CN113033347A - Interactive risk assessment method for human behavior and scene analysis - Google Patents
Interactive risk assessment method for human behavior and scene analysis Download PDFInfo
- Publication number
- CN113033347A CN113033347A CN202110262263.XA CN202110262263A CN113033347A CN 113033347 A CN113033347 A CN 113033347A CN 202110262263 A CN202110262263 A CN 202110262263A CN 113033347 A CN113033347 A CN 113033347A
- Authority
- CN
- China
- Prior art keywords
- matching degree
- text
- feature
- behavior
- target
- 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 49
- 238000012502 risk assessment Methods 0.000 title claims abstract description 29
- 238000004458 analytical method Methods 0.000 title claims abstract description 20
- 230000002452 interceptive effect Effects 0.000 title claims abstract description 20
- 238000012360 testing method Methods 0.000 claims abstract description 15
- 230000006399 behavior Effects 0.000 claims description 87
- 230000004927 fusion Effects 0.000 claims description 33
- 230000015654 memory Effects 0.000 claims description 24
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000012706 support-vector machine Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 230000009471 action Effects 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 11
- 239000000463 material Substances 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000012854 evaluation process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000005452 bending Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/194—Calculation of difference between files
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/757—Matching configurations of points or features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/48—Matching video sequences
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/49—Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Software Systems (AREA)
- Evolutionary Biology (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Human Computer Interaction (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Technology Law (AREA)
- Medical Informatics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the application provides an interactive risk assessment method for human behavior and scene analysis, which relates to the technical field of risk assessment and comprises the steps of converting the reply voice of a tested person into a reply text; determining the text matching degree of the reply text and the reply reference text; separating the figure image and the background image in the field test video of the tested person to obtain a target figure image and a target background image; matching the feature points in the target background image with the feature points in the blacklist background image to obtain the feature point matching degree; calculating the target character image as the input of a pre-trained human behavior recognition model to obtain a behavior characteristic parameter corresponding to the target character image; and determining fraud risk parameters corresponding to the tested person according to the text matching degree, the feature point matching degree and the behavior feature parameters. The method provided by the embodiment of the application can be used for efficiently and accurately evaluating the fraud risk.
Description
Technical Field
The present document relates to the technical field of risk assessment, and in particular, to an interactive risk assessment method for human behavior and scene analysis.
Background
In order to ensure the authenticity of the material provided, fraud risk assessment of the user-provided material is often required to assess whether a risk of fraud exists, such as an authenticity assessment of personal certification material during a credit process.
At present, a common method for evaluating fraud risk is risk evaluation based on a scale, and due to the fact that the scale scheme is long in time and the scale evaluation method is too subjective, personal prejudice is easily added, and therefore evaluation efficiency and accuracy are low.
Therefore, how to provide an effective solution to improve the efficiency and accuracy of fraud risk assessment has become an urgent problem in the prior art.
Disclosure of Invention
The embodiment of the application provides an interactive risk assessment method for human behavior and scene analysis, which is used for solving the problems of low efficiency and accuracy of fraud risk assessment in the prior art.
In order to solve the above technical problem, the embodiment of the present application is implemented as follows:
the embodiment of the application provides an interactive risk assessment method for human behavior and scene analysis, which comprises the following steps:
converting the answer voice of the tested person to the specified question into an answer text, wherein the specified question is generated based on the background data provided by the tested person;
determining the text matching degree of the reply text and the reply reference text based on the Euclidean distance between the reply text and the reply reference text corresponding to the specified question;
separating the character image and the background image in the field test video of the tested person through a semantic segmentation model to obtain a target character image and a target background image;
extracting feature points in the target background image through a scale invariant feature transformation algorithm;
matching the feature points in the target background image with the feature points in a preset blacklist background image to obtain a feature point matching degree;
calculating the target character image as the input of a pre-trained human behavior recognition model to obtain a behavior characteristic parameter corresponding to the target character image;
and determining a fraud risk parameter corresponding to the tested person according to the text matching degree, the feature point matching degree and the behavior feature parameter, wherein the fraud risk parameter represents the probability of the tested person having fraud behaviors.
Optionally, the method further includes:
generating the specified question and the reply reference text corresponding to the specified question according to the background information;
converting the specified question into an audio file;
and playing the audio file so that the testee can answer to the questions in the audio file to obtain the answer voice.
Optionally, the determining fraud risk parameters corresponding to the testee according to the text matching degree, the feature point matching degree and the behavior feature parameters includes:
performing data fusion on the text matching degree, the feature point matching degree and the behavior feature parameters to obtain fusion data;
and classifying the fusion data through a support vector machine algorithm to obtain the fraud risk parameter.
Optionally, the performing data fusion on the text matching degree, the feature point matching degree, and the behavior feature parameter to obtain fusion data includes:
performing data fusion on a plurality of groups of feature data corresponding to different time periods and the text matching degree respectively to obtain a plurality of fusion data;
classifying the fusion data through a support vector machine algorithm to obtain the fraud risk parameter, wherein the classifying includes:
classifying the fusion data through a support vector machine algorithm to obtain the fraud risk parameters;
the set of feature data comprises feature point matching degree and behavior feature parameters corresponding to the same time period.
Optionally, the determining fraud risk parameters corresponding to the testee according to the text matching degree, the feature point matching degree and the behavior feature parameters includes:
performing data fusion on the text matching degree, the feature point matching degree and the behavior feature parameters to obtain fusion data;
and classifying the fusion data through an extreme gradient lifting algorithm to obtain the fraud risk parameter.
Optionally, the performing operation with the target person image as an input of a pre-trained human behavior recognition model to obtain a behavior feature parameter corresponding to the target person image includes:
and calculating the character image as the input of a pre-trained action recognition model or a long-short term memory network model to obtain the behavior characteristic parameters.
The technical scheme adopted by the embodiment of the application can achieve the following beneficial effects:
the method comprises the steps of obtaining a target character image and a target background image by determining the text matching degree of a reply text of a tested person and a reply reference text, separating the character image and the background image in a field test video to obtain the target character image and the target background image, determining the feature point matching degree of the target background image and a blacklist background image in the field test video, performing operation by taking the target character image as the input of a pre-trained human behavior recognition model to obtain a behavior feature parameter corresponding to the target character image, and determining a fraud risk parameter corresponding to the tested person according to the obtained text matching degree, the feature point matching degree and the behavior feature parameter. In the process, risk assessment is carried out by comprehensively considering parameters of different dimensions, so that fraud risk can be accurately assessed, and the whole assessment process is convenient and fast. Meanwhile, subjective bias of individuals cannot be integrated in the evaluation process, and the accuracy of evaluation is further guaranteed.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure without limiting the disclosure in any way. In the drawings:
fig. 1 is a schematic flowchart of an interactive risk assessment method for human behavior and scene analysis according to an embodiment of the present application.
Fig. 2 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Fig. 3 is a schematic structural diagram of an interactive risk assessment device for human behavior and scene analysis according to an embodiment of the present application.
Detailed Description
In order to make the purpose, technical solutions and advantages of this document more clear, the technical solutions of this document will be clearly and completely described below with reference to specific embodiments of this document and corresponding drawings. It is to be understood that the embodiments described are only a few embodiments of this document, and not all embodiments. All other embodiments obtained by a person skilled in the art without making creative efforts based on the embodiments in this document belong to the protection scope of this document.
In order to improve efficiency and accuracy of fraud risk assessment, the embodiment of the application provides an interactive risk assessment method for human behavior and scene analysis.
The following describes in detail an interactive risk assessment method for human behavior and scene analysis provided in the embodiments of the present application.
The interactive risk assessment method for human behavior and scene analysis provided by the embodiment of the application can be applied to a user terminal, and the user terminal can be, but is not limited to, a personal computer, a smart phone, a tablet computer, a laptop portable computer, a personal digital assistant and the like.
It is to be understood that the described execution body does not constitute a limitation of the embodiments of the present application.
Optionally, the flow of the interactive risk assessment method for human behavior and scene analysis is shown in fig. 1, and may include the following steps:
in step S101, a response voice of the subject to the specified question is converted into a response text.
Wherein the specified question is generated based on the background data provided by the subject. For example, the background data provided by the testee includes a home address, a work unit, a historical work unit, etc., and the specified question may be "where is your home address? "," where your work unit address is ", etc.
The user terminal has audio playing and collecting functions, and can convert the generated specified questions in the text format into audio files and play the audio files after the specified questions are generated, so that the testee can answer the questions in the audio files. When the testee answers, the user terminal acquires the answer voice of the testee and then converts the answer voice of the testee to the specified question into an answer text.
Step S102, determining the text matching degree of the reply text and the reply reference text based on the Euclidean distance between the reply text and the reply reference text corresponding to the specified question.
The user terminal also generates and specifies a question reply reference text according to the information recorded in the background material.
If false contents exist in the background material provided by the testee, probably because the false contents cannot be accurately memorized, the contents in the reply text changed when the specified question is answered and the contents in the reply reference text have large differences, so that the text matching degree of the reply text and the reply reference text can be determined by calculating the Euclidean distance between the reply text and the reply reference text corresponding to the specified question, so as to be convenient for subsequent fraud detection.
The larger the Euclidean distance between the reply text and the reply reference text is, the larger the difference between the reply text and the reply reference text is, and the lower the text matching degree between the reply text and the reply reference text is.
In the embodiment of the present application, the number of the reply texts and the reply reference texts may be multiple and are in one-to-one correspondence. Therefore, the obtained answer text and the answer reference text may have a plurality of text matching degrees.
And step S103, separating the character image and the background image in the field test video of the tested person through a semantic segmentation model to obtain a target character image and a target background image.
And step S104, extracting the feature points in the target background image through a scale-invariant feature transformation algorithm.
In the embodiment of the application, feature points in the target background image can be extracted by a Scale-invariant feature transform (SIFT) algorithm at a certain time interval (for example, 3 seconds) to obtain feature points in the target background image in different time periods.
And step S105, matching the feature points in the target background image with the feature points in the preset blacklist background image to obtain the feature point matching degree.
In the embodiment of the application, the background images are extracted in advance according to a plurality of test videos known to have fraud, and a plurality of blacklist background images are obtained. After the feature points in the target background image are extracted, the feature points in the target background image can be matched with the feature points in the plurality of blacklist background images to obtain the feature point matching degree.
The feature point matching degree may be a multi-dimensional vector, and the value of each dimension in the multi-dimensional vector represents the matching degree of the feature point in the target background image and the feature point in a blacklist background image. If 4 blacklist background images are assumed, matching the feature points in the target background image with the feature points in the 4 blacklist background images, and the obtained feature point matching degree can be a four-dimensional vector.
And step S106, calculating the target character image as the input of the human behavior recognition model trained in advance to obtain the behavior characteristic parameters corresponding to the target character image.
In the embodiment of the application, a human behavior recognition model for human behavior recognition is trained in advance, and the human behavior can be, but is not limited to, ear grasping, cheek supporting, communication with unrelated people, head bending, question answering and the like.
After obtaining the target person image, the user terminal may perform an operation using the target person image as an input of a human behavior recognition model trained in advance at intervals (the interval time is synchronized with the time of extracting the feature points in the target background image), so as to obtain a plurality of behavior feature parameters corresponding to the target person image. The behavior feature parameter may be a multi-dimensional vector, the value of each dimension in the multi-dimensional vector being used to indicate whether a certain behavior occurs. For example, the behavior recognized by the human behavior recognition model is 5-dimensional behaviors such as ear grasping, cheek supporting, communication with unrelated people, head bending, question answering and the like, and the obtained behavior characteristic parameters can be represented by a five-dimensional vector.
In the embodiment of the present application, the human behavior recognition model may be, but is not limited to, a Temporal Shift Module (TSM) model or a Long Short-Term Memory network (LSTM) model.
And S107, determining fraud risk parameters corresponding to the tested person according to the text matching degree, the feature point matching degree and the behavior feature parameters.
Wherein, the fraud risk parameter represents the probability of the fraud existing in the tested person.
Specifically, the text matching degree, the feature point matching degree and the behavior feature parameters can be subjected to data fusion to obtain fusion data, and then the fusion data is classified to obtain fraud risk parameters corresponding to the testee.
During fusion, the text matching degree can be quantized, and then vector fusion is performed on the quantized text matching degree, the feature point matching degree and the behavior feature parameters to obtain fusion data.
For example, if the matching degree of the text after quantization is (1, 0), the matching degree of one feature point is (0, 0, 1), and one behavior feature parameter is (1, 1, 1), the fused data obtained by vector fusion can be represented as (1, 0, 0, 0, 1, 1, 1).
Because a feature point matching degree and a behavior feature parameter can be determined at certain intervals, when classification is carried out, a plurality of groups of feature data corresponding to different time periods can be respectively subjected to data fusion with the text matching degree to obtain a plurality of fusion data, and then the fusion data are classified to obtain fraud risk parameters. The set of feature data comprises feature point matching degree and behavior feature parameters corresponding to the same time period.
The fraud risk parameter characterizes the probability of the presence of fraud by the test subject. Further, the user terminal may determine whether a fraud risk exists according to the probability of the fraud, and if the probability of the fraud existing in the tested person is greater than or equal to a set threshold, the fraud risk is considered to exist.
The user terminal may also classify multiple risk levels according to the probability of fraudulent activity. For example, a low risk may be classified when the probability of fraud being present is below 2%, a medium risk may be classified when the probability of fraud being present is 2% -5%, and a high risk may be classified when the probability of fraud being present is greater than 5%. Therefore, the method can be widely applied to various risk evaluations as a risk evaluation basis.
The interactive risk assessment method for human behavior and scene analysis, provided by the embodiment of the application, includes the steps of determining the text matching degree of a reply text and a reply reference text of a tested person, separating a character image and a background image in a field test video to obtain a target character image and a target background image, determining the feature point matching degree of the target background image and a blacklist background image in the field test video, performing operation by using the target character image as input of a pre-trained human behavior recognition model to obtain behavior feature parameters corresponding to the target character image, and determining fraud risk parameters corresponding to the tested person according to the obtained text matching degree, feature point matching degree and behavior feature parameters. In the process, risk assessment is carried out by comprehensively considering parameters of different dimensions, so that fraud risk can be accurately assessed, long-time waiting is not needed in the whole assessment process, convenience and rapidness are realized, and timeliness is good. Meanwhile, subjective bias of individuals cannot be integrated in the evaluation process, and the accuracy of evaluation is further guaranteed. In addition, whether fraud risks exist or not can be determined or a plurality of risk levels can be divided according to the probability of the fraud behaviors, so that the method can be widely applied to various risk evaluations as a risk evaluation basis.
Fig. 2 is a schematic structural diagram of an electronic device according to an embodiment of the present application. Referring to fig. 2, at a hardware level, the electronic device includes a processor, and optionally further includes an internal bus, a network interface, and a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory, such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.
The processor, the network interface, and the memory may be connected to each other via an internal bus, which may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 2, but this does not indicate only one bus or one type of bus.
And the memory is used for storing programs. In particular, the program may include program code comprising computer operating instructions. The memory may include both memory and non-volatile storage and provides instructions and data to the processor.
The processor reads a corresponding computer program from the nonvolatile memory to the memory and then runs the computer program to form the interactive risk assessment device for human behavior and scene analysis on a logic level. The processor is used for executing the program stored in the memory and is specifically used for executing the following operations:
converting the answer voice of the tested person to the specified question into an answer text, wherein the specified question is generated based on the background data provided by the tested person;
determining the text matching degree of the reply text and the reply reference text based on the Euclidean distance between the reply text and the reply reference text corresponding to the specified question;
separating the character image and the background image in the field test video of the tested person through a semantic segmentation model to obtain a target character image and a target background image;
extracting feature points in the target background image through a scale invariant feature transformation algorithm;
matching the feature points in the target background image with the feature points in a preset blacklist background image to obtain a feature point matching degree;
calculating the target character image as the input of a pre-trained human behavior recognition model to obtain a behavior characteristic parameter corresponding to the target character image;
and determining a fraud risk parameter corresponding to the tested person according to the text matching degree, the feature point matching degree and the behavior feature parameter, wherein the fraud risk parameter represents the probability of the tested person having fraud behaviors.
The method executed by the interactive risk assessment device for human behavior and scene analysis disclosed in the embodiment of fig. 2 of the present application may be applied to or implemented by a processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps and logic blocks disclosed in one or more embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with one or more embodiments of the present application may be embodied directly in the hardware decoding processor, or in a combination of the hardware and software modules included in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor.
The electronic device may further execute the method in the embodiment shown in fig. 1, and implement the functions of the interactive risk assessment apparatus for human behavior and scene analysis in the embodiment shown in fig. 1, which are not described herein again in this application embodiment.
Of course, besides the software implementation, the electronic device of the present application does not exclude other implementations, such as a logic device or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and may also be hardware or a logic device.
Embodiments of the present application also provide a computer-readable storage medium storing one or more programs, where the one or more programs include instructions, which when executed by a portable electronic device including a plurality of application programs, enable the portable electronic device to perform the method of the embodiment shown in fig. 1, and are specifically configured to:
converting the answer voice of the tested person to the specified question into an answer text, wherein the specified question is generated based on the background data provided by the tested person;
determining the text matching degree of the reply text and the reply reference text based on the Euclidean distance between the reply text and the reply reference text corresponding to the specified question;
separating the character image and the background image in the field test video of the tested person through a semantic segmentation model to obtain a target character image and a target background image;
extracting feature points in the target background image through a scale invariant feature transformation algorithm;
matching the feature points in the target background image with the feature points in a preset blacklist background image to obtain a feature point matching degree;
calculating the target character image as the input of a pre-trained human behavior recognition model to obtain a behavior characteristic parameter corresponding to the target character image;
and determining a fraud risk parameter corresponding to the tested person according to the text matching degree, the feature point matching degree and the behavior feature parameter, wherein the fraud risk parameter represents the probability of the tested person having fraud behaviors.
Fig. 3 is a schematic structural diagram of an interactive risk assessment device for human behavior and scene analysis according to an embodiment of the present application. Referring to fig. 3, in one software implementation, the interactive risk assessment device for human behavior and scene analysis may include:
the text conversion module is used for converting the answer voice of the tested person to the specified question into an answer text, wherein the specified question is generated based on the background data provided by the tested person;
a first determining module, configured to determine a text matching degree between the reply text and a reply reference text corresponding to the specified question based on a euclidean distance between the reply text and the reply reference text;
the separation module is used for separating the character image and the background image in the field test video of the tested person through a semantic segmentation model to obtain a target character image and a target background image;
the extraction module is used for extracting the feature points in the target background image through a scale-invariant feature transformation algorithm;
the matching module is used for matching the feature points in the target background image with the feature points in a preset blacklist background image to obtain the feature point matching degree;
the operation module is used for performing operation by taking the target character image as the input of a human behavior recognition model trained in advance to obtain behavior characteristic parameters corresponding to the target character image;
and the second determining module is used for determining a fraud risk parameter corresponding to the tested person according to the text matching degree, the feature point matching degree and the behavior feature parameter, wherein the fraud risk parameter represents the probability of the tested person having fraud behaviors.
Optionally, the interactive risk assessment apparatus for human behavior and scene analysis further includes:
the generating module is used for generating the specified question and the reply reference text corresponding to the specified question according to the background information;
the audio conversion module is used for converting the specified question into an audio file;
and the playing module is used for playing the audio file so that the testee can answer the questions in the audio file to obtain the answer voice.
According to the technical scheme provided by the embodiment of the application, the text matching degree of the answer text and the answer reference text of the tested person is determined, the character image and the background image in the field test video are separated to obtain the target character image and the target background image, the feature point matching degree of the target background image and the blacklist background image in the field test video is determined, the target character image is used as the input of a pre-trained human behavior recognition model to be operated to obtain the behavior feature parameter corresponding to the target character image, and then the fraud risk parameter corresponding to the tested person is determined according to the obtained text matching degree, the feature point matching degree and the behavior feature parameter. In the process, risk assessment is carried out by comprehensively considering parameters of different dimensions, so that fraud risk can be accurately assessed, long-time waiting is not needed in the whole assessment process, convenience and rapidness are realized, and timeliness is good. Meanwhile, subjective bias of individuals cannot be integrated in the evaluation process, and the accuracy of evaluation is further guaranteed. In addition, whether fraud risks exist or not can be determined or a plurality of risk levels can be divided according to the probability of the fraud behaviors, so that the method can be widely applied to various risk evaluations as a risk evaluation basis.
The foregoing description of specific embodiments of the present application has been presented. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
In short, the above description is only a preferred embodiment of the present application, and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
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 like elements in a process, method, article, or apparatus that comprises the element.
The embodiments in the present application are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
Claims (6)
1. An interactive risk assessment method for human behavior and scene analysis is characterized by comprising the following steps:
converting the answer voice of the tested person to the specified question into an answer text, wherein the specified question is generated based on the background data provided by the tested person;
determining the text matching degree of the reply text and the reply reference text based on the Euclidean distance between the reply text and the reply reference text corresponding to the specified question;
separating the character image and the background image in the field test video of the tested person through a semantic segmentation model to obtain a target character image and a target background image;
extracting feature points in the target background image through a scale invariant feature transformation algorithm;
matching the feature points in the target background image with the feature points in a preset blacklist background image to obtain a feature point matching degree;
calculating the target character image as the input of a pre-trained human behavior recognition model to obtain a behavior characteristic parameter corresponding to the target character image;
and determining a fraud risk parameter corresponding to the tested person according to the text matching degree, the feature point matching degree and the behavior feature parameter, wherein the fraud risk parameter represents the probability of the tested person having fraud behaviors.
2. The method of claim 1, further comprising:
generating the specified question and the reply reference text corresponding to the specified question according to the background information;
converting the specified question into an audio file;
and playing the audio file so that the testee can answer to the questions in the audio file to obtain the answer voice.
3. The method according to claim 1, wherein the determining fraud risk parameters corresponding to the testee according to the text matching degree, the feature point matching degree and the behavior feature parameters comprises:
performing data fusion on the text matching degree, the feature point matching degree and the behavior feature parameters to obtain fusion data;
and classifying the fusion data through a support vector machine algorithm to obtain the fraud risk parameter.
4. The method according to claim 3, wherein the performing data fusion on the text matching degree, the feature point matching degree, and the behavior feature parameter to obtain fused data comprises:
performing data fusion on a plurality of groups of feature data corresponding to different time periods and the text matching degree respectively to obtain a plurality of fusion data;
classifying the fusion data through a support vector machine algorithm to obtain the fraud risk parameter, wherein the classifying includes:
classifying the fusion data through a support vector machine algorithm to obtain the fraud risk parameters;
the set of feature data comprises feature point matching degree and behavior feature parameters corresponding to the same time period.
5. The method according to claim 1, wherein the determining fraud risk parameters corresponding to the testee according to the text matching degree, the feature point matching degree and the behavior feature parameters comprises:
performing data fusion on the text matching degree, the feature point matching degree and the behavior feature parameters to obtain fusion data;
and classifying the fusion data through an extreme gradient lifting algorithm to obtain the fraud risk parameter.
6. The method of claim 1, wherein the computing the target person image as an input to a pre-trained human behavior recognition model to obtain behavior feature parameters corresponding to the target person image comprises:
and calculating the character image as the input of a pre-trained action recognition model or a long-short term memory network model to obtain the behavior characteristic parameters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110262263.XA CN113033347A (en) | 2021-03-10 | 2021-03-10 | Interactive risk assessment method for human behavior and scene analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110262263.XA CN113033347A (en) | 2021-03-10 | 2021-03-10 | Interactive risk assessment method for human behavior and scene analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113033347A true CN113033347A (en) | 2021-06-25 |
Family
ID=76469395
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110262263.XA Pending CN113033347A (en) | 2021-03-10 | 2021-03-10 | Interactive risk assessment method for human behavior and scene analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113033347A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180204111A1 (en) * | 2013-02-28 | 2018-07-19 | Z Advanced Computing, Inc. | System and Method for Extremely Efficient Image and Pattern Recognition and Artificial Intelligence Platform |
| CN109509080A (en) * | 2018-10-12 | 2019-03-22 | 深圳壹账通智能科技有限公司 | Supply chain finance business processing method, device, computer equipment and storage medium |
| CN109543516A (en) * | 2018-10-16 | 2019-03-29 | 深圳壹账通智能科技有限公司 | Signing intention judgment method, device, computer equipment and storage medium |
| CN110020770A (en) * | 2017-12-27 | 2019-07-16 | 埃森哲环球解决方案有限公司 | Risk and information management based on artificial intelligence |
| WO2020107756A1 (en) * | 2018-11-27 | 2020-06-04 | 深圳前海微众银行股份有限公司 | Credit anti-fraud method, system, device and computer-readable storage medium |
| CN111339940A (en) * | 2020-02-26 | 2020-06-26 | 中国工商银行股份有限公司 | Video risk identification method and device |
| WO2020191382A1 (en) * | 2019-03-21 | 2020-09-24 | Warner Bros. Entertainment Inc. | Automatic media production risk assessment using electronic dataset |
| CN111861240A (en) * | 2020-07-27 | 2020-10-30 | 深圳前海微众银行股份有限公司 | Suspicious user identification method, device, equipment and readable storage medium |
| CN111860369A (en) * | 2020-07-24 | 2020-10-30 | 河南中原消费金融股份有限公司 | Fraud identification method and device and storage medium |
| CN112001785A (en) * | 2020-07-21 | 2020-11-27 | 小花网络科技(深圳)有限公司 | Network credit fraud identification method and system based on image identification |
-
2021
- 2021-03-10 CN CN202110262263.XA patent/CN113033347A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180204111A1 (en) * | 2013-02-28 | 2018-07-19 | Z Advanced Computing, Inc. | System and Method for Extremely Efficient Image and Pattern Recognition and Artificial Intelligence Platform |
| CN110020770A (en) * | 2017-12-27 | 2019-07-16 | 埃森哲环球解决方案有限公司 | Risk and information management based on artificial intelligence |
| CN109509080A (en) * | 2018-10-12 | 2019-03-22 | 深圳壹账通智能科技有限公司 | Supply chain finance business processing method, device, computer equipment and storage medium |
| CN109543516A (en) * | 2018-10-16 | 2019-03-29 | 深圳壹账通智能科技有限公司 | Signing intention judgment method, device, computer equipment and storage medium |
| WO2020107756A1 (en) * | 2018-11-27 | 2020-06-04 | 深圳前海微众银行股份有限公司 | Credit anti-fraud method, system, device and computer-readable storage medium |
| WO2020191382A1 (en) * | 2019-03-21 | 2020-09-24 | Warner Bros. Entertainment Inc. | Automatic media production risk assessment using electronic dataset |
| CN111339940A (en) * | 2020-02-26 | 2020-06-26 | 中国工商银行股份有限公司 | Video risk identification method and device |
| CN112001785A (en) * | 2020-07-21 | 2020-11-27 | 小花网络科技(深圳)有限公司 | Network credit fraud identification method and system based on image identification |
| CN111860369A (en) * | 2020-07-24 | 2020-10-30 | 河南中原消费金融股份有限公司 | Fraud identification method and device and storage medium |
| CN111861240A (en) * | 2020-07-27 | 2020-10-30 | 深圳前海微众银行股份有限公司 | Suspicious user identification method, device, equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109544166B (en) | Risk identification method and risk identification device | |
| CN108763952B (en) | Data classification method and device and electronic equipment | |
| CN110826006B (en) | Abnormal collection behavior identification method and device based on privacy data protection | |
| CN111881707B (en) | Image reproduction detection method, identity verification method, model training method and device | |
| CN108399482B (en) | Contract evaluation method and device and electronic equipment | |
| CN110072140B (en) | Video information prompting method, device, equipment and storage medium | |
| CN111401238B (en) | Method and device for detecting character close-up fragments in video | |
| WO2024093403A1 (en) | Intent recognition method and apparatus, and device and readable storage medium | |
| CN112488138A (en) | User category identification method and device, electronic equipment and storage medium | |
| CN111353514A (en) | Model training method, image recognition method, device and terminal equipment | |
| CN116108150A (en) | Intelligent question-answering method, device, system and electronic equipment | |
| CN117409419A (en) | Image detection method, device and storage medium | |
| CN110334936B (en) | Method, device and equipment for constructing credit qualification scoring model | |
| CN114091551A (en) | Pornographic image identification method and device, electronic equipment and storage medium | |
| CN112908315A (en) | Question-answer intention judgment method based on voice characteristics and voice recognition | |
| CN113129298A (en) | Definition recognition method of text image | |
| CN113052064A (en) | Attention detection method based on face orientation, facial expression and pupil tracking | |
| CN113283978B (en) | Financial risk assessment method based on biological basis, behavioral characteristics and business characteristics | |
| CN110047473B (en) | Man-machine cooperative interaction method and system | |
| CN112149678A (en) | Character recognition method and device for special language and recognition model training method and device | |
| CN117496984A (en) | Interaction method, device and equipment of target object and readable storage medium | |
| CN113033347A (en) | Interactive risk assessment method for human behavior and scene analysis | |
| CN114842849B (en) | Voice dialogue detection method and device | |
| CN115019788A (en) | Voice interaction method, system, terminal equipment and storage medium | |
| CN113284027A (en) | Method for training group recognition model, and method and device for recognizing abnormal group |
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 |