CN112699348A - Method and device for verifying nuclear body information, computer equipment and storage medium - Google Patents
Method and device for verifying nuclear body information, computer equipment and storage medium Download PDFInfo
- Publication number
- CN112699348A CN112699348A CN202011561989.5A CN202011561989A CN112699348A CN 112699348 A CN112699348 A CN 112699348A CN 202011561989 A CN202011561989 A CN 202011561989A CN 112699348 A CN112699348 A CN 112699348A
- Authority
- CN
- China
- Prior art keywords
- information
- verification
- core
- user
- verifying
- 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 53
- 238000012795 verification Methods 0.000 claims abstract description 288
- 230000011218 segmentation Effects 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 10
- 230000001960 triggered effect Effects 0.000 claims description 7
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 12
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 6
- 238000012790 confirmation Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 229910052742 iron Inorganic materials 0.000 description 3
- 239000011258 core-shell material Substances 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000000284 extract 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
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
- G06F21/31—User authentication
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
The invention discloses a method and a device for verifying nuclear body information, computer equipment and a storage medium, wherein the method comprises the following steps: receiving a verification request for verifying the core-body information of the user and extracting a plurality of questioning information for performing first core-body verification on the user from a risk core-body questioning and answering library; receiving a plurality of answer information aiming at the first core verification input by a user and verifying according to a first verification rule to obtain a verification result of the first core verification; if the user fails, extracting a plurality of questioning information for performing second core-body verification on the user from the risk core-body questioning and answering library; and receiving a plurality of answer information of the second core verification input by the user and verifying according to the second verification rule to obtain a verification result of whether the user passes the core information verification. The invention is based on the artificial intelligence recognition technology, not only reduces the labor cost, but also ensures the reality and the accuracy of each user, each information and each link content when the user is verified.
Description
Technical Field
The invention belongs to the technical field of artificial intelligence recognition, and particularly relates to a method and a device for verifying core information, computer equipment and a storage medium.
Background
After the client transacts the related business online, secondary confirmation of risk authentication needs to be continuously carried out on the client with risk. In the prior art, a manual service method is usually adopted to carry out secondary confirmation of risk authentication on the risky clients, which results in a large expenditure of labor cost, and meanwhile, when the risky clients are large in number, manual operation errors are prone to occur, and successful verification of the core-body information of the clients cannot be guaranteed.
Disclosure of Invention
The embodiment of the invention provides a method and a device for verifying kernel-body information, computer equipment and a storage medium, aiming at solving the problems of low efficiency and higher cost in the prior art when carrying out secondary confirmation of risk authentication on a risky client.
In a first aspect, an embodiment of the present invention provides a method for verifying core-body information, including:
receiving a verification request for verifying the core-body information of the user;
extracting a plurality of question information for performing first core body verification on the user from a preset risk core body question-answering library according to the verification request;
receiving a plurality of answer information aiming at the first core verification input by the user and verifying the plurality of answer information aiming at the first core verification according to a preset first verification rule to obtain a verification result of the first core verification;
if the verification result of the first core-body verification fails, extracting a plurality of questioning information for performing second core-body verification on the user from the risk core-body questioning and answering library;
and receiving a plurality of answer information of the second core verification input by the user and verifying the plurality of answer information of the second core verification according to a preset second verification rule to obtain a verification result of whether the user passes the core information verification.
In a second aspect, an embodiment of the present invention provides an apparatus for verifying core-body information, including:
a receiving unit, configured to receive a verification request for verifying the core-body information of the user;
the first extraction unit is used for extracting a plurality of questioning information for carrying out first core verification on the user from the risk core questioning and answering library according to the verification request;
the first verification unit is used for receiving a plurality of answer information of the first core verification input by the user and verifying the plurality of answer information of the first core verification according to a preset first verification rule to obtain a verification result of the first core verification;
a second extracting unit, configured to extract, if a verification result of the first core verification fails, multiple pieces of question information for performing second core verification on the user from the risk core question-answering library;
and the second checking unit is used for receiving the plurality of answer information of the second core verification input by the user and checking the plurality of answer information of the second core verification according to a preset second checking rule to obtain a checking result of whether the user passes the core information checking.
In a third aspect, an embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor, when executing the computer program, implements the method for verifying the core-body information according to the first aspect.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and the computer program, when executed by a processor, causes the processor to execute the method for verifying the core-body information according to the first aspect.
The embodiment of the invention provides a method and a device for verifying nuclear body information, computer equipment and a storage medium, wherein the method comprises the following steps: receiving a verification request for verifying the core-body information of the user; extracting a plurality of question information for performing first core body verification on the user from a preset risk core body question-answering library according to the verification request; receiving a plurality of answer information aiming at the first core verification input by the user and verifying the plurality of answer information aiming at the first core verification according to a preset first verification rule to obtain a verification result of the first core verification; if the verification result of the first core-body verification fails, extracting a plurality of questioning information for performing second core-body verification on the user from the risk core-body questioning and answering library; and receiving a plurality of answer information of the second core verification input by the user and verifying the plurality of answer information of the second core verification according to a preset second verification rule to obtain a verification result of whether the user passes the core information verification. By the method, labor cost can be reduced, service problems caused by insufficient manpower can be relieved, the trueness and accuracy of each user, each information and each link content can be ensured, and subsequent risk problems caused by manual misoperation can be avoided.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flowchart of a method for verifying the nuclear body information according to an embodiment of the present invention;
fig. 2 is a schematic view of an application scenario of a method for verifying nuclear body information according to an embodiment of the present invention;
fig. 3 is a sub-flow diagram of a method for verifying the nuclear body information according to an embodiment of the present invention;
fig. 4 is another schematic flowchart of a method for verifying the nuclear body information according to an embodiment of the present invention;
fig. 5 is a schematic sub-flow chart of a method for verifying the nuclear body information according to an embodiment of the present invention;
fig. 6 is another sub-flow diagram of the method for verifying the nuclear body information according to the embodiment of the present invention;
fig. 7 is another sub-flowchart of the method for verifying the nuclear body information according to the embodiment of the present invention;
fig. 8 is another sub-flowchart of the method for verifying the nuclear body information according to the embodiment of the present invention;
fig. 9 is a schematic block diagram of an apparatus for verifying the core-body information according to an embodiment of the present invention;
fig. 10 is a schematic block diagram of a sub-unit of an apparatus for verifying the nuclear body information according to an embodiment of the present invention;
fig. 11 is a schematic block diagram of another sub-unit of the apparatus for verifying the nuclear body information according to the embodiment of the present invention;
fig. 12 is a schematic block diagram of another sub-unit of the apparatus for verifying the nuclear body information according to the embodiment of the present invention;
fig. 13 is a schematic block diagram of another sub-unit of the apparatus for verifying the nuclear body information according to the embodiment of the present invention;
fig. 14 is a schematic block diagram of another sub-unit of the apparatus for verifying the nuclear body information according to the embodiment of the present invention;
FIG. 15 is a schematic block diagram of a computer device provided by an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
Referring to fig. 1 and fig. 2, fig. 1 is a schematic flow chart illustrating a method for verifying the core-body information according to an embodiment of the present invention; fig. 2 is a schematic view of an application scenario of the method for verifying the nuclear body information according to the embodiment of the present invention. The method for verifying the nuclear body information is applied to a server, after the server receives a verification request for verifying the nuclear body information of a user, which is sent by user terminal equipment such as a laptop, a tablet personal computer and the like, the server generates question information matched with the user for many times and sends the question information to a user terminal, the user answers according to the question information, the user terminal sends the answer to the server for verification to obtain a verification result for verifying the nuclear body information of the user, the labor cost can be reduced, the service problem caused by insufficient manpower can be relieved, the reality and the accuracy of each user, each information and each link content can be ensured, and subsequent risk problems caused by manual misoperation can be avoided. The method for verifying the nuclear body information will be described in detail below.
As shown in fig. 1, the method includes the following steps S110 to S150.
S110, receiving a verification request for verifying the core-body information of the user.
And the verification request is request information of secondary confirmation for risk authentication of the user, which is sent by the user terminal, received by the server after the user completes service transaction at the user terminal. The verification request comprises service information of the user for transacting the service online and identity information of the user, wherein the identity information comprises the name, the sex, the telephone, the address of the user and service records transacted by the user.
And S120, extracting a plurality of questioning information for performing first core verification on the user from a preset risk core questioning and answering library according to the verification request.
Specifically, the risk core question-answering library is a database for storing question information matched with a user, the user needs to input corresponding identity information and related service information online in the process of handling corresponding services, and the server generates question information matched with the user according to the corresponding identity information and the related service information and stores the question information in the risk core question-answering library. Generally, before a user transacts business online, the user needs to manually input identity information of the user, such as name, telephone, age, sex, and the like, and after the identity information of the user and the corresponding business of the user are obtained, question information related to the user is generated according to the identity information of the user and the transacted business information. For example, if the name of the user is Zhang III, question information of asking for your last name is generated according to Zhang III, and the question information and the identity information of the user are stored in the risk core information base. Therefore, when secondary confirmation of risk authentication needs to be carried out on the user, the server calls the risk core question-answering library according to the verification request and extracts a plurality of question information related to the user from the risk core question-answering library to carry out core verification on the user. The plurality of question information related to the user may be question information related to name verification, identity card number verification, address verification, or the like related to the user. In the embodiment of the present invention, the plurality of question information verified by the first kernel is three question information.
In another embodiment, as shown in fig. 3, before step S120, the method further includes: s1201, S1202, and S1203.
S1201, acquiring a plurality of names consistent with the real names of the users from a preset name information base.
Specifically, the name information base is an information base used for storing common names, and after the server acquires the identity information of the user, the server acquires the real name of the user from the identity information and acquires a plurality of names which are the same as the surnames in the real name of the user from the name information base according to the surnames in the real name of the user. For example, if the name of the user is zhang three, the names obtained from the name information base are zhang three, zhang four, zhang five, zhang six, etc.
S1202, acquiring a plurality of addresses corresponding to the real addresses of the users from a preset address knowledge graph.
Specifically, the address map is a pre-constructed knowledge map related to the user address, and the address knowledge map sequentially comprises provinces, cities, counties, districts, streets, buildings, units, floors and room numbers from the upper layer to the lower layer by taking the country as the center. And after the server acquires the real address of the user, acquiring a plurality of address information related to the street from the address knowledge map according to the street in the real address of the user. For example: if the street information in the real address of the user is a peace street, a plurality of address information corresponding to the real address of the user, such as ' 1 st 2 units 1302 of the peace street iron machine flourishing home garden in the mountainous area of Wuhan city in Hubei province, 2 nd 2 units 1302 of the peace street iron machine flourishing home garden in the mountainous area of Wuhan city in Hubei province, 2 st 1 unit 1302 of the peace street iron machine flourishing home garden in the mountainous area of Wuhan city in Hubei province ', and the like ' are obtained from the peace street in the address knowledge map.
S1203, generating a plurality of pieces of question information related to the user based on the plurality of names, the plurality of addresses, the real names, the real addresses and the service information of the user.
Specifically, the question information is a plurality of question information, and each question information includes any one or more of a real name and a real address of the user and service information of the user. The service information of the user is the service information transacted online by the user. For example, when the real name of the user is Zhang III, the question asking information may be "ask you to call Zhang III or Zhang IV".
S130, receiving a plurality of answer information aiming at the first core verification input by the user and verifying the plurality of answer information aiming at the first core verification according to a preset first verification rule to obtain a verification result of the first core verification.
Specifically, after the server acquires a plurality of pieces of question information related to the user from the risk core question-answering library, the plurality of pieces of question information verified by the first core are sequentially sent to the user terminal to ask the user, the user answers each piece of question information in a voice video mode after receiving each piece of question information sent by the server every time, after the user terminal acquires a voice video of each piece of question information answered by the user, the user terminal acquires voice information of the user from the voice video and converts the voice information into the text information through a voice conversion model in the user terminal, and after the voice information is converted into the text information, the voice information is sent to the server in the form of the text information. After receiving the text information of each question answering information of the user, the server continuously sends the next question information to the user terminal. After the server sends all the question information for performing the first core-body verification on the user, the server respectively analyzes and identifies the text information of the question information answered by the user each time and compares the text information with the correct answer of the question information, and if any one of the plurality of question information is inconsistent with the correct answer of the question information, the verification result for performing the first core-body verification on the user is failure.
In another embodiment, as shown in fig. 4, step S130 includes sub-steps S131, S132, and S133.
