CN113609256A - Smart court management system and method based on big data - Google Patents
Smart court management system and method based on big data Download PDFInfo
- Publication number
- CN113609256A CN113609256A CN202110896652.8A CN202110896652A CN113609256A CN 113609256 A CN113609256 A CN 113609256A CN 202110896652 A CN202110896652 A CN 202110896652A CN 113609256 A CN113609256 A CN 113609256A
- Authority
- CN
- China
- Prior art keywords
- court
- search
- case
- auxiliary
- local
- 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.)
- Granted
Links
Images
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
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3346—Query execution using probabilistic model
-
- 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
- G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/383—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/194—Calculation of difference between files
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/54—Interprogram communication
- G06F9/542—Event management; Broadcasting; Multicasting; Notifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services; Handling legal documents
Abstract
The invention provides an intelligent court management system and method based on big data. The system comprises: the case information broadcasting module is used for acquiring the broadcast information of the case to be processed and sending the broadcast information to other court local ends; the case searching module is used for searching similar cases and related cases according to the broadcast information, obtaining real-time searching evaluation indexes, judging whether the case searching is stopped or not, and obtaining related cases after the case searching is stopped; and the case search control module is used for obtaining the first auxiliary judging result, the weight of the first auxiliary judging result and the final auxiliary judging result, and adjusting a preset search evaluation index threshold value or a preset search time threshold value according to whether the final auxiliary judging result is the same as the first auxiliary judging result of the local court end. According to the invention, the auxiliary trial results of the cases to be processed are comprehensively obtained by the local end of each court, and the search strategies of the related cases are updated in real time, so that the effectiveness of the auxiliary trial results is ensured, and the efficiency of the system is improved.
Description
Technical Field
The application relates to the technical field of big data and intelligent judicial, in particular to a smart court management system and method based on big data.
Background
The intelligent court is based on modern artificial intelligence, integrates the judicial law, the justice and the law of the judicial law, the constitution reform and the technical change, supports judicial judgment, litigation service and judicial management in a highly information mode, and realizes organization, construction, operation and management of the national court of all-service online handling, all-flow legal disclosure and all-around intelligent service. One of the important technologies is to assist in case trial by using the internet technology, in the prior art, related cases and similar cases of the cases under trial can be directly searched and analyzed by using a case information center database according to the information of the cases under trial, and the cases under trial can be assisted by the searched related cases and similar cases.
The prior art scheme has the following problems: the content of the case database is very complex and various, and the searching efficiency is very low when searching cases, so that the centralized system architecture is difficult to ensure the data security.
Disclosure of Invention
In order to solve the above problems, the present invention provides a big data based intelligent court management system, which comprises: the case information broadcasting module is used for acquiring the broadcast information of the case to be processed and sending the broadcast information to other court local ends;
the case searching module is used for searching similar cases and related cases according to the broadcast information at the local end of the court, and obtaining real-time searching evaluation indexes according to the overall correlation between the searched cases and the cases to be processed and the number of the searched cases; if the real-time search evaluation index or the search time meets the preset condition, stopping case search to obtain a related case;
the case search control module is used for obtaining a first auxiliary judgment result of the local end of the court according to the related case information and the case information to be processed; obtaining the weight of the first auxiliary judgment result at the local end of each court according to case search evaluation indexes, the confidence coefficient of the first auxiliary judgment result and search time; accumulating the weights of the same first auxiliary judging results, and taking the judging result with the maximum accumulated weight as a final auxiliary judging result; and adjusting the search evaluation index or the preset condition of the search time of the local end of the court according to whether the final auxiliary judgment result is the same as the first auxiliary judgment result of the local end of the court.
Preferably, the case search control module is further configured to obtain a confidence level of the first auxiliary judgment result, and input the related case information and the case information to be processed into a classification network to obtain a first auxiliary judgment result at the local end of the court; the confidence coefficient is a probability value when the first auxiliary judgment result is output.
Preferably, the real-time search evaluation index is updated in real time along with the change of the number of cases obtained by searching until the search is stopped.
Preferably, the first auxiliary judgment result weight of the local end of each court is obtained according to the search evaluation index, the search time emergency degree adjustment coefficient and the first auxiliary judgment result confidence coefficient; the urgency degree adjustment coefficient is used for adjusting the influence degree of the search time on the weight according to the feedback time required by the court local side transmitting the broadcast information.
Preferably, adjusting the search evaluation index or the preset condition of the search time at the local court end according to whether the final auxiliary trial result is the same as the first auxiliary trial result at the local court end comprises: if the final auxiliary judgment result is different from the first auxiliary judgment result, improving the search evaluation index of the local end of the court or the preset condition of the search time; if the final auxiliary judgment result is the same as the first auxiliary judgment result, reducing search evaluation indexes or preset conditions of search time of the local end of the court; and alternately adjusting the search evaluation index and the search time.
Preferably, the adjusting the search evaluation index or the preset condition of the search time at the local end of the court comprises: the preset condition of the search time comprises a search time threshold, the preset condition of the search evaluation index comprises a search evaluation index threshold, and the search evaluation index threshold adjustment value of the court local end is obtained by adjusting the number of times of the court local end, the sum of the cumulative weights of the final trial results, the weight of the first auxiliary trial result of the court local end and the basic adjustment value of the search evaluation index; and obtaining a search time threshold value adjusting value by the adjusting times of the local court end, the sum of the accumulated weights of the final trial results, the weight of the first auxiliary trial result of the local court end and the search time basic adjusting value.
The application also provides a smart court management method based on the big data, and the adopted technical scheme is as follows:
acquiring broadcast information of a case to be processed, and sending the broadcast information to other court local ends;
searching similar cases and related cases according to broadcast information at the local end of the court, and obtaining real-time search evaluation indexes according to the overall correlation between the searched cases and the cases to be processed and the number of the searched cases; if the real-time search evaluation index or the search time meets the preset condition, stopping case search to obtain a related case;
obtaining a first auxiliary judgment result of the local end of the court according to the relevant case information and the case information to be processed; obtaining the weight of the first auxiliary judgment result at the local end of each court according to case search evaluation indexes, the confidence coefficient of the first auxiliary judgment result and search time; accumulating the weights of the same first auxiliary judging results, and taking the judging result with the maximum accumulated weight as a final auxiliary judging result; and adjusting the search evaluation index or the preset condition of the search time of the local end of the court according to whether the final auxiliary judgment result is the same as the first auxiliary judgment result of the local end of the court.
The invention has the following beneficial effects: compared with the prior art, the first auxiliary judging result is given weight, case auxiliary judging data are generated by case auxiliary through a multi-court local end, auxiliary information is provided for a case acceptance end, the condition of 'same case and different judgments' is avoided to a certain extent, searching and analyzing of related cases can be carried out more quickly, and the system efficiency is improved; broadcast information verification can improve disaster tolerance capability and avoid data of the database from being tampered.
Drawings
FIG. 1 is a block diagram of the system of the present invention.
Detailed Description
To further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description will be given to a method and system for efficiently compressing video communication data based on artificial intelligence according to the present invention, with reference to the accompanying drawings and preferred embodiments, and the detailed description thereof. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
Example 1:
the specific scenes aimed by the invention are as follows: in the intelligent court scene, local servers are deployed in all the courts for data storage and interaction, local servers store local databases and combined databases, and the combined databases are shared by multiple local terminals based on a block chain account idea, so that the case data of all the local terminals are stored, and the data disaster tolerance capability is improved; the local database only contains case data at the local end, so that case searching is facilitated.
The embodiment provides a big data-based intelligent court management system, and a system framework is shown in fig. 1.
And the case information broadcasting module is used for acquiring the broadcast information of the case to be processed and sending the broadcast information to other court local ends.
And performing natural language processing on the case to be processed to acquire semantic information of a case text, so as to facilitate subsequent searching of related cases.
After a case to be processed is obtained at the local end of a court, the text information of the case is analyzed, and when the text information of the case to be processed is divided into basic information and case information through word segmentation and text classification technologies, the basic information comprises: information on the identity, sex, age, occupation, litigation type, legal regulation and the like of the original notice and the defended notice; case information is specific case description information. Basic information and case information acquired after the case information to be processed is processed are used as case broadcast information and are broadcast to local ends of various courts through a distributed system.
The case searching module is used for searching similar cases and related cases according to the broadcast information at the local end of the court, and obtaining real-time searching evaluation indexes according to the overall correlation between the searched cases and the cases to be processed and the number of the searched cases; and if the real-time search evaluation index or the search time meets the preset condition, stopping case search to obtain the related case.
And after receiving case broadcast information at the local end, searching cases in a local database in a mode of searching according to the basic information and searching according to the case information, wherein the extracted files comprise related cases (from basic information search) and similar cases (from case information search).
Firstly, searching similar cases and related cases at local ends of courts according to received broadcast information of the cases to be processed, obtaining the similarity between the similar cases and the related cases and the cases to be processed, wherein the similarity between the similar cases and the cases to be processed is delta-beta, the similarity between the related cases and the cases to be processed is delta-alpha, and setting corresponding threshold values mδThe searched cases are primarily screened by the threshold, so the threshold is set to be less than 0.5. The similarity is obtained by a text similarity algorithm, which is a known technology, and an implementer can realize the similarity by adopting the methods of Jaccard similarity, TF-IDF, deep learning and the like. And screening out cases with similarity greater than a similarity threshold value with the case to be processed for subsequent processing.
Integral correlation of searched cases and cases to be processed
In the formula, wβAnd wαWeight values of similar cases and related cases respectively, satisfy wα+wβThe weights can be adjusted by an implementer according to actual conditions, wherein the weights represent the significance that similar cases have larger influence on the overall relevance and related cases have smaller influence on the overall relevance;
the similarity mean value of the similar case and the case to be processed,
the similarity mean value of the associated case and the case to be processed is obtained; acquiring the number N of the currently searched cases, and searching the evaluation index f ═ 1-e in real time-εN) And epsilon, the number of cases searched has influence on the real-time search evaluation, and the real-time search evaluation index is updated in real time along with the number of cases obtained by searching until the search is stopped. In this embodiment, each time a new case is obtained by searching, the case is further searchedAnd searching the evaluation index in real time.
The method for judging whether the search is stopped is as follows: setting a search time threshold T and a search evaluation index threshold as preset conditions, wherein the preset conditions are initially set by a local terminal and are used for judging whether case search is stopped or not and updating according to feedback information of a follow-up case search control module. Judging whether the real-time search evaluation index is larger than a preset search evaluation index threshold value m or not, if so, stopping searching and generating broadcast information; otherwise, judging whether the search time is smaller than a preset search time threshold value T, if not, stopping searching and generating broadcast information; if the conditions for stopping searching are not met, continuing searching at the local side of the court, screening similar cases and related cases according to the similarity threshold value, and then judging whether to stop searching or not; the broadcast information comprises position identification of cases in a local database in a joint database, final case search evaluation indexes and search time t; and when other local ends receive the position identification, calculating by adopting the same real-time case search evaluation index calculation mode, and if the other local ends are the same, verifying.
The case search control module is used for obtaining a first auxiliary judgment result of the local end of the court according to the related case information and the case information to be processed; obtaining the weight of the first auxiliary judgment result at the local end of each court according to the case real-time search evaluation index, the confidence coefficient of the first auxiliary judgment result and the search time; accumulating the weights of the same first auxiliary judging results, and taking the judging result with the maximum accumulated weight as a final auxiliary judging result; and adjusting the search evaluation index or the preset condition of the search time of the local end of the court according to whether the final auxiliary judgment result is the same as the first auxiliary judgment result of the local end of the court.
The case search control module is also used for controlling whether other court local ends carry out case search: and the other local court ends search the relevant case information in the joint database according to the broadcast information and calculate search evaluation indexes, if the obtained search evaluation indexes and the search evaluation indexes in the broadcast information meet preset conditions, the broadcast information passes verification, the local database of the local court end searches the relevant cases, and otherwise, the case search is not carried out. Specifically, the verification of the broadcast information sent by the local court end is specifically as follows: the method comprises the steps that broadcast information of a certain court local end is sent to other court local ends, all local ends search and acquire relevant case information in a combined database through combined database marks in the broadcast information, case searching evaluation index calculation is carried out according to the case information, the number of cases and searching time in the broadcast information, and when more than half of local end evaluation indexes are consistent with evaluation indexes in the broadcast information, the broadcast information is verified; the broadcast information verification method has the advantages that the combined database cannot be tampered in use, and verification can be passed only when the data of the local database sending the broadcast is consistent with that of the combined database, so that the condition of malicious data attack is avoided. After the case at the local ends of the courts is searched, 0 is supplemented to the searched related case information, the searched related case information is expanded into fixed size data and case information data to be processed, Concat, and the fixed size data and the case information data are sent into an encoder, and first auxiliary judging results of the local ends of the courts are output through a full-connection layer network and a SoftMax function; the network training specifically comprises: a training data set is formed by adopting a plurality of groups of manually selected related case information and to-be-processed case information respectively, label data are court trial results, the trial results are judgment results specifically, and the judgment results comprise a plurality of categories such as a fine amount interval, a captive time interval, a futuristic time interval and the like, so that a first auxiliary trial result is generated through a classification network.
