Information verification method, device, computer equipment and storage medium

Abstract

The embodiments of this specification provide an information verification method, apparatus, computer equipment and storage medium. The method includes: receiving an information verification request to be verified; performing compliance verification on the information verification request to obtain a first verification score, the compliance verification including at least one of keyword verification, format verification and sender identification verification; when the first verification score meets the first preset condition, performing layered verification on the information verification request to obtain multiple second verification results, the layered verification includes multiple verification dimensions corresponding to the multiple second verification results; based on the verification weights corresponding to each of the multiple second verification results, the multiple second verification results are merged to obtain a deep verification result; if the deep verification result meets the second preset condition, it is determined that the information verification request has passed the verification. In this way, the information verification efficiency can be improved while improving the accuracy of information verification.

Description

Technical Field

[0001] The implementation methods in this specification relate to the field of data processing technology, and specifically to an information verification method, apparatus, computer equipment, and storage medium. Background Art

[0002] With the development of information technology, information or data in production and life has exploded, and information security and data compliance have become increasingly important. For example, a large amount of information or data will be generated in some business processes, testing processes, monitoring and logging processes. In order to ensure that the information or data in the process meets the requirements of laws, regulations or internal policies or rules, it is necessary to effectively verify the authenticity, legality or security of the information or data generated in the process.

[0003] In related technologies, information verification is usually carried out by manual verification. However, faced with complex network attack methods, constantly changing compliance requirements or growing data processing needs, manual verification methods are often unable to meet the needs of fast, large-scale and accurate verification, and their verification accuracy and efficiency need to be improved.

[0004] Therefore, there is an urgent need to provide an information verification method to improve the accuracy and efficiency of information verification. Summary of the invention

[0005] In view of this, multiple embodiments of this specification are dedicated to providing an information verification method, apparatus, computer device and storage medium to improve the accuracy of information verification while improving the efficiency of information verification.

[0006] An implementation manner of the present specification provides an information verification method, the method comprising: receiving an information verification request to be verified; performing compliance verification on the information verification request to obtain a first verification score, wherein the compliance verification includes at least one of keyword verification, format verification and sender identification verification; when the first verification score satisfies a first preset condition, performing layered verification on the information verification request to obtain multiple second verification results, wherein the layered verification includes multiple verification dimensions corresponding one-to-one to the multiple second verification results; based on the verification weights corresponding to each of the multiple second verification results, fusing the multiple second verification results to obtain a deep verification result, wherein the verification weight can represent the importance of the corresponding verification dimension; if the deep verification result satisfies the second preset condition, it is determined that the information verification request has passed the verification.

[0007] In some embodiments, the information verification request includes a content text from a current sender and a current sender identifier corresponding to the current sender, and the first verification score is the sum of at least one of a keyword verification score, a format verification score, and a sender identifier verification score; the compliance verification of the information verification request includes: performing the keyword verification on the content text according to a preset keyword set to obtain the keyword verification score, wherein the keyword verification score is related to the number of detected keywords in the detected keyword set of the content text and the word score of each detected keyword; and / or, performing the format verification on the content text according to a preset format set to obtain the format verification score; and / or, performing the sender identifier verification on the current sender identifier according to a preset sender identifier set to obtain the sender identifier verification score.

[0008] In some embodiments, the keyword verification of the content text according to a preset keyword set to obtain the keyword verification score includes: performing word extraction on the content text to obtain an extracted word set of the content text, wherein the extracted word set includes one or more extracted words; performing keyword detection on the extracted word set of the content text according to the preset keyword set to determine a detected keyword set of the content text, wherein the detected keyword set includes one or more detected keywords; determining an initial keyword verification score of the content text according to the number of the detected keywords and the word score of each of the detected keywords; and calculating the The word weight of each extracted word in the extracted word set is determined, wherein the word weight of the extracted word can characterize the importance of the extracted word in the content text; the detected keywords in the detected keyword set are taken as current detected keywords in turn, and for each extracted word in the extracted word set, the context relevance score of the current detected keyword is determined based on the similarity between the current detected keyword and each extracted word, and the word weight of each extracted word; the initial keyword verification score is adjusted based on the context relevance score of each detected keyword in the detected keyword set to obtain the keyword verification score.

[0009] In some implementations, the keyword verification score is determined by the following formula: ; ; ;in, represents the initial keyword verification score, Represents the set of detected keywords The total number of keywords detected in Represents any detected keyword in the detected keyword set, Indicates the word score of any detected keyword, The first preset score is less than 0; Represents the extracted word set The total number of words extracted from represents any extracted word in the extracted word set, Represents the word weight of any extracted word, Represents the similarity between any detected keyword and any extracted word, represents the contextual relevance score of any detected keyword; Indicates the keyword verification score, Represents the adjustment factor.

[0010] In some implementations, the format verification score is determined by the following formula:

[0011] ; ;in, Indicates the format verification score, Represents a collection of preset formats The total number of preset formats in Represents the content text, Represents any preset format in the preset format set. is the second preset score and is less than 0, If and Returns 1 if there is a match, 0 otherwise.

[0012] In some implementations, the sender identity verification score is determined by the following formula:

[0013] ;in, Indicates the sender identity verification score, Indicates the preset sender ID set The total number of preset sender identifiers in represents any preset sender identifier in the preset sender identifier set, Represents the content text, is the third preset score and is less than 0, Indicates that if the current sender ID of the content text M is the same as the preset sender ID Returns 1 if there is a match, 0 otherwise.

[0014] In some embodiments, the information verification request includes content text from the current sender and / or time-related information of the information verification request, and the content text is a text generated based on one or more specified transactions in a specified process; the multiple verification dimensions in the layered verification include at least one of the following: integrity verification, timeliness verification, type parameter verification, transaction relevance verification, and transaction status verification; wherein the integrity verification is used to verify the integrity of the content text, the timeliness verification is based on the time-related information to verify the timeliness of the information verification request, the type parameter verification is used to verify the type and parameters of the content text, the transaction relevance verification is used to verify the relevance between the specified transaction of the content text and the preset transaction, and the transaction status verification is used to compare and verify the current status of the specified transaction of the content text with the preset status of the specified transaction.

[0015] In some embodiments, the multiple second verification results are fused based on the verification weights corresponding to each of the multiple second verification results to obtain a deep verification result, including: performing nonlinear transformation on the multiple second verification results according to an exponential function to obtain second verification enhancement results corresponding to each of the multiple second verification results, wherein the nonlinear transformation is used to enhance the distinction between the multiple second verification results to amplify the differences between the multiple second verification results; determining result correlation information between the multiple second verification results, wherein the result correlation information is represented by a covariance matrix; generating the deep verification result based on the verification weights corresponding to each of the multiple second verification results, the second verification enhancement results corresponding to each of the multiple second verification results, and the result correlation information between the multiple second verification results.

[0016] In some embodiments, the method further includes: obtaining current request load information and current processing capacity information, wherein the current request load information is determined based on one or more of the information verification requests currently received, the current request load information is used to describe the number of the information verification requests that currently need to be processed, and the current processing capacity information is used to describe the number of the information verification requests that can currently be processed; based on the current request load information and the current processing capacity information, determining delay fluctuation information, wherein the delay fluctuation information can represent the current processing pressure for the received information verification requests; and according to the delay fluctuation information, allocating computing resources or adjusting the request processing strategy for the information verification requests.

[0017] An embodiment of the present specification provides an information verification device, which includes: an information receiving module, which is used to receive an information verification request to be verified; an information pre-check module, which is used to perform compliance verification on the information verification request to obtain a first verification score, wherein the compliance verification includes at least one of keyword verification, format verification and sender identification verification; a layered verification module, which is used to perform layered verification on the information verification request when the first verification score meets a first preset condition to obtain multiple second verification results, wherein the layered verification includes multiple verification dimensions that correspond one to one with the multiple second verification results; a verification result fusion module, which is used to fuse the multiple second verification results based on the verification weights corresponding to each of the multiple second verification results to obtain a deep verification result, wherein the verification weight can represent the importance of the corresponding verification dimension; a verification result determination module, which is used to determine that the information verification request has passed the verification if the deep verification result meets the second preset condition.

[0018] An embodiment of the present specification provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the information verification method described in any of the above embodiments is implemented.

[0019] An embodiment of the present specification provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the information verification method described in any of the above embodiments is implemented.

[0020] The multiple implementation methods provided in this specification perform compliance verification on a received information verification request to obtain a first verification score, wherein the compliance verification includes at least one of keyword verification, format verification, and sender identification verification. Then, when the first verification score satisfies a first preset condition, a layered verification is performed on the information verification request to obtain multiple second verification results, wherein the layered verification includes multiple verification dimensions corresponding one-to-one to the multiple second verification results. Then, based on the verification weights corresponding to each of the multiple second verification results, the multiple second verification results are fused to obtain a deep verification result, wherein the verification weight can represent the importance of the corresponding verification dimension. Then, if the deep verification result satisfies the second preset condition, it is determined that the information verification request has passed the verification. In this way, the accuracy of information verification can be improved while the efficiency of information verification can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A schematic diagram of an information verification system provided for an embodiment of this specification;

[0022] Figure 2 A flowchart of an information verification method provided in an embodiment of this specification;

[0023] Figure 3 A schematic diagram of an information verification device provided in an embodiment of this specification;

[0024] Figure 4 A schematic diagram of a computer device provided for embodiments of the present specification. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the solution of this specification, the technical solution in the implementation of this specification will be clearly and completely described below in conjunction with the drawings in the implementation of this specification. Obviously, the described implementation is only a part of the implementation of this specification, not all of the implementations. Based on the implementation in this specification, all other implementations obtained by ordinary technicians in this field without creative work are within the scope of protection of this specification.

[0026] This specification provides an example of a scenario for an information verification system. Figure 1 , Figure 1 Schematic diagram of an information verification system provided in an embodiment of the present specification. The information verification system 100 may include a sender 110 and a verification platform 120. The sender 110 may transmit the data to be verified to the verification platform 120 through an information verification request, and the verification platform 120 may receive the information verification request from the sender and perform verification. The number of senders 110 may be one or more.

[0027] Exemplarily, the information verification system 100 may further include a configuration terminal 130. The configuration terminal may be used to configure configuration data for information verification, for example, a rule or rule set for information verification may be configured, and for another example, a verification dimension of the information verification process and a verification weight of the verification dimension may be configured, and the configured configuration data may be transmitted to the verification platform 120, so that the verification platform may verify the received information verification request based on the configuration data.

[0028] In this scenario example, the sender 110 may collect relevant data to be verified, and the relevant data may be data generated in a standardized business process, a test process, an experimental process, or a monitoring and logging process. For example, the relevant data may be data generated by data collection, mining, processing, analysis, and other operations in these processes. Exemplarily, the relevant data may be data involving personal privacy, financial transactions, or sensitive information. To ensure that the relevant data complies with the requirements of laws, regulations, internal policies, or other set rules, the sender 110 may transmit the relevant data to be verified to the verification platform 120, so that the authenticity, compliance, or security of the relevant data can be verified through the verification platform 120.

[0029] Exemplarily, the relevant data may be generated by one or more transactions in a standardized business process, a testing process, an experimental process, or a monitoring and logging process, wherein a transaction may be a series of operations performed as a single logical work unit in the corresponding process, and the transaction or the series of operations may either be completely successful or rolled back or undone in the event of an error, so as to maintain the consistency and integrity of the relevant data.

[0030] The sender 110 may be a terminal or a user, and the user may be a user account logged in on the terminal. The verification platform 120 may be a client or a server.

[0031] The client may be an electronic device with network access capability. For example, the client may be a desktop computer, a tablet computer, a laptop computer, a smart phone, a digital assistant, etc. Alternatively, the client may also be software that can be run in the electronic device. The server may be an electronic device with certain computing and processing capabilities. It may have a network communication module, a processor, a memory, etc. Exemplarily, the server may also be a distributed server, which may be a system with multiple processors, memories, network communication modules, etc. operating in collaboration. Alternatively, the server may also be a server cluster formed by several servers. Alternatively, with the development of science and technology, the server may also be a new technical means that can realize the corresponding functions of the implementation method of the specification. For example, it may be a new form of "server" based on quantum computing.

[0032] This specification provides a method for verifying information. Figure 2 , Figure 2 It is a flowchart of an information verification method provided by this embodiment. This embodiment provides method operation steps as shown in the flowchart, but may include more or fewer operation steps based on conventional or non-creative labor. The order of steps listed in the embodiment is only one execution method among many step execution sequences, and does not represent the only execution sequence. When the actual system or server product is executed, it can be executed sequentially or in parallel according to the method shown in the embodiment (for example, in a parallel processor or multi-threaded processing environment). This method can be applied to the verification platform in the information verification system, specifically as Figure 2 As shown, the information verification method may include the following steps.

[0033] Step S210: receiving an information verification request to be verified.

[0034] In some cases, the sender can transmit the relevant data to be verified to the verification platform through an information verification request. The verification platform can receive the information verification request from the sender and verify the information verification request and the relevant data.

[0035] Step S220: Perform compliance verification on the information verification request to obtain a first verification score, wherein the compliance verification includes at least one of keyword verification, format verification, and sender identification verification.

[0036] In some cases, the verification platform may obtain a pre-check rule set for compliance verification from the configuration end, wherein the pre-check rule set may include multiple pre-check rules.

[0037] In some other cases, the verification platform may be preset with a pre-check rule set, wherein the pre-check rule set may be obtained from a configuration end.

[0038] Exemplarily, the pre-check rule set may include at least one of the following: a preset keyword set, a preset format set, and a preset sender identification set. In other words, any pre-check rule in the pre-check rule set may be any one of the preset keyword set, the preset format set, and the preset sender identification set.

[0039] Among them, the preset keyword set is used to perform keyword verification on the information verification request, the preset format set is used to perform format verification on the information verification request, and the preset sender identification set is used to perform sender identification verification on the information verification request.

[0040] Specifically, to improve verification efficiency, compliance verification can be first performed based on a pre-check rule set for information verification requests to achieve pre-check, and deep verification can be performed after the pre-check passes. In this way, more significant compliance defects can be quickly identified, thereby improving information verification efficiency.

[0041] Step S230: When the first verification score satisfies the first preset condition, perform layered verification on the information verification request to obtain multiple second verification results, wherein the layered verification includes multiple verification dimensions corresponding to the multiple second verification results.

[0042] The first preset condition may be a compliance condition preset for compliance verification.

[0043] Specifically, the first verification score satisfies the first preset condition, indicating that the information verification request passes the compliance verification, or in other words, that the information verification request passes the pre-inspection. At this time, in order to improve the verification accuracy of the information verification request, the information verification request can be layered verified based on multiple verification dimensions to obtain multiple second verification results corresponding to the multiple verification dimensions.

[0044] Among them, layered verification can refer to verifying information verification requests according to multiple verification dimensions.

[0045] Step S240: Based on the verification weights corresponding to the multiple second verification results, the multiple second verification results are merged to obtain a deep verification result, wherein the verification weight can indicate the importance of the corresponding verification dimension.

[0046] Specifically, multiple verification dimensions can be respectively configured with corresponding verification weights, wherein the verification weights can be determined based on the importance and credibility of the corresponding verification dimensions. After obtaining the second verification results corresponding to each of the multiple verification dimensions, the multiple second verification results can be fused based on the verification weights to obtain a deep verification result, so that the verification accuracy of the information verification request can be further improved based on the importance and credibility of different verification dimensions.

[0047] Step S250: If the deep verification result meets the second preset condition, it is determined that the information verification request passes the verification.

[0048] The second preset condition may be a pass condition preset for a deep verification result after a fusion of a plurality of second verification results.

[0049] In the above implementation, a first verification score is obtained by performing compliance verification on the received information verification request, wherein the compliance verification includes at least one of keyword verification, format verification and sender identification verification. Then, it is determined whether the first verification score satisfies the first preset condition. If the first verification score satisfies the first preset condition, the information verification request is layeredly verified to obtain multiple second verification results, wherein the layered verification includes multiple verification dimensions corresponding to the multiple second verification results one by one. Then, based on the verification weights corresponding to each of the multiple second verification results, the multiple second verification results are fused to obtain a deep verification result, wherein the verification weight can represent the importance of the corresponding verification dimension. Finally, it is determined whether the deep verification result satisfies the second preset condition. If the deep verification result satisfies the second preset condition, it is determined that the information verification request has passed the verification. In this way, the accuracy of information verification can be improved while the efficiency of information verification can be improved.

[0050] In some embodiments, the information verification request may include the content text from the current sender and the current sender identifier corresponding to the current sender. In other words, the relevant data to be verified includes the content text of the current sender and the current sender identifier corresponding to the current sender.

[0051] The current sender may refer to a sender that transmits an information verification request to the verification platform among one or more senders connected to the verification platform.

[0052] In this implementation, the first verification score may be the sum of at least one of a keyword verification score, a format verification score, and a sender identification verification score.

[0053] Specifically, performing compliance verification on the information verification request to obtain a first verification score may include one or more of steps S310 - S330 .

[0054] Step S310: Perform keyword verification on the content text according to a preset keyword set to obtain a keyword verification score, wherein the keyword verification score is related to the number of detected keywords in the detected keyword set of the content text and the word score of each detected keyword.

[0055] Specifically, keyword detection can be performed on the content text according to a preset keyword set to determine the detected keywords of the content text, or in other words, the number of detected keywords of the content text can be determined; then, the keyword verification score of the content text can be determined according to the number of detected keywords and the word score of each detected keyword, that is, the keyword verification score of the content text can be determined according to the word scores of all detected keywords.

[0056] The word score may be a keyword score corresponding to any detected keyword, which is a preset score. For example, the word scores of different detected keywords may be the same or different, that is, the keyword verification score of the content text may be related to the number of detected keywords and the fixed word scores, and may also be related to the importance of the detected keywords. For example, if the importance of different detected keywords is different, the corresponding word scores are also different.

[0057] Step S320: Perform format verification on the content text according to the preset format set to obtain a format verification score.

[0058] The preset format set may include at least one of the following: a date format matching rule and a numerical format matching rule. The date format matching rule may be used to verify the format of the date content in the content text, and the numerical format matching rule may be used to verify the format of the numerical content in the content text.

[0059] Specifically, the format of the date content may be determined based on the content text, and the format of the date content may be matched and verified based on the date format matching rule, so that a format verification score of the content text may be obtained.

[0060] Step S330: According to a preset sender identification set, the sender identification verification is performed on the current sender identification to obtain a sender identification verification score.

[0061] The preset sender identification set may include one or more preset sender identifications. The preset sender identification refers to the sender identification of the sender that is pre-set, pre-arranged or planned in the verification platform. The current sender identification is any one of the preset sender identification set.

[0062] Specifically, the current sender identifier may be verified based on whether each preset sender identifier in the preset sender identifier set matches the current sender identifier, thereby determining a sender identifier verification score.

[0063] In some implementations, keyword verification is performed on the content text according to a preset keyword set to obtain a keyword verification score, which may include the following steps S410-S430.

[0064] Step S410: extracting words from the content text to obtain an extraction word set of the content text, wherein the extraction word set includes one or more extraction words.

[0065] Specifically, based on relevant extraction methods of Natural Language Processing (NLP), words may be extracted from the content text to obtain an extracted word set of the content text.

[0066] Exemplarily, the extraction word set may include one or more extraction words.

[0067] Step S420: Perform keyword detection on the extracted word set of the content text according to the preset keyword set to determine the detected keyword set of the content text, wherein the detected keyword set includes one or more detected keywords.

[0068] Specifically, each extracted word in the extracted word set can be matched according to each preset keyword in the preset keyword set, and the extracted word in the extracted word set that matches any preset keyword can be identified and used as the detected keyword. In this way, the detected keyword set of the content text can be obtained.

[0069] Step S430: Determine the keyword verification score of the content text according to the number of detected keywords and the word score of each detected keyword.

[0070] For example, the word score corresponding to each detected keyword in the detected keyword set is the same. If the word score corresponding to each detected keyword is the same, the keyword verification score can be directly determined based on the word score and the number of detected keywords in the detected keyword set. As an example, the keyword verification score can be determined by Formula 1.

[0071] Formula 1

[0072] in, It can represent the keyword verification score. Represents the set of detected keywords The total number of keywords detected in Indicates the word score of any detected keyword, It is the first preset score and is less than 0.

[0073] In some implementations, keyword verification is performed on the content text according to a preset keyword set to obtain a keyword verification score, which may include steps S510-S540.

[0074] Step S510: Determine an initial keyword verification score of the content text according to the number of detected keywords and the word score of each detected keyword.

[0075] In some cases, in order to perform fuzzy matching on content texts and effectively handle contextual relationships in content texts, the relevance of detected keywords in the context of content texts can be evaluated, and the final keyword verification score can be determined based on the relevance of detected keywords in the context of content texts. This will help understand the meaning of detected keywords in the actual context of content texts, reduce false positives and negatives, and thus improve the detection accuracy and depth of detected keywords.

[0076] Exemplarily, the initial keyword verification score can also be determined by Formula 1, or in other words, the keyword verification score determined by the formula can be used as the initial keyword verification score. That is, in Formula 1, It can represent the initial keyword verification score, Represents the set of detected keywords The total number of keywords detected in Indicates the word score of any detected keyword, It is the first preset score and is less than 0.

[0077] Step S520: Calculate the word weight of each extracted word in the extracted word set, wherein the word weight of the extracted word can represent the importance of the extracted word in the content text.

[0078] Step S530: Take the detected keywords in the detected keyword set as the current detected keywords in turn, and for each extracted word in the extracted word set, determine the context relevance score of the current detected keyword based on the similarity between the current detected keyword and each extracted word, and the word weight of each extracted word.

[0079] By sequentially taking the detected keywords in the detected keyword set as the current detected keywords and determining the context relevance score of the current detected keywords, it is possible to determine the context relevance score of each detected keyword in the detected keyword set.

[0080] Step S540: Based on the context relevance score of each detected keyword in the detected keyword set, the initial keyword verification score is adjusted to obtain a keyword verification score.

[0081] Exemplarily, after the initial keyword verification score is determined by Formula 1, the keyword verification score or the adjusted keyword verification score may be determined by Formula 2 and Formula 3.

[0082] The keyword verification score can be determined by a formula.

[0083] Formula 2

[0084] Formula 3

[0085] in, It can represent the initial keyword verification score, Represents any detected keyword in the detected keyword set, Represents the extracted word set The total number of words extracted from represents any extracted word in the extracted word set, Represents the word weight of any extracted word, Represents the similarity between any detected keyword and any extracted word, represents the contextual relevance score of any detected keyword; represents the adjusted keyword verification score, Represents the adjustment coefficient, which is used to control the influence of the context relevance score on the keyword verification score.

[0086] In some implementations, the format verification score may be determined by Formula 4 and Formula 5.

[0087] Formula 4

[0088] Formula 5

[0089] in, Indicates the format verification score, Represents a collection of preset formats The total number of preset formats in Represents the content text, Represents any preset format in the preset format set. is the second preset score and is less than 0, If and Returns 1 if there is a match, 0 otherwise.

[0090] In some implementations, the sender identity verification score may be determined using Formula 6.

[0091] Formula 6

[0092] in, Indicates the sender identity verification score, Indicates the preset sender ID set The total number of preset sender identifiers in represents any preset sender identifier in the preset sender identifier set, Represents the content text, is the third preset score and is less than 0, Indicates that if the current sender ID of the content text is the same as the preset sender ID Returns 1 if there is a match, 0 otherwise.

[0093] In the above implementation, the first verification score can be determined by Formula 7 or Formula 8. Wherein, Represents the first verification score.

[0094] Formula 7

[0095] Formula 8

[0096] In some implementations, the word weight of any extracted word may be determined based on the word frequency of the extracted word in the content text.

[0097] In some implementations, whether the first verification score satisfies the first preset condition can be expressed by Formula 9.

[0098] Formula 9

[0099] in, is the set threshold, i.e. the first preset condition, Indicates that the verification is passed. Indicates that verification failed.

[0100] In the above implementation, by performing a more comprehensive pre-check on the information verification request based on a preset keyword set, a preset format set, and a preset sender identification set, the comprehensiveness of the preliminary compliance verification is improved, and complex and changeable information verification requests can be handled more flexibly. In keyword verification, the keyword verification score can be adjusted according to the contextual relevance of the detected keywords in the text content. In this way, the accuracy of keyword detection can be effectively improved, and sensitive words or non-compliant extracted words in the text content can be accurately identified, while reducing misjudgments and omissions caused by isolated keyword matching. In addition, through a more comprehensive pre-check, the processing efficiency and response speed of the information verification request can be improved when performing in-depth verification on the information verification request later, which is particularly important for scenarios that process a large number of information verification requests.

[0101] In some implementations, the information verification request may include not only the content text from the current sender but also time-related information of the information verification request.

[0102] In this embodiment, the content text may be text generated based on one or more specified transactions in a specified process. Exemplarily, the specified process may be a standardized business process, a test process, an experimental process, or a monitoring and logging process, and the specified process may include multiple transactions, and the specified transaction may be one of the multiple transactions. For example, the content text may be text data recorded or collected by one or more detection steps in a detection experiment process.

[0103] In this embodiment, the multiple verification dimensions in the layered verification may include at least one of the following: integrity verification, timeliness verification, type parameter verification, transaction correlation verification, and transaction status verification.

[0104] Among them, integrity verification can be used to verify the integrity of the content text, timeliness verification can verify the timeliness of the information verification request based on time-related information, type parameter verification is used to verify the type and parameters of the content text, transaction correlation verification is used to verify the correlation between the specified transaction of the content text and the preset transaction, and transaction status verification is used to compare and verify the current status of the specified transaction of the content text with the preset status of the specified transaction.

[0105] In this implementation, integrity verification may be performed based on a set elliptic curve encryption, or may be performed based on a nonlinear hybrid hash function.

[0106] Exemplarily, the following uses a nonlinear hybrid hash function for verification as an example for explanation, wherein the nonlinear hybrid hash function may be one or more nonlinear hash functions, such as SHA-256, SHA-3, etc. Before the current sender sends the content text through an information verification request, it may calculate a first hash value of the content text based on the selected nonlinear hybrid hash function, and then send the content text and the first hash value together to the verification platform through the information verification request. After receiving the information verification request, the verification platform may calculate a second hash value based on the received content text. If the first hash value is equal to the second hash value, it indicates that the content text or the information verification request carrying the content text has not been tampered with during transmission. In this way, integrity verification of the information verification request or the content text carried by the information verification request may be achieved.

[0107] As an example, the method for determining the first hash value or the second hash value may be determined by formula 10.

[0108] Formula 10

[0109] in, Indicates the content text a hash value of, for example, a first hash value or a second hash value; and It is a preset coefficient vector that can be used in nonlinear hybrid hash functions to increase randomness; Indicates the length of the content text. Is the first The ASCII value of the character; represents the modulo operation, is a prime number and can be used to make the hash value of the content text evenly distributed.

[0110] In this embodiment, the time-related information of the information verification request may include the time zone information of the current sender, and one or more of the generation time of the content text, the sending time of the information verification request, and the receiving time of the information verification request. The timeliness verification may be verified based on the time zone information carried by the information verification request, and at least one of the generation time of the content text, the sending time of the information verification request, and the receiving time of the information verification request.

[0111] Exemplarily, the verification platform may be preset with a specified time limit, and the verification platform may determine whether it is within the specified time limit based on the specified time limit and the received time-related information.

[0112] In this embodiment, the verification platform can be preset with preset types and preset parameters of the content text. When verifying the type parameters of the content, the received content text can be parsed, and the content and format in the content text can be analyzed to construct a content matrix of the content text. Then, the current eigenvalue is calculated based on the content matrix. Then, the current type and current parameters of the content text are determined based on the current eigenvalue. Then, a judgment is made based on whether the current type matches the preset type and whether the current parameters match the preset parameters, thereby verifying the type and parameters of the content text.

[0113] As another example, the verification platform may be preset with a specified matrix. When verifying the type parameters of the content text, the type and parameters of the content text may be verified based on the current eigenvalue of the content matrix corresponding to the content text and the preset specified matrix. For example, the type parameter verification may be represented by Formula 11.

[0114] Formula 11

[0115] in, a content matrix representing the content text, It can represent the verification results of the type and parameters of the content matrix for the content text. Indicates successful verification. Indicates that verification failed. represents the eigenvalue of the content matrix, that is, the current eigenvalue. It means that the type and parameters of the content text match the preset type and parameters.

[0116] In this embodiment, the verification platform can be configured with preset transactions, so that it can verify the content text related to the preset transaction, or in other words, it can verify the content text that is highly correlated with the preset transaction, so as to screen out the content text that is highly correlated with the preset transaction. Specifically, when verifying the transaction relevance of the content text, the designated transaction corresponding to the content text can be determined based on the content text, and the correlation or matching degree between the designated transaction and the preset transaction can be evaluated or associated to obtain an associated evaluation score. The higher the associated evaluation score, the stronger the correlation between the designated transaction and the preset transaction. If the associated evaluation score is greater than the set associated evaluation score threshold, the transaction relevance verification of the content text is passed.

[0117] In this embodiment, the verification platform can determine that one or more specified transactions in a specified process such as a business process, a test process, an experimental process, or a monitoring and logging process have respective preset states, so that the content text that conforms to the preset state can be verified, or in other words, the content text that conforms to the preset state can be screened. Specifically, when verifying the transaction state, the current state of the specified transaction of the content text can be determined based on the content text, and it is determined whether the current state meets or complies with the preset state. If it meets, the verification passes, otherwise the verification fails.

[0118] In some embodiments, the information verification request may also include a sender authority attribute corresponding to the current sender, wherein the sender authority attribute can represent the authority level information of the current sender. Accordingly, the multiple verification dimensions in the layered verification may also include sender authority verification. The sender authority verification may verify the authority level of the current sender based on the sender authority attribute of the current sender, thereby determining whether the authority level of the current sender passes or fails. Specifically, the sender authority attribute may be information such as the department to which the current sender belongs and the authority level.

[0119] In the above implementation, through one or more of integrity verification, timeliness verification, type parameter verification, transaction relevance verification, transaction status verification, and sender authority verification, the information verification request can be subjected to layered verification in multiple verification dimensions on the basis that the information verification request has passed compliance verification. In this way, the accuracy of information verification can be improved while the efficiency of information verification is improved, and the verification dimensions can be better adapted to the transaction logic and scenarios of the content text carried by the information verification request.

[0120] In some implementations, based on the verification weights corresponding to the multiple second verification results, the multiple second verification results are merged to obtain the deep verification result, which may include the following steps S610-S640:

[0121] Step S610: According to the exponential function, nonlinear transformation is performed on the multiple second verification results respectively to obtain second verification enhancement results corresponding to the multiple second verification results respectively, wherein the nonlinear transformation is used to enhance the distinction between the multiple second verification results to amplify the difference between the multiple second verification results.

[0122] In some cases, multiple second verification results under multiple verification dimensions can be integrated to improve the verification accuracy and verification efficiency of the verification results and reduce the error caused by a single verification dimension.

[0123] In some other cases, any of the multiple second verification results may be an evaluation score corresponding to the verification pass result or verification fail result under the corresponding verification dimension. For example, taking integrity verification among multiple verification dimensions as an example, if the verification result of integrity verification is verification pass, the corresponding second verification result may be 1, and if the verification result of integrity verification is verification fail, the corresponding second verification result may be 0.1. Similarly, the second verification results corresponding to timeliness verification, type parameter verification, transaction relevance verification, and transaction status verification may be determined in the same manner.

[0124] Exemplarily, the second verification enhancement result may be determined by formula 12. Wherein, represents any second verification result among a plurality of second verification results, represents the second verification enhancement result corresponding to any second verification result, is a regularization parameter that can be used to adjust the magnification of the result. Represents the adjustment coefficient, which can be used to further fine-tune the results.

[0125] Formula 12

[0126] Step S620: Determine result correlation information between multiple second verification results, wherein the result correlation information is represented by a covariance matrix.

[0127] Step S630: Generate a deep verification result based on the verification weights corresponding to each of the plurality of second verification results, the second verification enhancement results corresponding to each of the plurality of second verification results, and the result correlation information between the plurality of second verification results.

[0128] Exemplarily, the depth verification result can be determined by formula 13.

[0129] Formula 13

[0130] in, Indicates the deep verification result. represents any second verification result among a plurality of second verification results, represents the second verification enhancement result corresponding to any second verification result, represents the verification weight of any second verification result, represents the number of multiple second verification results or the number of multiple verification dimensions, represents the covariance matrix, that is, the result correlation information between multiple second verification results, To include all second verification enhancement results Vector.

[0131] Specifically, after obtaining the depth verification result, the depth verification result can be determined according to the second preset condition. If the depth verification result meets the second preset condition, it is determined that the information verification request has passed the verification; otherwise, it is determined that the information verification request has not passed the verification.

[0132] Exemplarily, judging the depth verification result according to the second preset condition can be expressed by formula 14, where: Indicates the judgment result of the deep verification result, represents the second preset condition, which is a preset threshold value. Indicates the depth verification result.

[0133] Formula 14

[0134] In some implementations, the information verification method may further include the following steps S710-S730.

[0135] Step S710: Obtain current request load information and current processing capacity information, wherein the current request load information is determined based on one or more information verification requests currently received, the current request load information is used to describe the number of information verification requests that need to be processed currently, and the current processing capacity information is used to describe the number of information verification requests that can be processed currently.

[0136] In some cases, in order to ensure stability and response time when processing a large number of concurrent information verification requests, thereby improving the efficiency of information verification, the processing capacity of the information verification system or verification platform can be adjusted and scheduled.

[0137] Among them, the current request load information is used to describe the current request load, which may refer to the number of information verification requests currently received, that is, the current workload. The current processing capacity information is used to describe the current processing capacity, which may refer to the number of information verification requests that can be processed at present. Exemplarily, the current request load or the current processing capacity may be related to the overall processing capacity of the information verification system, which may include but is not limited to the computing power of the verification platform, network bandwidth, number of threads, etc.

[0138] Step S720: Determine delay fluctuation information based on current request load information and current processing capability information, wherein the delay fluctuation information can represent the current processing pressure for the received information verification request.

[0139] Among them, the delay fluctuation information can describe the delay fluctuation of the response time for processing information verification requests, or in other words, the delay fluctuation information can describe the instability and volatility exhibited by the response time of information verification requests. This delay fluctuation is usually manifested as significant differences in response times between different information verification requests, even if these different information verification requests are similar.

[0140] Exemplarily, the delay fluctuation information may be determined based on Formula 15.

[0141] Formula 15

[0142] in, Indicates delay fluctuation information, , , is the preset adjustment coefficient, Used for balance The degree of impact on the delay fluctuation information can reflect the impact of long-term load fluctuations; Used for balance The degree of impact on the delay fluctuation information can reflect the acceleration or deceleration of the load change trend; Used for balance The degree of influence on the delay fluctuation information is used to control the influence of the nonlinear adjustment item on the delay fluctuation information.

[0143] arrive The time period between represents the time period or time interval corresponding to the current request load and the current processing capacity. The current request load information and the current processing capacity information are based on arrive The time period between arrive During the time period between, the cumulative difference between the current request load and the current processing capacity, as well as the load change trend, can be calculated. Indicated in arrive Any time in the period between.

[0144] Indicates time The request load, Indicates time processing capabilities.

[0145] Indicated in arrive The cumulative difference or cumulative effect between the request load and the processing capacity in the time period between the two periods can reflect the cumulative impact of the request load exceeding the processing capacity in the long term.

[0146] The acceleration of the requested load change can represent the dynamic trend of the requested load change.

[0147] is a nonlinear adjustment term. and When the difference is large, the nonlinear adjustment term can be used to adjust and The difference between them is smoothed to reduce the probability of overload caused by a sudden large request load.

[0148] Step S730: Allocate computing resources or adjust the request processing strategy for the information verification request according to the delay fluctuation information.

[0149] Specifically, after the delay fluctuation information is determined, the delay fluctuation information may be evaluated to allocate computing resources of the information verification system or adjust computing resources and request processing strategies of the verification platform according to the evaluation result.

[0150] Exemplarily, if the delay fluctuation information is positive, or in other words, the delay fluctuation information is greater than or equal to 0, it indicates that the current request load exceeds the current processing capacity. At this time, it is necessary to increase the computing resources of the verification platform or optimize the request processing strategy of the verification platform. If the delay fluctuation information is less than 0, it indicates that the current processing capacity of the verification platform is in excess. At this time, part of the computing resources of the verification platform can be reallocated in the information verification system. In this way, dynamic adjustment of computing resources or request processing strategies in the information verification system can be achieved, and changes in the current request load caused by a large number of concurrent information verification requests can be responded to in real time, and the current processing capacity can be optimized, thereby minimizing delay fluctuations and reducing overload risks, thereby enabling the verification of information verification requests to run efficiently and stably.

[0151] This specification provides an information verification device, which can be applied to the verification platform in the information verification system. Figure 3 The information verification device may include an information receiving module 810, an information pre-checking module 820, a layered verification module 830, a verification result fusion module 840 and a verification result determination module 850.

[0152] An information receiving module 810 is used to receive a verification request for information to be verified;

[0153] An information pre-check module 820, configured to perform compliance verification on the information verification request to obtain a first verification score, wherein the compliance verification includes at least one of keyword verification, format verification, and sender identification verification;

[0154] A hierarchical verification module 830, configured to perform hierarchical verification on the information verification request to obtain a plurality of second verification results if the first verification score satisfies a first preset condition, wherein the hierarchical verification includes a plurality of verification dimensions corresponding to the plurality of second verification results one by one;

[0155] A verification result fusion module 840 is used to fuse the multiple second verification results based on the verification weights corresponding to the multiple second verification results to obtain a deep verification result, wherein the verification weight can indicate the importance of the corresponding verification dimension;

[0156] The verification result determination module 850 is configured to determine whether the information verification request has passed the verification if the deep verification result satisfies a second preset condition.

[0157] Regarding the specific functions and effects achieved by the information verification device, please refer to other embodiments of this specification for comparative explanation, and no further details will be given here. Each module in the information verification device can be implemented in whole or in part by software, hardware, and a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0158] The embodiments of the present specification also provide a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a computer, the computer executes the information verification method in any of the above embodiments.

[0159] The embodiments of the present specification also provide a computer program product including instructions, which, when executed by a computer, enables the computer to execute the information verification method in any of the above embodiments.

[0160] The embodiments of the present specification also provide a computer device, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the information verification method in the above embodiments is implemented.

[0161] In some embodiments, see Figure 4 The computer device can be a terminal or a client, and its internal structure diagram can be as follows Figure 4As shown. The computer device includes a processor, a memory, and a communication interface connected through a system bus. Among them, the processor of the computer device is used 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 the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, an information verification method is implemented.

[0162] It should be understood that the specific examples herein are only intended to help those skilled in the art to better understand the embodiments of the present specification, rather than to limit the scope of the present invention.

[0163] It can be understood that in the various implementations of this specification, the size of the sequence number of each process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the implementation methods of this specification.

[0164] It can be understood that the various embodiments described in this specification can be implemented individually or in combination, and the embodiments of this specification are not limited to this.

[0165] Unless otherwise specified, all technical and scientific terms used in the embodiments of this specification have the same meaning as those generally understood by those skilled in the art of the technical field of this specification. The terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the scope of this specification. The term "and / or" used in this specification includes any and all combinations of one or more related listed items. The singular forms of "a", "above", and "the" used in the embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0166] It can be understood that the processor of the embodiment of this specification can be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method implementation can be completed by the hardware integrated logic circuit or software instructions in the processor. The above processor can be a general processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiment of this specification can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiment of this specification can be directly embodied as a hardware decoding processor to perform, or the hardware and software modules in the decoding processor are combined and executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0167] It is understood that the memory in the embodiments of this specification may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (programmable ROM, PROM), an erasable programmable read-only memory (erasablePROM, EPROM), an electrically erasable programmable read-only memory (EEPROM) or a flash memory. The volatile memory may be a random access memory (RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0168] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this specification.

[0169] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method implementation methods and will not be repeated here.

[0170] The above is only a specific implementation of this specification, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in this specification, which should be included in the protection scope of this specification. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An information verification method, characterized in that: The method comprises: receiving a request for verification of information to be verified; Performing compliance verification on the information verification request to obtain a first verification score, wherein the compliance verification includes at least one of keyword verification, format verification, and sender identification verification; In the case where the first verification score satisfies a first preset condition, performing hierarchical verification on the information verification request to obtain a plurality of second verification results, wherein the hierarchical verification includes a plurality of verification dimensions corresponding one to one to the plurality of second verification results; Based on the verification weights corresponding to the plurality of second verification results, the plurality of second verification results are merged to obtain a deep verification result, wherein the verification weight can indicate the importance of the corresponding verification dimension; If the deep verification result meets the second preset condition, it is determined that the information verification request passes the verification; The information verification request includes a content text from the current sender and / or time-related information of the information verification request, and the content text is a text generated based on one or more specified transactions in a specified process; the multiple verification dimensions in the layered verification include at least one of the following: integrity verification, timeliness verification, type parameter verification, transaction relevance verification, and transaction status verification; The integrity verification is used to verify the integrity of the content text, the timeliness verification is used to verify the timeliness of the information verification request based on the time-related information, the type parameter verification is used to verify the type and parameters of the content text, the transaction relevance verification is used to verify the relevance between the specified transaction of the content text and the preset transaction, and the transaction status verification is used to compare and verify the current status of the specified transaction of the content text with the preset status of the specified transaction; Among them, based on the verification weights corresponding to each of the multiple second verification results, the multiple second verification results are fused to obtain a deep verification result, including: according to an exponential function, the multiple second verification results are respectively nonlinearly transformed to obtain the second verification enhancement results corresponding to each of the multiple second verification results, wherein the nonlinear transformation is used to enhance the distinction between the multiple second verification results to amplify the difference between the multiple second verification results; determine the result correlation information between the multiple second verification results, wherein the result correlation information is represented by a covariance matrix; based on the verification weights corresponding to each of the multiple second verification results, the second verification enhancement results corresponding to each of the multiple second verification results, and the result correlation information between the multiple second verification results, the deep verification result is generated.

2. The method according to claim 1, characterized in that The information verification request includes a content text from a current sender and a current sender identifier corresponding to the current sender, and the first verification score is a sum of at least one of a keyword verification score, a format verification score, and a sender identifier verification score; The performing compliance verification on the information verification request includes: According to a preset keyword set, the keyword verification is performed on the content text to obtain the keyword verification score, wherein the keyword verification score is related to the number of detected keywords in the detected keyword set of the content text and the word score of each detected keyword; and / or, According to a preset format set, performing the format verification on the content text to obtain the format verification score; and / or, The sender identity verification is performed on the current sender identity according to a preset sender identity set to obtain the sender identity verification score.

3. The method according to claim 2, characterized in that The step of performing keyword verification on the content text according to a preset keyword set to obtain the keyword verification score includes: Performing word extraction on the content text to obtain an extraction word set of the content text, wherein the extraction word set includes one or more extraction words; According to the preset keyword set, keyword detection is performed on the extracted word set of the content text to determine the detected keyword set of the content text, wherein the detected keyword set includes one or more detected keywords; Determining an initial keyword verification score of the content text according to the number of the detected keywords and the word score of each of the detected keywords; Calculating the word weight of each of the extracted words in the extracted word set, wherein the word weight of the extracted word can represent the importance of the extracted word in the content text; Sequentially taking the detected keywords in the detected keyword set as current detected keywords, and for each of the extracted words in the extracted word set, determining the context relevance score of the current detected keyword based on the similarity between the current detected keyword and each of the extracted words, and the word weight of each of the extracted words; The initial keyword verification score is adjusted based on the context relevance score of each of the detected keywords in the detected keyword set to obtain the keyword verification score.

4. The method according to claim 3, characterized in that The keyword verification score is determined by the following formula: ； ； ； in, represents the initial keyword verification score, Represents the set of detected keywords The total number of keywords detected in Represents any detected keyword in the detected keyword set, Indicates the word score of any detected keyword, The first preset score is less than 0; Represents the extracted word set The total number of words extracted from represents any extracted word in the extracted word set, Represents the word weight of any extracted word, Represents the similarity between any detected keyword and any extracted word, represents the contextual relevance score of any detected keyword; Indicates the keyword verification score, Represents the adjustment factor.

5. The method according to claim 2, characterized in that: The format validation score is determined by the following formula: ； ； in, Indicates the format verification score, Represents a collection of preset formats The total number of preset formats in Represents the content text, Represents any preset format in the preset format set. is the second preset score and is less than 0, If and Returns 1 if there is a match, 0 otherwise.

6. The method according to claim 2, characterized in that The sender identity verification score is determined by the following formula: ； in, Indicates the sender identity verification score, Indicates the preset sender ID set The total number of preset sender identifiers in represents any preset sender identifier in the preset sender identifier set, Represents the content text, is the third preset score and is less than 0, Indicates that if the current sender ID of the content text M is the same as the preset sender ID Returns 1 if there is a match, 0 otherwise.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: Obtaining current request load information and current processing capacity information, wherein the current request load information is determined based on one or more information verification requests currently received, the current request load information is used to describe the number of the information verification requests that need to be processed currently, and the current processing capacity information is used to describe the number of the information verification requests that can be processed currently; Determining delay fluctuation information based on the current request load information and the current processing capacity information, wherein the delay fluctuation information can represent a current processing pressure for the received information verification request; According to the delay fluctuation information, computing resources are allocated or a request processing strategy for the information verification request is adjusted.

8. An information verification device, characterized in that: The device is used to implement the method according to claim 1, and the device comprises: An information receiving module, used for receiving a verification request for information to be verified; An information pre-check module, configured to perform compliance verification on the information verification request to obtain a first verification score, wherein the compliance verification includes at least one of keyword verification, format verification, and sender identification verification; a hierarchical verification module, configured to perform hierarchical verification on the information verification request to obtain a plurality of second verification results when the first verification score satisfies a first preset condition, wherein the hierarchical verification includes a plurality of verification dimensions corresponding one-to-one to the plurality of second verification results; A verification result fusion module, configured to fuse the plurality of second verification results based on verification weights corresponding to the plurality of second verification results to obtain a deep verification result, wherein the verification weight can indicate the importance of the corresponding verification dimension; A verification result determination module, configured to determine that the information verification request has passed the verification if the deep verification result satisfies a second preset condition; The information verification request includes a content text from the current sender and / or time-related information of the information verification request, and the content text is a text generated based on one or more specified transactions in a specified process; the multiple verification dimensions in the layered verification include at least one of the following: integrity verification, timeliness verification, type parameter verification, transaction relevance verification, and transaction status verification; The integrity verification is used to verify the integrity of the content text, the timeliness verification is used to verify the timeliness of the information verification request based on the time-related information, the type parameter verification is used to verify the type and parameters of the content text, the transaction relevance verification is used to verify the relevance between the specified transaction of the content text and the preset transaction, and the transaction status verification is used to compare and verify the current status of the specified transaction of the content text with the preset status of the specified transaction; Among them, based on the verification weights corresponding to each of the multiple second verification results, the multiple second verification results are fused to obtain a deep verification result, including: according to an exponential function, the multiple second verification results are respectively nonlinearly transformed to obtain the second verification enhancement results corresponding to each of the multiple second verification results, wherein the nonlinear transformation is used to enhance the distinction between the multiple second verification results to amplify the difference between the multiple second verification results; determine the result correlation information between the multiple second verification results, wherein the result correlation information is represented by a covariance matrix; based on the verification weights corresponding to each of the multiple second verification results, the second verification enhancement results corresponding to each of the multiple second verification results, and the result correlation information between the multiple second verification results, the deep verification result is generated.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the information verification method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the information verification method according to any one of claims 1 to 7 is implemented.

Images