CN115269710A - Full-flow portrait processing method, system, device and storage medium - Google Patents
Full-flow portrait processing method, system, device and storage medium Download PDFInfo
- Publication number
- CN115269710A CN115269710A CN202210518532.9A CN202210518532A CN115269710A CN 115269710 A CN115269710 A CN 115269710A CN 202210518532 A CN202210518532 A CN 202210518532A CN 115269710 A CN115269710 A CN 115269710A
- Authority
- CN
- China
- Prior art keywords
- case
- portrait
- preliminary
- label
- information
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 31
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 37
- 238000005516 engineering process Methods 0.000 claims abstract description 35
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000007781 pre-processing Methods 0.000 claims abstract description 15
- 238000011835 investigation Methods 0.000 claims abstract description 12
- 238000000034 method Methods 0.000 claims description 26
- 238000004458 analytical method Methods 0.000 claims description 15
- 238000010801 machine learning Methods 0.000 claims description 12
- 238000005065 mining Methods 0.000 claims description 11
- 238000004140 cleaning Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims 2
- 238000007689 inspection Methods 0.000 description 24
- 230000006870 function Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 9
- 238000011156 evaluation Methods 0.000 description 5
- 238000007726 management method Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000000750 progressive effect Effects 0.000 description 2
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 238000013467 fragmentation Methods 0.000 description 1
- 238000006062 fragmentation reaction Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/26—Visual data mining; Browsing structured data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a full-flow portrait processing method, a system, a device and a storage medium. The full-flow portrait processing method realizes targeted portrait service for business data by acquiring multi-dimensional original data in a business system and obtaining fact data information after preprocessing, so as to draw case preliminary portrait and inspector preliminary portrait; and a prediction algorithm and a technology outside invisible knowledge are adopted to further obtain a prediction label on the basis of the preliminary portrait, so that accurate case division and risk investigation are realized by using the prediction label, and the original data of a business system is fully utilized to improve the efficiency of case examination and handling and the reasonability of case allocation. The invention can be widely applied to the technical field of image processing.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to a full-flow image processing method, system, device, and storage medium.
Background
With the advent of artificial intelligence and the field of big data, research on portrait technology has been developed and has become a focus of attention of many scholars. In recent years, with the development of information-based inspection, it has become a natural task to apply image knowledge to the field of inspection.
The prior art has the characteristics of fragmentation, low facet quality and multisource isomerism, and the problems in law enforcement activities cannot be effectively found and solved, so that the prior art for processing the inspection portrait cannot pertinently provide complete and clear portrait service for the inspection business, the resources of the inspection business data cannot be fully utilized, namely, the prior art data knowledge of the inspection business cannot provide help for inspecting and handling cases, the inspection and handling efficiency can be reduced, and the case allocation rationality can be reduced.
Disclosure of Invention
The present invention aims to solve at least to some extent one of the technical problems existing in the prior art.
Therefore, an object of the embodiments of the present invention is to provide a full-flow image processing method, system, device and storage medium, so as to fully utilize original data of a business system to improve efficiency of checking and handling cases and reasonableness of case allocation.
In order to achieve the technical purpose, the technical scheme adopted by the embodiment of the invention comprises the following steps:
in a first aspect, an embodiment of the present invention provides a full-flow portrait processing method, where the network on chip includes multiple routing nodes, and the method includes the following steps:
acquiring original data in a service system, wherein the original data comprises structured data and unstructured data;
preprocessing the original data to acquire fact data information;
according to the fact data information, performing label modeling and identification by adopting a machine learning method to finish drawing of a preliminary portrait, wherein the preliminary portrait comprises a case preliminary portrait and a surveyor preliminary portrait;
according to the preliminary portrait, a prediction label is obtained by adopting a prediction algorithm and an invisible knowledgement technology;
and carrying out case division and risk investigation according to the prediction label.
The full-process portrait processing method of the embodiment of the invention realizes targeted portrait service for business data by acquiring multi-dimensional original data in a business system, preprocessing the original data to obtain fact data information, and further drawing primary case portrait and primary examiner portrait; and a prediction algorithm and an invisible knowledge technology are adopted to further obtain a prediction label on the basis of the primary portrait, so that accurate case division and risk investigation are realized by using the prediction label, and the original data of a business system is fully utilized to improve the efficiency of case examination and handling and the reasonability of case distribution.
In addition, the full-flow image processing method according to the above embodiment of the present invention may further have the following additional technical features:
further, in the full-flow portrait processing method according to the embodiment of the present invention, the preprocessing includes data cleaning and text mining;
the preprocessing the original data to acquire fact data information includes:
performing data cleaning on the original data;
and adopting a classification and clustering algorithm to carry out text mining on the original data after data cleaning to obtain the fact data information.
Further, in an embodiment of the present invention, the performing label modeling and identification by using a machine learning method according to the fact data information to complete the drawing of the case preliminary portrait includes:
performing disassembly analysis on the fact data information to obtain a first case label, wherein the first case label comprises case information, specific personnel information and prediction information;
and drawing the case preliminary portrait according to the first case label.
Further, in an embodiment of the present invention, the performing label modeling and identification by using a machine learning method according to the fact data information to complete the drawing of the preliminary portrait of the inspector includes:
performing disassembly analysis on the fact data information to obtain a first inspector label, wherein the first inspector label comprises basic inspector information, case handling information and assistant inspector tool information;
and drawing the preliminary portrait of the examiner according to the first examiner label.
Further, in an embodiment of the present invention, the deriving a prediction label by using a prediction algorithm and an implicit knowledge technology according to the preliminary sketch includes:
extracting the characteristics of the preliminary image to obtain fine-grained characteristic information;
and obtaining a prediction label by adopting a prediction algorithm and an invisible knowledge technology according to the fine-grained characteristic information.
Further, in an embodiment of the present invention, the performing feature extraction on the preliminary image to obtain fine-grained feature information includes:
performing feature extraction on the preliminary image by adopting a common feature extraction technology to obtain coarse-grained feature information;
and performing duplicate removal and disambiguation on the coarse-grained characteristic information by adopting a characteristic difference analysis technology to obtain the fine-grained characteristic information.
Further, in one embodiment of the present invention, the forecast tags include a second case tag including case attributes, staff-specific attributes and case forecasts, and a second auditor tag including auditor attributes, auditor case handling capabilities and auditor assistance requirements;
the step of obtaining a prediction label by adopting a prediction algorithm and an invisible knowledge technology according to the fine-grained characteristic information comprises the following steps:
converting the first case label into the second case label by adopting a prediction algorithm and an invisible knowledge technology according to the fine-grained characteristic information;
and converting the first inspection official label into the second inspection official label by adopting a prediction algorithm and an invisible external knowledge technology according to the fine-grained characteristic information.
In a second aspect, an embodiment of the present invention provides a full-flow image processing system, including:
the system comprises an original data acquisition module, a data processing module and a data processing module, wherein the original data acquisition module is used for acquiring original data in a service system, and the original data comprises structured data and unstructured data;
the fact data information acquisition module is used for preprocessing the original data to acquire fact data information;
the preliminary portrait drawing module is used for performing label modeling and identification by adopting a machine learning method according to the fact data information to finish drawing of a preliminary portrait, wherein the preliminary portrait comprises a case preliminary portrait and an inspector preliminary portrait;
the prediction label generation module is used for obtaining a prediction label by adopting a prediction algorithm and an invisible knowledgement technology according to the preliminary portrait;
and the prediction module is used for carrying out case division and risk investigation according to the prediction label.
In a third aspect, an embodiment of the present invention provides a full-flow portrait processing apparatus, including:
at least one processor;
at least one memory for storing at least one program;
when the at least one program is executed by the at least one processor, the at least one program causes the at least one processor to implement a method of full-flow representation processing as described in the first aspect.
In a fourth aspect, an embodiment of the present invention provides a storage medium, in which a processor-executable program is stored, and the processor-executable program is used to implement a full-flow portrait processing method according to the first aspect when executed by a processor.
Advantages and benefits of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application:
the embodiment of the invention realizes the targeted image service for the business data by acquiring the multi-dimensional original data in the business system and preprocessing the original data to obtain the fact data information so as to draw the preliminary picture of the case and the preliminary picture of the inspector; and a prediction algorithm and a technology outside invisible knowledge are adopted to further obtain a prediction label on the basis of the preliminary portrait, so that accurate case division and risk investigation are realized by using the prediction label, and the original data of a business system is fully utilized to improve the efficiency of case examination and handling and the reasonability of case allocation.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following description is made on the drawings of the embodiments of the present application or the related technical solutions in the prior art, and it should be understood that the drawings in the following description are only for convenience and clarity of describing some embodiments in the technical solutions of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic flow chart diagram illustrating a full-flow image processing method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a first case label and a second case label according to an embodiment of a full-flow image processing method of the present invention;
FIG. 3 is a schematic diagram of a first inspector label and a second inspector label according to an embodiment of a full-process image processing method of the present invention;
FIG. 4 is a schematic diagram of a full-flow image processing system according to an embodiment of the present invention;
FIG. 5 is a block diagram of a full-flow image processing system according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a full-flow image processing apparatus according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative and are only for the purpose of explaining the present application and are not to be construed as limiting the present application. The step numbers in the following embodiments are provided only for convenience of illustration, the order between the steps is not limited at all, and the execution order of each step in the embodiments can be adapted according to the understanding of those skilled in the art.
The terms "first," "second," "third," and "fourth," etc. in the description and claims of the invention and in the accompanying drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements but may alternatively include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the invention. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
The invention provides a full-flow portrait processing method and system. The method and the system realize the targeted image service for the business data by acquiring the multi-dimensional original data in the business system, preprocessing the original data to obtain the fact data information, and further drawing the preliminary image of the case and the preliminary image of the inspector; and a prediction algorithm and a technology outside invisible knowledge are adopted to further obtain a prediction label on the basis of the preliminary portrait, so that accurate case division and risk investigation are realized by using the prediction label, and the original data of a business system is fully utilized to improve the efficiency of case examination and handling and the reasonability of case allocation.
A full-flow portrait processing method and system according to an embodiment of the present invention will be described in detail below with reference to the accompanying drawings, and first, a full-flow portrait processing method according to an embodiment of the present invention will be described with reference to the accompanying drawings.
Referring to fig. 1, an embodiment of the present invention provides a full-flow image processing method, and the full-flow image processing method in the embodiment of the present invention may be applied to a terminal, a server, or software running in the terminal or the server. The terminal may be, but is not limited to, a tablet computer, a notebook computer, a desktop computer, and the like. The server may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a network service, cloud communication, middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like. The full-flow portrait processing method in the embodiment of the invention mainly comprises the following steps:
s101, acquiring original data in a service system;
wherein the raw data comprises structured data and unstructured data.
It can be understood that the national inspection and inspection institutions transact cases through the unified service application system (namely the service system), issue procedural information, important case information and open legal documents through the Internet platform to form huge information data, extend the research work done in the portrait field at home and abroad to the current inspection and informatization work, and deeply fuse with the inspection and inspection institution unified service system, thereby playing an obvious role in promoting the auxiliary inspection and official case handling.
Specifically, in the embodiment of the invention, by real-time docking with the unified business application system, the case evaluation system, the team management system, the attendance system and other business systems, case handling procedural information, physical information, file materials and case evaluation and examination information of the inspectors dispersed in different business systems are uniformly docked, manual introduction and intervention are not needed, different data resources are closely fused, integration of different application systems is realized, and the track efficiency of the inspectors is displayed in multiple dimensions.
The structured data of the embodiment of the invention is the structured data of case cards, and the unstructured data is the unstructured data of documents and files.