And then, after the verification is passed, giving a weight to the first auxiliary judgment result of the local end of each court, specifically comprising the following steps: giving a weight based on the case search evaluation index f and the search time t, wherein the weight of a first auxiliary judgment result at the local end of the kth court is Wk＝μ(1-τ1tk)*fk，τ1Adjusting the coefficient for emergency degree with a value range of [0, 1%]And the method is used for adjusting the influence degree of time on the weight according to the feedback time set at the local end of the transmission case, where μ is the confidence of the first auxiliary trial result, that is, in this embodiment, the first auxiliary trial result is output to the network after the corresponding SoftMax processingThe probability value of (a) is used for representing the influence of the classification confidence coefficient on the weight, only the local end weight of the court not less than 0 is reserved, fk、tkRespectively are the search evaluation index and the search time of the local end of the kth court. And all local ends accumulate the weights of the first auxiliary judging results, finally select the first auxiliary judging result with the maximum weight accumulated value and the information of the court local end search related case corresponding to the first auxiliary judging result and transmit the information to the local end of the court where the case to be processed is located, so as to provide auxiliary information for the case to be processed when the case is processed.
Then, according to whether the final auxiliary trial result is the same as the first auxiliary trial result of the local court end, adjusting the search evaluation index of the local court end or the preset condition of the search time, specifically: if the final auxiliary judgment result is different from the first auxiliary judgment result, improving the search evaluation index of the local end of the court or the preset condition of the search time; if the final auxiliary judgment result is the same as the first auxiliary judgment result, reducing search evaluation indexes or preset conditions of search time of the local end of the court; and alternately adjusting the preset search evaluation index and the preset search time.
Adjusting the threshold value of the search evaluation index of the court local end according to the adjustment times of the court local end, the sum of the accumulated weights of the final trial results, the weight of the first auxiliary trial result of the court local end and the basic adjustment value of the search evaluation index; the search time threshold adjustment value is obtained by the adjustment times of the local court end, the sum of the accumulated weights of the final trial results, the weight of the first auxiliary trial result of the local court end and the search time basic adjustment value, and specifically comprises the following steps:
the adjustment value of the search time threshold T is zTThe adjustment value of the search evaluation index threshold value m is zmWherein, in the step (A),
wherein f is1(p) is the adjustment order influence coefficient, f1(p) 1-epsilonp, where epsilonp is the time adjustment factor, set to 0.01 in this application, and p is the number of adjustments, obtained by counting in a system accumulator, and accumulatedIs limited to [0, 100 ]]，
The influence coefficient of the weight ratio on the time adjustment value is as follows:
σ1for the time influence coefficient, set to 4, W in this embodimentoutSum of weights for the final auxiliary trial result class, hTThe time adjustment value is set to 5s in this application for the base search;
wherein the content of the first and second substances,
the weight is the influence coefficient, sigma, of the comparison threshold adjustment value2For the threshold influence coefficient, the same is set to 4, h in the present embodimentmThe base threshold adjustment value, set to 0.1 in this application; it should be noted that, because the case data included in each local end is different and the location distribution is different, the optimal search time and the threshold value of each local end are different, the application suggests that the adjustment coefficient, the influence coefficient and the base value can be set according to the actual situation, so as to improve the speed of stabilizing the optimal search time and the threshold value of the local end and reduce the occurrence of the jump situation.
The purpose of the above adjustment is to obtain a higher auxiliary data weight, which is similar to the reward in the blockchain, and each local terminal will select the optimal search time and threshold value for obtaining a higher weight, which can greatly improve the efficiency of the whole system.
