CN109472424B - Method and device for predicting actual criminal period of crime, storage medium and server - Google Patents
Method and device for predicting actual criminal period of crime, storage medium and server Download PDFInfo
- Publication number
- CN109472424B CN109472424B CN201811546756.0A CN201811546756A CN109472424B CN 109472424 B CN109472424 B CN 109472424B CN 201811546756 A CN201811546756 A CN 201811546756A CN 109472424 B CN109472424 B CN 109472424B
- Authority
- CN
- China
- Prior art keywords
- crime
- criminal
- information
- name
- matching
- 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
Images
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method, a device, a storage medium and a server for predicting the actual criminal period of a crime, wherein the method comprises the following steps: sequentially obtaining a crime name and a crime area input by a user based on a user terminal input interface; automatically matching corresponding crime conditions and the list information of the influence factors influencing the sentencing in sequence based on the crime names and the crime areas; according to the received crime condition information input by the user based on the crime condition and the influence factor information based on the influence factor list information influencing the sentencing; searching and matching in a case database according to the crime name, the crime area, the crime condition information and the influence factor information; and carrying out criminal period data extraction on the mutually matched criminal case, and acquiring the actual criminal prediction criminal period based on the extracted criminal period data. In the embodiment of the invention, case matching can be carried out through the relevant information input by the user, the actual criminal period in the matched case is extracted for prediction, and the working efficiency of judges and lawyers is greatly improved.
Description
Technical Field
The invention relates to the technical field of data prediction, in particular to a prediction method, a prediction device, a storage medium and a server for the actual criminal period of a crime.
Background
In legal assistance or legal appeal, when a user needs to carry out crime criminal term prediction on a certain crime name, case and criminal episode depth analysis is carried out by a judge or lawyer with abundant experience, and then the corresponding crime criminal term prediction can be given, so that the working intensity and the working pressure of the judge or lawyer are greatly increased.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides a method, a device, a storage medium and a server for predicting the actual criminal period of a crime, which can be used for carrying out case matching through relevant information input by a user, extracting the actual criminal period in the matched case for prediction and greatly improving the working efficiency of judges and lawyers.
In order to solve the above technical problem, an embodiment of the present invention provides a method for predicting the actual criminal period of a crime, where the method includes:
sequentially obtaining a crime name and a crime area input by a user based on a user terminal input interface;
automatically matching corresponding crime conditions and the list information of the influence factors influencing the sentencing in sequence based on the crime names and the crime areas;
according to the received crime condition information input by the user based on the crime condition and the influence factor information based on the influence factor list information influencing the sentencing;
searching and matching the crime names, the crime areas, the crime condition information and the influence factor information in a case database to obtain mutually matched crime cases;
and carrying out criminal period data extraction on the mutually matched criminal cases, and acquiring criminal actual prediction criminal periods based on the extracted criminal period data.
Optionally, the obtaining the crime name and the crime area sequentially based on the user terminal input interface includes:
based on the crime name list information or the input box provided by the user terminal input interface, the user selects to click the corresponding crime name field in the crime name list information for inputting or manually input a crime text field in the input box;
automatically matching the corresponding input crime name field in a crime name database to obtain a crime name; or analyzing and identifying the crime name of the manually input crime text field based on an NLP analysis model to obtain the crime name;
after the name of a crime is obtained, providing crime area list information based on a user terminal input interface, and selecting and clicking a corresponding area field in the crime area list information by a user for inputting;
and automatically matching the corresponding input area fields in the database of the crime area to obtain the crime area.
Optionally, the automatic matching of the corresponding crime conditions and the list information of the influence factors influencing the sentencing based on the crime names and the crime areas includes:
and according to the crime names and the crime areas, respectively and automatically matching in a corresponding crime condition database and an influence factor database influencing the sentry to obtain the list information of the crime conditions and the influence factors influencing the sentry.
Optionally, the crime conditions include a single-item selecting crime condition, a plurality of-item selecting crime conditions, and a text input crime condition;
the shadow of influence includes from heavy episodes, from light episodes, specific subject matter, and illicit deterrent events.
Optionally, the retrieving and matching processing in the case database according to the crime name, the crime area, the crime condition information and the influence factor information, and the obtaining of the mutually matched criminal cases includes:
extracting keyword information in the crime name, the crime area, the crime condition information and the influence factor information respectively;
and searching and matching the extracted keyword information in a case database to obtain mutually matched criminal cases.
Optionally, the extracting the keyword information in the crime name, the crime area, the crime condition information, and the influence factor information respectively includes:
and analyzing the crime name, the crime area, the crime condition information and the influence factor information respectively based on an NLP analysis model, and extracting corresponding keyword information after analysis.
Optionally, the criminal case matching with each other is subjected to criminal period data extraction, and obtaining the criminal actual prediction criminal period based on the extracted criminal period data includes:
carrying out criminal period field and criminal period field position matching treatment in the mutually matched criminal case by adopting criminal period keywords, and matching to obtain the criminal period field and criminal period field position in the mutually matched criminal case;
extracting corresponding criminal phase data based on the criminal phase fields in the matched criminal case and the positions of the criminal phase fields;
sequencing the criminal phase data and calculating the average value in sequence to obtain the maximum value, the minimum value and the average value in the criminal phase data;
and acquiring the actual criminal prediction criminal period based on the maximum value, the minimum value and the average value in the criminal period data.
Optionally, the method further includes:
and carrying out visual processing based on the actual criminal prediction penalty period of the crime, and pushing a visual processing result to a user terminal interface.
Optionally, the visually processing based on the crime actual forecast criminal period includes:
extracting the field information of the year, the month and the area in the mutually matched appraising cases;
and performing data visualization processing based on the extracted year, month and area field information and the maximum value, the minimum value and the average value in the criminal period data to obtain a case-criminal period distributed icon and a criminal period-year distributed icon.
In addition, an embodiment of the present invention further provides a device for predicting the actual criminal period of a crime, where the device includes:
the first information receiving module: the system comprises a user terminal input interface, a crime name and a crime area, wherein the crime name and the crime area are sequentially acquired by the user input interface;
a first matching module: the system comprises a crime management system, a crime management system and a crime management system, wherein the crime management system is used for automatically matching corresponding crime conditions and influence factor list information influencing criminals in sequence based on the crime names and the crime areas;
a second information receiving module: the system comprises a crime condition information acquisition unit, a crime condition information acquisition unit and an influence factor information acquisition unit, wherein the crime condition information acquisition unit is used for acquiring crime condition information input by a user based on the crime condition and influence factor information based on influence factor list information of influence quantums;
a second matching module: the criminal case database is used for retrieving and matching crime names, crime areas, crime condition information and influence factor information in the case database to obtain criminal cases matched with each other;
a prediction module: and the criminal case matching module is used for extracting criminal period data of the criminal cases matched with each other, and acquiring criminal actual prediction criminal period based on the extracted criminal period data.
In addition, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements the method for predicting the actual criminal period of a crime as described in any one of the above.
In addition, an embodiment of the present invention further provides a server, including:
one or more processors;
a memory;
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications configured to: a method of predicting the actual crime stage of a crime as described in any one of the above is carried out.
In the embodiment of the invention, the corresponding judgment cases are matched in the case database through the matching algorithm according to the corresponding conditions input by the user, the parameters of the criminal period, the year, the month, the area and the like in the judgment cases are extracted for visual processing, and the prediction result is obtained, so that the accuracy of the prediction result is greatly improved, and the working efficiency of judges and lawyers is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a crime actual criminal period prediction method in an embodiment of the invention;
fig. 2 is a schematic flow chart of a crime actual criminal period prediction method in another embodiment of the invention;
fig. 3 is a schematic view showing the constitution of a crime actual criminal period predicting apparatus in the embodiment of the present invention;
fig. 4 is a schematic view showing the constitution of a crime actual criminal period predicting apparatus according to another embodiment of the present invention;
fig. 5 is a schematic diagram of a server composition structure in the embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Examples
Referring to fig. 1, fig. 1 is a flow chart of a method for predicting the actual criminal period of a crime in an embodiment of the invention.
As shown in fig. 1, a method for predicting the actual criminal period of a crime, the method comprising:
s11: sequentially obtaining a crime name and a crime area input by a user based on a user terminal input interface;
in the specific implementation process of the present invention, the obtaining of the crime name and the crime area sequentially based on the user terminal input interface comprises: based on the crime name list information or the input box provided by the user terminal input interface, the user selects to click the corresponding crime name field in the crime name list information for inputting or manually input a crime text field in the input box; automatically matching the corresponding input crime name field in a crime name database to obtain a crime name; or analyzing and identifying the crime name of the manually input crime text field based on an NLP analysis model to obtain the crime name; after the name of a crime is obtained, providing crime area list information based on a user terminal input interface, and selecting and clicking a corresponding area field in the crime area list information by a user for inputting; and automatically matching the corresponding input area fields in the database of the crime area to obtain the crime area.
Specifically, the user terminal comprises any one of intelligent terminal devices such as a smart phone, a tablet computer and a personal computer, wherein the user terminal is applied with corresponding user application software, after the application software is opened, providing an input interface for a user terminal through application software, providing the user input or selected crime name list information on the input interface, inputting by clicking the corresponding crime name field in the crime name list information, or directly and manually inputting a corresponding crime name field, transmitting the crime name field to a server by application software on the user terminal based on an internet network communication protocol after receiving the crime name field input by the user, after receiving the field with the crime name, the server adopts the crime name field to carry out corresponding matching in a crime name database, and obtains the crime name matched with the crime name field through matching; the server feeds back and provides crime area list information to a user terminal interface after obtaining crime names matched with the crime name field for the user to select and input, the user selects and inputs the crime area field in the crime area list information, the crime area field is transmitted to the server based on an internet network communication protocol, and the server automatically matches the input crime area field in a corresponding database for storing the crime area after receiving the crime area field, so that the crime area corresponding to the crime area field input by the user is obtained accurately.
Specifically, after receiving a field with a crime name, the server adopts the field to carry out corresponding matching in a crime name database, obtains the crime name matched with the field with the crime name through matching, carries out word vector calculation and text classification tools through an NLP (Natural language Processing) algorithm, is matched with a weighting model, automatically judges which crime name the field character information input by a user belongs to at the maximum probability, and a background is used for pushing a prediction link of the crime name; NLP word vector calculation and text classification tools belong to shallow networks, are high in precision and are many orders of magnitude faster than deep networks in training time.
S12: automatically matching corresponding crime conditions and the list information of the influence factors influencing the sentencing in sequence based on the crime names and the crime areas;
in the specific implementation process of the invention, the list information of the corresponding crime conditions and the influence factors influencing the sentencing, which is automatically matched in sequence based on the crime names and the crime areas, comprises the following steps: and according to the crime names and the crime areas, respectively and automatically matching in a corresponding crime condition database and an influence factor database influencing the sentry to obtain the list information of the crime conditions and the influence factors influencing the sentry.
Further, the crime conditions comprise a single-item selecting crime condition, a plurality of-item selecting crime conditions and a text input crime condition; the shadow of influence includes from heavy episodes, from light episodes, specific subject matter, and illicit deterrent events.
Specifically, the server performs corresponding matching on the obtained crime name and the crime area in a corresponding database, such as a crime condition database and an influence factor database influencing criminal; the crime condition database stores crime condition list information of different crime names and crime areas; the influence factor database for influencing criminal expression stores different influence factors for influencing criminal expression in advance according to different crime names and crime areas, the influence factors may be inconsistent in each crime name and each crime area, and in the case judgment process, the conditions of the influence factors are considered to be different, the conditions may be different in the same crime name and different areas, the same crime conditions may be different, and the criminal period may be judged to be different.
Firstly, according to the corresponding crime name and crime area, the corresponding matching is carried out in a crime condition database, the crime condition input by the user and/or selected by the user is matched, then the automatic matching is respectively carried out in an influence factor database influencing the sentencing, and the list information of the influence factors influencing the sentencing is matched.
The influence factors include but are not limited to the secondary influence factors and/or the secondary influence factors, and each influence factor includes a plurality of field inputs, such as the secondary influence factors including criminals, presidents, intentional crimes during disasters, and culmination crimes; the factors influencing the mild conditions comprise tame, self-beginning, standing work, dirt-removing and claim-removing, guilty in the court, and the like; specific subject situations are divided into reduction of criminal phase and direct negation of crime on a case-by-case basis.
S13: according to the received crime condition information input by the user based on the crime condition and the influence factor information based on the influence factor list information influencing the sentencing;
in the specific implementation process of the invention, firstly, a user can select input or manually input a corresponding crime condition field on a user terminal interface according to a crime condition; then the user selects to input or manually input the corresponding influence factor on the user terminal interface according to the influence factor information of the list information of the influence factors influencing the sentencing.
S14: searching and matching the crime names, the crime areas, the crime condition information and the influence factor information in a case database to obtain mutually matched crime cases;
in the specific implementation process of the invention, the retrieving and matching processing in the case database according to the crime name, the crime area, the crime condition information and the influence factor information, and the obtaining of the mutually matched criminal case comprises the following steps: extracting keyword information in the crime name, the crime area, the crime condition information and the influence factor information respectively; and searching and matching the extracted keyword information in a case database to obtain mutually matched criminal cases.
Further, the extracting the keyword information in the crime name, the crime area, the crime condition information, and the influence factor information respectively includes: and analyzing the crime name, the crime area, the crime condition information and the influence factor information respectively based on an NLP analysis model, and extracting corresponding keyword information after analysis.
Specifically, after receiving crime names, crime areas, crime condition information and influence factor information, the server constructs feature vectors by using the information, and combines a bag of words (BOF) model in the natural language processing field with N-Gram features, so that words can be accurately segmented and the sequence after the words are segmented can be adjusted. The bag of words model (BOF) is a standard target classification framework consisting of 4 parts of feature extraction, feature clustering, feature coding, feature aggregation and classifier classification. The N-Gram feature is an algorithm based on a statistical language model, is also called a first-order Markov chain, and is a byte fragment sequence with the length of N formed by performing sliding window operation on the content in the text with the size of N according to bytes. Each byte segment is called as a gram, the occurrence frequency of all the grams is counted, and filtering is carried out according to a preset threshold value to form a key gram list, namely a vector feature space of the text; each gram in the list is a feature vector dimension; firstly, roughly dividing the input information into speech segment sequences; then carrying out Bi-gram cutting treatment; and finally, filtering to obtain a feature vector list.
The NLP analysis model structure adopts an input, mapping (hiding) and output structure, wherein X (1) to X (n) represent a feature vector of each word in a text, paragraphs can be represented by mean values of all words after embedding and accumulation, and finally, a label of an output layer is obtained through one time of nonlinear transformation from a hidden layer. The model inputs a sequence of words (a piece of text or a sentence) and outputs the probability that the sequence of words belongs to different categories. The hidden layers are summed and averaged by the input layers and multiplied by a weighting matrix a. The output layer is obtained by multiplying the hidden layer by the weight matrix B. In order to improve the operation time and the running time, the model uses a hierarchical Softmax skill, is built on the basis of Huffman coding, codes tags and can greatly reduce the number of model prediction targets.
Specifically, the output layer is a formula of multiplying the hidden layer by the weight matrix B as follows:
wherein, ynDenotes true label, xnRepresenting a feature vector list (N-Gram features after document N normalization), wherein A and B respectively represent weight matrixes; n is 1,2,3, …, N is a positive integer.
The feature vector is constructed and then input into an NLP analysis model for analysis, and fields with weights larger than a preset threshold value are extracted from results output in the NLP analysis model to serve as keyword information.
S15: and carrying out criminal period data extraction on the mutually matched criminal cases, and acquiring criminal actual prediction criminal periods based on the extracted criminal period data.
In the specific implementation process of the invention, the criminal period data extraction is performed on the mutually matched criminal cases, and the obtaining of the criminal actual prediction criminal period based on the extracted criminal period data comprises the following steps: carrying out criminal period field and criminal period field position matching treatment in the mutually matched criminal case by adopting criminal period keywords, and matching to obtain the criminal period field and criminal period field position in the mutually matched criminal case; matching criminal cases; sequencing the criminal phase data and calculating the average value in sequence to obtain the maximum value, the minimum value and the average value in the criminal phase data; and acquiring the actual criminal prediction criminal period based on the maximum value, the minimum value and the average value in the criminal period data.
Specifically, NLP analysis algorithm is adopted to analyze and process matched criminal case, so that criminal period fields and positions of the criminal period fields in the criminal case are obtained; then extracting the number of the corresponding criminal period data on the field through a number extraction algorithm; the criminal data of all the criminal cases are subjected to statistical sequencing, the criminal data can be sequenced from large to small, and also can be sequenced from small to large, and the criminal data needs to be converted into a unified format, a unified unit format, a year or a month; then accumulating all the criminal phase data to obtain an average value of the criminal phase data; and acquiring the actual crime prediction criminal period according to the maximum value and the minimum value in the sequencing result and the calculated average value.
In the embodiment of the invention, the corresponding judgment cases are matched in the case database through the matching algorithm according to the corresponding conditions input by the user, the parameters of the criminal period, the year, the month, the area and the like in the judgment cases are extracted for visual processing, and the prediction result is obtained, so that the accuracy of the prediction result is greatly improved, and the working efficiency of judges and lawyers is improved.
Examples
Referring to fig. 2, fig. 2 is a flow chart of a method for predicting the actual criminal period of a crime in another embodiment of the present invention.
As shown in fig. 2, a method for predicting the actual criminal period of a crime, the method comprising:
s21: sequentially obtaining a crime name and a crime area input by a user based on a user terminal input interface;
s22: automatically matching corresponding crime conditions and the list information of the influence factors influencing the sentencing in sequence based on the crime names and the crime areas;
s23: according to the received crime condition information input by the user based on the crime condition and the influence factor information based on the influence factor list information influencing the sentencing;
s24: searching and matching the crime names, the crime areas, the crime condition information and the influence factor information in a case database to obtain mutually matched crime cases;
s25: carrying out criminal period data extraction on the mutually matched criminal cases, and acquiring criminal actual prediction criminal periods based on the extracted criminal period data;
in the specific implementation process of the present invention, the implementation manners in steps S21-S25 may specifically refer to the above embodiments, and are not described herein again.
S26: and carrying out visual processing based on the actual criminal prediction penalty period of the crime, and pushing a visual processing result to a user terminal interface.
In a specific implementation process of the present invention, the visually processing based on the crime actual forecast criminal term includes: extracting the field information of the year, the month and the area in the mutually matched appraising cases; and performing data visualization processing based on the extracted year, month and area field information and the maximum value, the minimum value and the average value in the criminal period data to obtain a case-criminal period distributed icon and a criminal period-year distributed icon.
Specifically, the information of the year, month and area fields in the mutually matched criminal cases is obtained in the analysis process through the NLP analysis model in the steps; then extracting corresponding data from the field information of the year, month and area of the corresponding criminal case; after extracting corresponding year, month and area field information, adding the maximum value, the minimum value and the average value in the criminal period data to perform data visualization processing; the visualization processing is processed through a visualization processing algorithm set on the server, and after the processing, visualization icons such as case-criminal period distributed icons and criminal period-year distributed icons can be obtained and transmitted to a user terminal interface based on an internet transmission protocol to be viewed by a user.
In the embodiment of the invention, the corresponding judgment cases are matched in the case database through the matching algorithm according to the corresponding conditions input by the user, the parameters of the criminal period, the year, the month, the area and the like in the judgment cases are extracted for visual processing, and the prediction result is obtained, so that the accuracy of the prediction result is greatly improved, and the working efficiency of judges and lawyers is improved.
Examples
Referring to fig. 3, fig. 3 is a schematic structural diagram of a device for predicting the actual criminal period of a crime in an embodiment of the present invention.
As shown in fig. 3, a prediction apparatus for the actual criminal period of a crime, the apparatus comprising:
the first information receiving module 11: the system comprises a user terminal input interface, a crime name and a crime area, wherein the crime name and the crime area are sequentially acquired by the user input interface;
in the specific implementation process of the present invention, the obtaining of the crime name and the crime area sequentially based on the user terminal input interface comprises: based on the crime name list information or the input box provided by the user terminal input interface, the user selects to click the corresponding crime name field in the crime name list information for inputting or manually input a crime text field in the input box; automatically matching the corresponding input crime name field in a crime name database to obtain a crime name; or analyzing and identifying the crime name of the manually input crime text field based on an NLP analysis model to obtain the crime name; after the name of a crime is obtained, providing crime area list information based on a user terminal input interface, and selecting and clicking a corresponding area field in the crime area list information by a user for inputting; and automatically matching the corresponding input area fields in the database of the crime area to obtain the crime area.
Specifically, the user terminal comprises any one of intelligent terminal devices such as a smart phone, a tablet computer and a personal computer, wherein the user terminal is applied with corresponding user application software, after the application software is opened, providing an input interface for a user terminal through application software, providing the user input or selected crime name list information on the input interface, inputting by clicking the corresponding crime name field in the crime name list information, or directly and manually inputting a corresponding crime name field, transmitting the crime name field to a server by application software on the user terminal based on an internet network communication protocol after receiving the crime name field input by the user, after receiving the field with the crime name, the server adopts the crime name field to carry out corresponding matching in a crime name database, and obtains the crime name matched with the crime name field through matching; the server feeds back and provides crime area list information to a user terminal interface after obtaining crime names matched with the crime name field for the user to select and input, the user selects and inputs the crime area field in the crime area list information, the crime area field is transmitted to the server based on an internet network communication protocol, and the server automatically matches the input crime area field in a corresponding database for storing the crime area after receiving the crime area field, so that the crime area corresponding to the crime area field input by the user is obtained accurately.
Specifically, after receiving a field with a crime name, the server adopts the field to carry out corresponding matching in a crime name database, obtains the crime name matched with the field with the crime name through matching, carries out word vector calculation and text classification tools through an NLP (Natural language Processing) algorithm, is matched with a weighting model, automatically judges which crime name the field character information input by a user belongs to at the maximum probability, and a background is used for pushing a prediction link of the crime name; NLP word vector calculation and text classification tools belong to shallow networks, are high in precision and are many orders of magnitude faster than deep networks in training time.
The first matching module 12: the system comprises a crime management system, a crime management system and a crime management system, wherein the crime management system is used for automatically matching corresponding crime conditions and influence factor list information influencing criminals in sequence based on the crime names and the crime areas;
in the specific implementation process of the invention, the list information of the corresponding crime conditions and the influence factors influencing the sentencing, which is automatically matched in sequence based on the crime names and the crime areas, comprises the following steps: and according to the crime names and the crime areas, respectively and automatically matching in a corresponding crime condition database and an influence factor database influencing the sentry to obtain the list information of the crime conditions and the influence factors influencing the sentry.
Further, the crime conditions comprise a single-item selecting crime condition, a plurality of-item selecting crime conditions and a text input crime condition; the shadow of influence includes from heavy episodes, from light episodes, specific subject matter, and illicit deterrent events.
Specifically, the server performs corresponding matching on the obtained crime name and the crime area in a corresponding database, such as a crime condition database and an influence factor database influencing criminal; the crime condition database stores crime condition list information of different crime names and crime areas; the influence factor database for influencing criminal expression stores different influence factors for influencing criminal expression in advance according to different crime names and crime areas, the influence factors may be inconsistent in each crime name and each crime area, and in the case judgment process, the conditions of the influence factors are considered to be different, the conditions may be different in the same crime name and different areas, the same crime conditions may be different, and the criminal period may be judged to be different.
Firstly, according to the corresponding crime name and crime area, the corresponding matching is carried out in a crime condition database, the crime condition input by the user and/or selected by the user is matched, then the automatic matching is respectively carried out in an influence factor database influencing the sentencing, and the list information of the influence factors influencing the sentencing is matched.
The influence factors include but are not limited to the secondary influence factors and/or the secondary influence factors, and each influence factor includes a plurality of field inputs, such as the secondary influence factors including criminals, presidents, intentional crimes during disasters, and culmination crimes; the factors influencing the mild conditions comprise tame, self-beginning, standing work, dirt-removing and claim-removing, guilty in the court, and the like; specific subject situations are divided into reduction of criminal phase and direct negation of crime on a case-by-case basis.
The second information receiving module 13: the system comprises a crime condition information acquisition unit, a crime condition information acquisition unit and an influence factor information acquisition unit, wherein the crime condition information acquisition unit is used for acquiring crime condition information input by a user based on the crime condition and influence factor information based on influence factor list information of influence quantums;
in the specific implementation process of the invention, firstly, a user can select input or manually input a corresponding crime condition field on a user terminal interface according to a crime condition; then the user selects to input or manually input the corresponding influence factor on the user terminal interface according to the influence factor information of the list information of the influence factors influencing the sentencing.
The second matching module 14: the criminal case database is used for retrieving and matching crime names, crime areas, crime condition information and influence factor information in the case database to obtain criminal cases matched with each other;
in the specific implementation process of the invention, the retrieving and matching processing in the case database according to the crime name, the crime area, the crime condition information and the influence factor information, and the obtaining of the mutually matched criminal case comprises the following steps: extracting keyword information in the crime name, the crime area, the crime condition information and the influence factor information respectively; and searching and matching the extracted keyword information in a case database to obtain mutually matched criminal cases.
Further, the extracting the keyword information in the crime name, the crime area, the crime condition information, and the influence factor information respectively includes: and analyzing the crime name, the crime area, the crime condition information and the influence factor information respectively based on an NLP analysis model, and extracting corresponding keyword information after analysis.
Specifically, after receiving crime names, crime areas, crime condition information and influence factor information, the server constructs feature vectors by using the information, and combines a bag of words (BOF) model in the natural language processing field with N-Gram features, so that words can be accurately segmented and the sequence after the words are segmented can be adjusted. The bag of words model (BOF) is a standard target classification framework consisting of 4 parts of feature extraction, feature clustering, feature coding, feature aggregation and classifier classification. The N-Gram feature is an algorithm based on a statistical language model, is also called a first-order Markov chain, and is a byte fragment sequence with the length of N formed by performing sliding window operation on the content in the text with the size of N according to bytes. Each byte segment is called as a gram, the occurrence frequency of all the grams is counted, and filtering is carried out according to a preset threshold value to form a key gram list, namely a vector feature space of the text; each gram in the list is a feature vector dimension; firstly, roughly dividing the input information into speech segment sequences; then carrying out Bi-gram cutting treatment; and finally, filtering to obtain a feature vector list.
The NLP analysis model structure adopts an input, mapping (hiding) and output structure, wherein X (1) to X (n) represent a feature vector of each word in a text, paragraphs can be represented by mean values of all words after embedding and accumulation, and finally, a label of an output layer is obtained through one time of nonlinear transformation from a hidden layer. The model inputs a sequence of words (a piece of text or a sentence) and outputs the probability that the sequence of words belongs to different categories. The hidden layers are summed and averaged by the input layers and multiplied by a weighting matrix a. The output layer is obtained by multiplying the hidden layer by the weight matrix B. In order to improve the operation time and the running time, the model uses a hierarchical Softmax skill, is built on the basis of Huffman coding, codes tags and can greatly reduce the number of model prediction targets.
Specifically, the output layer is a formula of multiplying the hidden layer by the weight matrix B as follows:
wherein, ynDenotes true label, xnRepresenting a feature vector list (N-Gram features after document N normalization), wherein A and B respectively represent weight matrixes; n is 1,2,3, …, N is a positive integer.
The feature vector is constructed and then input into an NLP analysis model for analysis, and fields with weights larger than a preset threshold value are extracted from results output in the NLP analysis model to serve as keyword information.
The prediction module 15: and the criminal case matching module is used for extracting criminal period data of the criminal cases matched with each other, and acquiring criminal actual prediction criminal period based on the extracted criminal period data.
In the specific implementation process of the invention, the criminal period data extraction is performed on the mutually matched criminal cases, and the obtaining of the criminal actual prediction criminal period based on the extracted criminal period data comprises the following steps: carrying out criminal period field and criminal period field position matching treatment in the mutually matched criminal case by adopting criminal period keywords, and matching to obtain the criminal period field and criminal period field position in the mutually matched criminal case; matching criminal cases; sequencing the criminal phase data and calculating the average value in sequence to obtain the maximum value, the minimum value and the average value in the criminal phase data; and acquiring the actual criminal prediction criminal period based on the maximum value, the minimum value and the average value in the criminal period data.
Specifically, NLP analysis algorithm is adopted to analyze and process matched criminal case, so that criminal period fields and positions of the criminal period fields in the criminal case are obtained; then extracting the number of the corresponding criminal period data on the field through a number extraction algorithm; the criminal data of all the criminal cases are subjected to statistical sequencing, the criminal data can be sequenced from large to small, and also can be sequenced from small to large, and the criminal data needs to be converted into a unified format, a unified unit format, a year or a month; then accumulating all the criminal phase data to obtain an average value of the criminal phase data; and acquiring the actual crime prediction criminal period according to the maximum value and the minimum value in the sequencing result and the calculated average value.
In the embodiment of the invention, the corresponding judgment cases are matched in the case database through the matching algorithm according to the corresponding conditions input by the user, the parameters of the criminal period, the year, the month, the area and the like in the judgment cases are extracted for visual processing, and the prediction result is obtained, so that the accuracy of the prediction result is greatly improved, and the working efficiency of judges and lawyers is improved.
Examples
Referring to fig. 4, fig. 4 is a schematic structural diagram of a device for predicting the actual criminal period of a crime in another embodiment of the present invention.
As shown in fig. 4, a prediction apparatus for the actual criminal period of a crime, the apparatus comprising:
the first information receiving module 21: the system comprises a user terminal input interface, a crime name and a crime area, wherein the crime name and the crime area are sequentially acquired by the user input interface;
the first matching module 22: the system comprises a crime management system, a crime management system and a crime management system, wherein the crime management system is used for automatically matching corresponding crime conditions and influence factor list information influencing criminals in sequence based on the crime names and the crime areas;
the second information receiving module 23: the system comprises a crime condition information acquisition unit, a crime condition information acquisition unit and an influence factor information acquisition unit, wherein the crime condition information acquisition unit is used for acquiring crime condition information input by a user based on the crime condition and influence factor information based on influence factor list information of influence quantums;
the second matching module 24: the criminal case database is used for retrieving and matching crime names, crime areas, crime condition information and influence factor information in the case database to obtain criminal cases matched with each other;
the prediction module 25: the criminal case matching system is used for extracting criminal data of the criminal cases matched with each other and acquiring criminal actual prediction criminal period based on the extracted criminal data;
in the specific implementation process of the present invention, please refer to the above embodiments for the specific implementation of the first information receiving module 21, the first matching module 22, the second information receiving module 23, the second matching module 24, and the predicting module 25, which will not be described herein again.
A pushing module: and the system is used for carrying out visualization processing based on the crime actual forecasting criminal term and pushing a visualization processing result to a user terminal interface.
In a specific implementation process of the present invention, the visually processing based on the crime actual forecast criminal term includes: extracting the field information of the year, the month and the area in the mutually matched appraising cases; and performing data visualization processing based on the extracted year, month and area field information and the maximum value, the minimum value and the average value in the criminal period data to obtain a case-criminal period distributed icon and a criminal period-year distributed icon.
Specifically, the information of the year, month and area fields in the mutually matched criminal cases is obtained in the analysis process through the NLP analysis model in the steps; then extracting corresponding data from the field information of the year, month and area of the corresponding criminal case; after extracting corresponding year, month and area field information, adding the maximum value, the minimum value and the average value in the criminal period data to perform data visualization processing; the visualization processing is processed through a visualization processing algorithm set on the server, and after the processing, visualization icons such as case-criminal period distributed icons and criminal period-year distributed icons can be obtained and transmitted to a user terminal interface based on an internet transmission protocol to be viewed by a user.
In the embodiment of the invention, the corresponding judgment cases are matched in the case database through the matching algorithm according to the corresponding conditions input by the user, the parameters of the criminal period, the year, the month, the area and the like in the judgment cases are extracted for visual processing, and the prediction result is obtained, so that the accuracy of the prediction result is greatly improved, and the working efficiency of judges and lawyers is improved.
Examples
An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method for predicting the actual criminal period of a crime according to any one of the technical solutions. The computer-readable storage medium includes, but is not limited to, any type of disk including floppy disks, hard disks, optical disks, CD-ROMs, and magneto-optical disks, ROMs (Read-Only memories), RAMs (Random AcceSS memories), EPROMs (EraSable Programmable Read-Only memories), EEPROMs (Electrically EraSable Programmable Read-Only memories), flash memories, magnetic cards, or optical cards. That is, a storage device includes any medium that stores or transmits a message in a form readable by a device (e.g., a computer, a cell phone), and may be a read-only memory, a magnetic or optical disk, or the like.
Referring to fig. 5, fig. 5 is a schematic diagram of a server structure according to an embodiment of the present invention.
As shown in fig. 5, the server includes a processor 502, a memory 503, an input unit 504, and a display unit 505. The structural elements shown in fig. 5 do not constitute a limitation of all servers and may have more or fewer components than those shown in fig. 5, or some of the components may be combined.
The memory 503 may be used to store the application 501 and various functional modules, and the processor 502 executes the application 501 stored in the memory 503, thereby performing various functional applications of the device and data processing. The memory may be internal or external memory, or include both internal and external memory. The internal memory may include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), flash memory, or random access memory. The external memory may include a hard disk, a floppy disk, a ZIP disk, a usb-disk, a magnetic tape, etc. The disclosed memory includes, but is not limited to, these types of memory. The disclosed memory is by way of example only and not by way of limitation.
The input unit 504 is used for receiving input of signals and receiving keywords input by a user. The input unit 504 may include a touch panel and other input devices. The touch panel can collect touch operations of a user on or near the touch panel (for example, operations of the user on or near the touch panel by using any suitable object or accessory such as a finger, a stylus and the like) and drive the corresponding connecting device according to a preset program; other input devices may include, but are not limited to, one or more of a physical keyboard, function keys (e.g., play control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like. The display unit 505 may be used to display information input by a user or information provided to the user and various menus of the terminal device. The display unit 505 may take the form of a liquid crystal display, an organic light emitting diode, or the like. The processor 502 is a control center of the terminal device, connects various parts of the entire device using various interfaces and lines, and performs various functions and processes data by operating or executing software programs and/or modules stored in the memory 502 and calling data stored in the memory.
As one embodiment, the server includes: one or more processors 502, a memory 503, one or more applications 501, wherein said one or more applications 501 are stored in the memory 503 and configured to be executed by said one or more processors 502, said one or more applications 501 being configured to perform the method of predicting the actual criminal period of a crime in the above described embodiment.
The server provided by the embodiment of the present invention can implement the embodiment of the method for predicting the actual crime stage provided by the embodiment of the present invention, and for the specific implementation of the functions, please refer to the description in the embodiment of the method, which is not described herein again.
In the embodiment of the invention, the corresponding judgment cases are matched in the case database through the matching algorithm according to the corresponding conditions input by the user, the parameters of the criminal period, the year, the month, the area and the like in the judgment cases are extracted for visual processing, and the prediction result is obtained, so that the accuracy of the prediction result is greatly improved, and the working efficiency of judges and lawyers is improved.
In addition, the method, the apparatus, the storage medium and the server for predicting the actual criminal period of a crime provided by the embodiment of the present invention are described in detail, and a specific example is used herein to explain the principle and the implementation of the present invention, and the description of the above embodiment is only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (11)
1. A method of predicting the actual criminal period of a crime, said method comprising:
sequentially obtaining a crime name and a crime area input by a user based on a user terminal input interface;
automatically matching corresponding crime conditions and the list information of the influence factors influencing the sentencing in sequence based on the crime names and the crime areas;
according to the received crime condition information input by the user based on the crime condition and the influence factor information input based on the influence factor list information of the influence bureaus;
searching and matching the crime names, the crime areas, the crime condition information and the influence factor information in a case database to obtain mutually matched crime cases;
carrying out criminal period data extraction on the mutually matched criminal cases, and acquiring criminal actual prediction criminal periods based on the extracted criminal period data;
the criminal period data extraction is carried out on the mutually matched criminal cases, and obtaining the criminal actual prediction criminal period based on the extracted criminal period data comprises the following steps:
carrying out criminal period field and criminal period field position matching treatment in the mutually matched criminal case by adopting criminal period keywords, and matching to obtain the criminal period field and criminal period field position in the mutually matched criminal case;
extracting corresponding criminal phase data based on the criminal phase fields in the matched criminal case and the positions of the criminal phase fields;
sequencing the criminal phase data and calculating the average value in sequence to obtain the maximum value, the minimum value and the average value in the criminal phase data;
and acquiring the actual criminal prediction criminal period based on the maximum value, the minimum value and the average value in the criminal period data.
2. The prediction method of claim 1, wherein the sequentially obtaining the crime name and the crime area input by the user based on the user terminal input interface comprises:
based on the crime name list information or the input box provided by the user terminal input interface, the user selects to click the corresponding crime name field in the crime name list information for inputting or manually input a crime text field in the input box;
automatically matching the corresponding input crime name field in a crime name database to obtain a crime name; or analyzing and identifying the crime name of the manually input crime text field based on an NLP analysis model to obtain the crime name;
after the name of a crime is obtained, providing crime area list information based on a user terminal input interface, and selecting and clicking a corresponding area field in the crime area list information by a user for inputting;
and automatically matching the corresponding input area fields in the database of the crime area to obtain the crime area.
3. The prediction method according to claim 1, wherein said automatically matching in sequence the corresponding crime conditions and the list information of the influence factors affecting the sentencing based on the crime name and the crime area comprises:
and according to the crime names and the crime areas, respectively and automatically matching in a corresponding crime condition database and an influence factor database influencing the sentry to obtain the list information of the crime conditions and the influence factors influencing the sentry.
4. The prediction method of claim 3, wherein the conviction condition comprises a single-item-selection conviction condition, a multiple-item-selection conviction condition, a text-input conviction condition;
the impact factors include from heavy episodes, from light episodes, specific subject situations, and illicit deterrent events.
5. The forecasting method according to claim 1, wherein the retrieving and matching processing in a case database according to the crime name, the crime area, the crime condition information and the influence factor information to obtain mutually matched crime cases comprises:
extracting keyword information in the crime name, the crime area, the crime condition information and the influence factor information respectively;
and searching and matching the extracted keyword information in a case database to obtain mutually matched criminal cases.
6. The prediction method according to claim 5, wherein the extracting keyword information from the crime name, the crime area, the crime condition information, and the influence factor information, respectively, comprises:
and analyzing the crime name, the crime area, the crime condition information and the influence factor information respectively based on an NLP analysis model, and extracting corresponding keyword information after analysis.
7. The prediction method according to claim 1, characterized in that the method further comprises:
and carrying out visual processing based on the actual criminal prediction penalty period of the crime, and pushing a visual processing result to a user terminal interface.
8. The prediction method according to claim 7, wherein said visually processing based on said crime actual prediction criminal term comprises:
extracting the field information of the year, the month and the area in the mutually matched appraising cases;
and performing data visualization processing based on the extracted year, month and area field information and the maximum value, the minimum value and the average value in the criminal period data to obtain a case-criminal period distributed icon and a criminal period-year distributed icon.
9. A device for predicting the actual criminal phase of a crime, said device comprising:
the first information receiving module: the system comprises a user terminal input interface, a crime name and a crime area, wherein the crime name and the crime area are sequentially acquired by the user input interface;
a first matching module: the system comprises a crime management system, a crime management system and a crime management system, wherein the crime management system is used for automatically matching corresponding crime conditions and influence factor list information influencing criminals in sequence based on the crime names and the crime areas;
a second information receiving module: the system comprises a crime condition information acquisition unit, a crime condition information acquisition unit and an influence factor information acquisition unit, wherein the crime condition information acquisition unit is used for acquiring crime condition information input by a user based on the crime condition and influence factor information input based on the influence factor list information of influence quantums;
a second matching module: the criminal case database is used for retrieving and matching crime names, crime areas, crime condition information and influence factor information in the case database to obtain criminal cases matched with each other;
a prediction module: the criminal case matching system is used for extracting criminal data of the criminal cases matched with each other and acquiring criminal actual prediction criminal period based on the extracted criminal data;
the prediction module: the system is also used for matching and processing the positions of the criminal field and the criminal field in the mutually matched criminal cases by using criminal keywords, and matching and obtaining the positions of the criminal field and the criminal field in the mutually matched criminal cases; extracting corresponding criminal phase data based on the criminal phase fields in the matched criminal case and the positions of the criminal phase fields; sequencing the criminal phase data and calculating the average value in sequence to obtain the maximum value, the minimum value and the average value in the criminal phase data; and acquiring the actual criminal prediction criminal period based on the maximum value, the minimum value and the average value in the criminal period data.
10. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out a method of predicting the actual criminal period of a crime according to any one of the claims 1 to 8.
11. A server, characterized in that it comprises:
one or more processors;
a memory;
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications configured to: -performing a method of predicting the actual crime stage according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811546756.0A CN109472424B (en) | 2018-12-18 | 2018-12-18 | Method and device for predicting actual criminal period of crime, storage medium and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811546756.0A CN109472424B (en) | 2018-12-18 | 2018-12-18 | Method and device for predicting actual criminal period of crime, storage medium and server |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109472424A CN109472424A (en) | 2019-03-15 |
| CN109472424B true CN109472424B (en) | 2020-06-02 |
Family
ID=65676329
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811546756.0A Active CN109472424B (en) | 2018-12-18 | 2018-12-18 | Method and device for predicting actual criminal period of crime, storage medium and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109472424B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110751316A (en) * | 2019-09-26 | 2020-02-04 | 平安科技（深圳）有限公司 | Method and device for predicting resolution result and terminal equipment |
| CN112749826B (en) * | 2019-10-31 | 2024-09-24 | 北京国双科技有限公司 | Criminal period prediction method, criminal period prediction device, storage medium and criminal period prediction equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101872439A (en) * | 2010-01-29 | 2010-10-27 | 秦野 | Common criminal law sentencing method and system for hundred accusations |
| CN107578355A (en) * | 2017-09-08 | 2018-01-12 | 北京博雅英杰科技股份有限公司 | A kind of measurement of penalty method and apparatus |
| CN107918921A (en) * | 2017-11-21 | 2018-04-17 | 南京擎盾信息科技有限公司 | Criminal case court verdict measure and system |
| CN108009284A (en) * | 2017-12-22 | 2018-05-08 | 重庆邮电大学 | Using the Law Text sorting technique of semi-supervised convolutional neural networks |
-
2018
- 2018-12-18 CN CN201811546756.0A patent/CN109472424B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101872439A (en) * | 2010-01-29 | 2010-10-27 | 秦野 | Common criminal law sentencing method and system for hundred accusations |
| CN107578355A (en) * | 2017-09-08 | 2018-01-12 | 北京博雅英杰科技股份有限公司 | A kind of measurement of penalty method and apparatus |
| CN107918921A (en) * | 2017-11-21 | 2018-04-17 | 南京擎盾信息科技有限公司 | Criminal case court verdict measure and system |
| CN108009284A (en) * | 2017-12-22 | 2018-05-08 | 重庆邮电大学 | Using the Law Text sorting technique of semi-supervised convolutional neural networks |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109472424A (en) | 2019-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111274365B (en) | Intelligent inquiry method and device based on semantic understanding, storage medium and server | |
| CN111385602B (en) | Video auditing method, medium and computer equipment based on multi-level and multi-model | |
| CN110175221B (en) | Junk short message identification method by combining word vector with machine learning | |
| CN107507028A (en) | User preference determines method, apparatus, equipment and storage medium | |
| CN111339249B (en) | Deep intelligent text matching method and device combining multi-angle features | |
| CN109472424B (en) | Method and device for predicting actual criminal period of crime, storage medium and server | |
| CN111061837A (en) | Topic identification method, device, equipment and medium | |
| Estevez-Velarde et al. | AutoML strategy based on grammatical evolution: A case study about knowledge discovery from text | |
| CN110222192A (en) | Corpus method for building up and device | |
| CN116049419A (en) | Threat information extraction method and system integrating multiple models | |
| Aghimien et al. | A review of the application of data mining for sustainable construction in Nigeria | |
| CN109376230B (en) | Crime prediction method, crime prediction system, storage medium, and server | |
| CN116467461A (en) | Data processing method, device, equipment and medium applied to power distribution network | |
| CN115827872A (en) | Training method of intention recognition model, and intention recognition method and device | |
| CN113569118A (en) | Self-media pushing method and device, computer equipment and storage medium | |
| CN116703682B (en) | Government affair data platform based on deep learning | |
| CN109815309A (en) | A kind of user information recommended method and system based on personalization | |
| using Relevance | A Meta-heuristic optimization approach for content based image retrieval using relevance feedback method | |
| CN111368168A (en) | Big data-based electricity price obtaining and predicting method, system and computer-readable storage medium | |
| CN117081941A (en) | Flow prediction method and device based on attention mechanism and electronic equipment | |
| CN113901801B (en) | Text content safety detection method based on deep learning | |
| CN112052336B (en) | Traffic emergency identification method and system based on social network platform information | |
| CN114691918A (en) | Radar image retrieval method and device based on artificial intelligence and electronic equipment | |
| KR102041915B1 (en) | Database module using artificial intelligence, economic data providing system and method using the same | |
| Chandu et al. | Improved Prediction Accuracy of House Price Using Decision Tree Algorithm over Linear Regression Algorithm |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200407 Address after: 510000 No.55 Zhongshan Avenue, Guangzhou, Guangdong Province Applicant after: SOUTH CHINA NORMAL University Applicant after: GUANGDONG BOWEI CHUANGYUAN TECHNOLOGY Co.,Ltd. Address before: 528315 Room 302, 5 Blocks, Poly Business Center, No. 8 Wenhua South Road, Dongping New Town, Lecong Town, Shunde District, Foshan City, Guangdong Province Applicant before: GUANGDONG BOWEI CHUANGYUAN TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |