CN110377618B - Method, device, computer equipment and storage medium for analyzing decision result - Google Patents
Method, device, computer equipment and storage medium for analyzing decision result Download PDFInfo
- Publication number
- CN110377618B CN110377618B CN201910520122.6A CN201910520122A CN110377618B CN 110377618 B CN110377618 B CN 110377618B CN 201910520122 A CN201910520122 A CN 201910520122A CN 110377618 B CN110377618 B CN 110377618B
- Authority
- CN
- China
- Prior art keywords
- analysis
- case
- vector
- result
- factor
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000004458 analytical method Methods 0.000 claims abstract description 293
- 239000013598 vector Substances 0.000 claims abstract description 166
- 230000014509 gene expression Effects 0.000 claims abstract description 85
- 238000007619 statistical method Methods 0.000 claims abstract description 18
- 230000015654 memory Effects 0.000 claims description 18
- 238000000605 extraction Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 12
- 238000013145 classification model Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 10
- 230000011218 segmentation Effects 0.000 claims description 7
- 238000010801 machine learning Methods 0.000 abstract description 4
- 230000010365 information processing Effects 0.000 abstract description 2
- 238000012545 processing Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 238000012512 characterization method Methods 0.000 description 3
- 238000012790 confirmation Methods 0.000 description 3
- 230000005484 gravity Effects 0.000 description 3
- 230000001427 coherent effect Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000003032 molecular docking Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000000007 visual effect Effects 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
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
-
- 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
-
- 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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Abstract
The application relates to a machine learning-based arbitration result analysis method, a machine learning-based arbitration result analysis device, a machine learning-based arbitration result analysis computer device and a storage medium. The method comprises the following steps: receiving a first arbitration analysis request sent by a terminal; the first arbitration analysis request contains a case identification; acquiring case information corresponding to a current case according to the case identification; generating a feature vector of the current case based on the case information; inputting the feature vector into a preset sequence model to obtain an analysis dimension expression; acquiring an analysis condition expression and a first SQL template, and filling the analysis dimension expression and the analysis condition expression into the first SQL template to obtain a first retrieval analysis statement; inquiring an approximate case of the current case in a preset case statistics table based on the first search analysis statement, carrying out statistical analysis on the judging result of the approximate case to obtain a first analysis result, and returning the first analysis result to the terminal. By adopting the method, the case information processing efficiency can be improved.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method and apparatus for analyzing a result of an arbitration, a computer device, and a storage medium.
Background
During the case approval process, judges and lawyers need to decide the current case and make decision. The arbitration decision is an arbitration result with legal effect, which is determined by the arbitration court by law on the basis of recognizing evidence and finding facts, and requests or requests for counterrequests and related matters of the requests are sent to the parties. However, the conventional method has a problem that it is difficult to accurately and efficiently provide reference information to judges and lawyers, so that the decision making is completely dependent on the processing experience of judges and lawyers, and the decision result generation efficiency is reduced.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a method, an apparatus, a computer device, and a storage medium for analyzing a result of a decision, which are capable of feeding back to a user a case processing situation of a conventional approximate case as a reference to assist the user in making a decision of a current case, thereby improving case processing efficiency.
A method of arbitration result analysis, the method comprising: receiving a first arbitration analysis request sent by a terminal; the first arbitration analysis request contains a case identifier; acquiring case information corresponding to the current case according to the case identification; generating a feature vector of the current case based on the case information; inputting the feature vector into a preset sequence model to obtain an analysis dimension expression; acquiring an analysis condition expression and a first SQL template, and filling the analysis dimension expression and the analysis condition expression into the first SQL template to obtain a first retrieval analysis statement; inquiring an approximate case of the current case in a preset case statistics table based on the first search analysis statement, carrying out statistical analysis on a judging result of the approximate case to obtain a first analysis result, and returning the first analysis result to the terminal.
In one embodiment, the generating the feature vector of the current case based on the case information includes: identifying whether corresponding factor values are recorded in the case information according to a plurality of preset target factors; if yes, extracting a factor value of a corresponding target factor; otherwise, calling a preset model to identify a factor description statement in the case information, calculating the similarity between the factor description statement and a plurality of preset template description statements, acquiring a reference factor value associated with the template description statement with the similarity exceeding a threshold value, and determining a factor value of a corresponding target factor of the current case according to the reference factor value; and calculating the characteristic vector of the current case based on the factor values respectively corresponding to the target factors.
In one embodiment, the sequence model includes an encoder, a decoder, and an attention module; the case statistics table comprises a plurality of field enumeration values; inputting the feature vector into a preset sequence model to obtain an analysis dimension expression, wherein the analysis dimension expression comprises the following steps: calling the encoder to forget a local vector containing analysis condition information in the feature vector to obtain a compressed vector; invoking the decoder to decode the compressed vector pair to obtain an initial matching probability corresponding to each field enumeration value; invoking the attention module to perform attention training on the compressed vector to obtain similarity weighting corresponding to each field enumeration value; adjusting the initial matching probability of the corresponding field enumeration value according to the similarity weighting to obtain a target matching probability corresponding to each field enumeration value; and generating an analysis dimension expression according to the field enumeration value with the highest target matching probability.
In one embodiment, the returning the first analysis result to the terminal includes: acquiring a first chart template, and determining a plurality of basic coordinates and coordinate elements according to a coordinate extraction rule recorded by the first chart template; extracting coordinate values corresponding to each coordinate element from the first analysis result; constructing a first analysis chart based on a plurality of basic coordinates and coordinate elements and coordinate values corresponding to the basic coordinates respectively; generating a suggested arbitration result of the current case according to the first analysis result, and calculating the confidence coefficient of the suggested arbitration result; and sending the first analysis chart, the suggested judging result and the corresponding confidence to the terminal.
In one embodiment, the method further comprises: receiving a second arbitration analysis request sent by the terminal; the second arbitration analysis request carries a retrieval analysis statement; acquiring table information of the case statistics table; generating a target vector according to the search analysis statement and the table information; inputting the target vector into a preset sequence model to obtain an analysis intention expression; inputting the target vector into a preset intention classification model to obtain a second SQL template; filling the analysis intention expression into the second SQL template to obtain a second retrieval analysis statement; inquiring related cases in the case statistics table based on the second search analysis statement, carrying out statistical analysis on the case information of the related cases, and returning the obtained second analysis result to the terminal.
In one embodiment, the table information includes a plurality of field enumeration values; the generating a target vector according to the search analysis statement and the table information comprises the following steps: performing word segmentation on the search analysis statement, calculating word vectors of each word segmentation, and recording the word vectors as first vectors; calculating word vectors corresponding to each field enumeration value, and recording the word vectors as second vectors; calculating the similarity of the first vector and different second vectors; and splicing the first vector with the second vector with the highest similarity to obtain the target vector.
An apparatus for analysis of a result of a arbitration, the apparatus comprising: the case feature extraction module is used for receiving a first arbitration analysis request sent by the terminal; the first arbitration analysis request contains a case identifier; acquiring case information corresponding to the current case according to the case identification; generating a feature vector of the current case based on the case information; the retrieval analysis statement generation module is used for inputting the feature vector into a preset sequence model to obtain an analysis dimension expression; acquiring an analysis condition expression and a first SQL template, and filling the analysis dimension expression and the analysis condition expression into the first SQL template to obtain a first retrieval analysis statement; the decision statistical analysis module is used for inquiring the approximate case of the current case in a preset case statistical table based on the first search analysis statement, carrying out statistical analysis on the decision result of the approximate case to obtain a first analysis result, and returning the first analysis result to the terminal.
In one embodiment, the case feature extraction module is further configured to identify, according to a plurality of preset target factors, whether corresponding factor values are recorded in the case information; if yes, extracting a factor value of a corresponding target factor; otherwise, calling a preset model to identify a factor description statement in the case information, calculating the similarity between the factor description statement and a plurality of preset template description statements, acquiring a reference factor value associated with the template description statement with the similarity exceeding a threshold value, and determining a factor value of a corresponding target factor of the current case according to the reference factor value; and calculating the characteristic vector of the current case based on the factor values respectively corresponding to the target factors.
A computer device comprising a memory storing a computer program and a processor implementing the steps of the arbitration result analysis method provided in any one of the embodiments of the present application when the computer program is executed.
A computer readable storage medium having stored thereon a computer program which when executed by a processor implements the steps of the arbitration result analysis method provided in any of the embodiments of the present application.
According to the method, the device, the computer equipment and the storage medium for analyzing the judging result, as a user can automatically analyze the case information of the current case by simply providing a case identifier, the input operation is simplified, and the judging analysis efficiency can be improved; not only can the case characteristics of the current case be automatically and accurately identified based on the case information obtained by deconstructing, but also the case characteristics can be automatically converted into retrieval analysis sentences in an SQL form based on a preset sequence model and a first SQL template, so that the manual participation is greatly reduced, and the end-to-end arbitration analysis in the true sense is realized; and combining a case statistical table which is pre-solved, so that the judging and analyzing efficiency can be further improved.
Drawings
FIG. 1 is an application scenario diagram of a seed decision analysis method in one embodiment;
FIG. 2 is a flow chart of a method of analyzing seed arbitration results in one embodiment;
FIG. 3 is a flow diagram illustrating steps of a natural language based arbitration analysis in one embodiment;
FIG. 4 is a block diagram showing a structure of a seed decision analysis device according to an embodiment;
fig. 5 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The method for analyzing the judging result can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smartphones, tablet computers, and portable wearable devices, and the server 104 may be implemented by a stand-alone server or a server cluster composed of a plurality of servers. When the user needs to perform a search analysis based on the current case, a first resolution request may be sent to the server 104 through the terminal 102. The first resolution request carries a case identification of the current case. The server 104 obtains the case information of the current case according to the case identification. The server 104 extracts case factors capable of representing different dimensional characteristics of the current case from the case information, and constructs feature vectors of the current case based on the extracted case factors. The server 104 is trained in advance based on the case information of the historical cases to obtain a sequence model, and is used for matching the feature vector with word vectors corresponding to different field enumeration values in the case statistics table, and generating an analysis dimension expression of the current case according to the matched field enumeration values. The server 104 inputs the feature vectors into the sequence model to obtain a plurality of analytical dimensional expressions. The server 104 presets a corresponding analysis condition expression and a first SQL template for a first analysis mode corresponding to the first arbitrated analysis request. The server 104 fills the analysis dimension expression and the analysis condition expression into the first SQL template to obtain a first retrieval analysis statement. The server 104 queries the approximate case of the current case in the preset case statistics table based on the first search analysis statement, performs statistical analysis on the judging result of the approximate case to obtain a first analysis result, returns the first analysis result to the terminal 102, and makes the user make the judging decision on the current case after knowing that the judging opinion of the previous approximate case is inclined according to the first analysis result. According to the analysis process of the judging result, the case characteristics of the current case are automatically and accurately identified based on the case information obtained through deconstructing, the case characteristics are automatically converted into the retrieval analysis statement in the SQL form based on the preset sequence model and the first SQL template, and the judging analysis efficiency can be improved by combining a case statistical table which is deconstructed in advance.
In one embodiment, as shown in fig. 2, a method for analyzing a result of arbitration is provided, and the method is applied to the server in fig. 1 for illustration, and includes the following steps:
step 202, receiving a first arbitration analysis request sent by a terminal; the first resolution request contains a case identification.
When the user performs the arbitration processing on the current case, if the case processing condition of the similar case or the related case needs to be referred, an arbitration analysis request can be sent to the server through the terminal. The arbitration request includes a first arbitration request and a second arbitration request for implementing different search analysis modes, respectively. Wherein the first arbitration analysis request is for implementing the first mode. The first mode is used for carrying out statistical analysis on the judging result of the approximate case of the current case, and is a targeted retrieval analysis mode based on the current case information. The second arbitration request is used to implement a second mode. The second mode identifies the search analysis intention according to the search analysis statement input by the user, and statistics is carried out on case information of related cases conforming to the search analysis intention, so that the second mode is a generalized search analysis mode based on the search analysis statement.
Step 204, according to the case identification, obtaining the case information corresponding to the current case.
When a first arbitration analysis request sent by the terminal is received, the server pulls the case information of the corresponding case from the database corresponding to the case processing platform according to the case identification. The server and the case processing platform directly realize data docking. If the data docking is not realized, the user can submit the case information of the current case to the server through the terminal.
Step 206, generating the feature vector of the current case based on the case information.
The server extracts case factors which can represent different dimensional characteristics of the current case from the case information, such as disputed focus types, case components, regions, legal relations and the like. The server constructs the feature vector of the current case based on the extracted case factors. The feature vector may be a word vector corresponding to each case factor. It is readily understood that the current case may correspond to a plurality of feature vectors.
And step 208, inputting the feature vector into a preset sequence model to obtain an analysis dimension expression.
And deconstructing case files of a large number of historical cases in advance, and constructing a case statistical table by utilizing the deconstructed case information. The case statistics table records case information of a plurality of history cases. As shown in table 1 below, the case information may include a case identification and a plurality of case factors deconstructed from the case file. The case file may be a litigation request book, a resolution document, etc. for the historical case. The case factors may be the result of arbitration, annual rate, subject, territory, referee time, court level or case law, etc. for the historical case.
TABLE 1
To ensure accuracy of the search analysis, the case statistics may be dynamically updated. The user can quickly respond to different retrieval analysis intents based on the case statistics. The search analysis intention refers to statistical analysis of which aspect of case information of which dimensions in the case statistics table the user desires to perform, and includes analysis of dimension intention and analysis of condition intention.
The server pre-trains the sequence model based on case information of a large number of real historical cases. The sequence model includes a dimensional sequence model and a conditional sequence model. The dimension sequence model and the condition sequence model may be different RNN models, such as LSTM (Long Short-Term Memory network), etc. The dimension sequence model is used for identifying analysis dimension intention of the user; the condition sequence model is used to identify the user's analysis condition intent. The first mode default analysis conditions are intended to be court opinion trends for past approximated cases. In other words, the analysis conditional expression of the first pattern (denoted as "first conditional expression") may be fixed, such as "intention=support ratio". The support ratio may be a ratio of the number of cases for which the arbitration result is supported to the number of cases for which the arbitration result is not supported.
The server calculates word vectors of each field enumeration value in the case statistics table according to the above. In another embodiment, the word vector can be pre-calculated by the server and recorded in the case statistics table, so that the vector matching efficiency can be improved, and the retrieval analysis efficiency can be further improved.
The server calculates the similarity between the feature vector and different word vectors in the case statistical table; and splicing the feature vector and the word vector with the highest similarity to obtain a target vector. In the first mode, the server inputs the target vector of the current case into the dimension sequence model, and outputs a plurality of analysis dimension expressions (named as "first dimension expressions") of the current case, such as "case by = financial borrowing disputes", "region = guangdong", "legal relation = guarantee relation", and the like.
Step 210, acquiring an analysis condition expression and a first SQL template, and filling the analysis dimension expression and the analysis condition expression into the first SQL template to obtain a first retrieval analysis statement.
The server presets a variety of SQL templates. Different SQL templates are used to satisfy the user's intent to analyze based on different dimensions and conditions. The server training trains the intent classification model. The intention classification model is used for determining which SQL template to choose according to the current user retrieval analysis intention. The first schema default SQL template is a first SQL template that need not be selected by the intent classification model.
The manner in which different SQL templates are populated may be different. And the server fills the first dimension expression and the first conditional expression into the first SQL template according to the filling mode of the first SQL template, so that the first retrieval analysis statement can be obtained.
Step 212, inquiring the approximate case of the current case in the preset case statistics table based on the first search analysis statement, performing statistical analysis on the judging result of the approximate case to obtain a first analysis result, and returning the first analysis result to the terminal.
The data query of multiple dimensions such as regions, case, legal relations and the like can be realized based on the first search analysis statement; data statistics of case support ratios can also be implemented. Because the case query is performed based on the case factors of multiple dimensions of the current case, the queried historical case can be recorded as an approximate case of the current case. And carrying out support proportion statistics based on the approximate case, so that the reference value of the first analysis result can be improved, namely the accuracy of the first analysis result is improved.
In another embodiment, if there are multiple approximate cases, the server calculates the approximation degree of each approximate case and the current case, obtains the case abstract of each approximate case, and sorts the multiple case abstracts according to the approximation degree; and returning the case abstracts of the plurality of ordered approximate cases to the terminal together, so that a user can refer to the case documents of the approximate cases with high similarity in further detail.
In this embodiment, according to a first arbitration analysis request sent by a terminal, case information of a current case may be obtained; based on the case information, a feature vector of the current case can be generated; inputting the feature vector into a preset sequence model to obtain a plurality of analysis dimensional expressions; based on a preset analysis condition expression and a first SQL template, filling the analysis dimension expression and the analysis condition expression into the first SQL template to obtain a first retrieval analysis statement; inquiring the approximate case of the current case in a preset case statistics table based on the first search analysis statement, and carrying out statistical analysis on the judging result of the approximate case, so that a first analysis result can be obtained, and the first analysis result can be returned to the terminal. Because the user can automatically deconstruct the case information of the current case by simply providing a case identifier, the input operation is simplified, and the judging and analyzing efficiency can be improved; not only can the case characteristics of the current case be automatically and accurately identified based on the case information obtained by deconstructing, but also the case characteristics can be automatically converted into retrieval analysis sentences in an SQL form based on a preset sequence model and a first SQL template, so that the manual participation is greatly reduced, and the end-to-end arbitration analysis in the true sense is realized; and combining a case statistical table which is pre-solved, so that the judging and analyzing efficiency can be further improved.
In one embodiment, generating a feature vector for a current case based on case information includes: identifying whether corresponding factor values are recorded in the case information according to a plurality of preset target factors; if yes, extracting a factor value of a corresponding target factor; otherwise, calling a preset model to identify a factor description statement in the case information, calculating the similarity between the factor description statement and a plurality of preset template description statements, acquiring a reference factor value associated with the template description statement with the similarity exceeding a threshold value, and determining a factor value of a corresponding target factor of the current case according to the reference factor value; and calculating the characteristic vector of the current case based on the factor values respectively corresponding to the target factors.
The target factor refers to a case factor for which a corresponding factor value needs to be acquired. The extraction modes of factor values of different case factors can be different. For the information content directly recorded in the plaintext in the case file, the factor value of the corresponding case factor, such as the judge time, can be obtained by utilizing keyword matching or regular matching. However, for the factor value which is not explicitly recorded in the case factor in the case file, it is required to refine the factor value based on a pre-trained semantic understanding model, such as a dispute focus type, a court view, and the like. Specifically, according to the multiple keyword sets provided by expert rules, multiple regular expressions are preset in the server. Different regular expressions are used to identify related descriptive statements (denoted as factor descriptive statements) corresponding to different target factors in the case file. The server calculates the characterization vector of the factor description statement, which is denoted as a factor vector. The server prestores one or more template description sentences corresponding to each target factor. The server calculates the characterization vector of the template description statement corresponding to the corresponding target factor and marks the characterization vector as a reference vector. The server obtains the similarity between the factor vector and each reference vector by calculating Euclidean distance, cosine similarity and the like of the two vectors. Each template description statement is associated with a corresponding reference factor value. The server can directly use the reference factor value as the factor value of the corresponding target factor of the current case, can also perform preset logic operation on the reference factor value, and uses the preset logic operation result as the factor value of the corresponding target factor of the current case. For example, the reference factor value is input into a preset formula, and the output of the preset formula is used as the factor value of the corresponding target factor of the previous case.
In the embodiment, the factor value of the target factor in the case information can be automatically extracted based on a large number of preset regular expressions and semantic understanding models, so that the manual participation is reduced, the case feature extraction efficiency is improved, and the judging information retrieval analysis efficiency is further improved.
In one embodiment, the sequence model includes an encoder, a decoder, and an attention module; the case statistics table comprises a plurality of field enumeration values; inputting the feature vector into a preset sequence model to obtain an analysis dimension expression, wherein the analysis dimension expression comprises the following steps: calling an encoder to forget a local vector containing analysis condition information in the feature vector to obtain a compressed vector; invoking a decoder to decode the compressed vector pair to obtain initial matching probability corresponding to each field enumeration value; invoking an attention module to perform attention training on the compressed vector to obtain similarity weighting corresponding to each field enumeration value; adjusting the initial matching probability of the corresponding field enumeration value according to the similarity weighting to obtain a target matching probability corresponding to each field enumeration value; and generating an analysis dimension expression according to the field enumeration value with the highest target matching probability.
In one embodiment, returning the first analysis result to the terminal includes: acquiring a first chart template, and determining a plurality of basic coordinates and coordinate elements according to a coordinate extraction rule recorded by the first chart template; extracting coordinate values corresponding to each coordinate element from the first analysis result; constructing a first analysis chart based on a plurality of basic coordinates and coordinate elements and coordinate values corresponding to the basic coordinates respectively; generating a suggested arbitration result of the current case according to the first analysis result, and calculating the confidence coefficient of the suggested arbitration result; and sending the first analysis chart, the suggested arbitration result and the corresponding confidence coefficient to the terminal.
The server presets various chart templates. The chart type of the chart template may be a line graph, a bar graph, a radar graph, etc. Each graph template is associated with a corresponding coordinate extraction rule. According to the coordinate extraction rule, a plurality of basic coordinates and coordinate elements and coordinate values corresponding to each basic coordinate can be extracted from the analysis result. In the embodiment, a first chart template can be selected by default in a first mode; in the second mode, different chart templates can be selected according to different retrieval analysis intents. For example, the target chart type corresponding to the search analysis sentence "proportion of contract dispute resolution cases in the Guangdong region 2018" may be a histogram. Wherein, the abscissa is the contract release result, and the coordinate elements are two discrete values of release and non-release; the ordinate is the case proportion, and the coordinate elements are continuous values of 0-100%.
In another embodiment, an alternative chart type corresponding to each analysis chart is preset, and one-key change of the chart type can be supported. And simultaneously, a plurality of options of alternative chart types are provided, so that the personalized requirements of the user can be greatly met while the feedback efficiency of the analysis result is ensured.
In yet another embodiment, the user is also supported to make changes to chart elements in the analysis chart. Specifically, the server receives an adjustment request for the analysis chart sent by the terminal. The adjustment request carries change information for one or more primitives in the analysis chart. And the server performs processing such as adding, deleting or changing the display position of the corresponding graphic element in the analysis chart according to the change information. By adjusting the analysis chart, the user can conveniently conduct further deep search on the basis of the original search result.
The proposed arbitration result may be generated based on the first analysis result. The server also calculates a confidence that the result of the arbitration is suggested. The confidence level may be calculated based on an average of approximations of the plurality of approximated cases with the current case, respectively. The proposed arbitration result and the corresponding confidence may be one or more sentences presented in natural language, such as "in view of 75% of the approximate cases being supported, the proposed arbitration result is supported, and the confidence is 66%".
In the embodiment, the analysis result is visually displayed in a chart mode, so that the analysis result is more visual. And when the analysis result is given, a specific suggested arbitration result and confidence are provided, so that a user can conveniently and rapidly and accurately make arbitration decisions, and the case information processing efficiency can be improved.
In one embodiment, as shown in fig. 3, the method further includes a step of natural language based arbitration analysis, specifically including:
step 302, receiving a second arbitration analysis request sent by the terminal; the second arbitration analysis request carries a retrieve analysis statement.
In the second mode, the user is supported to perform search analysis in the form of natural language. The search analysis statement may be one or more phrases formed in natural language. For example, "support rate of financial borrowing cases in Guangdong area", "specific gravity of dispute cases in 2018 Guangdong area contract release", "where cases related to lending disputes are generally distributed", and the like. The search analysis statement may be a statement that has a grammatical error and is semantically non-coherent. For example, "case interpretation trend of overdue repayment of loan in the last five years", such as Guangdong court ", and the like. For the search analysis statement with grammar errors and incoherent semantics, the server performs semantic analysis on the search analysis statement to generate one or more corresponding search intention statements with coherent semantics, generates a search intention confirmation prompt based on the search intention statement, and returns the search intention confirmation prompt to the terminal. The user can select one of the search intention sentences based on the search intention confirmation prompt, and the terminal transmits the selected information to the server. The server performs search analysis based on the search intention sentence selected by the user according to the method provided by the embodiment. In another embodiment, the search analysis statement may be a plurality of search fields, which is not limited thereto.
Step 304, table information of the case statistics table is obtained.
The server obtains the table information of the case statistics table. The table information comprises a table name, a plurality of table heads and a plurality of field enumeration values corresponding to each table head. Each header may be a case factor. For example, each field of the first row in table 1 is a header, and the fields of the other rows in each column are field enumeration values corresponding to the corresponding header, such as "Guangdong Shenzhen" and "Shanghai" are field enumeration values of the header "region" respectively.
Step 306, generating a target vector according to the search analysis statement and the table information.
In one embodiment, the table information includes a plurality of field enumeration values; generating a target vector according to the search analysis statement and the table information, including: word segmentation is carried out on the search analysis sentences, word vectors of each word segmentation are calculated, and the word vectors are recorded as first vectors; calculating word vectors corresponding to each field enumeration value, and recording the word vectors as second vectors; calculating the similarity between the first vector and different second vectors; and splicing the first vector with the second vector with the highest similarity to obtain the target vector.
The server performs word segmentation on the search analysis sentences, and performs optimization processing such as stop word replacement, synonym replacement and the like on the obtained multiple word segments. And the server performs One-hot independent encoding on each word after optimization processing to obtain a first vector corresponding to each word. The server calculates word vectors corresponding to each field enumeration value in the case statistics table based on word2vec and other algorithms, and records the word vectors as second vectors. The server calculates the similarity between the first vector and different second vectors; and splicing the first vector with the second vector with the highest similarity and reaching the threshold value to obtain the target vector. The first vector is spliced with the second vector with high similarity, so that the retrieval intention characteristics of the user are more obvious, and the model identification precision is improved.
And 308, inputting the target vector into a preset sequence model to obtain an analysis intention expression.
Unlike the first schema, the permission dimensions and analysis conditions based on the search analysis statement are varied, requiring dynamic determination based on the sequence model. The server calls a conditional sequence model to forget a local vector containing analysis dimension information in the target vector, and one or more analysis conditional expressions (recorded as second conditional expressions) are obtained.
The dimensional sequence model includes an encoder, a decoder, and an attention module. The encoder, decoder and attention module may be different RNN models. The encoder is used for encoding the search analysis statement, namely forgetting the local vector which corresponds to the analysis condition information in the plurality of target vectors to obtain a compressed vector. The compressed vector contains the sentence meaning of the search analysis sentence. The decoder is used for carrying out dimension reduction on the compressed vector and calculating the initial matching probability of the target vector and each field enumeration value based on the dimension reduced compressed vector mapping.
The attention module is used for performing attention training on the compressed vector after the dimension reduction, and calculating similarity weighting corresponding to each field enumeration value of the target vector. The decoder is further configured to adjust an initial matching probability of the target vector and the corresponding field enumeration value according to the similarity weighting, so as to obtain target matching probabilities of each target vector and different field enumeration values.
The server generates an analysis dimension expression (named as a second dimension expression) corresponding to the corresponding target vector based on the field enumeration value with the highest target matching probability. For example, a header corresponding to a field enumeration Value with the highest target matching probability is used as a Key Value, the field enumeration Value with the highest target matching probability or a field enumeration Value with the highest target matching probability is converted and then used as a Value, and a formed Key-Value Key Value pair can be used as a second dimension expression. The conversion processing of the field enumeration value with the highest target matching probability may be to replace a part of fields in the field enumeration value with specified characters such as a sign. For example, the user may perform search analysis on the search analysis statement "specific gravity of disputed cases in Guangdong region contract in 2018" to count only cases in Guangdong region, and if none of the field enumeration values in the case statistics table is "Guangdong", then the field enumeration value "Guangdong Shenzhen" with the highest target matching probability may be converted into "Guangdong x".
And step 310, inputting the target vector into a preset intention classification model to obtain a second SQL template.
The server sequentially inputs a plurality of target vectors corresponding to the retrieval analysis sentences into the intention classification model to obtain a target SQL template, and the target SQL template is recorded as a second SQL template. The intention classification model can be obtained by performing supervised training on the basic classification model based on a large number of simulated search analysis sentences and target SQL templates correspondingly marked by each search analysis sentence. The basic training model may be an RNN model (Recurrent neural network, recurrent neural network model).
And step 312, filling the analysis intention expression into a second SQL template to obtain a second retrieval analysis statement.
And the server fills the second conditional expression and the second dimension expression into the second SQL template according to the filling mode of the second SQL template, so that a second retrieval analysis statement can be obtained.
In another embodiment, the second conditional expression and the second dimension expression are noted as analysis intent expressions. The sequence model also outputs the intention intensity corresponding to each analysis intention expression, sorts the analysis intention expressions according to the intention intensity, and fills the analysis intention expressions into a target second SQL template according to the sorting to obtain a second retrieval analysis statement.
In yet another embodiment, each analysis intent expression has a corresponding intent expression word in the search analysis statement, for example, in the search analysis statement "where cases related to lending disputes are generally distributed", the intent expression "case by = lending disputes OR = lending disputes" corresponding intent expression word may be "lending disputes", and the intent = region "corresponding intent expression word may be" where ". The server sequentially fills a plurality of analysis intention expressions into the second SQL template according to the sequence of the intention expression word corresponding to the intention expression word in the retrieval analysis statement.
Step 314, inquiring the related cases in the case statistics table based on the second search analysis statement, performing statistical analysis on the case information of the related cases, and returning the obtained second analysis result to the terminal.
Based on different second search analysis sentences, the data inquiry of different dimensionalities such as judge time, region, case, and the like can be realized; and the data statistics of different conditions such as case specific gravity, case number, support rate and the like can be realized. And the server performs data query and statistical analysis in the case statistics table based on the second search analysis statement, and returns a second analysis result to the terminal.
For the case processing information query of the related cases in the past, the traditional mode directly judges the search intention of the user through the mode of presetting word lists, and does not support the user to search in a natural language mode. In addition, the preset vocabulary not only requires a lot of labor, but also has difficulty in ensuring the coverage rate of the vocabulary information, and once a certain search keyword input by a user is not covered in the vocabulary, search analysis fails.
In this embodiment, the user is supported to search in a natural language manner. It is easy to understand that natural language can express the search intention of the user more accurately than the single search keyword, so that the search analysis intention of the user can be mined more accurately based on the search analysis statement. The method and the device can further quickly and accurately identify the search analysis intention of the user through the machine learning pre-training sequence model and the intention classification model, and compared with a preset word list, the method and the device can reduce manual participation and realize end-to-end judgment information search analysis in a true sense. By combining a case statistical table which is pre-deconstructed, the retrieval and analysis efficiency of the judging information can be improved, and different retrieval and analysis intentions of a user can be responded quickly.
It should be understood that, although the steps in the flowcharts of fig. 2 to 3 are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 2-3 may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed sequentially, but may be performed alternately or alternately with at least a portion of the other steps or sub-steps of other steps.
In one embodiment, as shown in fig. 4, there is provided a arbitration result analyzing apparatus including: a case feature extraction module 402, a search analysis statement generation module 404, and a arbitration statistics analysis module 406, wherein:
a case feature extraction module 402, configured to receive a first arbitration analysis request sent by a terminal; the first arbitration analysis request contains a case identification; acquiring case information corresponding to a current case according to the case identification; and generating a characteristic vector of the current case based on the case information.
The search analysis statement generation module 404 is configured to input the feature vector into a preset sequence model to obtain an analysis dimensional expression; and acquiring an analysis condition expression and a first SQL template, and filling the analysis dimension expression and the analysis condition expression into the first SQL template to obtain a first retrieval analysis statement.
The decision statistics analysis module 406 is configured to query an approximate case of the current case in a preset case statistics table based on the first search analysis statement, perform statistics analysis on a decision result of the approximate case, obtain a first analysis result, and return the first analysis result to the terminal.
In one embodiment, the case feature extraction module 402 is further configured to identify, according to a plurality of preset target factors, whether corresponding factor values are recorded in the case information; if yes, extracting a factor value of a corresponding target factor; otherwise, calling a preset model to identify a factor description statement in the case information, calculating the similarity between the factor description statement and a plurality of preset template description statements, acquiring a reference factor value associated with the template description statement with the similarity exceeding a threshold value, and determining a factor value of a corresponding target factor of the current case according to the reference factor value; and calculating the characteristic vector of the current case based on the factor values respectively corresponding to the target factors.
In one embodiment, the sequence model includes an encoder, a decoder, and an attention module; the case statistics table comprises a plurality of field enumeration values; the search analysis statement generation module 404 is further configured to invoke an encoder to perform forgetting processing on a local vector containing analysis condition information in the feature vector, so as to obtain a compressed vector; invoking a decoder to decode the compressed vector pair to obtain initial matching probability corresponding to each field enumeration value; invoking an attention module to perform attention training on the compressed vector to obtain similarity weighting corresponding to each field enumeration value; adjusting the initial matching probability of the corresponding field enumeration value according to the similarity weighting to obtain a target matching probability corresponding to each field enumeration value; and generating an analysis dimension expression according to the field enumeration value with the highest target matching probability.
In one embodiment, the arbitration statistic analysis module 406 is further configured to obtain a first chart template, and determine a plurality of basic coordinates and coordinate elements according to a coordinate extraction rule recorded by the first chart template; extracting coordinate values corresponding to each coordinate element from the first analysis result; constructing a first analysis chart based on a plurality of basic coordinates and coordinate elements and coordinate values corresponding to the basic coordinates respectively; generating a suggested arbitration result of the current case according to the first analysis result, and calculating the confidence coefficient of the suggested arbitration result; and sending the first analysis chart, the suggested arbitration result and the corresponding confidence coefficient to the terminal.
In one embodiment, the apparatus further comprises an analysis intent recognition module 408 for receiving a second arbitration analysis request sent by the terminal; the second arbitration analysis request carries a retrieval analysis statement; acquiring table information of a case statistics table; generating a target vector according to the search analysis statement and the table information; inputting the target vector into a preset sequence model to obtain an analysis intention expression; the search analysis statement generation module 404 is further configured to input the target vector into a preset intention classification model to obtain a second SQL template; filling the analysis intention expression into a second SQL template to obtain a second retrieval analysis statement; the decision statistical analysis module 406 is further configured to query the case statistics table for related cases based on the second search analysis statement, perform statistical analysis on case information of the related cases, and return the obtained second analysis result to the terminal.
In one embodiment, the table information includes a plurality of field enumeration values; the analysis intention recognition module 408 is further configured to segment the search analysis sentence, calculate a word vector of each segment, and record the word vector as a first vector; calculating word vectors corresponding to each field enumeration value, and recording the word vectors as second vectors; calculating the similarity between the first vector and different second vectors; and splicing the first vector with the second vector with the highest similarity to obtain the target vector.
For specific limitations of the arbitration result analysis means, reference is made to the above limitations of the arbitration result analysis method, and no further description is given here. The respective modules in the above-described arbitration result analyzing means may be implemented in whole or in part by software, hardware, and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 5. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing a case statistics table, an SQL template and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of arbitration result analysis.
It will be appreciated by those skilled in the art that the structure shown in fig. 5 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the arbitration result analysis method provided in any of the embodiments of the present application.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples represent only a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (10)
1. A method of arbitration result analysis, the method comprising:
receiving a first arbitration analysis request sent by a terminal; the first arbitration analysis request contains a case identifier;
acquiring case information corresponding to the current case according to the case identification;
generating a feature vector of a current case based on the case information, wherein the feature vector comprises calling a preset model to identify factor description sentences in the case information, calculating the similarity between the factor description sentences and a plurality of preset template description sentences, acquiring a reference factor value associated with the template description sentences with the similarity exceeding a threshold value, and determining a factor value of a corresponding target factor of the current case according to the reference factor value; calculating the characteristic vector of the current case based on factor values respectively corresponding to a plurality of target factors;
Inputting the feature vector into a preset sequence model to obtain an analysis dimension expression, wherein the analysis dimension expression comprises the following steps: the sequence model includes an encoder, a decoder, and an attention module; the case statistics table comprises a plurality of field enumeration values; calling the encoder to forget a local vector containing analysis condition information in the feature vector to obtain a compressed vector; invoking the decoder to decode the compressed vector pair to obtain an initial matching probability corresponding to each field enumeration value; invoking the attention module to perform attention training on the compressed vector to obtain similarity weighting corresponding to each field enumeration value; adjusting the initial matching probability of the corresponding field enumeration value according to the similarity weighting to obtain a target matching probability corresponding to each field enumeration value; generating the analysis dimension expression according to the field enumeration value with the highest target matching probability;
acquiring an analysis condition expression and a first SQL template, and filling the analysis dimension expression and the analysis condition expression into the first SQL template to obtain a first retrieval analysis statement;
inquiring an approximate case of the current case in a preset case statistics table based on the first search analysis statement, carrying out statistical analysis on a judging result of the approximate case to obtain a first analysis result, and returning the first analysis result to the terminal.
2. The method of claim 1, wherein the generating a feature vector for a current case based on the case information comprises:
identifying whether corresponding factor values are recorded in the case information according to a plurality of preset target factors;
if yes, extracting a factor value of a corresponding target factor;
and calculating the characteristic vector of the current case based on the factor values respectively corresponding to the target factors.
3. The method of claim 1, wherein the returning the first analysis result to the terminal comprises:
acquiring a first chart template, and determining a plurality of basic coordinates and coordinate elements according to a coordinate extraction rule recorded by the first chart template;
extracting coordinate values corresponding to each coordinate element from the first analysis result;
constructing a first analysis chart based on a plurality of basic coordinates and coordinate elements and coordinate values corresponding to the basic coordinates respectively;
generating a suggested arbitration result of the current case according to the first analysis result, and calculating the confidence coefficient of the suggested arbitration result;
and sending the first analysis chart, the suggested judging result and the corresponding confidence to the terminal.
4. The method according to claim 1, wherein the method further comprises:
Receiving a second arbitration analysis request sent by the terminal; the second arbitration analysis request carries a retrieval analysis statement;
acquiring table information of the case statistics table;
generating a target vector according to the search analysis statement and the table information;
inputting the target vector into a preset sequence model to obtain an analysis intention expression;
inputting the target vector into a preset intention classification model to obtain a second SQL template;
filling the analysis intention expression into the second SQL template to obtain a second retrieval analysis statement;
inquiring related cases in the case statistics table based on the second search analysis statement, carrying out statistical analysis on the case information of the related cases, and returning the obtained second analysis result to the terminal.
5. The method of claim 4, wherein the table information includes a plurality of field enumeration values; the generating a target vector according to the search analysis statement and the table information comprises the following steps:
performing word segmentation on the search analysis statement, calculating word vectors of each word segmentation, and recording the word vectors as first vectors;
calculating word vectors corresponding to each field enumeration value, and recording the word vectors as second vectors;
Calculating the similarity of the first vector and different second vectors;
and splicing the first vector with the second vector with the highest similarity to obtain the target vector.
6. An apparatus for analysis of a result of a arbitration, the apparatus comprising:
the case feature extraction module is used for receiving a first arbitration analysis request sent by the terminal; the first arbitration analysis request contains a case identifier; acquiring case information corresponding to the current case according to the case identification; generating a feature vector of a current case based on the case information, wherein the feature vector comprises calling a preset model to identify factor description sentences in the case information, calculating the similarity between the factor description sentences and a plurality of preset template description sentences, acquiring a reference factor value associated with the template description sentences with the similarity exceeding a threshold value, and determining a factor value of a corresponding target factor of the current case according to the reference factor value; calculating the characteristic vector of the current case based on factor values respectively corresponding to a plurality of target factors;
the search analysis statement generation module is used for inputting the feature vector into a preset sequence model to obtain an analysis dimension expression, and comprises the following steps: the sequence model includes an encoder, a decoder, and an attention module; the case statistics table comprises a plurality of field enumeration values; calling the encoder to forget a local vector containing analysis condition information in the feature vector to obtain a compressed vector; invoking the decoder to decode the compressed vector pair to obtain an initial matching probability corresponding to each field enumeration value; invoking the attention module to perform attention training on the compressed vector to obtain similarity weighting corresponding to each field enumeration value; adjusting the initial matching probability of the corresponding field enumeration value according to the similarity weighting to obtain a target matching probability corresponding to each field enumeration value; generating an analysis dimension expression according to the field enumeration value with the highest target matching probability; acquiring an analysis condition expression and a first SQL template, and filling the analysis dimension expression and the analysis condition expression into the first SQL template to obtain a first retrieval analysis statement;
The decision statistical analysis module is used for inquiring the approximate case of the current case in a preset case statistical table based on the first search analysis statement, carrying out statistical analysis on the decision result of the approximate case to obtain a first analysis result, and returning the first analysis result to the terminal.
7. The apparatus of claim 6, wherein the case feature extraction module is further configured to identify whether corresponding factor values are recorded in the case information according to a plurality of preset target factors; if yes, extracting a factor value of a corresponding target factor; and calculating the characteristic vector of the current case based on the factor values respectively corresponding to the target factors.
8. The apparatus of claim 6, wherein the arbitration statistics analysis module is further configured to obtain a first chart template, and determine a plurality of base coordinates and coordinate elements according to a coordinate extraction rule recorded by the first chart template; extracting coordinate values corresponding to each coordinate element from the first analysis result; constructing a first analysis chart based on a plurality of basic coordinates and coordinate elements and coordinate values corresponding to the basic coordinates respectively; generating a suggested arbitration result of the current case according to the first analysis result, and calculating the confidence coefficient of the suggested arbitration result; and sending the first analysis chart, the suggested judging result and the corresponding confidence to the terminal.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 5 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910520122.6A CN110377618B (en) | 2019-06-17 | 2019-06-17 | Method, device, computer equipment and storage medium for analyzing decision result |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910520122.6A CN110377618B (en) | 2019-06-17 | 2019-06-17 | Method, device, computer equipment and storage medium for analyzing decision result |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110377618A CN110377618A (en) | 2019-10-25 |
| CN110377618B true CN110377618B (en) | 2024-01-05 |
Family
ID=68248915
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910520122.6A Active CN110377618B (en) | 2019-06-17 | 2019-06-17 | Method, device, computer equipment and storage medium for analyzing decision result |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110377618B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110889786A (en) * | 2019-12-02 | 2020-03-17 | 北明软件有限公司 | Legal action insured advocate security use judging service method based on LSTM technology |
| CN113283760B (en) * | 2021-05-31 | 2023-04-18 | 浙江环玛信息科技有限公司 | Case flow analysis report generation method and system |
| CN115878807B (en) * | 2023-02-27 | 2023-05-12 | 中关村科学城城市大脑股份有限公司 | Urban brain-based one-net office case classification method and system |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102765643A (en) * | 2012-05-31 | 2012-11-07 | 天津大学 | Elevator fault diagnosis and early-warning method based on data drive |
| US9579397B1 (en) * | 2009-05-05 | 2017-02-28 | Hopkins Bruce Research Corporation | Computer-implemented systems and methods for analyzing court activity |
| CN106970987A (en) * | 2017-03-29 | 2017-07-21 | 陈�峰 | A kind of data analysing method and device |
| CN107153689A (en) * | 2017-04-29 | 2017-09-12 | 安徽富驰信息技术有限公司 | A kind of case search method based on Topic Similarity |
| CN107818138A (en) * | 2017-09-28 | 2018-03-20 | 银江股份有限公司 | A kind of case legal regulation recommends method and system |
| CN107885874A (en) * | 2017-11-28 | 2018-04-06 | 上海智臻智能网络科技股份有限公司 | Data query method and apparatus, computer equipment and computer-readable recording medium |
| CN108038091A (en) * | 2017-10-30 | 2018-05-15 | 上海思贤信息技术股份有限公司 | A kind of similar calculating of judgement document's case based on figure and search method and system |
| WO2018096514A1 (en) * | 2016-11-28 | 2018-05-31 | Thomson Reuters Global Resources | System and method for finding similar documents based on semantic factual similarity |
| CN109376227A (en) * | 2018-10-29 | 2019-02-22 | 山东大学 | A kind of prison term prediction technique based on multitask artificial neural network |
| CN109582950A (en) * | 2018-09-25 | 2019-04-05 | 南京大学 | A kind of judgement document argues appraisal procedure |
-
2019
- 2019-06-17 CN CN201910520122.6A patent/CN110377618B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9579397B1 (en) * | 2009-05-05 | 2017-02-28 | Hopkins Bruce Research Corporation | Computer-implemented systems and methods for analyzing court activity |
| CN102765643A (en) * | 2012-05-31 | 2012-11-07 | 天津大学 | Elevator fault diagnosis and early-warning method based on data drive |
| WO2018096514A1 (en) * | 2016-11-28 | 2018-05-31 | Thomson Reuters Global Resources | System and method for finding similar documents based on semantic factual similarity |
| CN106970987A (en) * | 2017-03-29 | 2017-07-21 | 陈�峰 | A kind of data analysing method and device |
| CN107153689A (en) * | 2017-04-29 | 2017-09-12 | 安徽富驰信息技术有限公司 | A kind of case search method based on Topic Similarity |
| CN107818138A (en) * | 2017-09-28 | 2018-03-20 | 银江股份有限公司 | A kind of case legal regulation recommends method and system |
| CN108038091A (en) * | 2017-10-30 | 2018-05-15 | 上海思贤信息技术股份有限公司 | A kind of similar calculating of judgement document's case based on figure and search method and system |
| CN107885874A (en) * | 2017-11-28 | 2018-04-06 | 上海智臻智能网络科技股份有限公司 | Data query method and apparatus, computer equipment and computer-readable recording medium |
| CN109582950A (en) * | 2018-09-25 | 2019-04-05 | 南京大学 | A kind of judgement document argues appraisal procedure |
| CN109376227A (en) * | 2018-10-29 | 2019-02-22 | 山东大学 | A kind of prison term prediction technique based on multitask artificial neural network |
Non-Patent Citations (1)
| Title |
|---|
| Interpretable Charge Predictions for Criminal Cases: Learning to Generate Court Views from Fact Descriptions;Hai Ye et al;《arXiv:1802.08504v1 [cs.CL]》;第1-11页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110377618A (en) | 2019-10-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111160017B (en) | Keyword extraction method, phonetics scoring method and phonetics recommendation method | |
| CN110765244B (en) | Method, device, computer equipment and storage medium for obtaining answering operation | |
| CN109871446B (en) | Refusing method in intention recognition, electronic device and storage medium | |
| CN109783655B (en) | Cross-modal retrieval method and device, computer equipment and storage medium | |
| CN109829629B (en) | Risk analysis report generation method, apparatus, computer device and storage medium | |
| WO2020077895A1 (en) | Signing intention determining method and apparatus, computer device, and storage medium | |
| US11244205B2 (en) | Generating multi modal image representation for an image | |
| CN110457431B (en) | Knowledge graph-based question and answer method and device, computer equipment and storage medium | |
| EP3855324A1 (en) | Associative recommendation method and apparatus, computer device, and storage medium | |
| WO2020237869A1 (en) | Question intention recognition method and apparatus, computer device, and storage medium | |
| CN109522393A (en) | Intelligent answer method, apparatus, computer equipment and storage medium | |
| US20160378863A1 (en) | Selecting representative video frames for videos | |
| CN110377631B (en) | Case information processing method, device, computer equipment and storage medium | |
| CN110377618B (en) | Method, device, computer equipment and storage medium for analyzing decision result | |
| CN110334179B (en) | Question-answer processing method, device, computer equipment and storage medium | |
| CN110377733B (en) | Text-based emotion recognition method, terminal equipment and medium | |
| CN110362798B (en) | Method, apparatus, computer device and storage medium for judging information retrieval analysis | |
| CN113157863A (en) | Question and answer data processing method and device, computer equipment and storage medium | |
| CN112651236B (en) | Method and device for extracting text information, computer equipment and storage medium | |
| CN110990533A (en) | Method and device for determining standard text corresponding to query text | |
| CN111985228A (en) | Text keyword extraction method and device, computer equipment and storage medium | |
| WO2019201024A1 (en) | Method, apparatus and device for updating model parameter, and storage medium | |
| CN110362592B (en) | Method, device, computer equipment and storage medium for pushing arbitration guide information | |
| CN113886531A (en) | Intelligent question and answer determining method and device, computer equipment and storage medium | |
| CN111552810B (en) | Entity extraction and classification method, entity extraction and classification device, computer equipment and storage medium |
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 |