And finally, updating a local database and a joint database of the local end of the court, ensuring the consistency of database data, and improving the disaster tolerance capability of the system, specifically comprising the following steps:
updating time points are two types, the first type is that when the final auxiliary judgment result is fed back to the local end of the court of the case to be processed, the local database of the local end of the court where the case to be processed is located is updated, and case information and corresponding auxiliary judgment information are added; the second type is that when a case to be processed is processed at the local side of the court, the joint database stored at the local side of other court is updated, the joint database comprises the local side information of the court where the case to be processed is located and the final trial result data, the information and the final trial result data are broadcasted to all the local sides of other court, the case to be processed is identified to be completed, and it needs to be stated that when the joint database is updated, legal documents such as a decision document are required to be used as verification, and the authenticity of the updated data is ensured; the local database and the federated database are not modifiable except at the update time point.
Example 2:
the present embodiment provides a method embodiment. A big data-based intelligent court management method comprises the following steps:
acquiring broadcast information of a case to be processed, and sending the broadcast information to other court local ends;
searching similar cases and related cases according to broadcast information at the local end of the court, and obtaining real-time search evaluation indexes according to the overall correlation between the searched cases and the cases to be processed and the number of the searched cases; if the real-time search evaluation index or the search time meets the preset condition, stopping case search to obtain a related case;
obtaining a first auxiliary judgment result of the local end of the court according to the relevant case information and the case information to be processed; obtaining the weight of the first auxiliary judgment result at the local end of each court according to case search evaluation indexes, the confidence coefficient of the first auxiliary judgment result and search time; accumulating the weights of the same first auxiliary judging results, and taking the judging result with the maximum accumulated weight as a final auxiliary judging result; and adjusting the search evaluation index or the preset condition of the search time of the local end of the court according to whether the final auxiliary judgment result is the same as the first auxiliary judgment result of the local end of the court.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the spirit and principles of the present invention, and any modifications, equivalents, improvements and the like that are made therein are intended to be included within the scope of the present invention.
Claims (10)
1. A big data-based intelligent court management system, the system comprising:
the case information broadcasting module is used for acquiring the broadcast information of the case to be processed and sending the broadcast information to other court local ends;
the case searching module is used for searching similar cases and related cases according to the broadcast information at the local end of the court, and obtaining real-time searching evaluation indexes according to the overall correlation between the searched cases and the cases to be processed and the number of the searched cases; if the real-time search evaluation index or the search time meets the preset condition, stopping case search to obtain a related case;
the case search control module is used for obtaining a first auxiliary judgment result of the local end of the court according to the related case information and the case information to be processed; obtaining the weight of the first auxiliary judgment result at the local end of each court according to case search evaluation indexes, the confidence coefficient of the first auxiliary judgment result and search time; accumulating the weights of the same first auxiliary judging results, and taking the judging result with the maximum accumulated weight as a final auxiliary judging result; and adjusting the search evaluation index or the preset condition of the search time of the local end of the court according to whether the final auxiliary judgment result is the same as the first auxiliary judgment result of the local end of the court.
2. The system of claim 1, wherein the case control module is further configured to obtain a confidence level of the first auxiliary trial result, and input the related case information and the case information to be processed into a classification network to obtain a first auxiliary trial result at a local end of the court; the confidence coefficient is a probability value when the first auxiliary judgment result is output.
3. The system according to claim 1, wherein the real-time search evaluation index is updated in real time as the number of cases obtained by searching changes until the search stops.
4. The system of claim 1, wherein the first auxiliary trial result weight of the local side of each court is obtained according to the search evaluation index, the search time urgency adjustment coefficient, and the first auxiliary trial result confidence; the urgency degree adjustment coefficient is used for adjusting the influence degree of the search time on the weight according to the feedback time required by the court local side transmitting the broadcast information.
5. The system of claim 1, wherein the adjusting the search evaluation index or the preset condition of the search time at the local side of the court according to whether the final auxiliary trial result is the same as the first auxiliary trial result at the local side of the court comprises: if the final auxiliary judgment result is different from the first auxiliary judgment result, improving the search evaluation index of the local end of the court or the preset condition of the search time; if the final auxiliary judgment result is the same as the first auxiliary judgment result, reducing search evaluation indexes or preset conditions of search time of the local end of the court; and alternately adjusting the search evaluation index and the search time.
6. The system of claim 1, wherein the adjusting the preset condition of the search evaluation index or the search time of the local court end comprises:
the preset condition of the search time comprises a search time threshold, the preset condition of the search evaluation index comprises a search evaluation index threshold, and the search evaluation index threshold adjustment value of the court local end is obtained by adjusting the number of times of the court local end, the sum of the cumulative weights of the final trial results, the weight of the first auxiliary trial result of the court local end and the basic adjustment value of the search evaluation index; and obtaining a search time threshold value adjusting value by the adjusting times of the local court end, the sum of the accumulated weights of the final trial results, the weight of the first auxiliary trial result of the local court end and the search time basic adjusting value.