S131, obtaining text information of each answer information in the multiple answer information verified by the first core, and performing word segmentation processing on the text information according to a preset word segmentation model to obtain a single word in the text information.
Specifically, the word segmentation model is a model for performing word segmentation processing on the text information to obtain a single word in the text information. The specific word segmentation process is as follows: and setting the number of Chinese characters contained in the longest entry in a preset dictionary as L, and starting processing from the tail of the character string of the Chinese sentence. At the beginning of each cycle, the last L characters of the character string are taken as processing objects, and the dictionary is searched. If the dictionary has such an L word, the matching is successful, and the processing object is segmented as a word; if the Chinese sentence is not successful, the first Chinese character of the processing object is removed, the rest character strings are used as new processing objects, matching is carried out again until the segmentation is successful, namely, one round of matching is completed, a word is segmented, and the steps are circulated until all the words in the Chinese sentence are segmented.
For example, the length of the longest word in the dictionary is 3, for a character string of the Chinese sentence that "i is not four, the first character is 3 characters that" is four "as the character string to be processed, and the word is not in the dictionary, so the matching fails; removing the first character, taking the remaining 'Zhang four' as a new character string to be processed, wherein the dictionary has the word, and the matching is successful; the first word at the cut is "zhang si". And then taking the remaining character string ' i ' is not ' in the Chinese sentence, and taking the second word ' is not ' at the segmentation part. So circulating, the result of the final segmentation is as follows: "I", "not", "Zhang Si".
S132, conducting named entity recognition on the single words in the text information according to a preset named entity recognition model to obtain words with entity names in the text information.
Specifically, the named entity recognition model is a model for recognizing a named entity for a single word in the text information. The Named Entity Recognition (NER) is one of Natural Language Processing (NLP), for example, when the text information of the user answering the question information is "i call zhang san", the text information is subjected to word segmentation processing to obtain three words of "i", "call", "zhang", and then the three words of "i", "call", "zhang" are subjected to named entity recognition to finally obtain the word "zhang san" of the name class.
S133, checking the words with the entity names in the text information to obtain a checking result of the first core-body checking.
Specifically, the text information is the text information of each answer information in the multiple answer information of the first core-body verification, after a named word in the text information is obtained, the named word is compared with a standard answer to obtain whether the answer of the user is correct, so that a result of whether the user passes the first core-body verification is obtained, and if the answer of the user passes the first core-body verification, the user completes verification of the core-body information; and if the verification result does not pass, the user performs second core verification. In the embodiment of the invention, if any answer information in the answer information does not pass, the user needs to perform the second verification.
In another embodiment, as shown in fig. 5, step S133 includes sub-steps S1331, S1332, S1333, S1334 and S1335.
And S1331, judging whether the words with the entity names in the text information trigger preset trigger rules.
Specifically, the triggering rule is rule information for triggering a verification result that the verification of the core body information is successful for the user when the text information has words matched with the answer of the question information. When the text information does not contain words with the same answers as the answers corresponding to the question information, the triggering rule is not triggered, and the user can be temporarily judged to be unsuccessful in verifying the identity verification information; and when the text information contains words with the same answers as the answers corresponding to the question information, triggering the triggering rule, and judging that the verification of the user verification information is successful at the moment, so that a verification result of the first verification of the user verification is obtained.
And S1332, if the trigger rule is not triggered, inputting the text information into a preset syntactic analysis model to obtain a syntactic tree of the text information.
Specifically, the syntactic analysis model is a pre-trained syntactic analysis model, after the text information is input into the syntactic analysis model, part-of-speech tagging is performed on each word in the text information, entity naming information of each word is acquired after the part-of-speech tagging is completed, and finally, constituent sentence analysis is performed on each word in the text information to output a syntactic tree of the text information, wherein the syntactic tree is a syntactic tree of semantic information of the text information, and the semantic information of the text information can be acquired through the syntactic tree.
And S1333, obtaining semantic information of the text information according to the syntax tree of the text information.
Specifically, the syntax tree is a syntax tree including an analysis result of the text information, that is, after the syntax tree of the text information is constructed by the text information, semantic information of the text information can be obtained.
And S1334, judging whether the semantic information of the text information is consistent with the preset first answer semantic.
Obtaining semantic information of the text information in the syntax tree, then comparing the semantic information with the semantics of the standard answer corresponding to the question information, so as to obtain result information whether the semantic information of the text information is the same as the semantics of the answer corresponding to the question information, if so, obtaining a verification result of the user passing through the first kernel-body verification, and further passing through the kernel-body information verification; if not, the verification result that the user does not pass the first verification can be obtained, and the second verification is started.
And S1335, when the semantic information of the text information is inconsistent with the first answer semantic, the verification result of the first core-body verification fails.
Specifically, the first answer semantics is semantic information of a standard answer of each question in a plurality of questions answered by the user through the first kernel verification, that is, the standard answer of each question has a corresponding syntax tree. And when the semantic information of the text information is inconsistent with the first answer semantic, the verification result of the first core-body verification fails, and the user starts to perform second core-body verification.
And S140, if the verification result of the first core verification fails, extracting a plurality of question information for performing second core verification on the user from the risk core question-answering library.
Specifically, the multiple pieces of question information of the second core verification are acquired in the same manner as the multiple pieces of question information of the first core verification, where the multiple pieces of question information of the first core verification may be the same as or different from the multiple pieces of question information of the second core verification. And when the verification result of the first core-body verification fails, the user terminal only prompts that the answer information input by the user is wrong, so that the same question information can be sent to the user when the second core-body verification is carried out on the user. In this embodiment of the present invention, the plurality of question information verified by the second core entity is three question information.
S150, receiving a plurality of answer information of the second core verification input by the user and verifying the plurality of answer information of the second core verification according to a preset second verification rule to obtain a verification result whether the user passes the core information verification.
Specifically, the preset second check rule is rule information used for checking whether the plurality of answer information of the second core body check passes the second core body check, if the user passes the second core body check, it can be determined that the user passes the core body information check, and if the user does not pass the second core body check, it can be determined that the user does not pass the core body information check. After receiving the text information of each answer information in the multiple answer information of the second core body verification input by the user, the server also processes the text information to obtain a word with an entity name in the text information, and matches the word with the answer of each question information to obtain a result of whether each answer information in the multiple answer information of the second core body verification is matched with the corresponding question information, so as to obtain a verification result of the core body information verification of the user.
In another embodiment, as shown in fig. 6, step S150 includes sub-steps S151, S152, S153, S154, and S155.
And S151, obtaining a word of each answer information in the plurality of answer information verified by the second core, and judging whether the word of each answer information in the plurality of answer information verified by the second core triggers the triggering rule.
Specifically, the method for acquiring the word of each answer information in the multiple answer information verified by the second core is the same as the method for acquiring the word of each answer information in the multiple answer information verified by the first core, and is not limited herein. Whether the words of each answer information in the multiple answer information of the second verification trigger the triggering rule can be obtained by judging whether the words of each answer information exist in the corresponding answers in the multiple answer information of the second verification, and then the verification result of whether the user successfully performs the second verification on the core body is obtained.
And S152, if the trigger rule is not triggered, obtaining a syntax tree of answer information which does not trigger the trigger rule in the plurality of answer information verified by the second core.
Specifically, if the word in any one of the plurality of answer information of the second verification does not trigger the trigger rule, it may be determined that the second verification for the user has not passed, a syntax tree of answer information that does not trigger the preset trigger rule needs to be constructed, the answer information that does not trigger the trigger rule is verified through the syntax tree, and a verification result indicating whether the answer information passes the verification is obtained. The construction method of the syntax tree of the answer information which does not trigger the trigger rule is the same as the syntax tree constructed in the first core verification, and the construction method is not repeated here.
S153, obtaining semantic information of the answer information which does not trigger the trigger rule according to the syntax tree of the answer information which does not trigger the trigger rule.
Specifically, the syntax tree of the answer information that does not trigger the trigger rule includes semantic information of the answer information that does not trigger the trigger rule, that is, after the syntax tree of the answer information that does not trigger the trigger rule is constructed by the answer information that does not trigger the trigger rule, the semantic information of the answer information that does not trigger the trigger rule can be obtained.
S154, judging whether the semantic information of the answer information which does not trigger the trigger rule is consistent with the preset second semantic information.
Specifically, by obtaining semantic information of the answer information which does not trigger the trigger rule in the syntax tree, and then comparing the semantic information with the semantics of the standard answer of the answer information, result information can be obtained whether the semantic information of the answer information is the same as the semantics of the standard answer of the answer information, and if the semantic information of the answer information is the same as the semantics of the standard answer of the answer information, the user passes through the verification of the self-check information; if not, the user fails the verification of the core body information.
S155, when the semantic information of the answer information which does not trigger the triggering rule is inconsistent with the second semantic information, the verification result of the verification of the core-body information fails.
In another embodiment, as shown in fig. 7, after step S155, steps S1551, S1552, S1553 and S1554 are further included.
S1551, intercepting the video image of each frame from the voice video of the user answering the plurality of question information verified by the second core body.
Specifically, after the user terminal obtains the voice video of each piece of question information answered by the user, the user terminal decodes the voice video to obtain a video image of each frame in the voice video, intercepts the video image of each frame in the voice video and sends the video image to the server, and after the server receives the video image of each frame in the voice video, the server can identify the video image of each frame.
S1552, identifying the video image of each frame according to a preset image identification model to obtain an identification result of the video image.
The image recognition model is used for recognizing the video image of each frame to obtain user image information when the user answers the question information, and then the model for recognizing whether the user is obtained according to the user image information. In the embodiment of the invention, the pre-trained deep residual error neural network is adopted to extract the characteristics of the characteristic information of the user in each frame of video image and verify the user through the characteristic information.
In another embodiment, as shown in fig. 8, step S1552 includes sub-steps S15521, S15522 and S15523.
S15521, extracting the characteristics of the eyes of the user in the video image of each frame according to a preset target extraction model to obtain the eye characteristic information of the user.
Specifically, the feature information of the eye region of the user when answering the plurality of question information of the second nuclear verification is extracted, and then the user is identified and verified. The target extraction model is a depth residual error neural network model which is trained in advance and used for extracting the features of the eye region of the user in the video image of each frame in the voice information. After the characteristic information of the eye region of the user in the video image of each frame in the audio and video is extracted through the depth residual neural network model, the characteristic information of the eye region of the user in the video image of each frame is classified and identified to identify and verify the user.
S15522, classifying and identifying the eye feature information according to a preset expression identification model to obtain identified eye feature information.
Specifically, a plurality of groups of feature information of the eye region of the user in the video image of each frame output by the target extraction model are received, feature information with the highest confidence coefficient is obtained from the plurality of groups of feature information, the similarity between the feature information with the highest confidence coefficient of the eye region of the user in each frame and the eye feature information of the user in the user database is calculated, and if the similarity is lower than a preset threshold value, a user impersonated and deputyed by others in the voice video is obtained; and if the similarity is higher than a preset threshold value, the user in the voice video is the real user.
S15523, comparing the recognized eye feature information with the eye feature information of the user in a user database to obtain a recognition result of the video image.
The embodiment of the invention adopts the Euclidean distance to calculate the similarity between the feature information with the highest confidence coefficient of the eye region of the user in each frame and the eye feature information of the user in the user database, wherein the Euclidean distance is a commonly adopted distance definition and refers to the real distance between two points in an n-dimensional space or the natural length of a vector. The euclidean distance calculation formula between the feature vector with the highest confidence coefficient of the eye region of the user in the current frame and the feature vector with the highest confidence coefficient of the eye region of the user in the next frame is as follows:
where n denotes the dimension of the vector, x1kThe feature vector with the highest confidence coefficient of the eye region of the user in the previous frame, x2kAnd the feature vector with the highest confidence coefficient of the eye region of the user in the next frame. The preset threshold may be set according to actual conditions, and is not limited herein. And classifying and identifying the characteristic information of the eye region of the user in the video image of each frame through the expression identification model so as to further verify the user, thereby further reducing the phenomena of impersonation and proxy when the user performs online service processing.
S1553, when the identification result is that the identified image is the image of the user, determining that the verification of the nuclear body information of the user is passed.
S1554, when the identification result is that the identified image is not the image of the user, determining that the verification of the core-body information of the user fails.
In the method for verifying the nuclear body information provided by the embodiment of the invention, a verification request for verifying the nuclear body information of a user is received; extracting a plurality of question information for performing first core body verification on the user from a preset risk core body question-answering library according to the verification request; receiving a plurality of answer information aiming at the first core verification input by the user and verifying the plurality of answer information aiming at the first core verification according to a preset first verification rule to obtain a verification result of the first core verification; if the verification result of the first core-body verification fails, extracting a plurality of questioning information for performing second core-body verification on the user from the risk core-body questioning and answering library; and receiving a plurality of answer information of the second core verification input by the user and verifying the plurality of answer information of the second core verification according to a preset second verification rule to obtain a verification result of whether the user passes the core information verification. By the method, labor cost can be reduced, service problems caused by insufficient manpower can be relieved, the trueness and accuracy of each user, each information and each link content can be ensured, and subsequent risk problems caused by manual misoperation can be avoided.
The embodiment of the present invention further provides a device 100 for verifying the core information, which is used in any embodiment of the method for verifying the core information. Specifically, referring to fig. 9, fig. 9 is a schematic block diagram of an apparatus 100 for verifying the core-shell information according to an embodiment of the present invention.
As shown in fig. 9, the apparatus 100 for verifying the core-shell information includes a receiving unit 110, a first extracting unit 120, a first verifying unit 130, a second extracting unit 140, and a second verifying unit 150.
A receiving unit 110, configured to receive a verification request for verifying the core-body information of the user.
A first extracting unit 120, configured to extract, according to the verification request, multiple pieces of question information for performing a first verification on the user from the risk verification question-and-answer library.
In another embodiment of the present invention, the apparatus 110 for verifying the core-body information further includes: a first acquisition unit 1201, a second acquisition unit 1202, and a generation unit 1203.
A first obtaining unit 1201, configured to obtain a plurality of names that are consistent with the real name of the user from a preset name information base.
The second obtaining unit 1202 obtains a plurality of addresses corresponding to real addresses of the users from a preset address knowledge map.
A generating unit 1203 is configured to generate a plurality of pieces of question information related to the user based on the plurality of names, the plurality of addresses, the real name, the real address, and the service information of the user.
The first verification unit 130 is configured to receive multiple pieces of answer information for the first core verification input by the user and verify the multiple pieces of answer information for the first core verification according to a preset first verification rule to obtain a verification result of the first core verification.
In another embodiment of the present invention, as shown in fig. 10, the first checking unit 130 includes: a word segmentation unit 131, a named entity recognition unit 132 and a third verification unit 133.
The word segmentation unit 131 is configured to obtain a text letter of each answer information in the multiple answer information of the first core verification and perform word segmentation processing on the text information according to a preset word segmentation model to obtain a single word in the text information.
And a named entity recognition unit 132, configured to perform named entity recognition on a single word in the text information according to a preset named entity recognition model to obtain a word with an entity name in the text information.
A third checking unit 133, configured to check a term with an entity name in the text information to obtain a checking result of the first verification.
In another embodiment of the present invention, as shown in fig. 11, the third verifying unit 133 includes: a first determination unit 1331, a third acquisition unit 1332, a fourth acquisition unit 1333, a second determination unit 1334 and a fourth verification unit 1335.
A first determining unit 1331, configured to determine whether a word with an entity name in the text information triggers a preset triggering rule.
A third obtaining unit 1332, configured to, if the trigger rule is not triggered, input the text information into a preset syntax analysis model to obtain a syntax tree of the text information.
A fourth obtaining unit 1333, configured to obtain semantic information of the text information according to a syntax tree of the text information.
A second determining unit 1334, configured to determine whether semantic information of the text information is consistent with a preset first answer semantic.
A fourth checking unit 1335, configured to, when the semantic information of the text information is inconsistent with the first answer semantic, fail to check the first verification result.
A second extracting unit 140, configured to extract, if the verification result of the first core verification fails, multiple pieces of question information for performing second core verification on the user from the risk core question-and-answer library.
The second checking unit 150 is configured to receive a plurality of answer information of the second core verification input by the user and check the plurality of answer information of the second core verification according to a preset second verification rule to obtain a verification result of whether the user passes the core information verification.
In another embodiment of the present invention, as shown in fig. 12, the second verification unit 150 includes: a third judging unit 151, a fifth acquiring unit 152, a sixth acquiring unit 153, a fourth judging unit 154, and a fifth verifying unit 155.
A third determining unit 151, configured to obtain a word of each answer information in the multiple answer information of the second core verification and determine whether the word of each answer information in the multiple answer information of the second core verification triggers the trigger rule.
A fifth obtaining unit 152, configured to obtain, if the trigger rule is not triggered, a syntax tree of answer information that does not trigger the trigger rule in the multiple answer information of the second kernel verification.
A sixth obtaining unit 153, configured to obtain semantic information of the answer information that does not trigger the trigger rule according to the syntax tree of the answer information that does not trigger the trigger rule.
A fourth determining unit 154, configured to determine whether semantic information of the answer information that does not trigger the trigger rule is consistent with preset second semantic information.
A fifth checking unit 155, configured to, when the semantic information of the answer information that does not trigger the trigger rule is inconsistent with the second semantic information, fail to check the verification result of the core-body information.
In another embodiment of the present invention, as shown in fig. 13, the fifth verification unit 155 includes: an interception unit 1551, a first identification unit 1552, a first determination unit 1553 and a second determination unit 1554.
An intercepting unit 1551, configured to intercept a video image of each frame from a voice video of the user answering the plurality of question information verified by the second kernel.
The first identifying unit 1552 is configured to identify the video image of each frame according to a preset image identification model to obtain an identification result of the video image.
In another embodiment of the present invention, as shown in fig. 14, the first identifying unit 1552 includes: a feature extraction unit 15521, a second recognition unit 15522 and a comparison unit 15523.
A feature extraction unit 15521, configured to perform feature extraction on the eyes of the user in the video image of each frame according to a preset target extraction model to obtain eye feature information of the user.
And the second identifying unit 15522 is configured to perform classification and identification on the eye feature information according to a preset expression identification model to obtain identified eye feature information.
A comparing unit 15523, configured to compare the identified eye feature information with the eye feature information of the user in the user database to obtain an identification result of the video image.
A first determining unit 1553, configured to determine that the verification of the core-body information of the user is passed when the identification result is that the identified image is the image of the user.
A second determining unit 1554, configured to determine that the verification of the core-body information of the user fails when the identification result is that the identified image is not the image of the user.
The apparatus 100 for verifying the core information provided in the embodiment of the present invention is configured to execute the above-mentioned verification request for receiving the core information verification performed on the user; extracting a plurality of question information for performing first core body verification on the user from a preset risk core body question-answering library according to the verification request; receiving a plurality of answer information aiming at the first core verification input by the user and verifying the plurality of answer information aiming at the first core verification according to a preset first verification rule to obtain a verification result of the first core verification; if the verification result of the first core-body verification fails, extracting a plurality of questioning information for performing second core-body verification on the user from the risk core-body questioning and answering library; and receiving a plurality of answer information of the second core verification input by the user and verifying the plurality of answer information of the second core verification according to a preset second verification rule to obtain a verification result of whether the user passes the core information verification.
Referring to fig. 15, fig. 15 is a schematic block diagram of a computer device according to an embodiment of the present invention.
Referring to fig. 15, the device 500 includes a processor 502, memory, and a network interface 505 connected by a system bus 501, where the memory may include a non-volatile storage medium 503 and an internal memory 504.
The non-volatile storage medium 503 may store an operating system 5031 and a computer program 5032. The computer program 5032, when executed, may cause the processor 502 to perform a method of verification of core identity information.
The processor 502 is used to provide computing and control capabilities that support the operation of the overall device 500.
The internal memory 504 provides an environment for running the computer program 5032 in the non-volatile storage medium 503, and when the computer program 5032 is executed by the processor 502, the processor 502 can be caused to execute a method for verifying the core identity information.
The network interface 505 is used for network communication, such as providing transmission of data information. Those skilled in the art will appreciate that the configuration shown in fig. 15 is a block diagram of only a portion of the configuration associated with aspects of the present invention and is not intended to limit the apparatus 500 to which aspects of the present invention may be applied, and that a particular apparatus 500 may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
Wherein the processor 502 is configured to run the computer program 5032 stored in the memory to implement the following functions: receiving a verification request for verifying the core-body information of the user; extracting a plurality of question information for performing first core body verification on the user from a preset risk core body question-answering library according to the verification request; receiving a plurality of answer information aiming at the first core verification input by the user and verifying the plurality of answer information aiming at the first core verification according to a preset first verification rule to obtain a verification result of the first core verification; if the verification result of the first core-body verification fails, extracting a plurality of questioning information for performing second core-body verification on the user from the risk core-body questioning and answering library; and receiving a plurality of answer information of the second core verification input by the user and verifying the plurality of answer information of the second core verification according to a preset second verification rule to obtain a verification result of whether the user passes the core information verification.
Those skilled in the art will appreciate that the embodiment of the apparatus 500 shown in fig. 15 does not constitute a limitation on the specific construction of the apparatus 500, and in other embodiments, the apparatus 500 may include more or fewer components than shown, or some components may be combined, or a different arrangement of components. For example, in some embodiments, the apparatus 500 may only include the memory and the processor 502, and in such embodiments, the structure and function of the memory and the processor 502 are the same as those of the embodiment shown in fig. 15, and are not repeated herein.
It should be understood that in the present embodiment, the Processor 502 may be a Central Processing Unit (CPU), and the Processor 502 may also be other general-purpose processors 502, a Digital Signal Processor 502 (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, etc. The general-purpose processor 502 may be a microprocessor 502 or the processor 502 may be any conventional processor 502 or the like.
In another embodiment of the present invention, a computer storage medium is provided. The storage medium may be a non-volatile computer-readable storage medium. The storage medium stores a computer program 5032, wherein the computer program 5032 when executed by the processor 502 performs the steps of: receiving a verification request for verifying the core-body information of the user; extracting a plurality of question information for performing first core body verification on the user from a preset risk core body question-answering library according to the verification request; receiving a plurality of answer information aiming at the first core verification input by the user and verifying the plurality of answer information aiming at the first core verification according to a preset first verification rule to obtain a verification result of the first core verification; if the verification result of the first core-body verification fails, extracting a plurality of questioning information for performing second core-body verification on the user from the risk core-body questioning and answering library; and receiving a plurality of answer information of the second core verification input by the user and verifying the plurality of answer information of the second core verification according to a preset second verification rule to obtain a verification result of whether the user passes the core information verification.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses, devices and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided by the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only a logical division, and there may be other divisions when the actual implementation is performed, or units having the same function may be grouped into one unit, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electric, mechanical or other form of connection.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment of the present invention.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a storage medium. Based on such understanding, the technical solution of the present invention essentially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product stored in a storage medium and including instructions for causing a device 500 (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a magnetic disk, or an optical disk.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A method for verifying the nuclear body information is characterized by comprising the following steps:
receiving a verification request for verifying the core-body information of the user;
extracting a plurality of question information for performing first core body verification on the user from a preset risk core body question-answering library according to the verification request;
receiving a plurality of answer information aiming at the first core verification input by the user and verifying the plurality of answer information aiming at the first core verification according to a preset first verification rule to obtain a verification result of the first core verification;
if the verification result of the first core-body verification fails, extracting a plurality of questioning information for performing second core-body verification on the user from the risk core-body questioning and answering library;
and receiving a plurality of answer information of the second core verification input by the user and verifying the plurality of answer information of the second core verification according to a preset second verification rule to obtain a verification result of whether the user passes the core information verification.
2. The method for verifying the identity information of the user according to claim 1, wherein before extracting the plurality of questioning information for performing the first identity verification on the user from a preset risk identity questioning and answering library according to the verification request, the method comprises:
acquiring a plurality of names consistent with the real names of the users from a preset name information base;
acquiring a plurality of addresses corresponding to real addresses of the users from a preset address knowledge graph;
generating a plurality of questioning information related to the user based on the plurality of names, the plurality of addresses, the real name, the real address, and business information of the user.
3. The method for verifying the core-body information according to claim 1, wherein the verifying the plurality of answer information of the first core-body verification according to a preset first verification rule to obtain a verification result of the first core-body verification comprises:
acquiring text information of each answer information in the plurality of answer information verified by the first core, and performing word segmentation processing on the text information according to a preset word segmentation model to obtain a single word in the text information;
carrying out named entity recognition on a single word in the text information according to a preset named entity recognition model so as to obtain a word with an entity name in the text information;
and checking the words with the entity names in the text information to obtain a checking result of the first core-body checking.
4. The method for verifying the identity information of the user according to claim 3, wherein the verifying the entity-named word in the text information to obtain the verification result of the first identity verification comprises:
judging whether the words with the entity names in the text information trigger preset trigger rules or not;
if the trigger rule is not triggered, inputting the text information into a preset syntactic analysis model to obtain a syntactic tree of the text information;
obtaining semantic information of the text information according to the syntax tree of the text information;
judging whether the semantic information of the text information is consistent with the preset first answer semantics;
and when the semantic information of the text information is inconsistent with the first answer semantic, the verification result of the first core-body verification fails.
5. The method for verifying the core-body information according to claim 4, wherein the verifying the plurality of answer information verified by the second core body according to a preset second verification rule to obtain a verification result of whether the user passes the core-body information verification comprises:
obtaining words of each answer information in the plurality of answer information verified by the second core entity and judging whether the words of each answer information in the plurality of answer information verified by the second core entity trigger the triggering rule or not;
if the trigger rule is not triggered, obtaining a syntax tree of answer information which does not trigger the trigger rule in the plurality of answer information verified by the second core;
obtaining semantic information of the answer information which does not trigger the trigger rule according to the syntax tree of the answer information which does not trigger the trigger rule;
judging whether the semantic information of the answer information which does not trigger the trigger rule is consistent with preset second semantic information or not;
and when the semantic information of the answer information which does not trigger the triggering rule is inconsistent with the second semantic information, the verification result of the verification of the core-body information fails.
6. The method for verifying the core-body information according to claim 5, wherein when the semantic information of the answer information that does not trigger the trigger rule is inconsistent with the second semantic information, the method further includes, after a verification result of the core-body information verification fails:
intercepting a video image of each frame from a voice video of the user answering the plurality of question messages verified by the second core;
identifying the video image of each frame according to a preset image identification model to obtain an identification result of the video image;
when the identification result is that the identified image is the image of the user, determining that the verification of the nuclear body information of the user is passed;
and when the identification result is that the identified image is not the image of the user, determining that the verification of the nuclear body information of the user fails.
7. The method for verifying the nuclear body information according to claim 6, wherein the recognizing the video image of each frame according to a preset image recognition model to obtain the recognition result of the video image comprises:
extracting the features of the eyes of the user in the video image of each frame according to a preset target extraction model to obtain the eye feature information of the user;
classifying and identifying the eye feature information according to a preset expression identification model to obtain identified eye feature information;
and comparing the recognized eye feature information with the eye feature information of the user in a user database to obtain a recognition result of the video image.
8. An apparatus for verifying nuclear information, comprising:
a receiving unit, configured to receive a verification request for verifying the core-body information of the user;
the first extraction unit is used for extracting a plurality of questioning information for carrying out first core verification on the user from the risk core questioning and answering library according to the verification request;
the first verification unit is used for receiving a plurality of answer information of the first core verification input by the user and verifying the plurality of answer information of the first core verification according to a preset first verification rule to obtain a verification result of the first core verification;
a second extracting unit, configured to extract, if a verification result of the first core verification fails, multiple pieces of question information for performing second core verification on the user from the risk core question-answering library;
and the second checking unit is used for receiving the plurality of answer information of the second core verification input by the user and checking the plurality of answer information of the second core verification according to a preset second checking rule to obtain a checking result of whether the user passes the core information checking.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of verifying the core-body information according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, causes the processor to perform the method of nuclear information verification as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011561989.5A CN112699348A (en) | 2020-12-25 | 2020-12-25 | Method and device for verifying nuclear body information, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011561989.5A CN112699348A (en) | 2020-12-25 | 2020-12-25 | Method and device for verifying nuclear body information, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112699348A true CN112699348A (en) | 2021-04-23 |
Family
ID=75510556
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011561989.5A Pending CN112699348A (en) | 2020-12-25 | 2020-12-25 | Method and device for verifying nuclear body information, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112699348A (en) |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104050247A (en) * | 2014-06-04 | 2014-09-17 | 上海美琦浦悦通讯科技有限公司 | Method for realizing quick retrieval of mass videos |
| CN104112114A (en) * | 2013-10-30 | 2014-10-22 | 北京安捷天盾科技发展有限公司 | Identity verification method and device |
| US20180046785A1 (en) * | 2016-08-15 | 2018-02-15 | International Business Machines Corporation | Multiple-Point Cognitive Identity Challenge System |
| CN108287820A (en) * | 2018-01-12 | 2018-07-17 | 北京神州泰岳软件股份有限公司 | A kind of generation method and device of text representation |
| CN108510398A (en) * | 2017-07-25 | 2018-09-07 | 平安科技（深圳）有限公司 | Annuity method for processing business, system, server and storage medium |
| CN109726396A (en) * | 2018-12-20 | 2019-05-07 | 泰康保险集团股份有限公司 | Semantic matching method, device, medium and the electronic equipment of question and answer text |
| CN109767335A (en) * | 2018-12-15 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Double record quality detecting methods, device, computer equipment and storage medium |
| CN110046491A (en) * | 2019-03-05 | 2019-07-23 | 北京达佳互联信息技术有限公司 | Method of calibration, device, electronic equipment and the storage medium of close guarantor's problem |
| CN110134795A (en) * | 2019-04-17 | 2019-08-16 | 深圳壹账通智能科技有限公司 | Generate method, apparatus, computer equipment and the storage medium of validation problem group |
| US20190311102A1 (en) * | 2014-08-28 | 2019-10-10 | Facetec, Inc. | Method to verify and identify blockchain with user question data |
| CN110321420A (en) * | 2019-07-04 | 2019-10-11 | 河海大学常州校区 | The intelligent Answer System generated based on question sentence |
| CN110351094A (en) * | 2019-07-03 | 2019-10-18 | 平安科技（深圳）有限公司 | Character verification method, device, computer equipment and storage medium |
| CN110569507A (en) * | 2019-09-09 | 2019-12-13 | 北京金鑫魔方科技有限责任公司 | semantic recognition method, device, equipment and storage medium |
| CN110889734A (en) * | 2019-01-10 | 2020-03-17 | 广东乐心医疗电子股份有限公司 | Order processing method and device, electronic equipment and storage medium |
| CN110909539A (en) * | 2019-10-15 | 2020-03-24 | 平安科技（深圳）有限公司 | Word generation method, system, computer device and storage medium of corpus |
| CN111241517A (en) * | 2015-08-07 | 2020-06-05 | 阿里巴巴集团控股有限公司 | Method and device for constructing biological characteristic verification question-answer library |
| CN111708874A (en) * | 2020-08-24 | 2020-09-25 | 湖南大学 | Man-machine interaction question-answering method and system based on intelligent complex intention recognition |
| CN111738008A (en) * | 2020-07-20 | 2020-10-02 | 平安国际智慧城市科技股份有限公司 | Entity identification method, device and equipment based on multilayer model and storage medium |
| CN111814487A (en) * | 2020-07-17 | 2020-10-23 | 科大讯飞股份有限公司 | Semantic understanding method, device, equipment and storage medium |
-
2020
- 2020-12-25 CN CN202011561989.5A patent/CN112699348A/en active Pending
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104112114A (en) * | 2013-10-30 | 2014-10-22 | 北京安捷天盾科技发展有限公司 | Identity verification method and device |
| CN104050247A (en) * | 2014-06-04 | 2014-09-17 | 上海美琦浦悦通讯科技有限公司 | Method for realizing quick retrieval of mass videos |
| US20190311102A1 (en) * | 2014-08-28 | 2019-10-10 | Facetec, Inc. | Method to verify and identify blockchain with user question data |
| CN111241517A (en) * | 2015-08-07 | 2020-06-05 | 阿里巴巴集团控股有限公司 | Method and device for constructing biological characteristic verification question-answer library |
| US20180046785A1 (en) * | 2016-08-15 | 2018-02-15 | International Business Machines Corporation | Multiple-Point Cognitive Identity Challenge System |
| CN108510398A (en) * | 2017-07-25 | 2018-09-07 | 平安科技（深圳）有限公司 | Annuity method for processing business, system, server and storage medium |
| CN108287820A (en) * | 2018-01-12 | 2018-07-17 | 北京神州泰岳软件股份有限公司 | A kind of generation method and device of text representation |
| CN109767335A (en) * | 2018-12-15 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Double record quality detecting methods, device, computer equipment and storage medium |
| CN109726396A (en) * | 2018-12-20 | 2019-05-07 | 泰康保险集团股份有限公司 | Semantic matching method, device, medium and the electronic equipment of question and answer text |
| CN110889734A (en) * | 2019-01-10 | 2020-03-17 | 广东乐心医疗电子股份有限公司 | Order processing method and device, electronic equipment and storage medium |
| CN110046491A (en) * | 2019-03-05 | 2019-07-23 | 北京达佳互联信息技术有限公司 | Method of calibration, device, electronic equipment and the storage medium of close guarantor's problem |
| CN110134795A (en) * | 2019-04-17 | 2019-08-16 | 深圳壹账通智能科技有限公司 | Generate method, apparatus, computer equipment and the storage medium of validation problem group |
| CN110351094A (en) * | 2019-07-03 | 2019-10-18 | 平安科技（深圳）有限公司 | Character verification method, device, computer equipment and storage medium |
| CN110321420A (en) * | 2019-07-04 | 2019-10-11 | 河海大学常州校区 | The intelligent Answer System generated based on question sentence |
| CN110569507A (en) * | 2019-09-09 | 2019-12-13 | 北京金鑫魔方科技有限责任公司 | semantic recognition method, device, equipment and storage medium |
| CN110909539A (en) * | 2019-10-15 | 2020-03-24 | 平安科技（深圳）有限公司 | Word generation method, system, computer device and storage medium of corpus |
| CN111814487A (en) * | 2020-07-17 | 2020-10-23 | 科大讯飞股份有限公司 | Semantic understanding method, device, equipment and storage medium |
| CN111738008A (en) * | 2020-07-20 | 2020-10-02 | 平安国际智慧城市科技股份有限公司 | Entity identification method, device and equipment based on multilayer model and storage medium |
| CN111708874A (en) * | 2020-08-24 | 2020-09-25 | 湖南大学 | Man-machine interaction question-answering method and system based on intelligent complex intention recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020232861A1 (en) | Named entity recognition method, electronic device and storage medium | |
| CN108447471B (en) | Speech recognition method and speech recognition device | |
| WO2019174131A1 (en) | Identity authentication method, server, and computer readable storage medium | |
| CN110334179B (en) | Question-answer processing method, device, computer equipment and storage medium | |
| CN108876588A (en) | A kind of loan measures and procedures for the examination and approval, device, server and storage medium | |
| CN106649739B (en) | Multi-round interactive information inheritance identification method and device and interactive system | |
| CN111506709B (en) | Entity linking method and device, electronic equipment and storage medium | |
| CN109522397B (en) | Information processing method and device | |
| CN113094478B (en) | Expression reply method, device, equipment and storage medium | |
| US10997609B1 (en) | Biometric based user identity verification | |
| WO2022116419A1 (en) | Automatic determination method and apparatus for domain name infringement, electronic device, and storage medium | |
| CN109635625B (en) | Intelligent identity verification method, equipment, storage medium and device | |
| US20230410222A1 (en) | Information processing apparatus, control method, and program | |
| CN112632248A (en) | Question answering method, device, computer equipment and storage medium | |
| WO2020024415A1 (en) | Voiceprint recognition processing method and apparatus, electronic device and storage medium | |
| CN113436614A (en) | Speech recognition method, apparatus, device, system and storage medium | |
| CN109660621A (en) | A kind of content delivery method and service equipment | |
| CN111818067B (en) | Flow characteristic extraction method and device | |
| CN113705164A (en) | Text processing method and device, computer equipment and readable storage medium | |
| CN109388695B (en) | User intention recognition method, apparatus and computer-readable storage medium | |
| CN110929519B (en) | Entity attribute extraction method and device | |
| CN111062345A (en) | Training method and device of vein recognition model and vein image recognition device | |
| CN112699348A (en) | Method and device for verifying nuclear body information, computer equipment and storage medium | |
| CN115618415A (en) | Sensitive data identification method and device, electronic equipment and storage medium | |
| CN114676237A (en) | Sentence similarity determining method and device, computer equipment and storage medium |
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 |