CN112579732A - Sentencing prediction method and device - Google Patents
Sentencing prediction method and device Download PDFInfo
- Publication number
- CN112579732A CN112579732A CN201910941266.9A CN201910941266A CN112579732A CN 112579732 A CN112579732 A CN 112579732A CN 201910941266 A CN201910941266 A CN 201910941266A CN 112579732 A CN112579732 A CN 112579732A
- Authority
- CN
- China
- Prior art keywords
- criminal
- subject
- crime
- portrait
- dimensions
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 239000013598 vector Substances 0.000 claims description 25
- 238000012216 screening Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 19
- 238000011840 criminal investigation Methods 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 13
- 238000004590 computer program Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 239000002245 particle Substances 0.000 description 4
- 239000003795 chemical substances by application Substances 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012552 review Methods 0.000 description 2
- 206010011878 Deafness Diseases 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000013604 expression vector Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000010813 municipal solid waste Substances 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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
-
- 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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services; Handling legal documents
Abstract
According to the criminal prediction method and device, after the crime information of a criminal body is obtained, the server can generate the criminal body image of the criminal body according to the crime information, determine a similar criminal body similar to the criminal body, and determine the criminal result of the similar criminal body as the reference criminal result of the criminal body. Furthermore, a judge or law enforcement officer can refer to the criminal investigation result of the criminal subject to determine the criminal period, so that the judging result determining process is time-saving and labor-saving.
Description
Technical Field
The invention relates to the field of criminal subject criminal investigation, in particular to a criminal investigation prediction method and a criminal investigation prediction device.
Background
The sentencing refers to the result of a criminal penalty amount. And determining whether to judge the penalty and judge the judicial activities of the criminal law result on the basis of the crime of the criminal suspect or the defendant being identified as a crime. Mainly comprises the steps of judging the name of a criminal, criminal species and criminal period.
The criminal determination process is time-consuming and labor-consuming, and if the criminal results of the past cases can be referred, the criminal result determination method plays a great role.
Disclosure of Invention
In view of the above, the present invention provides a sentencing prediction method and apparatus that overcomes, or at least partially solves, the above problems.
A sentencing prediction method, comprising:
obtaining crime information for describing a criminal subject;
generating a criminal subject image of the criminal subject according to the criminal information;
determining a similar criminal subject similar to the criminal subject based on the criminal subject representation;
and determining the criminal result of the similar criminal subject as a reference criminal result of the criminal subject.
Optionally, generating a criminal subject representation of the criminal subject according to the criminal information includes:
obtaining a criminal subject portrait model; the criminal subject portrait model comprises all dimension information of preset criminal dimensions; the number of the preset crime dimensions is multiple;
acquiring actual dimension information under the preset crime dimension from the crime information, and determining an actual association relation between different preset crime dimensions;
and taking the actual dimension information under the preset crime dimensions and the actual association relationship between different preset crime dimensions as the crime subject portrait.
Optionally, determining an actual association relationship between different preset crime dimensions includes:
using actual dimension information under the preset crime dimension as a knowledge element group;
and determining knowledge representation vectors among different knowledge tuples, and taking the knowledge representation vectors as actual association relations among different preset crime dimensions.
Optionally, determining a similar criminal subject similar to the criminal subject based on the criminal subject representation comprises:
acquiring a historical crime subject portrait of a historical crime subject; the historical criminal subject portrait comprises historical dimension information under different preset criminal dimensions and historical association relations among the different preset criminal dimensions;
and screening out the historical criminal subject portrait which is completely the same as the criminal subject portrait from the historical criminal subject portrait, and taking the criminal subject corresponding to the screened historical criminal subject portrait as a similar criminal subject.
A crime prediction device comprising:
the information acquisition module is used for acquiring crime information for describing a crime subject;
the portrait generation module is used for generating a criminal subject portrait of the criminal subject according to the criminal information;
a subject determination module to determine a similar criminal subject similar to the criminal subject based on the criminal subject representation;
a result determination module for determining the crime result of the similar criminal subject as a reference crime result of the criminal subject.
Optionally, the representation generation module includes: the model acquisition submodule is used for acquiring a criminal subject portrait model; the criminal subject portrait model comprises all dimension information of preset criminal dimensions; the number of the preset crime dimensions is multiple;
the data determination submodule is used for acquiring actual dimension information under the preset crime dimension from the crime information and determining an actual incidence relation between different preset crime dimensions;
and the portrait generation submodule is used for taking the actual dimension information under the preset crime dimensions and the actual association relationship between different preset crime dimensions as the portrait of the crime main body.
Optionally, when the data determination submodule is configured to determine an actual association relationship between different preset crime dimensions, the data determination submodule is specifically configured to:
and taking the actual dimension information under the preset crime dimension as a knowledge element group, determining knowledge representation vectors among different knowledge element groups, and taking the knowledge representation vectors as actual association relations among different preset crime dimensions.
Optionally, the subject determination module includes:
the portrait acquisition submodule is used for acquiring a portrait of a historical crime subject of the historical crime subject; the historical criminal subject portrait comprises historical dimension information under different preset criminal dimensions and historical association relations among the different preset criminal dimensions;
and a main body determination submodule for screening out the historical criminal main body portrait which is completely the same as the criminal main body portrait from the historical criminal main body portrait, and taking the criminal main body corresponding to the screened historical criminal main body portrait as a similar criminal main body.
A storage medium comprising a stored program, wherein a device in which the storage medium is located is controlled to perform the above-described sentencing prediction method when the program is run.
An electronic device comprising at least one processor, and at least one memory, bus connected to the processor; the processor and the memory complete mutual communication through the bus; the processor is adapted to invoke program instructions in the memory to perform the aforementioned sentencing prediction method.
By means of the technical scheme, the criminal prediction method and the device provided by the invention have the advantages that the server can generate the criminal body portrait of the criminal body according to the criminal information after acquiring the criminal information of the criminal body, determine the similar criminal body similar to the criminal body, and determine the criminal measuring result of the similar criminal body as the reference criminal measuring result of the criminal body. Furthermore, a judge or law enforcement officer can refer to the criminal investigation result of the criminal subject to determine the criminal period, so that the judging result determining process is time-saving and labor-saving.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 illustrates a method flow diagram of a crime prediction method provided by an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating a criminal subject portrait model according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating a data extraction scenario provided by an embodiment of the invention;
FIG. 4 illustrates a method flow diagram of another crime prediction method provided by an embodiment of the present invention;
FIG. 5 is a schematic diagram of a criminal body portrait according to an embodiment of the invention;
fig. 6 is a schematic structural diagram illustrating a crime prediction apparatus provided by an embodiment of the present invention;
fig. 7 shows a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The embodiment of the present invention provides a sentencing prediction method, and with reference to fig. 1, the sentencing prediction method may include:
and S11, acquiring crime information for describing the criminal subject.
The above information may be contents in criminal law documents (prosecution opinions, prosecution, criminal proposal, criminal referee documents, etc.), and examples of description of the information may be:
1) in 5 months in 2018, a man is robbed by holding a knife, the number of the robbed cash is 1 ten thousand yuan, and the man escapes from the scene after being killed.
2) The defendant is a good one, male, Han nationality, junior middle school culture degree, and is of no industry, living in Shanzhou region of the three gorges city of Henan province. The dangerous driving crime is waited for in 2018 on 5-17 th day and arrested on 10-11 th day.
S12, generating a criminal subject image of the criminal subject according to the criminal information.
The criminal body portrait describes specific criminal information of a criminal body, and is generated based on a criminal body portrait model, wherein the criminal body portrait model is the most complete particle dimension of the criminal body portrait determined by law experts according to criminal laws and regulations and standardized guidance opinions of all regions and criminals. Specifically referring to fig. 2, the criminal subject portrait model may be a portrait of a criminal subject constructed from attribute information, criminal information, and criminal process information, centered on the criminal subject. For example, common crimes in the attribute information may include main crimes, subordinate crimes, education drive crimes and crime group chief molars, in practical applications, one crime subject may be one of the main crimes, subordinate crimes and subordinate crimes, and may also be one or more of the education drive crimes and the crime group chief molars, and the other attribute information, quantitative criminal information and crime process information are similar.
The content acquisition sources of the individual grain dimensions in the crime subject representation model are referred to in table 3. Taking attribute information as an example, the attribute information can be obtained from a corresponding criminal legal document, such as a "criminal subject information segment" in a prosecution opinion, a prosecution, a criminal proposal, a official prosecution report, and the like, and the image dimension is several dimensions, such as "criminal responsibility age/criminal responsibility ability/criminal president/deaf mute/disabled person/elderly person/minor" and the like, that is, specific information of the image dimensions needs to be extracted from the corresponding legal document, and the extraction mode or technology is "extraction by using a text analysis technology and through a dictionary, a regular expression, a keyword, a named entity recognition mode". Namely, the content of the image dimension is obtained from the legal document by adopting the technology. Likewise, criminal process information is similar to criminal information.
After generating the crime subject image model, the crime subject image of the crime subject in the embodiment may be obtained by the crime subject image model, and specifically, referring to fig. 4, the method may include:
s21, obtaining the criminal subject portrait model.
The criminal subject portrait model comprises all dimension information of preset criminal dimensions; the number of the preset crime dimensions is multiple, and the preset crime dimensions are each dimension under the attribute information, the criminal measuring information and the crime process information, such as common crime, criminal liability ability and the like. The above-mentioned principal, subordinate, etc. are dimension information of the attribute information.
S22, acquiring actual dimension information under the preset crime dimension from the crime information, and determining actual association relations between different preset crime dimensions.
The criminal subject portrait model determines a plurality of dimensions, and now analyzes the criminal information of the criminal subject in the embodiment to obtain the actual dimension information of each preset criminal dimension.
For example, using case number (xxxx) xxxx criminal initial xxx as an example, the criminal subject and the subject image particle dimension, i.e. the actual dimension information under each preset criminal dimension, are first determined.
The criminal subject is controlled to be 'fraud', the dimensions of the subject figure and the particles are as follows:
attribute information dimension, including gender/date of birth/nationality/cultural degree/household registration/criminal status (leading/trailing)
Criminal information dimension, pre-crime department/crime amount/trash/first order
Crime process information dimension, fraud instrument (building virtual electronic platform/sending false transaction information), crime purpose (intentional crime/crime of mistake)
The scheme is totally 6 crime subjects, and each crime subject performs information extraction and association according to the particle dimensions to form 6 crime subject figures.
For each criminal subject, after actual dimension information under a preset criminal dimension is obtained, actual association relations among different preset criminal dimensions also need to be obtained.
In practical applications, the knowledge representation vector is used to represent the actual association. Specifically, the actual dimension information of each preset crime dimension is used as a knowledge element group, and the content of the knowledge element group is a group of characters, specifically, the actual dimension information of the preset crime dimension.
Then, a knowledge representation vector of any two knowledge tuples is calculated, and a process of obtaining the knowledge representation vector by using knowledge tuple calculation is introduced by way of example, which is specifically as follows:
still as illustrated in the above example, each dimension is taken as a group of knowledge, such as criminal agent a-gender-male, criminal agent a-cultural degree-college subject, criminal agent B-criminal status-chief; criminal subject B-from scratch;
an algorithm model (similar to a word vector determination model) is utilized between the knowledge tuples to search for knowledge representation vectors, such as a set of vectors formed between a Ju 1-fraud means-sending false transaction information and a Ju 1-crime purpose-intentional crime in the present case. A group of vectors is formed between the Wangshuai, the crime amount, the transaction commission charge of 80 percent and the Wangshuai, the crime status and the chief. The final crime subject representation can be seen in fig. 5. Wherein the indication representation vector is an n-dimensional vector, such as a 50-dimensional vector.
And S23, taking the actual dimension information under the preset crime dimension and the actual incidence relation between different preset crime dimensions as the crime subject portrait.
Specifically, the criminal subject portrait includes not only actual dimension information under a preset criminal dimension, but also actual association relations between different preset criminal dimensions, that is, a plurality of knowledge tuples and knowledge representation vectors between the knowledge tuples, which may specifically refer to fig. 5.
S13, based on the image of the criminal subject, determining a similar criminal subject similar to the criminal subject.
In practical application, after a criminal subject portrait model is constructed, all previously filed criminal cases are acquired, criminal subject portraits of each criminal subject in the criminal cases are constructed, in order to avoid confusion with the criminal subject portraits of the criminal subject to be analyzed, the criminal subject portraits filed in the embodiment are called historical criminal subject portraits, the historical criminal subject portraits are similar to the criminal subject portraits generation process, and historical dimension information under different preset criminal dimensions and historical association relations among different preset criminal dimensions are included.
Then, a historical criminal subject image identical to the criminal subject image is selected from the historical criminal subject images, and the criminal subject corresponding to the selected historical criminal subject image is used as a similar criminal subject.
In the screening, the screening process may adopt a machine learning manner. The fact that the knowledge groups are identical means that actual dimension information under preset crime dimensions is identical, and actual association relations between different preset crime dimensions are identical, that is, included knowledge groups are identical, and knowledge expression vectors between the knowledge groups are identical.
S14, determining the crime result of the similar criminal subject as the reference crime result of the criminal subject.
The screened similar crime main bodies are similar to the information of the crime main body to be analyzed in the invention, namely the similar crime main bodies have the same crime process as the crime main body in the embodiment, and at the moment, the crime result, namely the crime result, aiming at the similar crime main bodies can be directly obtained and output.
Case examiners can determine the criminal result of the criminal subject according to the criminal result, so that the case examination process of the examiners is convenient, and time and labor are saved.
In addition, the present embodiment proposes a method using text analysis and machine learning to extract attribute information and crime information of a criminal subject and construct a complete criminal subject image model using these information. And (3) accurately predicting the sentencing result through matching the model and the model.
In this embodiment, the server may generate a criminal subject portrait of the criminal subject according to the criminal information after obtaining the criminal information of the criminal subject, determine a similar criminal subject similar to the criminal subject, and determine a criminal result of the similar criminal subject as a reference criminal result of the criminal subject. Furthermore, a judge or law enforcement officer can refer to the criminal investigation result of the criminal subject to determine the criminal period, so that the judging result determining process is time-saving and labor-saving. Moreover, the embodiment of the invention provides the knowledge representation vector between the knowledge tuples, so that similar criminal subjects can be accurately found, and the influence on criminal result output caused by inaccurate case screening is avoided. In addition, the embodiment of the invention can cover all stages in the criminal field, and can provide criminal prediction in a detection stage, a review and prosecution stage and a judge stage, thereby assisting the official examination and case handling staff to work.
Alternatively, on the basis of the embodiment of the sentention prediction method, another embodiment of the present invention provides a sentention prediction device, and referring to fig. 6, the sentention prediction device may include:
an information acquisition module 101, configured to acquire crime information describing a criminal subject;
an image generation module 102, configured to generate a crime subject image of the crime subject according to the crime information;
a subject determination module 103 for determining a similar criminal subject similar to the criminal subject based on the criminal subject representation;
a result determination module 104 for determining the crime-like subject's crime result as the crime-like subject's reference crime result.
Further, the representation generation module includes: the model acquisition submodule is used for acquiring a criminal subject portrait model; the criminal subject portrait model comprises all dimension information of preset criminal dimensions; the number of the preset crime dimensions is multiple;
the data determination submodule is used for acquiring actual dimension information under the preset crime dimension from the crime information and determining an actual incidence relation between different preset crime dimensions;
and the portrait generation submodule is used for taking the actual dimension information under the preset crime dimensions and the actual association relationship between different preset crime dimensions as the portrait of the crime main body.
Further, when the data determination submodule is configured to determine an actual association relationship between different preset crime dimensions, the data determination submodule is specifically configured to:
and taking the actual dimension information under the preset crime dimension as a knowledge element group, determining knowledge representation vectors among different knowledge element groups, and taking the knowledge representation vectors as actual association relations among different preset crime dimensions.
Further, the subject determination module includes:
the portrait acquisition submodule is used for acquiring a portrait of a historical crime subject of the historical crime subject; the historical criminal subject portrait comprises historical dimension information under different preset criminal dimensions and historical association relations among the different preset criminal dimensions;
and a main body determination submodule for screening out the historical criminal main body portrait which is completely the same as the criminal main body portrait from the historical criminal main body portrait, and taking the criminal main body corresponding to the screened historical criminal main body portrait as a similar criminal main body.
In this embodiment, the server may generate a criminal subject portrait of the criminal subject according to the criminal information after obtaining the criminal information of the criminal subject, determine a similar criminal subject similar to the criminal subject, and determine a criminal result of the similar criminal subject as a reference criminal result of the criminal subject. Furthermore, a judge or law enforcement officer can refer to the criminal investigation result of the criminal subject to determine the criminal period, so that the judging result determining process is time-saving and labor-saving. Moreover, the embodiment of the invention provides the knowledge representation vector between the knowledge tuples, so that similar criminal subjects can be accurately found, and the influence on criminal result output caused by inaccurate case screening is avoided. In addition, the embodiment of the invention can cover all stages in the criminal field, and can provide criminal prediction in a detection stage, a review and prosecution stage and a judge stage, thereby assisting the official examination and case handling staff to work.
It should be noted that, for the working processes of each module and sub-module in this embodiment, please refer to the corresponding description in the above embodiments, which is not described herein again.
The sentencing prediction device comprises a processor and a memory, wherein the model acquisition submodule, the data determination submodule, the portrait generation submodule and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.
The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. The kernel can be provided with one or more than one kernel, and criminal evidences are provided for judges or law enforcement personnel by adjusting kernel parameters.
An embodiment of the present invention provides a storage medium having a program stored thereon, which when executed by a processor implements the sentencing prediction method.
An embodiment of the present invention provides a processor, configured to run a program, where the method for forecasting tortuosity is executed when the program runs.
An embodiment of the present invention provides a device 70, and referring to fig. 7, the device 70 includes at least one processor 701, at least one memory 702 connected to the processor, and a bus 703; the processor 701 and the memory 702 complete mutual communication through a bus 703; the processor 701 is arranged to call program instructions in the memory 702 to perform the aforementioned sentencing prediction method. The device 70 herein may be a server, a PC, a PAD, a cell phone, etc.
The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device:
a sentencing prediction method, comprising:
obtaining crime information for describing a criminal subject;
generating a criminal subject image of the criminal subject according to the criminal information;
determining a similar criminal subject similar to the criminal subject based on the criminal subject representation;
and determining the criminal result of the similar criminal subject as a reference criminal result of the criminal subject.
Further, generating a criminal subject representation of the criminal subject based on the criminal information includes:
obtaining a criminal subject portrait model; the criminal subject portrait model comprises all dimension information of preset criminal dimensions; the number of the preset crime dimensions is multiple;
acquiring actual dimension information under the preset crime dimension from the crime information, and determining an actual association relation between different preset crime dimensions;
and taking the actual dimension information under the preset crime dimensions and the actual association relationship between different preset crime dimensions as the crime subject portrait.
Further, determining an actual association relationship between different preset crime dimensions includes:
using actual dimension information under the preset crime dimension as a knowledge element group;
and determining knowledge representation vectors among different knowledge tuples, and taking the knowledge representation vectors as actual association relations among different preset crime dimensions.
Further, determining a similar criminal subject similar to the criminal subject based on the criminal subject representation includes:
acquiring a historical crime subject portrait of a historical crime subject; the historical criminal subject portrait comprises historical dimension information under different preset criminal dimensions and historical association relations among the different preset criminal dimensions;
and screening out the historical criminal subject portrait which is completely the same as the criminal subject portrait from the historical criminal subject portrait, and taking the criminal subject corresponding to the screened historical criminal subject portrait as a similar criminal subject.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a device includes one or more processors (CPUs), memory, and a bus. The device may also include input/output interfaces, network interfaces, and the like.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip. The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A crime prediction method, comprising:
obtaining crime information for describing a criminal subject;
generating a criminal subject image of the criminal subject according to the criminal information;
determining a similar criminal subject similar to the criminal subject based on the criminal subject representation;
and determining the criminal result of the similar criminal subject as a reference criminal result of the criminal subject.
2. The crime prediction method according to claim 1, wherein generating a crime subject image of the crime subject based on the crime information comprises:
obtaining a criminal subject portrait model; the criminal subject portrait model comprises all dimension information of preset criminal dimensions; the number of the preset crime dimensions is multiple;
acquiring actual dimension information under the preset crime dimension from the crime information, and determining an actual association relation between different preset crime dimensions;
and taking the actual dimension information under the preset crime dimensions and the actual association relationship between different preset crime dimensions as the crime subject portrait.
3. The sentencing prediction method of claim 2, where determining an actual correlation between different of the pre-set criminal dimensions comprises:
using actual dimension information under the preset crime dimension as a knowledge element group;
and determining knowledge representation vectors among different knowledge tuples, and taking the knowledge representation vectors as actual association relations among different preset crime dimensions.
4. The crime prediction method of claim 2, wherein determining a similar criminal subject similar to the criminal subject based on the criminal subject representation comprises:
acquiring a historical crime subject portrait of a historical crime subject; the historical criminal subject portrait comprises historical dimension information under different preset criminal dimensions and historical association relations among the different preset criminal dimensions;
and screening out the historical criminal subject portrait which is completely the same as the criminal subject portrait from the historical criminal subject portrait, and taking the criminal subject corresponding to the screened historical criminal subject portrait as a similar criminal subject.
5. A crime prediction device, comprising:
the information acquisition module is used for acquiring crime information for describing a crime subject;
the portrait generation module is used for generating a criminal subject portrait of the criminal subject according to the criminal information;
a subject determination module to determine a similar criminal subject similar to the criminal subject based on the criminal subject representation;
a result determination module for determining the crime result of the similar criminal subject as a reference crime result of the criminal subject.
6. The sentry prediction device of claim 5, characterized in that the representation generation module comprises: the model acquisition submodule is used for acquiring a criminal subject portrait model; the criminal subject portrait model comprises all dimension information of preset criminal dimensions; the number of the preset crime dimensions is multiple;
the data determination submodule is used for acquiring actual dimension information under the preset crime dimension from the crime information and determining an actual incidence relation between different preset crime dimensions;
and the portrait generation submodule is used for taking the actual dimension information under the preset crime dimensions and the actual association relationship between different preset crime dimensions as the portrait of the crime main body.
7. The sentencing prediction device of claim 6, where the data determination sub-module, when configured to determine the actual correlation between different pre-set crime dimensions, is specifically configured to:
and taking the actual dimension information under the preset crime dimension as a knowledge element group, determining knowledge representation vectors among different knowledge element groups, and taking the knowledge representation vectors as actual association relations among different preset crime dimensions.
8. The sentencing prediction device of claim 6, where the subject determination module comprises:
the portrait acquisition submodule is used for acquiring a portrait of a historical crime subject of the historical crime subject; the historical criminal subject portrait comprises historical dimension information under different preset criminal dimensions and historical association relations among the different preset criminal dimensions;
and a main body determination submodule for screening out the historical criminal main body portrait which is completely the same as the criminal main body portrait from the historical criminal main body portrait, and taking the criminal main body corresponding to the screened historical criminal main body portrait as a similar criminal main body.
9. A storage medium, characterized in that the storage medium comprises a stored program, wherein a device on which the storage medium is located is controlled to perform the sentencing prediction method according to any of claims 1-4 when the program is run.
10. An electronic device, characterized in that the device comprises at least one processor, and at least one memory, a bus connected to the processor; the processor and the memory complete mutual communication through the bus; the processor is adapted to invoke program instructions in the memory to perform the sentencing prediction method according to any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910941266.9A CN112579732A (en) | 2019-09-30 | 2019-09-30 | Sentencing prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910941266.9A CN112579732A (en) | 2019-09-30 | 2019-09-30 | Sentencing prediction method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112579732A true CN112579732A (en) | 2021-03-30 |
Family
ID=75116270
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910941266.9A Pending CN112579732A (en) | 2019-09-30 | 2019-09-30 | Sentencing prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112579732A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6405213B1 (en) * | 1997-05-27 | 2002-06-11 | Hoyt M. Layson | System to correlate crime incidents with a subject's location using crime incident data and a subject location recording device |
| CN109241528A (en) * | 2018-08-24 | 2019-01-18 | 讯飞智元信息科技有限公司 | A kind of measurement of penalty prediction of result method, apparatus, equipment and storage medium |
| CN109949185A (en) * | 2019-03-15 | 2019-06-28 | 南京邮电大学 | Judicial case judgement system and method based on Event Tree Analysis |
| CN110287292A (en) * | 2019-07-04 | 2019-09-27 | 科大讯飞股份有限公司 | A kind of judge's measurement of penalty irrelevance prediction technique and device |
-
2019
- 2019-09-30 CN CN201910941266.9A patent/CN112579732A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6405213B1 (en) * | 1997-05-27 | 2002-06-11 | Hoyt M. Layson | System to correlate crime incidents with a subject's location using crime incident data and a subject location recording device |
| CN109241528A (en) * | 2018-08-24 | 2019-01-18 | 讯飞智元信息科技有限公司 | A kind of measurement of penalty prediction of result method, apparatus, equipment and storage medium |
| CN109949185A (en) * | 2019-03-15 | 2019-06-28 | 南京邮电大学 | Judicial case judgement system and method based on Event Tree Analysis |
| CN110287292A (en) * | 2019-07-04 | 2019-09-27 | 科大讯飞股份有限公司 | A kind of judge's measurement of penalty irrelevance prediction technique and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111695033B (en) | Enterprise public opinion analysis method, enterprise public opinion analysis device, electronic equipment and medium | |
| CN108108902B (en) | Risk event warning method and device | |
| Saumya et al. | Detection of spam reviews: a sentiment analysis approach | |
| US20190026605A1 (en) | Neural network model training method and apparatus, living body detecting method and apparatus, device and storage medium | |
| CN112860841B (en) | Text emotion analysis method, device, equipment and storage medium | |
| CN111242083B (en) | Text processing method, device, equipment and medium based on artificial intelligence | |
| CN111062389A (en) | Character recognition method and device, computer readable medium and electronic equipment | |
| US20180336580A1 (en) | Evaluation device, evaluation method, and storage medium | |
| Hessel et al. | The abduction of sherlock holmes: A dataset for visual abductive reasoning | |
| US20230410222A1 (en) | Information processing apparatus, control method, and program | |
| CN108717519B (en) | Text classification method and device | |
| CN110334107B (en) | Qualification review method, device and server based on data analysis | |
| CN115222443A (en) | Client group division method, device, equipment and storage medium | |
| Kralj Novak et al. | Handling disagreement in hate speech modelling | |
| CN113568934B (en) | Data query method and device, electronic equipment and storage medium | |
| Kinchin | Technology, displaced?: The risks and potential of artificial intelligence for fair, effective, and efficient refugee status determination | |
| CN114037545A (en) | Client recommendation method, device, equipment and storage medium | |
| CN114579523A (en) | Double-recording file quality inspection method and device, computer equipment and storage medium | |
| CN109660621A (en) | A kind of content delivery method and service equipment | |
| KR20220063483A (en) | Apparatus and method for analyzing sentiment of text data based on machine learning | |
| CN112579732A (en) | Sentencing prediction method and device | |
| CN114491134B (en) | Trademark registration success rate analysis method and system | |
| CN115618415A (en) | Sensitive data identification method and device, electronic equipment and storage medium | |
| CN115358817A (en) | Intelligent product recommendation method, device, equipment and medium based on social data | |
| CN114153939A (en) | Text recognition method and device |
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 |