7. The system of claim 1, wherein the case search control module is further configured to control whether other court local sides perform case search:
and the other local court ends search the relevant case information in the joint database according to the broadcast information and calculate search evaluation indexes, if the obtained search evaluation indexes and the search evaluation indexes in the broadcast information meet preset conditions, the broadcast information passes verification, the local database of the local court end searches the relevant cases, and otherwise, the case search is not carried out.
8. A smart court management method based on big data is characterized by comprising the following steps:
acquiring broadcast information of a case to be processed, and sending the broadcast information to other court local ends;
searching similar cases and related cases according to broadcast information at the local end of the court, and obtaining real-time search evaluation indexes according to the overall correlation between the searched cases and the cases to be processed and the number of the searched cases; if the real-time search evaluation index or the search time meets the preset condition, stopping case search to obtain a related case;
obtaining a first auxiliary judgment result of the local end of the court according to the relevant case information and the case information to be processed; obtaining the weight of the first auxiliary judgment result at the local end of each court according to case search evaluation indexes, the confidence coefficient of the first auxiliary judgment result and search time; accumulating the weights of the same first auxiliary judging results, and taking the judging result with the maximum accumulated weight as a final auxiliary judging result; and adjusting the search evaluation index or the preset condition of the search time of the local end of the court according to whether the final auxiliary judgment result is the same as the first auxiliary judgment result of the local end of the court.
9. The method according to claim 8, wherein the first auxiliary trial result weight of the local side of each court is obtained according to the search evaluation index, the search time urgency adjustment coefficient and the first auxiliary trial result confidence; the emergency degree adjusting coefficient is used for adjusting the influence degree of the searching time on the weight according to the feedback time required by the court local end for sending the broadcast information; inputting the related case information and the case information to be processed into a classification network to obtain a first auxiliary judgment result of the local end of the court; the confidence coefficient is a probability value when the first auxiliary judgment result is output.
10. The method of claim 8, wherein the adjusting the search evaluation index or the preset condition of the search time at the local side of the court according to whether the final auxiliary trial result is the same as the first auxiliary trial result at the local side of the court comprises: if the final auxiliary judgment result is different from the first auxiliary judgment result, improving the search evaluation index of the local end of the court or the preset condition of the search time; if the final auxiliary judgment result is the same as the first auxiliary judgment result, reducing search evaluation indexes or preset conditions of search time of the local end of the court; and alternately adjusting the search evaluation index and the search time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110896652.8A CN113609256B (en) | 2021-08-05 | 2021-08-05 | Smart court management system and method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110896652.8A CN113609256B (en) | 2021-08-05 | 2021-08-05 | Smart court management system and method based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113609256A true CN113609256A (en) | 2021-11-05 |
| CN113609256B CN113609256B (en) | 2022-03-15 |
Family
ID=78307136
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110896652.8A Active CN113609256B (en) | 2021-08-05 | 2021-08-05 | Smart court management system and method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113609256B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104573106A (en) * | 2015-01-30 | 2015-04-29 | 浙江大学城市学院 | Intelligent urban construction examining and approving method based on case-based reasoning technology |
| CN108428200A (en) * | 2018-03-16 | 2018-08-21 | 浙江大学城市学院 | A kind of the electric business field patent infringement decision-making system and determination method of case-based reasioning |
| US20180336202A1 (en) * | 2017-05-18 | 2018-11-22 | 0934781 B.C. Ltd | System and method to represent documents for search in a graph |
| CN110472048A (en) * | 2019-07-19 | 2019-11-19 | 平安科技（深圳）有限公司 | A kind of auxiliary judgement method, apparatus and terminal device |
| CN110675288A (en) * | 2019-08-16 | 2020-01-10 | 平安科技（深圳）有限公司 | Intelligent auxiliary trial method and device, computer equipment and storage medium |
| CN111758111A (en) * | 2019-09-11 | 2020-10-09 | 阿里巴巴集团控股有限公司 | System and method for digital asset management |
| CN112115193A (en) * | 2020-11-23 | 2020-12-22 | 腾讯科技（深圳）有限公司 | Case ratio query method, device, equipment and storage medium based on block chain |
| CN112131370A (en) * | 2020-11-23 | 2020-12-25 | 四川大学 | Question-answer model construction method and system, question-answer method and device and trial system |
-
2021
- 2021-08-05 CN CN202110896652.8A patent/CN113609256B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104573106A (en) * | 2015-01-30 | 2015-04-29 | 浙江大学城市学院 | Intelligent urban construction examining and approving method based on case-based reasoning technology |
| US20180336202A1 (en) * | 2017-05-18 | 2018-11-22 | 0934781 B.C. Ltd | System and method to represent documents for search in a graph |
| CN108428200A (en) * | 2018-03-16 | 2018-08-21 | 浙江大学城市学院 | A kind of the electric business field patent infringement decision-making system and determination method of case-based reasioning |
| CN110472048A (en) * | 2019-07-19 | 2019-11-19 | 平安科技（深圳）有限公司 | A kind of auxiliary judgement method, apparatus and terminal device |
| CN110675288A (en) * | 2019-08-16 | 2020-01-10 | 平安科技（深圳）有限公司 | Intelligent auxiliary trial method and device, computer equipment and storage medium |
| CN111758111A (en) * | 2019-09-11 | 2020-10-09 | 阿里巴巴集团控股有限公司 | System and method for digital asset management |
| CN112115193A (en) * | 2020-11-23 | 2020-12-22 | 腾讯科技（深圳）有限公司 | Case ratio query method, device, equipment and storage medium based on block chain |
| CN112131370A (en) * | 2020-11-23 | 2020-12-25 | 四川大学 | Question-answer model construction method and system, question-answer method and device and trial system |
Non-Patent Citations (3)
| Title |
|---|
| Y. LIU 等: "Semantics and Structure Based Recommendation of Similar Legal Cases", 《2019 IEEE 14TH INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS AND KNOWLEDGE ENGINEERING (ISKE)》 * |
| 方曦 等: "基于AHP与TOPSIS方法的中文搜索引擎评价体系", 《科技导报》 * |
| 高鲁嘉: "人工智能时代我国司法智慧化的机遇、挑战及发展路径", 《山东大学学报(哲学社会科学版)》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113609256B (en) | 2022-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10095950B2 (en) | Systems and methods for image processing | |
| CN108710651B (en) | Automatic classification method for large-scale customer complaint data | |
| AU2005264153B2 (en) | A method for determining near duplicate data objects | |
| CN106991085B (en) | Entity abbreviation generation method and device | |
| CN111694924A (en) | Event extraction method and system | |
| CN105512273A (en) | Image retrieval method based on variable-length depth hash learning | |
| CN109308319B (en) | Text classification method, text classification device and computer readable storage medium | |
| CN110807324A (en) | Video entity identification method based on IDCNN-crf and knowledge graph | |
| US10387805B2 (en) | System and method for ranking news feeds | |
| CN111538827A (en) | Case recommendation method and device based on content and graph neural network and storage medium | |
| JP2019079536A (en) | Data identification method based on associative clustering deep learning neutral network | |
| CN111125429A (en) | Video pushing method and device and computer readable storage medium | |
| CN112148868A (en) | Law recommendation method based on law co-occurrence | |
| CN114282059A (en) | Video retrieval method, device, equipment and storage medium | |
| CN110688515A (en) | Text image semantic conversion method and device, computing equipment and storage medium | |
| CN113609256B (en) | Smart court management system and method based on big data | |
| CN110162769B (en) | Text theme output method and device, storage medium and electronic device | |
| CN113222109A (en) | Internet of things edge algorithm based on multi-source heterogeneous data aggregation technology | |
| CN111695874B (en) | Judicial decision auxiliary system, judicial decision auxiliary method, judicial decision auxiliary equipment and storable medium | |
| Shin et al. | Approach for video classification with multi-label on youtube-8m dataset | |
| CN115794798B (en) | Market supervision informatization standard management and dynamic maintenance system and method | |
| CN111460817A (en) | Method and system for recommending criminal legal document related law provision | |
| CN116452353A (en) | Financial data management method and system | |
| CN113177164B (en) | Multi-platform collaborative new media content monitoring and management system based on big data | |
| CN110069598A (en) | A kind of smart mediation method and system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |