CN117521051A - Verification problem processing method, device, computer equipment and storage medium - Google Patents
Verification problem processing method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN117521051A CN117521051A CN202311567242.4A CN202311567242A CN117521051A CN 117521051 A CN117521051 A CN 117521051A CN 202311567242 A CN202311567242 A CN 202311567242A CN 117521051 A CN117521051 A CN 117521051A
- Authority
- CN
- China
- Prior art keywords
- verification
- analysis model
- answer
- question
- type
- 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
- 238000012795 verification Methods 0.000 title claims abstract description 627
- 238000003672 processing method Methods 0.000 title abstract description 13
- 238000004458 analytical method Methods 0.000 claims abstract description 283
- 238000012545 processing Methods 0.000 claims abstract description 92
- 238000000034 method Methods 0.000 claims abstract description 49
- 238000004590 computer program Methods 0.000 claims abstract description 26
- 238000012549 training Methods 0.000 claims description 23
- 230000001960 triggered effect Effects 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 abstract description 12
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000012015 optical character recognition Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 241000590419 Polygonia interrogationis Species 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004801 process automation Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/45—Structures or tools for the administration of authentication
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/19—Recognition using electronic means
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Hardware Design (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present application relates to a verification problem processing method, apparatus, computer device, storage medium and computer program product, which can be used in the field of artificial intelligence technology, and also in the field of financial science and technology or other related fields. The method comprises the following steps: identifying the verification problem image of the financial system to obtain a verification problem in the verification problem image; selecting a verification problem analysis model corresponding to the problem type of the verification problem from a plurality of verification problem analysis models as a target verification problem analysis model; analyzing the verification questions through a target verification question analysis model to obtain verification answers of the verification questions; and according to the verification answer, carrying out answer processing on the verification question. The method can improve the efficiency of verification problem processing.
Description
Technical Field
The present application relates to the field of artificial intelligence, and in particular, to a method, an apparatus, a computer device, a storage medium, and a computer program product for processing verification problems.
Background
With the development of computer technology, automation technology is widely applied in various fields, and the working efficiency is effectively improved. However, in the process of logging in a website, verification problems that require manual participation are often encountered, which limits the full automation of the workflow. Therefore, how to efficiently deal with the verification problem has become an important research direction.
The conventional technology generally performs verification problem processing by a manual processing mode; however, this method requires a lot of manual processing time to perform verification problem processing, resulting in low efficiency of verification problem processing.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a verification problem processing method, apparatus, computer device, computer-readable storage medium, and computer program product that can improve the efficiency of verification problem processing.
In a first aspect, the present application provides a verification problem handling method. The method comprises the following steps:
identifying verification problem images of a financial system to obtain verification problems in the verification problem images;
selecting a verification problem analysis model corresponding to the problem type of the verification problem from a plurality of verification problem analysis models as a target verification problem analysis model;
analyzing the verification questions through the target verification question analysis model to obtain verification answers of the verification questions;
and according to the verification answer, carrying out answer processing on the verification question.
In one embodiment, before selecting a verification problem analysis model corresponding to a problem type of the verification problem from a plurality of verification problem analysis models, the method further includes:
Identifying the verification problem to obtain text information in the verification problem;
determining characteristic text information in the text information;
and determining the problem type of the verification problem according to the characteristic text information.
In one embodiment, the determining, according to the feature text information, the question type of the verification question includes:
under the condition that the characteristic text information represents digital information and operator information, confirming that the problem type of the verification problem is an operation problem type;
confirming that the question type is a judgment question type under the condition that the characteristic text information represents selection information, color information or graphic information;
and confirming that the question type is a coordinate question type under the condition that the characteristic text information represents click information.
In one embodiment, the plurality of verification problem resolution models at least includes an operation problem resolution model, a judgment problem resolution model, and a coordinate problem resolution model;
the selecting, from the plurality of verification problem analysis models, a verification problem analysis model corresponding to a problem type of the verification problem as a target verification problem analysis model includes:
When the problem type is the operation problem type, selecting the operation problem analysis model from the plurality of verification problem analysis models as the target verification problem analysis model; the operation problem analysis model is used for analyzing and processing the verification problem of the operation problem type;
when the problem type is the judging problem type, selecting the judging problem analysis model from the plurality of verification problem analysis models as the target verification problem analysis model; the judgment problem analysis model is used for analyzing and processing the verification problem of the judgment problem type;
selecting the coordinate problem analysis model from the plurality of verification problem analysis models as the target verification problem analysis model under the condition that the problem type is the coordinate problem type; the coordinate problem analysis model is used for analyzing and processing the verification problem of the coordinate problem type.
In one embodiment, the analyzing the verification question through the target verification question analysis model to obtain a verification answer of the verification question includes:
Under the condition that the target verification problem analysis model is the operation problem analysis model, performing operation analysis processing on the verification problem through the operation problem analysis model to obtain an operation result of the verification problem, wherein the operation result is used as a verification answer of the verification problem;
under the condition that the target verification problem analysis model is the judgment problem analysis model, judging and analyzing the verification problem through the judgment problem analysis model to obtain a judgment result of the verification problem, wherein the judgment result is used as a verification answer of the verification problem;
and under the condition that the target verification problem analysis model is the coordinate problem analysis model, carrying out coordinate analysis processing on the verification problem through the coordinate problem analysis model to obtain a coordinate result of the verification problem, and taking the coordinate result as a verification answer of the verification problem.
In one embodiment, the answer processing for the verification question according to the verification answer includes:
executing an answer operation corresponding to the verification answer in a verification answer operation area of the verification question;
after the answer processing is performed on the verification questions according to the verification answers, the method further comprises the following steps:
In case the answer operation verifies, a login instruction is triggered.
In one embodiment, the method further comprises:
acquiring a sample verification question and a real verification answer of the sample verification question;
analyzing the sample verification questions through a to-be-trained verification question analysis model to obtain prediction verification answers of the sample verification questions;
and training the verification problem analysis model to be trained according to the difference between the prediction verification answer and the real verification answer to obtain the verification problem analysis model.
In a second aspect, the present application also provides an authentication problem handling apparatus. The device comprises:
the image recognition module is used for recognizing the verification problem image of the financial system to obtain the verification problem in the verification problem image;
the model selecting module is used for selecting a verification problem analysis model corresponding to the problem type of the verification problem from a plurality of verification problem analysis models, and taking the verification problem analysis model as a target verification problem analysis model;
the problem analysis module is used for analyzing the verification problem through the target verification problem analysis model to obtain a verification answer of the verification problem;
And the question processing module is used for carrying out answer processing on the verification questions according to the verification answers.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:
identifying verification problem images of a financial system to obtain verification problems in the verification problem images;
selecting a verification problem analysis model corresponding to the problem type of the verification problem from a plurality of verification problem analysis models as a target verification problem analysis model;
analyzing the verification questions through the target verification question analysis model to obtain verification answers of the verification questions;
and according to the verification answer, carrying out answer processing on the verification question.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
identifying verification problem images of a financial system to obtain verification problems in the verification problem images;
Selecting a verification problem analysis model corresponding to the problem type of the verification problem from a plurality of verification problem analysis models as a target verification problem analysis model;
analyzing the verification questions through the target verification question analysis model to obtain verification answers of the verification questions;
and according to the verification answer, carrying out answer processing on the verification question.
In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of:
identifying verification problem images of a financial system to obtain verification problems in the verification problem images;
selecting a verification problem analysis model corresponding to the problem type of the verification problem from a plurality of verification problem analysis models as a target verification problem analysis model;
analyzing the verification questions through the target verification question analysis model to obtain verification answers of the verification questions;
and according to the verification answer, carrying out answer processing on the verification question.
The verification problem processing method, the device, the computer equipment, the storage medium and the computer program product are used for identifying the verification problem image of the financial system to obtain the verification problem in the verification problem image; selecting a verification problem analysis model corresponding to the problem type of the verification problem from a plurality of verification problem analysis models as a target verification problem analysis model; analyzing the verification questions through the target verification question analysis model to obtain verification answers of the verification questions; and according to the verification answer, carrying out answer processing on the verification question. The method comprises the steps of identifying verification problem images of a financial system to obtain verification problems, selecting a target verification problem analysis model corresponding to the verification problem type from a plurality of verification problem analysis models, analyzing the verification problems by using the target verification problem analysis model to obtain verification answers, and finally answering the verification problems according to the verification answers; through the steps, an automatic process from question identification to answer is realized, and the efficiency and accuracy of question verification processing are improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the drawings that are required to be used in the embodiments or the related technical descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to the drawings without inventive effort for a person having ordinary skill in the art.
FIG. 1 is a flow diagram of a verification problem processing method in one embodiment;
FIG. 2 is a flow diagram of the steps for determining a problem type in one embodiment;
FIG. 3 is a schematic flow diagram of model training in one embodiment;
FIG. 4 is a flow chart of a verification problem processing method in another embodiment;
FIG. 5 is a schematic flow chart of model training in another embodiment;
FIG. 6 is a block diagram of an apparatus for handling verification problems in one embodiment;
fig. 7 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use, and processing of the related data are required to meet the related regulations.
In an exemplary embodiment, as shown in fig. 1, there is provided a verification problem processing method, and this embodiment is illustrated by applying the method to a terminal; it will be appreciated that the method may also be applied to a server, and may also be applied to a system comprising a terminal and a server, and implemented by interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers and the like; the server may be implemented as a stand-alone server or as a server cluster composed of a plurality of servers. In this embodiment, the method includes the steps of:
step S101, identifying the verification problem image of the financial system to obtain the verification problem in the verification problem image.
Wherein the financial system may be a financial institution's system.
The verification problem image can be various verification code pictures appearing in a financial system login or business processing page.
The verification problem may be specific problem content extracted from the verification code picture through an identification technology, such as an arithmetic title.
Optionally, the terminal recognizes a verification image (verification code image) in the financial system using an OCR (optical character recognition/word recognition) model, converts the word content in the image into text data processable by a computer, and obtains a verification problem in the verification problem image.
Step S102, selecting a verification problem analysis model corresponding to the problem type of the verification problem from a plurality of verification problem analysis models as a target verification problem analysis model.
The plurality of verification problem analysis models can be preset and trained problem analysis model libraries of different types, and can comprise an arithmetic problem model, a judgment problem model and the like.
The target verification problem analysis model can be a specific analysis model which is matched and selected to be most suitable from an analysis model library according to the current verification problem type.
Optionally, the terminal selects a verification problem analysis model matched with the current verification problem type from a plurality of verification problem analysis models designed in advance according to the verification problem type of the identified verification problem, and the verification problem analysis model is used as a target verification problem analysis model.
Step S103, analyzing the verification questions through a target verification question analysis model to obtain verification answers of the verification questions.
The analysis processing may be processing of analyzing and calculating the verification problem through a target verification problem analysis model, extracting key information, and obtaining an answer to the problem.
The verification answer may be a correct answer of the current verification question obtained after calculation through the analytical model.
Optionally, the terminal uses the selected target verification problem analysis model to conduct deep analysis processing on the verification problem, extracts key information and conducts logic reasoning calculation, so that a correct answer of the verification problem is obtained and is used as a verification answer of the verification problem.
Step S104, according to the verification answer, answer processing is carried out on the verification question.
The answer processing may be to provide a response result, such as filling out an answer or selecting an answer item, for the verification question according to the verification answer.
Optionally, the terminal provides an answer to the verification question according to the obtained verification answer, for example, automatically fills out the answer or selects an answer item, etc., thereby completing the answer processing to the verification question.
In the verification problem processing method, verification problem images of the financial system are identified, and verification problems in the verification problem images are obtained; selecting a verification problem analysis model corresponding to the problem type of the verification problem from a plurality of verification problem analysis models as a target verification problem analysis model; analyzing the verification questions through a target verification question analysis model to obtain verification answers of the verification questions; and according to the verification answer, carrying out answer processing on the verification question. The method comprises the steps of identifying verification problem images of a financial system to obtain verification problems, selecting a target verification problem analysis model corresponding to the verification problem type from a plurality of verification problem analysis models, analyzing the verification problems by using the target verification problem analysis model to obtain verification answers, and finally answering the verification problems according to the verification answers; through the steps, an automatic process from question identification to answer is realized, and the efficiency and accuracy of question verification processing are improved.
In an exemplary embodiment, as shown in fig. 2, the step S102, before selecting a verification problem analysis model corresponding to a problem type of a verification problem from a plurality of verification problem analysis models, further includes a step of determining a problem type of the verification problem as a target verification problem analysis model, specifically including the following:
step S201, identifying the verification problem to obtain text information in the verification problem;
step S202, determining characteristic text information in the text information;
step S203, determining the problem type of the verification problem according to the characteristic text information.
The text information may be text content extracted from the verification problem by recognition techniques.
The feature text information may be a keyword, such as an arithmetic operation symbol, a selection keyword, or the like, which can reflect the type of the question in the text information.
The question type may be a question type to which the verification question determined according to the feature text information belongs, such as an arithmetic question, a selection question, and the like.
Optionally, the terminal identifies the verification problem in the verification problem image by using an OCR technology (model), and converts text content in the image into text data which can be processed by a computer, so as to obtain text information in the verification problem; identifying characteristic text information in the text information by using Natural Language Processing (NLP) technology or regular expression and other methods, such as identifying arithmetic operation symbols, selecting keywords and the like; and determining the specific problem type of the verification problem by using a preset problem type classification algorithm or model according to the characteristic text information.
According to the technical scheme provided by the embodiment, the problem type of the verification problem is determined through the characteristic text information in the text information, so that the problem type of the verification problem is effectively and accurately determined, and the efficiency and the accuracy of verification problem processing are improved.
In an exemplary embodiment, in the step, the problem type of the verification problem is determined according to the feature text information, and specifically includes the following contents: under the condition that the characteristic text information represents digital information and operator information, confirming that the problem type of the verification problem is an operation problem type; confirming that the question type is a judgment question type under the condition that the characteristic text information represents selection information, color information or graphic information; in the case where the feature text information indicates click information, the question type is confirmed to be a coordinate question type.
The digital information may be text representing a number, such as "1", "5", etc., in the characteristic text information.
Wherein the operator information may be text representing a numerical operator in the characteristic text information, such as "+", "-", etc.
The selection information may be text representing a selection title in the feature text information, such as a keyword "select" or the like.
The color information may be text representing a color in the characteristic text information, such as a keyword of "color", "red", or "green", etc.
The graphic information may be text representing graphics in the feature text information, such as keywords "graphics", "triangle", or "circle", etc.
The click information may be text representing a click operation in the feature text information, such as a keyword "click" or the like.
The question type may be a specific classification of the verification question determined according to the feature text information, and may include an operation question type, a determination question type, and a coordinate question type.
Optionally, the terminal performs judgment processing of the problem type of the verification problem according to the feature text information, and judges whether the feature text information contains digital information, operator information, selection information, color information, graphic information or click information; under the condition that the characteristic text information is identified to contain digital information and operator information, confirming that the problem type of the verification problem is an operation problem type; under the condition that the characteristic text information is identified to contain selection information, color information or graphic information, confirming that the problem type is a judgment problem type; and when the click information is identified to be contained in the characteristic text information, confirming that the problem type is a coordinate problem type.
According to the technical scheme provided by the embodiment, the problem type of the verification problem is determined to be the operation problem type, the judgment problem type or the coordinate problem type according to the characteristic text information, so that the problem type of the verification problem can be determined efficiently and accurately, and the efficiency and the accuracy of verification problem processing can be improved.
In an exemplary embodiment, in step S102, a verification problem analysis model corresponding to a problem type of a verification problem is selected from a plurality of verification problem analysis models as a target verification problem analysis model, and specifically includes the following: under the condition that the problem type is an operation problem type, selecting an operation problem analysis model from a plurality of verification problem analysis models as a target verification problem analysis model; the operation problem analysis model is used for analyzing and processing the verification problem of the operation problem type; under the condition that the problem type is the judgment problem type, selecting a judgment problem analysis model from a plurality of verification problem analysis models as a target verification problem analysis model; the judgment problem analysis model is used for analyzing and processing verification problems of judgment problem types; under the condition that the problem type is a coordinate problem type, selecting a coordinate problem analysis model from a plurality of verification problem analysis models as a target verification problem analysis model; the coordinate problem analysis model is used for analyzing and processing verification problems of the coordinate problem types.
The plurality of verification problem analysis models at least comprise an operation problem analysis model, a judgment problem analysis model and a coordinate problem analysis model.
The plurality of verification problem analysis models can be a set of preset and trained problem analysis models used for analyzing verification code problems of different types.
The operation problem analysis model can be a model special for analyzing operation type verification code problems, and can be used for identifying and calculating numbers, operation symbols and the like to obtain answers.
The judgment problem analysis model can be a model special for analyzing judgment type verification code problems, can identify and judge selection items, and selects correct answers.
The coordinate problem analysis model can be a model special for analyzing the coordinate type verification code problem, and can identify and position a graph area to be clicked to obtain a coordinate answer.
Optionally, the terminal judges the problem type of the verification problem; under the condition that the problem type is judged to be the operation problem type, selecting an operation problem analysis model from a plurality of verification problem analysis models as a target verification problem analysis model; under the condition that the problem type is judged to be the judging problem type, selecting a judging problem analysis model from a plurality of verification problem analysis models as a target verification problem analysis model; and under the condition that the problem type is judged to be the coordinate problem type, selecting a coordinate problem analysis model from a plurality of verification problem analysis models as a target verification problem analysis model.
According to the technical scheme provided by the embodiment, the target verification problem analysis model is determined to be the operation problem analysis model, the judgment problem analysis model or the coordinate problem analysis model according to the problem type of the verification problem, so that the target verification problem analysis model can be effectively and accurately determined, and the efficiency and the accuracy of verification problem processing can be improved.
In an exemplary embodiment, in step S103, the verification problem is parsed by the target verification problem parsing model to obtain a verification answer of the verification problem, which specifically includes the following contents: under the condition that the target verification problem analysis model is an operation problem analysis model, performing operation analysis processing on the verification problem through the operation problem analysis model to obtain an operation result of the verification problem, wherein the operation result is used as a verification answer of the verification problem; under the condition that the target verification problem analysis model is a judgment problem analysis model, judging and analyzing the verification problem through the judgment problem analysis model to obtain a judgment result of the verification problem, wherein the judgment result is used as a verification answer of the verification problem; and under the condition that the target verification problem analysis model is a coordinate problem analysis model, carrying out coordinate analysis processing on the verification problem through the coordinate problem analysis model to obtain a coordinate result of the verification problem, and taking the coordinate result as a verification answer of the verification problem.
The operation analysis processing may be processing for identifying and calculating a problem by using an operation problem analysis model.
The judgment analysis processing may be processing for identifying and judging the problem by judging the problem analysis model.
The coordinate analysis process may be a process of identifying and locating a problem by using a coordinate problem analysis model.
The verification answer of the verification question can be a question answer obtained after the question analysis model analysis processing, and can be an operation result, a judgment result or a coordinate result, and the answer can be used as an answer for finally answering the verification code question.
Optionally, the terminal judges which problem analysis model the target verification problem analysis model is; under the condition that the target verification problem analysis model is an operation problem analysis model, performing operation analysis processing on the verification problem through the operation problem analysis model to obtain an operation result of the verification problem output by the operation problem analysis model, and taking the operation result as a verification answer of the verification problem; when the target verification problem analysis model is a judgment problem analysis model, carrying out judgment analysis processing on the verification problem through the judgment problem analysis model to obtain a judgment result of the verification problem output by the judgment problem analysis model, and taking the judgment result as a verification answer of the verification problem; and under the condition that the target verification problem analysis model is a coordinate problem analysis model, carrying out coordinate analysis processing on the verification problem through the coordinate problem analysis model to obtain a coordinate result of the verification problem output by the coordinate problem analysis model, and taking the coordinate result as a verification answer of the verification problem.
According to the technical scheme provided by the embodiment, the verification problem is correspondingly analyzed through the operation problem analysis model, the judgment problem analysis model or the coordinate problem analysis model, so that an accurate verification answer is obtained, and the accuracy of verification problem processing is improved.
In an exemplary embodiment, in step S104, according to the verification answer, an answer process is performed on the verification question, which specifically includes the following: executing an answer operation corresponding to the verification answer in a verification answer operation area of the verification question; the step S104 further includes a step of triggering a login instruction after the answer processing is performed on the verification question according to the verification answer, and specifically includes the following steps: in case the answer operation verifies, a login instruction is triggered.
The verification answer operation area of the verification question may be an area, such as a gap-filling or clicking area, where an answer needs to be input in the verification code question interface.
The answer operation may be an operation performed in the verification answer operation area according to the verification answer, such as filling in the answer or clicking on a position in the image.
The login instruction may be an automatically triggered login instruction after successfully answering the verification code question, for example, the login instruction may be to click a "login" button to complete automatic login.
Optionally, after determining the verification answer, the terminal automatically performs a corresponding answer operation in a verification answer operation area of the verification code interface, for example, filling in the answer or clicking the position; if the answer operation is verified, automatically triggering a login instruction; and then carrying out subsequent automatic business process.
According to the technical scheme provided by the embodiment, the login instruction is triggered under the condition that the answer operation verification passes, so that automatic login is realized, and the efficiency of information login or login verification is improved.
In an exemplary embodiment, as shown in fig. 3, the method further includes a step of model training, which specifically includes the following:
step S301, obtaining a sample verification question and a true verification answer of the sample verification question;
step S302, analyzing the sample verification questions through a to-be-trained verification question analysis model to obtain prediction verification answers of the sample verification questions;
step S303, training the verification problem analysis model to be trained according to the difference between the prediction verification answer and the true verification answer to obtain the verification problem analysis model.
The sample verification problem may be a collection of real verification code problems for model training.
The true verification answer may be a correct answer corresponding to the sample verification question.
The to-be-trained verification problem analysis model can be a problem analysis model which is not yet trained, and training is needed according to sample data.
The prediction verification answer may be a prediction answer generated by the to-be-trained verification problem analysis model according to the sample verification problem.
The verification problem analysis model can be a problem analysis model trained by multiple rounds of samples.
Optionally, the terminal obtains a sample verification question and a true verification answer of the sample verification question; inputting the sample verification questions into a to-be-trained verification question analysis model, and analyzing the sample verification questions through the to-be-trained verification question analysis model to obtain predicted verification answers of the sample verification questions output by the to-be-trained verification question analysis model; and training the to-be-trained verification problem analysis model (which can be a model subjected to multiple rounds of sample training) according to the difference between the predicted verification answer and the true verification answer, so as to obtain a model after training, and taking the model as a verification problem analysis model.
According to the technical scheme, the verification problem analysis model to be trained is trained, so that the verification problem analysis model with higher efficiency and accuracy is obtained, and the efficiency and accuracy of verification problem processing are improved.
The following describes the verification problem processing method provided in the present application in an embodiment, where the method is applied to a terminal to illustrate, and the main steps include:
the method comprises the steps that firstly, a terminal obtains a sample verification question and a real verification answer of the sample verification question; analyzing the sample verification problem through a to-be-trained verification problem analysis model to obtain a prediction verification answer of the sample verification problem; and training the verification problem analysis model to be trained according to the difference between the predicted verification answer and the true verification answer to obtain the verification problem analysis model.
And secondly, the terminal identifies the verification problem image of the financial system to obtain the verification problem in the verification problem image.
Thirdly, the terminal identifies the verification problem to obtain text information in the verification problem; determining characteristic text information in the text information; under the condition that the characteristic text information represents digital information and operator information, confirming that the problem type of the verification problem is an operation problem type; confirming that the question type is a judgment question type under the condition that the characteristic text information represents selection information, color information or graphic information; in the case where the feature text information indicates click information, the question type is confirmed to be a coordinate question type.
Fourth, under the condition that the problem type is the operation problem type, the terminal selects an operation problem analysis model from a plurality of verification problem analysis models to serve as a target verification problem analysis model; the operation problem analysis model is used for analyzing and processing the verification problem of the operation problem type; under the condition that the problem type is the judgment problem type, selecting a judgment problem analysis model from a plurality of verification problem analysis models as a target verification problem analysis model; the judgment problem analysis model is used for analyzing and processing verification problems of judgment problem types; under the condition that the problem type is a coordinate problem type, selecting a coordinate problem analysis model from a plurality of verification problem analysis models as a target verification problem analysis model; the coordinate problem analysis model is used for analyzing and processing verification problems of the coordinate problem types.
Fifthly, under the condition that the target verification problem analysis model is an operation problem analysis model, the terminal performs operation analysis processing on the verification problem through the operation problem analysis model to obtain an operation result of the verification problem, and the operation result is used as a verification answer of the verification problem; under the condition that the target verification problem analysis model is a judgment problem analysis model, judging and analyzing the verification problem through the judgment problem analysis model to obtain a judgment result of the verification problem, wherein the judgment result is used as a verification answer of the verification problem; and under the condition that the target verification problem analysis model is a coordinate problem analysis model, carrying out coordinate analysis processing on the verification problem through the coordinate problem analysis model to obtain a coordinate result of the verification problem, and taking the coordinate result as a verification answer of the verification problem.
Sixthly, the terminal executes an answer operation corresponding to the verification answer in a verification answer operation area of the verification question; in case the answer operation verifies, a login instruction is triggered.
The plurality of verification problem analysis models at least comprise an operation problem analysis model, a judgment problem analysis model and a coordinate problem analysis model.
According to the technical scheme provided by the embodiment, verification questions in the verification question image are obtained by identifying the verification question image of the financial system, a target verification question analysis model corresponding to the verification question type is selected from a plurality of verification question analysis models, then the verification questions are analyzed by the target verification question analysis model to obtain verification answers, and finally the verification questions are answered according to the verification answers; through the steps, an automatic process from question identification to answer is realized, and the efficiency and accuracy of question verification processing are improved.
The verification problem processing method provided by the present application is described below by way of an application example, and the application example is described by way of example by applying the method to a terminal, referring to fig. 4, and the main steps include:
the first step, the terminal divides the verification code picture into a background picture and a label picture, and respectively carries out pretreatment to eliminate noise, improve the quality of the image, make the image clearer and facilitate better feature extraction.
And secondly, separating each label in the label graph by the terminal, wherein some labels are adhered together, and image edge detection and separation processing are required to be carried out on the labels.
The tag map may be key information in the verification code.
And thirdly, labeling the icon to be detected in the background image by the terminal, and producing a training set.
Fourthly, training and identifying the icons in the background map by the terminal according to the icons in the background map, and detecting the icons in the background map: (1) Identifying numbers, operation symbols and question marks, classifying the numbers, the operation symbols and the question marks into an arithmetic model, further performing logic operation to obtain a result, then replacing the question marks with the result, performing verification, and outputting the result if the verification passes (for example, 1+4=; (2) The key words such as 'select', 'color' or 'graph' are identified, and then classified into a judging type model, each item of the picture is identified and judged one by one according to the words such as 'red/triangle' to be selected in the title, and the 'red/triangle' in the picture is output as the correct item; (3) The key words are identified as 'clicking', and classified as a coordinate type verification code model, each coordinate picture in the verification code is identified and judged one by one according to the words to be clicked in the title, such as 'mop/desk lamp', and the coordinates of the 'mop/desk lamp' in the picture are output, if the title contains the 'sequential' key words, each coordinate picture in the verification code is identified and judged one by one, and the coordinates of the words to be clicked in the picture in the correct sequence are output.
For example, referring to fig. 4, the terminal intercepts the verification code picture through RPA (robot process automation), invokes the OCR recognition interface, recognizes each effective element in the verification code picture through OCR, and makes a judgment; if the number, the operation symbol and the question mark are identified, determining the number as an arithmetic model, operating the number to obtain a result, substituting the result into the question mark for verification, and outputting a correct operation result; if the key words of 'select', 'color' or 'graph' are identified, determining that the key words are a selection judgment type model, identifying the pictures which meet the conditions in the pictures, and outputting options of correct pictures; if the key words are identified to be 'clicked', determining the key words as a coordinate model, identifying the pictures which meet the conditions in the pictures, and outputting the coordinates of the correct pictures; if the above 3 cases are not satisfied, the model is determined to be a normal model, and the identified element information is directly output.
For example, referring to fig. 5, the model training, the terminal prepares a sample, extracts information, performs modeling scene validation (arithmetic type, selection judgment type, coordinate type), performs feature engineering training, and may include training model 1, training model 2, … … training model n (where n may represent a number), judging the evaluation effect of the model, adjusting model features and training parameters if not meeting expectations, performing model deployment if meeting expectations, and ending.
And fifthly, after the terminal performs specific scene logic processing and outputs reply content, the terminal automatically fills the verification information column by using the RPA to acquire information, clicks a login button to complete automatic login, and then performs subsequent service flow automatic processing.
The technical scheme provided by the application example realizes the specific scene of the intelligent question-answer verification code through the OCR intelligent recognition technology and is used for training a large amount of intelligent question-answer verification codes, the link of the verification code is effectively processed by the RPA automatic flow, the manual intervention is not needed again, and the manpower is completely and thoroughly released; and the efficiency and the accuracy of verification problem processing and login are improved.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a verification problem processing device for realizing the verification problem processing method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation of one or more embodiments of the verification problem processing device provided below may refer to the limitation of the verification problem processing method hereinabove, and will not be repeated herein.
In one exemplary embodiment, as shown in fig. 6, there is provided a verification problem processing apparatus, the apparatus 600 may include:
the image recognition module 601 is configured to recognize a verification problem image of a financial system, so as to obtain a verification problem in the verification problem image;
the model selection module 602 is configured to select, from a plurality of verification problem resolution models, a verification problem resolution model corresponding to a problem type of a verification problem as a target verification problem resolution model;
the question analysis module 603 is configured to analyze the verification question through a target verification question analysis model to obtain a verification answer of the verification question;
and the question processing module 604 is used for carrying out answer processing on the verification questions according to the verification answers.
In an exemplary embodiment, the apparatus 600 further comprises: the type determining module is used for identifying the verification problem and obtaining text information in the verification problem; determining characteristic text information in the text information; and determining the problem type of the verification problem according to the characteristic text information.
In an exemplary embodiment, the type determining module is further configured to confirm that the question type of the verification question is an operation question type in a case where the feature text information represents digital information and operator information; confirming that the question type is a judgment question type under the condition that the characteristic text information represents selection information, color information or graphic information; in the case where the feature text information indicates click information, the question type is confirmed to be a coordinate question type.
In one exemplary embodiment, the plurality of verification problem resolution models includes at least an operational problem resolution model, a judgment problem resolution model, and a coordinate problem resolution model; the model selecting module 602 is further configured to select, from a plurality of verification problem resolution models, an operation problem resolution model as a target verification problem resolution model when the problem type is an operation problem type; the operation problem analysis model is used for analyzing and processing the verification problem of the operation problem type; under the condition that the problem type is the judgment problem type, selecting a judgment problem analysis model from a plurality of verification problem analysis models as a target verification problem analysis model; the judgment problem analysis model is used for analyzing and processing verification problems of judgment problem types; under the condition that the problem type is a coordinate problem type, selecting a coordinate problem analysis model from a plurality of verification problem analysis models as a target verification problem analysis model; the coordinate problem analysis model is used for analyzing and processing verification problems of the coordinate problem types.
In an exemplary embodiment, the problem analysis module 603 is further configured to, when the target verification problem analysis model is an operation problem analysis model, perform operation analysis processing on the verification problem through the operation problem analysis model, to obtain an operation result of the verification problem, which is used as a verification answer of the verification problem; under the condition that the target verification problem analysis model is a judgment problem analysis model, judging and analyzing the verification problem through the judgment problem analysis model to obtain a judgment result of the verification problem, wherein the judgment result is used as a verification answer of the verification problem; and under the condition that the target verification problem analysis model is a coordinate problem analysis model, carrying out coordinate analysis processing on the verification problem through the coordinate problem analysis model to obtain a coordinate result of the verification problem, and taking the coordinate result as a verification answer of the verification problem.
In an exemplary embodiment, the question processing module 604 is further configured to perform an answer operation corresponding to the verification answer in a verification answer operation area for verifying the question; the apparatus 600 further comprises: and the instruction triggering module is used for triggering a login instruction under the condition that the answer operation verification passes.
In an exemplary embodiment, the apparatus 600 further comprises: the model training module is used for acquiring a sample verification question and a real verification answer of the sample verification question; analyzing the sample verification problem through a to-be-trained verification problem analysis model to obtain a prediction verification answer of the sample verification problem; and training the verification problem analysis model to be trained according to the difference between the predicted verification answer and the true verification answer to obtain the verification problem analysis model.
The respective modules in the above-described verification problem processing apparatus may be implemented in whole or in part by software, hardware, and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
It should be noted that the method and the device for processing the verification problem provided by the present application may be used in the application field related to the verification problem processing in the financial science and technology field, and may also be used in the processing related to the verification problem processing in any field other than the financial science and technology field.
In one exemplary embodiment, a computer device is provided, which may be a terminal, and an internal structure diagram thereof may be as shown in fig. 7. The computer device includes a processor, a memory, an input/output interface, a communication interface, a display unit, and an input means. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program, when executed by a processor, implements a method of validating a problem. The display unit of the computer device is used for forming a visual picture, and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be a key, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in fig. 7 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In an exemplary embodiment, a computer device is also provided, comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.
In one exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method embodiments described above.
In an exemplary embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (11)
1. A method of validating a question, the method comprising:
identifying verification problem images of a financial system to obtain verification problems in the verification problem images;
selecting a verification problem analysis model corresponding to the problem type of the verification problem from a plurality of verification problem analysis models as a target verification problem analysis model;
Analyzing the verification questions through the target verification question analysis model to obtain verification answers of the verification questions;
and according to the verification answer, carrying out answer processing on the verification question.
2. The method according to claim 1, further comprising, before selecting a verification problem resolution model corresponding to a problem type of the verification problem from a plurality of verification problem resolution models as a target verification problem resolution model:
identifying the verification problem to obtain text information in the verification problem;
determining characteristic text information in the text information;
and determining the problem type of the verification problem according to the characteristic text information.
3. The method of claim 2, wherein determining the question type of the verification question based on the feature text information comprises:
under the condition that the characteristic text information represents digital information and operator information, confirming that the problem type of the verification problem is an operation problem type;
confirming that the question type is a judgment question type under the condition that the characteristic text information represents selection information, color information or graphic information;
And confirming that the question type is a coordinate question type under the condition that the characteristic text information represents click information.
4. The method of claim 3, wherein the plurality of verification problem resolution models includes at least an operational problem resolution model, a judgment problem resolution model, and a coordinate problem resolution model;
the selecting, from the plurality of verification problem analysis models, a verification problem analysis model corresponding to a problem type of the verification problem as a target verification problem analysis model includes:
when the problem type is the operation problem type, selecting the operation problem analysis model from the plurality of verification problem analysis models as the target verification problem analysis model; the operation problem analysis model is used for analyzing and processing the verification problem of the operation problem type;
when the problem type is the judging problem type, selecting the judging problem analysis model from the plurality of verification problem analysis models as the target verification problem analysis model; the judgment problem analysis model is used for analyzing and processing the verification problem of the judgment problem type;
Selecting the coordinate problem analysis model from the plurality of verification problem analysis models as the target verification problem analysis model under the condition that the problem type is the coordinate problem type; the coordinate problem analysis model is used for analyzing and processing the verification problem of the coordinate problem type.
5. The method of claim 4, wherein the parsing the verification question through the target verification question parsing model to obtain a verification answer to the verification question comprises:
under the condition that the target verification problem analysis model is the operation problem analysis model, performing operation analysis processing on the verification problem through the operation problem analysis model to obtain an operation result of the verification problem, wherein the operation result is used as a verification answer of the verification problem;
under the condition that the target verification problem analysis model is the judgment problem analysis model, judging and analyzing the verification problem through the judgment problem analysis model to obtain a judgment result of the verification problem, wherein the judgment result is used as a verification answer of the verification problem;
and under the condition that the target verification problem analysis model is the coordinate problem analysis model, carrying out coordinate analysis processing on the verification problem through the coordinate problem analysis model to obtain a coordinate result of the verification problem, and taking the coordinate result as a verification answer of the verification problem.
6. The method of claim 1, wherein said answering the verification question based on the verification answer comprises:
executing an answer operation corresponding to the verification answer in a verification answer operation area of the verification question;
after the answer processing is performed on the verification questions according to the verification answers, the method further comprises the following steps:
in case the answer operation verifies, a login instruction is triggered.
7. The method according to claim 1, wherein the method further comprises:
acquiring a sample verification question and a real verification answer of the sample verification question;
analyzing the sample verification questions through a to-be-trained verification question analysis model to obtain prediction verification answers of the sample verification questions;
and training the verification problem analysis model to be trained according to the difference between the prediction verification answer and the real verification answer to obtain the verification problem analysis model.
8. An authentication problem processing apparatus, the apparatus comprising:
the image recognition module is used for recognizing the verification problem image of the financial system to obtain the verification problem in the verification problem image;
The model selecting module is used for selecting a verification problem analysis model corresponding to the problem type of the verification problem from a plurality of verification problem analysis models, and taking the verification problem analysis model as a target verification problem analysis model;
the problem analysis module is used for analyzing the verification problem through the target verification problem analysis model to obtain a verification answer of the verification problem;
and the question processing module is used for carrying out answer processing on the verification questions according to the verification answers.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
11. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311567242.4A CN117521051A (en) | 2023-11-22 | 2023-11-22 | Verification problem processing method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311567242.4A CN117521051A (en) | 2023-11-22 | 2023-11-22 | Verification problem processing method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117521051A true CN117521051A (en) | 2024-02-06 |
Family
ID=89758410
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311567242.4A Pending CN117521051A (en) | 2023-11-22 | 2023-11-22 | Verification problem processing method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117521051A (en) |
-
2023
- 2023-11-22 CN CN202311567242.4A patent/CN117521051A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111767228B (en) | Interface testing method, device, equipment and medium based on artificial intelligence | |
| CN110033018B (en) | Graph similarity judging method and device and computer readable storage medium | |
| CN110175609B (en) | Interface element detection method, device and equipment | |
| CN108062377A (en) | The foundation of label picture collection, definite method, apparatus, equipment and the medium of label | |
| CN106104570A (en) | Detection and extraction image document assembly create stream document | |
| CN112308069A (en) | Click test method, device, equipment and storage medium for software interface | |
| CN114860892B (en) | Hierarchical category prediction method, device, equipment and medium | |
| CN113821296B (en) | Visual interface generation method, electronic equipment and storage medium | |
| CN116501979A (en) | Information recommendation method, information recommendation device, computer equipment and computer readable storage medium | |
| CN116453125A (en) | Data input method, device, equipment and storage medium based on artificial intelligence | |
| CN116129179A (en) | Cross-modal model training method and device, electronic equipment and storage medium | |
| CN115631374A (en) | Control operation method, control detection model training method, device and equipment | |
| CN117521051A (en) | Verification problem processing method, device, computer equipment and storage medium | |
| CN115239590A (en) | Sample image generation method, device, equipment, medium and program product | |
| CN113742559A (en) | Keyword detection method and device, electronic equipment and storage medium | |
| CN113515701A (en) | Information recommendation method and device | |
| CN111898761B (en) | Service model generation method, image processing method, device and electronic equipment | |
| CN111127057A (en) | Multi-dimensional user portrait restoration method | |
| CN111598159B (en) | Training method, device, equipment and storage medium of machine learning model | |
| CN111507141B (en) | Picture identification method, service interface display method, system and equipment | |
| US20220253690A1 (en) | Machine-learning systems for simulating collaborative behavior by interacting users within a group | |
| CN117827273A (en) | Code identification method, apparatus, computer device and storage medium | |
| CN117391713A (en) | Information pushing method and device, electronic equipment and storage medium | |
| CN115311069A (en) | Real estate mortgage address verification method, device and system and storage medium | |
| CN118012552A (en) | Interface information processing method, apparatus, device, medium, and computer program product |
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 |