S102, preprocessing the original data to acquire fact data information;
wherein the preprocessing comprises data cleansing and text mining.
S102 may be further divided into the following steps S1021-S1022:
step S1021, data cleaning is carried out on the original data;
specifically, ETL data cleaning is carried out on the original data to obtain the original data after the data cleaning.
And step S1022, text mining is carried out on the original data after data cleaning by adopting a classification and clustering algorithm, and the fact data information is obtained.
Specifically, the original data after data cleaning is subjected to text mining, incomplete case information is predicted according to a classification algorithm, cases and inspectors are subjected to prediction classification, groups with the same characteristics are analyzed and mined according to a clustering algorithm to perform audience segmentation, and fact data information including specific personnel attribute information, victim attribute information and case handling attribute information is extracted from the original data.
S103, performing label modeling and identification by adopting a machine learning method according to the fact data information to finish drawing of a preliminary portrait;
wherein the preliminary representation comprises a case preliminary representation and an inspector preliminary representation.
Specifically, the method comprises the following two aspects of preliminary portrait drawing:
(1) According to the fact data information, performing label modeling and identification by adopting a machine learning method to finish drawing of the case preliminary portrait;
(2) And performing label modeling and identification by adopting a machine learning method according to the fact data information to finish drawing the preliminary portrait of the inspector.
Referring to fig. 2, for the preliminary case image drawing in step (1), the embodiment of the present invention specifically includes the following steps:
a. performing disassembly analysis on the fact data information to obtain a first case label;
wherein the first case label includes case information, specific person information, and prediction information.
Specifically, in one embodiment of the present invention, the case information includes case-related information such as case name, acceptance time, contractor information, and party information, the specific person information includes specific person name, gender, residence, age, and the like, and the prediction information includes information such as case complexity and case risk.
b. And drawing the preliminary case portrait according to the first case label.
Referring to fig. 3, for the rendering of the preliminary image of the detected organ in (2), the embodiment of the present invention specifically includes the following steps:
a. performing disassembly analysis on the fact data information to obtain a first inspector label;
wherein the first scout label comprises scout basic information, scout case information, and scout assistant tool information, each first scout label representing an attribute.
Specifically, in an embodiment of the present invention, the basic information of the inspector includes basic information of the inspector such as sex, age, academic calendar and unit, the case handling information of the inspector includes case handling duration, case type, case handling reason, case handling quantity, document examination and approval passing rate, node stay time and node return frequency, and the assistant tool information of the inspector includes case card backfill usage, class case push usage and knowledge base access amount.
c. And drawing the preliminary portrait of the examiner according to the first examiner label.
S104, according to the preliminary portrait, a prediction label is obtained by adopting a prediction algorithm and an invisible knowledge technology;
specifically, in the embodiment of the invention, based on the inspection business rules, a scientific and complete portrait index system is constructed by researching feature granularity analysis, multi-attribute simple algorithm technology and feature progressive mining model from four dimensions of case handling quantity, case handling quality, case handling efficiency and case handling effect and by classifying and summarizing the individual development information indexes of the inspectors. On the aspect of setting the case handling quantity index, the difference between cases is fully considered, the case weight coefficient management is newly designed, the conventional cases and the special case types are considered, the machine automatic measurement and manual flexible setting of the case weight coefficient are supported, and the reasonable evaluation of the case handling quantity is realized. In order to ensure the objectivity and the real-time property of index data extraction, the data of five main application systems, namely a key attack and hardening full-flow image system, a unified business system, a case quality evaluation and examination system, an attendance system, team management and the like, are connected in parallel, and the intelligent grabbing and real-time connection of the evaluation indexes and the business data is realized. Meanwhile, a data interface is reserved in the portrait system, and the problem of service management data drainage after the five application systems are upgraded and modified is better solved. By optimizing the algorithm analysis model, the system can automatically extract and form a visualized inspection service and team component data map of the whole hospital, department and individual, and provides comprehensive and scientific data support for service decision, team management and the like.
S104 may be further divided into the following steps S1041-S1042:
s1041, extracting the characteristics of the preliminary image to obtain fine-grained characteristic information;
specifically, in the embodiment of the present invention, a common feature extraction technique is first adopted to perform feature extraction on the preliminary image to obtain coarse-grained feature information, and then a feature difference analysis technique is adopted to perform de-duplication and disambiguation on the coarse-grained feature information to obtain the fine-grained feature information.
And S1042, obtaining a prediction label by adopting a prediction algorithm and an invisible knowledgement technology according to the fine-grained characteristic information.
The case prediction system comprises a prediction tag, a case attribute tag, a specific personnel attribute tag, a case prediction tag, a case attribute tag, a case handling capability tag, a case checking assistant tag and a case checking assistant tag, wherein the prediction tag comprises the second case tag and the second checking assistant tag.
In the embodiment of the invention, the advantages of relative macroscopicity and mesoscopic view of data are utilized to realize the deep analysis from individual case to class case, local to whole and phenomenon to essence, thereby capturing the rule of the inspection business from the data aspect, and serving the specific case handling of the microscopic aspect by monitoring data deviation and abnormity, drilling down and reversely checking to find the case handling problem and supervision clues of the individual case or the inspector. The high-quality data fusion can develop the traditional inspection and case handling visual field, improve the discovery and supervision level of the typed problems, create new inspection knowledge and further convert the new inspection knowledge into the business kinetic energy. When data are analyzed, the law is summarized more pertinently according to different service characteristics, analysis key points, associated maps and fusion data, the force point is found accurately, and four-major inspection is assisted practically, so that comprehensive, coordinated and full development is realized. The method mainly comprises the functions of knowledge modeling, associated graph construction, graph mining knowledge calculation, associated graph visualization display and the like.
Specifically, referring to fig. 2 and 3, the generation of predictive labels includes the following two aspects:
converting the first case label into the second case label by adopting a prediction algorithm and an invisible knowledge technology according to the fine-grained characteristic information;
and converting the first inspection official label into the second inspection official label by adopting a prediction algorithm and an invisible external knowledge technology according to the fine-grained characteristic information.
The case attribute is obtained by adopting a prediction algorithm and an invisible knowledgement technology according to the case information, the specific personnel attribute is obtained by adopting the prediction algorithm and the invisible knowledgement technology according to the specific personnel information, and the case prediction is obtained by adopting the prediction algorithm and the invisible knowledgement technology according to the prediction information; and obtaining the attribute of the examiner by adopting a prediction algorithm and an invisible knowledgement external technology according to the basic information of the examiner, obtaining the case handling capacity of the examiner by adopting the prediction algorithm and the invisible knowledgement external technology according to the case handling information of the examiner, and obtaining the auxiliary requirement of the examiner by adopting the prediction algorithm and the invisible knowledgement external technology according to the auxiliary tool information of the examiner.
And S105, carrying out case division and risk investigation according to the prediction label.
Specifically, firstly, predicting a case to be distributed according to a prediction label to obtain a prediction result, wherein the prediction result comprises case complexity prediction, case handling duration prediction and case handling capability prediction of an inspector, and the prediction method is not limited in this respect; and carrying out case division and risk investigation according to the prediction result.
According to the steps S101-S105, the full-flow portrait processing method provided by the embodiment of the invention realizes targeted portrait service for business data by acquiring multi-dimensional original data in a business system and preprocessing the original data to obtain fact data information, and further drawing a case preliminary portrait and an inspector preliminary portrait; and a prediction algorithm and a technology outside invisible knowledge are adopted to further obtain a prediction label on the basis of the preliminary portrait, so that accurate case division and risk investigation are realized by using the prediction label, and the original data of a business system is fully utilized to improve the efficiency of case examination and handling and the reasonability of case allocation.
Next, a full-flow image processing system according to an embodiment of the present application will be described with reference to the drawings.
FIG. 4 is a block diagram of a full-flow image processing system according to an embodiment of the present application.
The system specifically comprises:
an original data obtaining module 401, configured to obtain original data in a service system, where the original data includes structured data and unstructured data;
a fact data information obtaining module 402, configured to preprocess the original data to obtain fact data information;
a preliminary sketch drawing module 403, configured to perform label modeling and identification by using a machine learning method according to the fact data information, so as to complete drawing of a preliminary sketch, where the preliminary sketch includes a case preliminary sketch and an inspector preliminary sketch;
a prediction tag generation module 404, configured to obtain a prediction tag according to the preliminary portrait by using a prediction algorithm and an invisible knowledgement technology;
and the prediction module 405 is used for carrying out case division and risk investigation according to the prediction label.
FIG. 5 is a block diagram of a full-flow image processing system according to an embodiment of the present invention. The full-flow portrait processing system provided by the embodiment of the invention is based on data such as inspector data, case card data, business system data, inspectors and case analysis and evaluation, realizes portrait portrayal of multi-dimensional full flows such as inspectors and cases, displays full-flow tracking of case processes and inspector business handling flows and technically evaluates case full-flow tracking results through model training such as image mining deep learning, associated maps, feature progressive mining, feature granularity analysis and multi-attribute reduction algorithms and a full-flow portrait construction method combining researches and cases.
It can be seen that the contents in the foregoing method embodiments are all applicable to this system embodiment, the functions specifically implemented by this system embodiment are the same as those in the foregoing method embodiment, and the advantageous effects achieved by this system embodiment are also the same as those achieved by the foregoing method embodiment.
Referring to fig. 6, an embodiment of the present application provides a full-flow portrait processing apparatus, including:
at least one processor 601;
at least one memory 602 for storing at least one program;
when the at least one program is executed by the at least one processor 601, the at least one processor 601 implements the full flow representation processing method described in steps S101-S105.
Similarly, the contents in the method embodiments are all applicable to the apparatus embodiment, the functions specifically implemented by the apparatus embodiment are the same as those in the method embodiments, and the beneficial effects achieved by the apparatus embodiment are also the same as those achieved by the method embodiments.
In alternative embodiments, the functions/acts noted in the block diagrams may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Furthermore, the embodiments presented and described in the flowcharts of the present application are provided by way of example in order to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed, and in which sub-operations described as part of larger operations are performed independently.
Furthermore, although the present application is described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the functions and/or features may be integrated in a single physical device and/or software module, or one or more functions and/or features may be implemented in separate physical devices or software modules. It will also be understood that a detailed discussion regarding the actual implementation of each module is not necessary for an understanding of the present application. Rather, the actual implementation of the various functional modules in the apparatus disclosed herein will be understood within the ordinary skill of an engineer, given the nature, function, and internal relationship of the modules. Accordingly, those skilled in the art can, using ordinary skill, practice the present application as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are merely illustrative of and not intended to limit the scope of the application, which is to be determined by the appended claims along with their full scope of equivalents.
The functions may be stored in a computer-readable storage medium if they are implemented in the form of software functional units and sold or used as separate products. Based on such understanding, the technical solutions of the present application, which are essential or part of the technical solutions contributing to the prior art, may be embodied in the form of a software product, which is stored in a storage medium and includes several programs for enabling a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The logic and/or steps represented in the flowcharts or otherwise described herein, such as an ordered listing of executable programs that can be considered for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with a program execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the programs from the program execution system, apparatus, or device and execute the programs. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the program execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Further, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable program execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In the foregoing description of the specification, reference to the description of "one embodiment/example," "another embodiment/example," or "certain embodiments/examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present application have been shown and described, it will be understood by those of ordinary skill in the art that: numerous changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the application, the scope of which is defined by the claims and their equivalents.
While the present application has been described with reference to the preferred embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A full-flow image processing method is characterized by comprising the following steps:
acquiring original data in a service system, wherein the original data comprises structured data and unstructured data;
preprocessing the original data to acquire fact data information;
according to the fact data information, performing label modeling and identification by adopting a machine learning method to finish drawing of a preliminary portrait, wherein the preliminary portrait comprises a case preliminary portrait and a preliminary portrait of an inspector;
according to the preliminary portrait, a prediction algorithm and an invisible knowledgement technology are adopted to obtain a prediction label;
and carrying out case division and risk investigation according to the prediction label.
2. The full-flow representation processing method of claim 1, wherein said pre-processing includes data cleansing and text mining;
the preprocessing the original data to acquire fact data information includes:
performing data cleaning on the original data;
and adopting a classification and clustering algorithm to carry out text mining on the original data after data cleaning, and acquiring the fact data information.
3. The full-flow portrait processing method of claim 1, wherein the mapping of the preliminary portrait of the case is completed by performing label modeling and identification by using a machine learning method according to the fact data information, including:
performing disassembly analysis on the fact data information to obtain a first case label, wherein the first case label comprises case information, specific personnel information and prediction information;
and drawing the case preliminary portrait according to the first case label.
4. The full-flow portrait processing method according to claim 3, wherein the mapping of the preliminary portrait of the examiner is completed by performing label modeling and identification by using a machine learning method according to the fact data information, and includes:
performing disassembly analysis on the fact data information to obtain a first inspector label, wherein the first inspector label comprises basic inspector information, case handling information and assistant inspector tool information;
and drawing the preliminary image of the examiner according to the first examiner label.
5. The full-flow sketch processing method as claimed in claim 4, wherein said deriving a prediction tag from said preliminary sketch by using a prediction algorithm and a hidden knowledge-based technique comprises:
extracting the characteristics of the preliminary image to obtain fine-grained characteristic information;
and obtaining a prediction label by adopting a prediction algorithm and an invisible knowledge technology according to the fine-grained characteristic information.
6. The full-flow image processing method according to claim 5, wherein said performing feature extraction on the preliminary image to obtain fine-grained feature information comprises:
performing feature extraction on the preliminary image by adopting a common feature extraction technology to obtain coarse-grained feature information;
and performing de-duplication and disambiguation on the coarse-grained characteristic information by adopting a characteristic difference analysis technology to obtain the fine-grained characteristic information.
7. The full-flow representation processing method of claim 1, wherein the forecast tags include a second case tag and a second inspector tag, the second case tag includes case attributes, person-specific attributes and case forecasts, and the second inspector tag includes inspector attributes, inspector handling capabilities and inspector auxiliary requirements;
the step of obtaining a prediction label by adopting a prediction algorithm and an invisible knowledge technology according to the fine-grained characteristic information comprises the following steps:
converting the first case label into the second case label by adopting a prediction algorithm and an invisible knowledge technology according to the fine-grained characteristic information;
and converting the first inspector label into the second inspector label by adopting a prediction algorithm and an invisible knowledgeable technology according to the fine-grained characteristic information.
8. A full-flow representation processing system, comprising:
the system comprises an original data acquisition module, a data processing module and a data processing module, wherein the original data acquisition module is used for acquiring original data in a service system, and the original data comprises structured data and unstructured data;
the fact data information acquisition module is used for preprocessing the original data to acquire fact data information;
the preliminary portrait drawing module is used for performing label modeling and identification by adopting a machine learning method according to the fact data information to finish drawing of a preliminary portrait, wherein the preliminary portrait comprises a case preliminary portrait and an inspector preliminary portrait;
the prediction label generation module is used for obtaining a prediction label by adopting a prediction algorithm and an invisible knowledgement technology according to the preliminary portrait;
and the prediction module is used for carrying out case division and risk investigation according to the prediction label.
9. An image processing apparatus for a full-flow image, comprising:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement a full-flow representation processing method as recited in any of claims 1-7.
10. A storage medium having stored therein a program executable by a processor, characterized in that: the processor executable program when executed by a processor is for implementing a full flow representation processing method as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210518532.9A CN115269710A (en) | 2022-05-13 | 2022-05-13 | Full-flow portrait processing method, system, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210518532.9A CN115269710A (en) | 2022-05-13 | 2022-05-13 | Full-flow portrait processing method, system, device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115269710A true CN115269710A (en) | 2022-11-01 |
Family
ID=83759150
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210518532.9A Pending CN115269710A (en) | 2022-05-13 | 2022-05-13 | Full-flow portrait processing method, system, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115269710A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190026761A1 (en) * | 2013-06-13 | 2019-01-24 | Flytxt B.V. | Method and system for automated detection, classification and prediction of multi-scale, multidimensional trends |
| CN114091866A (en) * | 2021-11-12 | 2022-02-25 | 万洲电气股份有限公司 | Intelligent optimization energy-saving system based on energy consumption convenient combined analysis |
| CN114417011A (en) * | 2022-01-20 | 2022-04-29 | 北京北大英华科技有限公司 | Inspection service portrait knowledge fusion method and device, electronic equipment and storage medium |
-
2022
- 2022-05-13 CN CN202210518532.9A patent/CN115269710A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190026761A1 (en) * | 2013-06-13 | 2019-01-24 | Flytxt B.V. | Method and system for automated detection, classification and prediction of multi-scale, multidimensional trends |
| CN114091866A (en) * | 2021-11-12 | 2022-02-25 | 万洲电气股份有限公司 | Intelligent optimization energy-saving system based on energy consumption convenient combined analysis |
| CN114417011A (en) * | 2022-01-20 | 2022-04-29 | 北京北大英华科技有限公司 | Inspection service portrait knowledge fusion method and device, electronic equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 刘宏志, 北京理工大学出版社 * |
| 姜红玉等: "基于流式计算的实时用户画像系统研究", 《计算机技术与发展》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sun et al. | Embracing textual data analytics in auditing with deep learning. | |
| Zhang et al. | Parallel or intersecting lines? Intelligent bibliometrics for investigating the involvement of data science in policy analysis | |
| Chakraborty et al. | Comparative sentiment analysis on a set of movie reviews using deep learning approach | |
| CN109933699A (en) | A kind of construction method and device of academic portrait model | |
| Kim et al. | Inter-cluster connectivity analysis for technology opportunity discovery | |
| Huang et al. | Identification of topic evolution: network analytics with piecewise linear representation and word embedding | |
| CN112287679A (en) | Structured extraction method and system for text information in scientific and technological project review | |
| Huang et al. | Research on multi-label user classification of social media based on ML-KNN algorithm | |
| Sharafat et al. | Data mining for smart legal systems | |
| Jayagopal et al. | Data management and big data analytics: Data management in digital economy | |
| Graf et al. | A risk analysis of file formats for preservation planning | |
| Kim et al. | Two-phase edge outlier detection method for technology opportunity discovery | |
| Chen et al. | Big data applications | |
| He et al. | Word embedding based document similarity for the inferring of penalty | |
| CN116795978A (en) | Complaint information processing method and device, electronic equipment and medium | |
| CN115269710A (en) | Full-flow portrait processing method, system, device and storage medium | |
| CN114722146A (en) | Supply chain asset checking method, device, equipment and medium based on artificial intelligence | |
| Janev | Chapter 1 Ecosystem of Big Data | |
| US20210216542A1 (en) | Systems and method for dynamically updating materiality distributions and classifications | |
| Dahl et al. | Applications of machine learning in tabular document digitisation | |
| KR20230059364A (en) | Public opinion poll system using language model and method thereof | |
| Srivastava et al. | Social media analytics: current trends and future prospects | |
| Di Martino et al. | Anomalous witnesses and registrations detection in the Italian justice system based on big data and machine learning techniques | |
| Mikova | Recent trends in technology mining approaches: quantitative analysis of GTM Conference Proceedings | |
| Sun | Accounting Information Systems outputs: XBRL, AI and in-memory technologies |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20221101 |