computer instructions executable by the processor 401, and the processor 401 is configured to read the computer instructions from the memory 402 to implement the steps of the decision simulation execution method according to any of the foregoing embodiments.
For the above-described device embodiments, reference is made to the description of the method embodiments for the relevant points, since they essentially correspond to the method embodiments. The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the objectives of the disclosed solution. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
Computer readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media and memory devices including, for example, semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal magnetic disks or removable disks), magneto-optical disks, and CD-ROM and DVD-ROM disks. The processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry.
Finally, it should be noted that: while this specification contains many specific implementation details, these should not be construed as limitations on the scope of any invention or of what may be claimed, but rather as descriptions of features of specific embodiments of particular inventions. Certain features that are described in this specification in the context of separate embodiments can also be implemented in combination in a single embodiment. On the other hand, the various features described in the individual embodiments may also be implemented separately in the various embodiments or in any suitable subcombination. Furthermore, although features may be acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination may be directed to a subcombination or variation of a subcombination.
Similarly, although operations are depicted in the drawings in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In some cases, multitasking and parallel processing may be advantageous. Moreover, the separation of various system modules and components in the embodiments described above should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.
Thus, particular embodiments of the subject matter have been described. Other embodiments are within the scope of the following claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve desirable results. Furthermore, the processes depicted in the accompanying drawings are not necessarily required to be in the particular order shown, or sequential order, to achieve desirable results. In some implementations, multitasking and parallel processing may be advantageous.
The foregoing description of the preferred embodiments of the present disclosure is not intended to limit the disclosure, but rather to cover all modifications, equivalents, improvements and alternatives falling within the spirit and principles of the present disclosure.
Claims (9)
1. A decision simulation execution method, comprising the steps of:
S1, acquiring business and case data to be analyzed, and carrying out query preprocessing to form a query database;
S2, establishing a problem keyword index between the query database and the problem keyword index, and simultaneously establishing a predictive early warning information active pushing mechanism;
and S3, a one-dimensional virtual digital execution model is established, answers to the questions are obtained according to the question keyword indexes, and abnormal information is subjected to abnormal early warning according to the prediction early warning information pushing mechanism.
2. The decision simulation execution method according to claim 1, wherein in the step S3, the one-dimensional virtual digital execution model includes: an NLP model and an early warning model;
The pre-training method comprises the following steps:
For the NLP model, acquiring required data from the query database according to the natural language processing model, performing preprocessing on the text data of the execution cases, converting the preprocessed execution case data into vector representation by adopting a word embedding technology, performing deep analysis on the execution case data, determining case relevance, outputting an analysis result, and generating decision information;
And for the early warning model, collecting the illegal case data ascertained in a tag library, extracting key features of the illegal case data, training the key features by using a machine learning algorithm, and learning the distinction between the ascertained illegal case and a normal case to obtain features with prediction capability, and predicting the illegal possibility of the case according to the feature data of the case.
3. The method according to claim 2, wherein in the step S3, the method for obtaining answers to questions comprises: and the one-dimensional virtual digital execution model extracts key instructions in natural language through a voice recognition function and the NLP model, and matches the key instructions with the question key word index to obtain a question answer.
4. The decision simulation execution method according to claim 2, wherein in the step S3, the abnormality pre-warning method includes: and the early warning model automatically patrols and examines abnormal conditions which occur or are expected to occur in the service development process according to the label rule, and early warning is carried out in an active broadcasting mode.
5. The decision simulation execution method according to claim 1, wherein in the step S1, the service and case data includes a service query case, a data statistics case, a data prediction case, and a system operation case.
6. The method according to claim 5, wherein in the step S1, the method for preprocessing the query includes:
refining the business query cases to form an execution business question-answer database;
refining the data query cases to form an execution business entity fusion library and a dictionary library;
refining the data statistics cases to form a statistics index caliber rule base;
Refining the data prediction cases to form a tag rule base;
And refining the system operation cases to form an operation instruction library.
7. Decision simulation executing apparatus using the method according to any one of claims 1-6, comprising:
and a data preprocessing module: acquiring business and case data to be analyzed, and carrying out query preprocessing to form a query database;
and an index and mechanism establishment module: establishing a problem keyword index between the query database and the query database, and simultaneously establishing a predictive early warning information active pushing mechanism;
Question-answering and early warning module: and establishing a one-dimensional virtual digital execution model, acquiring a question answer according to the question keyword index, and carrying out abnormality early warning on the abnormality information according to the prediction early warning information pushing mechanism.
8. A computer readable storage medium having stored thereon a computer program, characterized in that the program when executed performs the steps of the decision simulation execution method of any of claims 1-6.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the decision simulation execution method according to any of claims 1-6 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311628827.2A CN117951260A (en) | 2023-11-30 | 2023-11-30 | Decision simulation execution method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311628827.2A CN117951260A (en) | 2023-11-30 | 2023-11-30 | Decision simulation execution method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117951260A true CN117951260A (en) | 2024-04-30 |
Family
ID=90799209
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311628827.2A Pending CN117951260A (en) | 2023-11-30 | 2023-11-30 | Decision simulation execution method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117951260A (en) |
-
2023
- 2023-11-30 CN CN202311628827.2A patent/CN117951260A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117271767B (en) | Operation and maintenance knowledge base establishing method based on multiple intelligent agents | |
| JP2021504789A (en) | ESG-based corporate evaluation execution device and its operation method | |
| CN114118507A (en) | Risk assessment early warning method and device based on multi-dimensional information fusion | |
| CN117787569B (en) | Intelligent auxiliary bid evaluation method and system | |
| CN116996325B (en) | Network security detection method and system based on cloud computing | |
| CN114254102B (en) | Natural language-based collaborative emergency response SOAR script recommendation method | |
| Wimmer et al. | Leveraging vision-language models for granular market change prediction | |
| CN117009509A (en) | Data security classification method, apparatus, device, storage medium and program product | |
| CN117666546B (en) | Distributed control system fault diagnosis method and device | |
| CN115063035A (en) | Customer evaluation method, system, equipment and storage medium based on neural network | |
| CN114548494A (en) | Visual cost data prediction intelligent analysis system | |
| Garcia de Alford et al. | Reducing age bias in machine learning: An algorithmic approach | |
| KR102596740B1 (en) | Method for predicting macroeconomic factors and stock returns in the context of economic uncertainty news sentiment using machine learning | |
| US20230252387A1 (en) | Apparatus, method and recording medium storing commands for providing artificial-intelligence-based risk management solution in credit exposure business of financial institution | |
| CN117196800A (en) | Digital management method for staff behaviors of banking outlets | |
| CN115391523A (en) | Wind power plant multi-source heterogeneous data processing method and device | |
| CN111221704B (en) | Method and system for determining running state of office management application system | |
| CN117951260A (en) | Decision simulation execution method and device | |
| US12118019B1 (en) | Smart data signals for artificial intelligence based modeling | |
| CN117422063B (en) | Big data processing method applying intelligent auxiliary decision and intelligent auxiliary decision system | |
| CN114818659B (en) | Text emotion source analysis method and system and storage medium | |
| CN118761819A (en) | Intelligent evaluation system for game account | |
| CN118551093A (en) | Feedback information hazard degree analysis system and method based on artificial intelligence | |
| CN117331535A (en) | Optimized intelligent customer service quality inspection robot development method | |
| CN116523289A (en) | Real-time wind control method and system based on intelligent threshold and rule engine |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |