CN110362592B - Method, device, computer equipment and storage medium for pushing arbitration guide information - Google Patents
Method, device, computer equipment and storage medium for pushing arbitration guide information Download PDFInfo
- Publication number
- CN110362592B CN110362592B CN201910520217.8A CN201910520217A CN110362592B CN 110362592 B CN110362592 B CN 110362592B CN 201910520217 A CN201910520217 A CN 201910520217A CN 110362592 B CN110362592 B CN 110362592B
- Authority
- CN
- China
- Prior art keywords
- case
- arbitration
- focus
- information
- statement
- 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 43
- 238000012545 processing Methods 0.000 claims abstract description 30
- 238000010801 machine learning Methods 0.000 claims abstract description 14
- 239000013598 vector Substances 0.000 claims description 89
- 238000004458 analytical method Methods 0.000 claims description 85
- 230000014509 gene expression Effects 0.000 claims description 20
- 230000015654 memory Effects 0.000 claims description 18
- 238000003062 neural network model Methods 0.000 claims description 17
- 238000012512 characterization method Methods 0.000 claims description 13
- 238000013145 classification model Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 12
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 description 7
- 230000005484 gravity Effects 0.000 description 6
- 238000012549 training Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000011218 segmentation Effects 0.000 description 4
- 238000007619 statistical method Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000012790 confirmation Methods 0.000 description 3
- 230000001427 coherent effect Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000003032 molecular docking Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000006403 short-term memory Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000013135 deep learning 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
- 238000009499 grossing Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
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
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/242—Query formulation
- G06F16/243—Natural language query formulation
-
- 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
- G06F16/2452—Query translation
- G06F16/24522—Translation of natural language queries to structured queries
-
- 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
- G06F16/3344—Query execution using natural language analysis
-
- 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
- G06F16/35—Clustering; Classification
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Technology Law (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to a machine learning-based arbitration guide information pushing method, a machine learning-based arbitration guide information pushing device, computer equipment and a storage medium. The method comprises the following steps: receiving an arbitration guiding request sent by a terminal; the request of the arbitration guide carries a case identification; acquiring a case file of the current case according to the case identifier; identifying a focus description sentence in the case file; calculating the similarity between the focus description statement and a plurality of preset template description statements; determining the focus type of the current case according to the template description statement of which the similarity exceeds a threshold value; and acquiring the arbitration guide information associated with the focus type, and returning the arbitration guide information to the terminal. By adopting the method, the user can be decided and guided, and the case processing efficiency is further improved.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method, an apparatus, a computer device, and a storage medium for pushing arbitration guide information.
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 manner of making a decision is entirely dependent on the processing experience of judges and lawyers, lacks guidance for current case processing opinions, and further reduces case processing efficiency.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a method, apparatus, computer device, and storage medium for delivering information of a decision guide, which can decide a user and further improve case processing efficiency.
A method of adjudication guideline information pushing, the method comprising: receiving an arbitration guiding request sent by a terminal; the request of the arbitration guide carries a case identification; acquiring a case file of the current case according to the case identifier; identifying a focus description sentence in the case file; calculating the similarity between the focus description statement and a plurality of preset template description statements; determining the focus type of the current case according to the template description statement of which the similarity exceeds a threshold value; and acquiring the arbitration guide information associated with the focus type, and returning the arbitration guide information to the terminal.
In one embodiment, the identifying the focus description statement in the case file includes: determining the splitting position of the case file according to the preset data quantity; detecting whether the split position is located between adjacent separators; if yes, splitting the case file at any separator in the adjacent separators; if not, splitting the case file at the splitting position; and calling a machine learning model to identify a focus description sentence in the plurality of case paragraphs obtained by splitting.
In one embodiment, the calculating the similarity between the focus description sentence and a plurality of preset template description sentences includes: preprocessing a plurality of focus description sentences to obtain preprocessed texts in different sequences; invoking a neural network model, wherein the neural network model comprises an LSTM and a full connection layer; the LSTM comprises a forget gate, an input gate and an output gate; forgetting the preprocessed text in the previous sequence through the forgetting door, and updating the preprocessed text input in the current sequence through the input door; calculating the text obtained after forgetting processing and the text obtained after updating through the output door to obtain a characterization vector corresponding to the text preprocessed in the current sequence; converting the characterization vector through the full connection layer to obtain a corresponding focus characteristic vector; acquiring reference feature vectors corresponding to a plurality of preset template description sentences; and calculating the similarity between the corresponding focus description statement and each template description statement based on the focus feature vector and the reference feature vector.
In one embodiment, before the acquiring the resolution guide information associated with the focus type, the method further includes: identifying relevant cases corresponding to each focus type based on a preset case statistics table; acquiring a case file of the related case, and recording the case file as a history file; identifying opinion description sentences in the history file; and generating the arbitration guide information of the corresponding focus type according to the opinion description statement.
In one embodiment, the returning the arbitration guide information to the terminal includes: acquiring one or more kinds of arbitration information associated with each focus type; if the judging opinion information is multiple, acquiring case descriptions of historical cases corresponding to each judging opinion information; calculating the coincidence degree of the corresponding historical case and the current case based on the case description; sorting the multiple types of arbitration information according to the fitness; and returning the sequenced multiple types of arbitration information to the terminal as arbitration guiding information.
In one embodiment, the arbitration request also carries a search analysis statement; the method comprises the following steps: acquiring a case statistical table and corresponding table information; 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 target SQL template; filling the analysis intention expression into the target SQL template to obtain an SQL query statement; inquiring related cases in the case statistics table based on the SQL inquiry statement, carrying out statistics analysis on case information of the related cases, and returning an analysis result to the terminal.
An arbitration guide information pushing apparatus, the apparatus comprising: the system comprises an arbitration guide request module, a terminal and a processing module, wherein the arbitration guide request module is used for receiving an arbitration guide request sent by the terminal; the request of the arbitration guide carries a case identification; the focus type identification module is used for acquiring a case file of the current case according to the case identifier; identifying a focus description sentence in the case file; calculating the focus description statement and a preset similarity of the plurality of template description sentences; determining the focus type of the current case according to the template description statement of which the similarity exceeds a threshold value; and the guide information pushing module is used for acquiring the arbitration guide information associated with the focus type and returning the arbitration guide information to the terminal.
A computer device comprising a memory storing a computer program and a processor implementing the steps of the arbitration guide information pushing method provided in any 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 sanctioned guide information pushing method provided in any one of the embodiments of the present application.
According to the method, the device, the computer equipment and the storage medium for pushing the arbitration guiding information, the case file of the current case can be obtained according to the arbitration guiding request sent by the terminal; the focus type of the current case can be determined according to the template description sentences with the similarity exceeding a threshold value by identifying the focus description sentences in the case file and calculating the similarity between the focus description sentences and a plurality of preset template description sentences; based on the focus type of the current case, corresponding associated judging guide information can be acquired; and returning the arbitration guide information to the terminal so as to conduct arbitration guide on the user. In the case processing process, the user can automatically identify the focus type of the current case by simply providing the case identification, and push corresponding arbitration guiding information based on the focus type, so that the user can be arbitrated, and the case processing efficiency can be improved.
Drawings
FIG. 1 is an application scenario diagram of an arbitration guide information push method in one embodiment;
FIG. 2 is a flow chart of a method for pushing arbitration guide information in one embodiment;
FIG. 3 is a flow diagram of the steps of natural language based arbitration analysis in one embodiment;
FIG. 4 is a block diagram of an apparatus for pushing arbitration guide information in one 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 pushing the arbitration guide information 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. During the case processing process, if the user needs to decide the current case, the terminal 102 may send a request for deciding the current case to the server 104. The resolution director request carries the case identification of the current case. Server 104 obtains the case file of the current case according to the case identification. The case file may be a litigation request book or the like. The server 104 invokes a preset machine learning model to identify the focus description statement in the case file. The server 104 pre-stores a plurality of template description sentences and focus types associated with each template description sentence. The server 104 calculates the similarity between each focus description sentence and a plurality of preset template description sentences, and compares whether the similarity exceeds a threshold value. If so, the server 104 obtains the focus type associated with the template description statement with the similarity exceeding the threshold value, thereby determining the focus type of the current case. Server 104 also obtains the focus type and the resolution information of each history case by deconstructing case files of a plurality of history cases. The server 104 generates corresponding arbitration guide information based on a plurality of kinds of arbitration opinion information corresponding to each focus type. And acquiring the resolution guide information associated with the focus types according to the focus type server 104 associated with the template description statement with the highest similarity, and returning the resolution guide information to the terminal. In the case processing process, the user can automatically identify the focus type of the current case by simply providing the case identification, and push corresponding arbitration guiding information based on the focus type, so that the user can be arbitrated, and the case processing efficiency can be improved.
In one embodiment, as shown in fig. 2, a method for pushing arbitration guiding information is provided, and the method is applied to the server in fig. 1 for illustration, and includes the following steps:
When the user needs to conduct guiding processing on the current case, the case identification of the current case can be filled in based on a litigation service platform on the terminal. The litigation service platform generates a resolution directive request based on the case identification and sends the resolution directive request to the server. And the server pulls the case file of the corresponding case from the database corresponding to the litigation service platform according to the case identification. The case file may be a litigation request book or the like. The server and litigation service platform directly realize data docking. If the data docking is not realized, the user can submit the case file of the current case to the server through the terminal.
The server deconstructs case files of a large number of historical cases in advance, and builds a case statistical table by using case information obtained by deconstructing. To ensure accuracy of the search analysis, the case statistics may be dynamically updated. The case statistics table records case information of a plurality of history cases. The case information may include a case identification and a plurality of case factors deconstructed from the case file. The case factors may be the case of history cases, the focus type of the disputed focus, the territory, the referee time, the arbitration view, etc.
In one embodiment, deconstructing a case file of a history case to obtain a plurality of case factors of corresponding cases, including: identifying whether corresponding factor values are recorded in the case file according to a plurality of preset target factors; if yes, extracting a factor value of a corresponding target factor; otherwise, calling a preset machine learning model to identify factor description sentences in the case file, 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 the case factor value of the corresponding target factor of the current case according to the reference factor value.
The target factor refers to a case factor for which a corresponding factor value needs to be acquired, and may be a focus type, a arbitration view, and the like. 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 based on a pre-trained machine learning model, such as focus type, arbitration view, etc.
The machine learning model may be trained based on a case file of a large number of sample cases for extracting target factors. Specifically, according to the multiple keyword sets provided by expert rules, multiple regular expressions are preset in the server. Different regular expressions are used for identifying related descriptive statements corresponding to different target factors in the case file. The server screens the description sentences related to the target factors in the case files of the sample cases through regular matching and records the description sentences as factor description sentences. And the server marks the target factor value of the screened factor description statement. Different factor description sentences and corresponding target factor values respectively form different samples. Training the initial model to be trained based on a large number of samples to obtain a machine learning model. The initial model to be trained may be an X-GBoost model or the like.
The server presets one or more template description statements for each target factor. Each template description statement is associated with a corresponding reference factor value. The server calculates the semantic similarity between the extracted factor description sentence and the corresponding template description sentence based on the machine learning model, and marks the reference factor value associated with the template description sentence with the highest similarity and reaching the threshold value as the target factor value of the corresponding target factor.
The factor description sentence may be a focus description sentence, a viewpoint description sentence, or the like according to the difference of the target case factors. 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 or cosine similarity of the two vectors. Each template description statement is associated with a corresponding reference factor value. The reference factor value may be a focus type, an arbitration point of view, etc. The server acquires the reference factor value associated with the template description statement with the highest similarity and reaching the threshold value, and takes the acquired reference factor value or the reference factor value as the factor value of the corresponding target factor of the current case after performing preset logic operation.
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 generation efficiency of the judging guide information is further improved. The server deconstructs the case file of the current case according to the mode to obtain a plurality of case factors of the current case, such as case list, focus type and the like.
And the server screens the approximate cases of the current case in the case statistics table according to the focus type. The server also pre-deconstructs the resolution opinion information corresponding to the historical cases of each focus type.
In one embodiment, before acquiring the resolution guide information associated with the focus type, the method further comprises: identifying relevant cases corresponding to each focus type based on a preset case statistics table; acquiring a case file of a related case, and recording the case file as a history file; identifying opinion description sentences in the history file; and generating the arbitration guide information of the corresponding focus type according to the opinion description statement.
The related cases refer to historical cases with the same focus type. The server identifies opinion description sentences in each history file according to the mode, and performs semantic smoothing processing on the opinion description sentences to obtain the judging opinion information of the corresponding history cases.
In one embodiment, returning the arbitration guide information to the terminal includes: acquiring one or more kinds of arbitration information associated with each focus type; if the judging opinion information is multiple, acquiring case descriptions of historical cases corresponding to each judging opinion information; calculating the coincidence degree of the corresponding historical case and the current case based on the case description; sorting the various pieces of arbitration opinion information according to the fitness; and returning the sequenced multiple types of arbitration information to the terminal as arbitration guiding information.
The server inquires the historical cases with the same focal type as the current case in the case statistics table and records the historical cases as approximate cases. The server acquires the resolution information of the approximate case, and generates corresponding resolution guide information based on the plurality of resolution information. The arbitration guiding information may be information for guiding the user to write the arbitration document of the current case, may be the arbitration document itself of the similar case, or may be arbitration opinion information extracted from the arbitration document of the similar case, that is, a part of content with a relatively large reference probability is cited.
If the resolution information of the approximate cases has a plurality of kinds, the server acquires the case description of each of the approximate cases. The case descriptions refer to a variety of case factors approximating the case, such as territories, decision times, court levels, etc. The server judges whether other case factors of the approximate case except the focus type are matched with the corresponding case factors of the current case or not so as to measure the coincidence degree of the approximate case and the current case.
In another embodiment, the server marks the part of the content with larger reference probability in the arbitration guiding information in a distinguishing way, so that a user can conveniently and quickly acquire the effective information in the push arbitration guiding information, the conversion rate of the arbitration guiding information is improved, and the generation efficiency of an arbitration book is further improved.
In this embodiment, according to an arbitration guiding request sent by a terminal, a case file of a current case may be obtained; the focus type of the current case can be determined according to the template description sentences with the similarity exceeding a threshold value by identifying the focus description sentences in the case file and calculating the similarity between the focus description sentences and a plurality of preset template description sentences; based on the focus type of the current case, corresponding associated judging guide information can be acquired; returning the arbitration guide information to the terminal can perform arbitration guide on the user. In the case processing process, the user can automatically identify the focus type of the current case by simply providing the case identification, and push corresponding arbitration guiding information based on the focus type, so that the user can be arbitrated, and the case processing efficiency can be improved.
In one embodiment, identifying the focus description statement in the case file includes: determining the splitting position of the case file according to the preset data quantity; detecting whether the splitting position is located between adjacent separators; if yes, splitting the case file at any separator in the adjacent separators; if not, splitting the case file at the splitting position; and calling a machine learning model to identify a focus description sentence in the plurality of case paragraphs obtained by splitting.
The server calculates the data amount of the case file and compares whether the data amount exceeds the target data amount. The target data size may be preset, or may be temporarily generated according to load monitoring results of other servers in the plurality of clusters. When the data volume exceeds the target data volume, the server can divide the case file into a plurality of case paragraphs with small data volume in advance, and then divide the case paragraphs into a plurality of case sentences respectively. Specifically, the server determines the splitting position of the case file according to the target data volume. For example, if the data size of the case file a is 720M and the target data size is 80M, the 80M-size position of the case file is marked as the first split position, the 160M-size position is marked as the second split position, and so on.
The server identifies whether each split location is located between adjacent separators. When the splitting position is positioned at the position where one separator is positioned, the server splits the case file at the splitting position to obtain a plurality of case paragraphs corresponding to the case file. When the splitting position is located between the adjacent separators, the server splits the corresponding case file at any one of the adjacent separators, namely, splits the former separator or the latter separator in the adjacent separators to obtain a plurality of case paragraphs corresponding to the case file. The server further calls the multithreading to split the case paragraphs into a plurality of case sentences according to the mode, or sends the case paragraphs to other servers in the cluster to split, so that file splitting efficiency is improved.
In this embodiment, two-stage splitting is performed on a case file with a large data volume, and the case file with the large data volume is split into case paragraphs with a small data volume, so that the case paragraphs can be split into a plurality of case sentences in parallel, and further the file splitting efficiency can be improved.
In one embodiment, calculating the similarity between the focus description sentence and a plurality of preset template description sentences includes: preprocessing a plurality of focus description sentences to obtain preprocessed texts in different sequences; invoking a neural network model, wherein the neural network model comprises an LSTM and a full connection layer; LSTM includes forget gate, input gate and output gate; forgetting the preprocessed text in the previous sequence through a forgetting door, and updating the preprocessed text input in the current sequence through an input door; calculating the text obtained after forgetting processing and the text obtained after updating through an output door to obtain a characterization vector corresponding to the preprocessed text in the current sequence; converting the representative vector through the full connection layer to obtain a corresponding focus characteristic vector; acquiring reference feature vectors corresponding to a plurality of preset template description sentences; and calculating the similarity between the corresponding focus description statement and each template description statement based on the focus feature vector and the reference feature vector.
The server preprocesses the focus description sentence. The pretreatment comprises the following steps: word segmentation, word stopping, simplified reproduction and the like. The word segmentation refers to the segmentation of one sentence. Deactivating words refers to removing words that are nonsensical for semantic understanding, such as "en," "o. The simplified and traditional Chinese information is converted into simplified Chinese.
The server builds a neural network model in advance. The neural network model can be obtained by deep learning in advance based on a large number of real historical cases of the problem base. After the preprocessing is completed, the server calls a neural network model, and vectorization processing is carried out on the focus description statement after the preprocessing through the neural network model. The content of the focus description sentence may be related to the content of which the previous time distance is long. In other words, the content of the question needs to be identified in conjunction with the context when describing the sentence in focus. Based on this, the neural network model is built using LSTM (Long Short-Term Memory) and full connectivity layers.
LSTM is used to identify whether two focus description statements are semantically related. LSTM includes a forget gate, an input gate, and an output gate. The forgetting gate can discard irrelevant information and redundant information among the contexts of the focus description sentences in the current sequence, so that the focus description sentences in the previous sequence can be reserved to the current sequence. The order here refers to the order in which the focus description statements appear in the case file. The input gate can update the content of the focus description sentences, i.e. determine how much of the focus description sentences of the current order can be saved. The output gate may control how many focus description statements may be output to the current output value of the LSTM.
The conventional LSTM first decides which focus description statements are discarded, i.e. forgotten, through a forget gate. After forgetting, the content of the focus description sentence is updated through the input gate. And then output through an output gate. The output results obtained in this way are generally of low accuracy. In order to effectively improve the accuracy of the output result, the embodiment optimizes the LSTM. Specifically, when the preprocessed text in the current period is obtained, forgetting processing is carried out on the preprocessed text in the previous sequence through a forgetting door; when the forgetting door performs forgetting processing, updating the preprocessed text in the current sequence through the input door; and calculating the text obtained after forgetting processing and the text obtained after updating through an output door to obtain a characterization vector corresponding to the preprocessed text in the current sequence.
And converting the characterization vector of the focus description sentence output by the LSTM through a full connection layer in the neural network model, thereby obtaining a focus characteristic vector corresponding to the focus description sentence.
The server pre-calculates the reference feature vector corresponding to each template description sentence in the above manner. And the server obtains the similarity of each focus description sentence to different template description sentences by calculating Euclidean distance and the like of the focus feature vector and the reference feature vector.
In this embodiment, compared with the conventional LSTM, when the focus description sentence of the current order is input, the focus description sentence of the previous order can be forgotten and the focus description sentence of the current order can be updated at the same time. Therefore, comprehensive consideration can be given to the forgetting process of the forgetting gate and the updating process of the input gate, and the accuracy of the output result is effectively improved.
In one embodiment, the arbitration request also carries a search analysis statement; as shown in fig. 3, the method further includes a step of natural language based arbitration analysis, specifically including:
In addition to referencing the resolution of historical cases, litigation service platforms also support users to retrieve and analyze the processing of past related cases from multiple dimensions based on natural language. Specifically, when the user needs to perform search analysis based on the current case, a request for resolution analysis can be sent to the server based on the litigation service platform. The resolution request carries a retrieval resolution statement.
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.
The server acquires the case statistics table and corresponding table information. 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.
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. For example, the term corresponding to the search analysis sentence "specific gravity of contract dispute case in Guangdong area in 2018" in the above example may be "2018", "Guangdong", "area", "contract dispute", "case", "and" specific gravity ". Wherein, the word "region", "case" can be removed as stop words; the term "specific gravity" may be replaced with the synonym "proportion". 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 the second vector of each field enumeration value in the case statistics table as described above. The server obtains the similarity between the first vector and each second vector by calculating the Euclidean distance between the first vector and the second vector and the like. The server compares whether the highest similarity reaches a threshold. If yes, the server splices the first vector with the second vector with the highest similarity 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 306, inputting the target vector into a preset sequence model to obtain an analysis intention expression.
The server pre-trains the sequence model based on case information of a large number of real historical cases. The sequence model is used for identifying the retrieval analysis intention of the user, namely mining potential information of analysis dimensions, analysis conditions and the like which can reflect the expectations of the user in the retrieval analysis statement. 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 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 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 server inputs the target vector into a preset sequence model to obtain one or more analysis intention expressions. Specifically, the same search analysis statement may correspond to a plurality of target vectors. Forgetting analysis dimension information contained in each target vector through LSTM, and screening to obtain analysis condition field values. The server generates an analysis condition expression from the analysis condition field value. For example, a preset "intention" field may be used as a Key Value, an analysis condition field Value or a Value after conversion of the analysis condition field Value, and a Key-Value Key Value pair formed may be used as an analysis condition expression.
The dimensional sequence model includes an encoder, a decoder, and an attention module. And the server calls an encoder to forget the local vector containing analysis condition information in the target vector, and a compressed vector is 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.
And the server generates an analysis dimension expression corresponding to the corresponding target vector based on the field enumeration value with the highest target matching probability. The analytical intent expression may be in the form of a Key-value Key value pair. 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 an analysis 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 308, inputting the target vector into a preset intention classification model to obtain a target SQL template.
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 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 (Recurrentneural network, recurrent neural network model). And 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 step 310, filling the analysis intention expression into a target SQL template to obtain an SQL query statement.
The manner in which different SQL templates are populated may be different. And the server fills the analysis intention expression into the target SQL template according to the filling mode of the target SQL template, so that the SQL query statement can be obtained.
Based on different SQL query sentences, the data query with 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 SQL query statement, and returns an 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. And the application supports the retrieval of the user 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.
In the embodiment, based on the sequence model and the intention classification model, the search analysis intention expressed by the user based on the search analysis statement can be accurately identified; 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 and 3 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as 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 and 3 may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the sub-steps or stages are performed necessarily occur in sequence, 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 an arbitration guide information pushing means, including: an arbitration request module 402, an arbitration request 402, and an guideline information push module 406, wherein:
An arbitration guiding request module 402, configured to receive an arbitration guiding request sent by a terminal; the resolution director request carries a case identification.
A focus type identifying module 404, configured to obtain a case file of a current case according to a case identifier; identifying a focus description sentence in a case file; calculating the similarity between the focus description statement and a plurality of preset template description statements; and determining the focus type of the current case according to the template description statement with the similarity exceeding the threshold value.
And the guide information pushing module 406 is configured to obtain the arbitration guide information associated with the focus type, and return the arbitration guide information to the terminal.
In one embodiment, the focus type identification module 404 is further configured to determine a splitting location of the case file according to a preset data amount; detecting whether the splitting position is located between adjacent separators; if yes, splitting the case file at any separator in the adjacent separators; if not, splitting the case file at the splitting position; and calling a machine learning model to identify a focus description sentence in the plurality of case paragraphs obtained by splitting.
In one embodiment, the focus type recognition module 404 is further configured to preprocess the plurality of focus description sentences to obtain preprocessed text in different orders; invoking a neural network model, wherein the neural network model comprises an LSTM and a full connection layer; LSTM includes forget gate, input gate and output gate; forgetting the preprocessed text in the previous sequence through a forgetting door, and updating the preprocessed text input in the current sequence through an input door; calculating the text obtained after forgetting processing and the text obtained after updating through an output door to obtain a characterization vector corresponding to the preprocessed text in the current sequence; converting the representative vector through the full connection layer to obtain a corresponding focus characteristic vector; acquiring reference feature vectors corresponding to a plurality of preset template description sentences; and calculating the similarity between the corresponding focus description statement and each template description statement based on the focus feature vector and the reference feature vector.
In one embodiment, the apparatus further includes a guide information deconstructing module 408, configured to identify, based on a preset case statistics table, a relevant case corresponding to each focus type; acquiring a case file of a related case, and recording the case file as a history file; identifying opinion description sentences in the history file; and generating the arbitration guide information of the corresponding focus type according to the opinion description statement.
In one embodiment, the guiding information pushing module 406 is further configured to obtain one or more types of arbitration information associated with each focus type; if the judging opinion information is multiple, acquiring case descriptions of historical cases corresponding to each judging opinion information; calculating the coincidence degree of the corresponding historical case and the current case based on the case description; sorting the various pieces of arbitration opinion information according to the fitness; and returning the sequenced multiple types of arbitration information to the terminal as arbitration guiding information.
In one embodiment, the arbitration request also carries a search analysis statement; the device further comprises a decision retrieval analysis module 410, which is used for acquiring a case statistical table and corresponding table information; 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 target SQL template; filling the analysis intention expression into a target SQL template to obtain an SQL query statement; inquiring related cases in the case statistics table based on SQL inquiry sentences, carrying out statistical analysis on case information of the related cases, and returning analysis results to the terminal.
For specific limitations on the arbitration guide information pushing means, reference may be made to the above limitation on the arbitration guide information pushing method, and no further description is given here. The respective modules in the above-described arbitration guide information pushing 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 plurality of template description sentences and the arbitration guide information associated with each template description sentence. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by a processor, implements a method of sanctioning guide information pushing.
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 implements the steps of the arbitration guideline information pushing method provided in any one 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 (8)
1. A method of adjudication guideline information pushing, the method comprising:
receiving an arbitration guiding request sent by a terminal; the request of the arbitration guide carries a case identification;
acquiring a case file of the current case according to the case identifier;
identifying a focus description sentence in the case file;
preprocessing a plurality of focus description sentences to obtain preprocessed texts in different sequences;
Invoking a neural network model, wherein the neural network model comprises an LSTM and a full connection layer; the LSTM comprises a forget gate, an input gate and an output gate;
forgetting the preprocessed text in the previous sequence through the forgetting door, and updating the preprocessed text input in the current sequence through the input door; calculating the text obtained after forgetting processing and the text obtained after updating through the output door to obtain a characterization vector corresponding to the text preprocessed in the current sequence;
converting the characterization vector through the full connection layer to obtain a corresponding focus characteristic vector;
acquiring reference feature vectors corresponding to a plurality of preset template description sentences;
calculating the similarity between the corresponding focus description statement and each template description statement based on the focus feature vector and the reference feature vector; determining the focus type of the current case according to the template description statement of which the similarity exceeds a threshold value;
identifying relevant cases corresponding to each focus type based on a preset case statistics table;
acquiring a case file of the related case, and recording the case file as a history file;
identifying opinion description sentences in the history file;
Generating arbitration guide information of the corresponding focus type according to the opinion description statement; the arbitration guide information is at least one of information for guiding a user to write an arbitration document of a current case, an arbitration document of an approximate case, and arbitration opinion information extracted from the arbitration document of the approximate case;
acquiring the arbitration guide information associated with the focus types, and acquiring one or more types of arbitration opinion information associated with each focus type;
if the judging opinion information is multiple, acquiring case descriptions of historical cases corresponding to each judging opinion information;
calculating the coincidence degree of the corresponding historical case and the current case based on the case description;
sorting the multiple types of arbitration information according to the fitness;
and returning the sequenced multiple types of arbitration information to the terminal as arbitration guiding information.
2. The method of claim 1, wherein the identifying the focus description statement in the case file comprises:
determining the splitting position of the case file according to the preset data quantity;
detecting whether the split position is located between adjacent separators;
if yes, splitting the case file at any separator in the adjacent separators;
If not, splitting the case file at the splitting position;
and calling a machine learning model to identify a focus description sentence in the plurality of case paragraphs obtained by splitting.
3. The method of claim 1, wherein the arbitration request further carries a retrieve analysis statement; the method comprises the following steps:
acquiring a case statistical table and corresponding table information;
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 target SQL template;
filling the analysis intention expression into the target SQL template to obtain an SQL query statement;
inquiring related cases in the case statistics table based on the SQL inquiry statement, carrying out statistics analysis on case information of the related cases, and returning an analysis result to the terminal.
4. An arbitration guide information pushing apparatus, the apparatus comprising:
the system comprises an arbitration guide request module, a terminal and a processing module, wherein the arbitration guide request module is used for receiving an arbitration guide request sent by the terminal; the request of the arbitration guide carries a case identification;
the focus type identification module is used for acquiring a case file of the current case according to the case identifier; identifying a focus description sentence in the case file; preprocessing a plurality of focus description sentences to obtain preprocessed texts in different sequences; invoking a neural network model, wherein the neural network model comprises an LSTM and a full connection layer; the LSTM comprises a forget gate, an input gate and an output gate; forgetting the preprocessed text in the previous sequence through the forgetting door, and updating the preprocessed text input in the current sequence through the input door; calculating the text obtained after forgetting processing and the text obtained after updating through the output door to obtain a characterization vector corresponding to the text preprocessed in the current sequence; converting the characterization vector through the full connection layer to obtain a corresponding focus characteristic vector; acquiring reference feature vectors corresponding to a plurality of preset template description sentences; calculating the similarity between the corresponding focus description statement and each template description statement based on the focus feature vector and the reference feature vector; determining the focus type of the current case according to the template description statement of which the similarity exceeds a threshold value;
The guide information deconstructing module is used for identifying relevant cases corresponding to each focus type based on a preset case statistical table; acquiring a case file of the related case, and recording the case file as a history file; identifying opinion description sentences in the history file; generating arbitration guide information of the corresponding focus type according to the opinion description statement; the arbitration guide information is at least one of information for guiding a user to write an arbitration document of a current case, an arbitration document of an approximate case, and arbitration opinion information extracted from the arbitration document of the approximate case;
the guide information pushing module is used for acquiring the arbitration guide information associated with the focus types and acquiring one or more types of arbitration opinion information associated with each focus type; if the judging opinion information is multiple, acquiring case descriptions of historical cases corresponding to each judging opinion information; calculating the coincidence degree of the corresponding historical case and the current case based on the case description; sorting the multiple types of arbitration information according to the fitness; and returning the sequenced multiple types of arbitration information to the terminal as arbitration guiding information.
5. The apparatus of claim 4, wherein the focus type identification module is further configured to determine a splitting location of the case file according to a preset data amount; detecting whether the split position is located between adjacent separators; if yes, splitting the case file at any separator in the adjacent separators; if not, splitting the case file at the splitting position; and calling a machine learning model to identify a focus description sentence in the plurality of case paragraphs obtained by splitting.
6. The apparatus of claim 4, wherein the arbitration directive request further carries a search analysis statement, the apparatus further comprising an arbitration search analysis module for obtaining a case statistics table and corresponding table information; 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 target SQL template; filling the analysis intention expression into the target SQL template to obtain an SQL query statement; inquiring related cases in the case statistics table based on the SQL inquiry statement, carrying out statistics analysis on case information of the related cases, and returning an analysis result to the terminal.
7. 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 of claims 1 to 3 when the computer program is executed.
8. 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 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910520217.8A CN110362592B (en) | 2019-06-17 | 2019-06-17 | Method, device, computer equipment and storage medium for pushing arbitration guide information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910520217.8A CN110362592B (en) | 2019-06-17 | 2019-06-17 | Method, device, computer equipment and storage medium for pushing arbitration guide information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110362592A CN110362592A (en) | 2019-10-22 |
| CN110362592B true CN110362592B (en) | 2023-06-23 |
Family
ID=68217331
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910520217.8A Active CN110362592B (en) | 2019-06-17 | 2019-06-17 | Method, device, computer equipment and storage medium for pushing arbitration guide information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110362592B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112199578B (en) * | 2020-08-28 | 2022-04-22 | 贝壳找房(北京)科技有限公司 | Information processing method and apparatus, electronic device, and storage medium |
| 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 (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN108694178A (en) * | 2017-04-06 | 2018-10-23 | 北京国双科技有限公司 | A kind of method and device for recommending judicial cognizance |
| CN109472017A (en) * | 2017-09-08 | 2019-03-15 | 北京国双科技有限公司 | Obtain the method and device that judgement document the court to be generated thinks section relevant information |
| CN109614479A (en) * | 2018-10-29 | 2019-04-12 | 山东大学 | A kind of judgement document's recommended method based on distance vector |
| CN109729126A (en) * | 2017-10-31 | 2019-05-07 | 北京国双科技有限公司 | Method for pushing, device, storage medium and the processor of textual resources |
-
2019
- 2019-06-17 CN CN201910520217.8A patent/CN110362592B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108694178A (en) * | 2017-04-06 | 2018-10-23 | 北京国双科技有限公司 | A kind of method and device for recommending judicial cognizance |
| CN109472017A (en) * | 2017-09-08 | 2019-03-15 | 北京国双科技有限公司 | Obtain the method and device that judgement document the court to be generated thinks section relevant information |
| 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 |
| CN109729126A (en) * | 2017-10-31 | 2019-05-07 | 北京国双科技有限公司 | Method for pushing, device, storage medium and the processor of textual resources |
| CN109614479A (en) * | 2018-10-29 | 2019-04-12 | 山东大学 | A kind of judgement document's recommended method based on distance vector |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110362592A (en) | 2019-10-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110096570B (en) | Intention identification method and device applied to intelligent customer service robot | |
| CN111160017B (en) | Keyword extraction method, phonetics scoring method and phonetics recommendation method | |
| CN110377632B (en) | Litigation result prediction method, litigation result prediction device, litigation result prediction computer device and litigation result prediction storage medium | |
| CN110765244B (en) | Method, device, computer equipment and storage medium for obtaining answering operation | |
| CN110021439B (en) | Medical data classification method and device based on machine learning and computer equipment | |
| CN110162627B (en) | Data increment method and device, computer equipment and storage medium | |
| CN110444198B (en) | Retrieval method, retrieval device, computer equipment and storage medium | |
| CN109829629B (en) | Risk analysis report generation method, apparatus, computer device and storage medium | |
| WO2021042503A1 (en) | Information classification extraction method, apparatus, computer device and storage medium | |
| CN109063217B (en) | Work order classification method and device in electric power marketing system and related equipment thereof | |
| CN111324743A (en) | Text relation extraction method and device, computer equipment and storage medium | |
| CN110377631B (en) | Case information processing method, device, computer equipment and storage medium | |
| CN113420113B (en) | Semantic recall model training and recall question and answer method, device, equipment and medium | |
| CN110362798B (en) | Method, apparatus, computer device and storage medium for judging information retrieval analysis | |
| CN110334186B (en) | Data query method and device, computer equipment and computer readable storage medium | |
| CN113192516B (en) | Voice character segmentation method, device, computer equipment and storage medium | |
| CN110309504B (en) | Text processing method, device, equipment and storage medium based on word segmentation | |
| CN111985228A (en) | Text keyword extraction method and device, computer equipment and storage medium | |
| US20220351634A1 (en) | Question answering systems | |
| CN110377618B (en) | Method, device, computer equipment and storage medium for analyzing decision result | |
| 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 | |
| CN110532229B (en) | Evidence file retrieval method, device, computer equipment and storage medium | |
| CN113569021B (en) | Method for classifying users, computer device and readable storage medium | |
| CN113570404B (en) | Target user positioning method, device and related equipment |
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 |