Review message generation method and device and storage medium

Abstract

The application discloses a review message generation method and device and a storage medium, which can be applied to various scenes such as cloud technology, artificial intelligence, intelligent transportation and Internet of Vehicles, and the method comprises the following steps: acquiring data transfer records and initial review messages; determining first review description information of data transfer object features based on the matching result of the data transfer object features and first description information; determining at least two candidate abnormal index description information corresponding to the transfer data features; determining the candidate abnormal index description information matched with the transfer data features as the abnormal index description information of the transfer data features; determining second review description information of the transfer data features based on the matching result of the abnormal index description information of the transfer data features and second description information; and generating a review message based on the first review description information and the second review description information. The application improves the generation efficiency and accuracy of the review message.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus and storage medium for generating review messages. Background Technology

[0002] In existing technologies, the data transaction review position requires manual review of initial review messages, mainly analyzing and judging from dimensions such as customer information and customer transaction behavior in the transaction log. This process lacks technical support and is labor-intensive. The secondary review requires a comprehensive review of the initial review messages, which is time-consuming, has a large workload, and is prone to errors, such as overlooking similar typos or missing words leading to grammatical inconsistencies (e.g., "single payment amount" should actually be "single transaction amount"). Therefore, the existing technology for initial review message review is time-consuming, inefficient, and prone to errors.

[0003] Therefore, it is necessary to provide a method, apparatus and storage medium for generating review messages, which improves the efficiency and accuracy of review message generation. Summary of the Invention

[0004] This application provides a method, apparatus, and storage medium for generating review messages, which can improve the efficiency and accuracy of review message generation.

[0005] On the one hand, this application provides a method for generating a review message, the method comprising:

[0006] Acquire data transfer records and preliminary review messages; the data transfer records include data transfer object characteristics and transferred data characteristics; the preliminary review messages include first descriptive information of the data transfer object characteristics and second descriptive information of the transferred data characteristics.

[0007] Based on the matching result between the data transfer object features and the first description information, the first review description information of the data transfer object features is determined;

[0008] Determine at least two candidate anomaly indicator descriptions corresponding to the transferred data features;

[0009] Candidate anomaly indicator description information that matches the transferred data features is determined as the anomaly indicator description information of the transferred data features.

[0010] Based on the matching result between the anomaly indicator description information of the transferred data features and the second description information, the second review description information of the transferred data features is determined;

[0011] A review message is generated based on the first review description information and the second review description information.

[0012] On the other hand, a review message generation apparatus is provided, the apparatus comprising:

[0013] The information acquisition module is used to acquire data transfer records and preliminary review messages; the data transfer records include data transfer object characteristics and transferred data characteristics; the preliminary review messages include first descriptive information of the data transfer object characteristics and second descriptive information of the transferred data characteristics.

[0014] The first review description information determination module is used to determine the first review description information of the data transfer object feature based on the matching result between the data transfer object feature and the first description information;

[0015] The candidate anomaly indicator description information determination module is used to determine at least two candidate anomaly indicator description information corresponding to the transferred data features.

[0016] An abnormal indicator description information determination module is used to determine the candidate abnormal indicator description information that matches the characteristics of the transferred data as the abnormal indicator description information of the characteristics of the transferred data.

[0017] The second review description information determination module is used to determine the second review description information of the transfer data feature based on the matching result between the abnormal indicator description information of the transfer data feature and the second description information;

[0018] The review message generation module is used to generate a review message based on the first review description information and the second review description information.

[0019] On the other hand, a review message generation device is provided, the device including a processor and a memory, the memory storing at least one instruction or at least one program, the at least one instruction or the at least one program being loaded and executed by the processor to implement the review message generation method as described above.

[0020] On the other hand, a computer storage medium is provided, which stores at least one instruction or at least one program, which is loaded and executed by a processor to implement the review message generation method as described above.

[0021] On the other hand, a computer program product or computer program is provided, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the review message generation method as described above.

[0022] The review message generation method, apparatus, and storage medium provided in this application have the following technical advantages:

[0023] This application acquires data transfer records and preliminary review messages; the data transfer records include data transfer object characteristics and transferred data characteristics; the preliminary review message includes first description information of the data transfer object characteristics and second description information of the transferred data characteristics; based on the matching result of the data transfer object characteristics and the first description information, first review description information of the data transfer object characteristics is determined; thereby enabling rapid review of the description information of the data transfer object characteristics in the preliminary review message; at least two candidate abnormal indicator description information corresponding to the transferred data characteristics are determined; the candidate abnormal indicator description information matching the transferred data characteristics is determined as the abnormal indicator description information of the transferred data characteristics; thereby enabling rapid determination of the description information corresponding to the transferred data characteristics based on the pre-set abnormal indicator description information; then, based on the matching result of the abnormal indicator description information of the transferred data characteristics and the second description information, second review description information of the transferred data characteristics is determined; thereby enabling rapid review of the description information of the transferred data characteristics in the preliminary review message; finally, based on the first review description information and the second review description information, a review message is generated; thereby improving the generation efficiency and accuracy of the review message and reducing labor costs. Attached Figure Description

[0024] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a schematic diagram of a review message generation system provided in an embodiment of this application;

[0026] Figure 2 This is a flowchart illustrating a method for generating a review message according to an embodiment of this application;

[0027] Figure 3 This is a flowchart illustrating a method for determining first review description information provided in an embodiment of this application;

[0028] Figure 4 This is a flowchart illustrating a method for determining anomaly indicator description information of transferred data characteristics according to an embodiment of this application;

[0029] Figure 5This is a flowchart illustrating another method for determining abnormal indicator description information of transferred data characteristics provided in an embodiment of this application;

[0030] Figure 6 This is a schematic diagram of a review message provided in an embodiment of this application;

[0031] Figure 7 This is a schematic diagram of a review message for a review rejection after user confirmation, provided in an embodiment of this application.

[0032] Figure 8 This is a schematic diagram of a review message that has been confirmed by the reviewing user and has not been rejected, provided in an embodiment of this application.

[0033] Figure 9 This is a flowchart illustrating another method for generating a review message provided in an embodiment of this application;

[0034] Figure 10 This is a flowchart illustrating the method for matching transaction features with candidate anomaly indicator description information provided in an embodiment of this application.

[0035] Figure 11 This is a schematic diagram of the structure of a review message generation device provided in an embodiment of this application;

[0036] Figure 12 This is a schematic diagram of the structure of a server provided in an embodiment of this application;

[0037] Figure 13 This is a schematic diagram of the structure of a blockchain system provided in an embodiment of this application;

[0038] Figure 14 This is a schematic diagram of the block structure provided in the embodiments of this application. Detailed Implementation

[0039] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0040] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0041] Please see Figure 1 , Figure 1 This is a schematic diagram of a review message generation system provided in an embodiment of this application, such as... Figure 1 As shown, the review message generation system may include at least server 01 and client 02.

[0042] Specifically, in this embodiment, the server 01 may include a standalone server, a distributed server, or a server cluster composed of multiple servers. It may also be a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. The server 01 may include a network communication unit, a processor, and a memory, etc. Specifically, the server 01 can be used to determine first review description information of the data transfer object characteristics based on the matching result of the data transfer object characteristics and the first description information; and to determine second review description information of the transferred data characteristics based on the matching result of the abnormal indicator description information of the transferred data characteristics and the second description information; and to generate a review message based on the first review description information and the second review description information.

[0043] Specifically, in this embodiment, the client 02 may include physical devices such as smartphones, desktop computers, tablets, laptops, digital assistants, smart wearable devices, smart speakers, in-vehicle terminals, and smart TVs. It may also include software running on the physical device, such as web pages provided to users by service providers, or applications provided to users by those service providers. Specifically, the client 02 can be used to view the review message corresponding to the initial message online.

[0044] The following describes a method for generating a review message according to this application. This method can be applied to... Figure 1In server 01; Figure 2 This is a flowchart illustrating a method for generating a review message according to an embodiment of this application. This specification provides the operational steps of the method described in the embodiments or flowchart, but based on conventional or non-inventive methods, more or fewer operational steps may be included. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only possible execution order. In actual system or server product execution, the method can be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment) as shown in the embodiments or accompanying drawings. Specifically, as... Figure 2 As shown, the method may include:

[0045] S201: Obtain data transfer records and preliminary review messages; the data transfer records include data transfer object characteristics and transferred data characteristics; the preliminary review messages include first descriptive information of the data transfer object characteristics and second descriptive information of the transferred data characteristics.

[0046] In this embodiment, the method can be applied to suspected money laundering transactions. The data transfer record can be a suspicious money laundering transaction log, which can be determined based on transaction logs. The descriptive information in the preliminary review message can all correspond to preliminarily determined abnormal features. These abnormal features can be characteristics that confirm a money laundering transaction, used to determine the money laundering transaction. The preliminary review message can be a suspicious money laundering transaction log, and can be a message obtained from the first review of the data transfer record. The data transfer object characteristics can be customer characteristics in the transaction log. The data transfer object can include data transfer recipients and data transfer senders. The data transfer object characteristics can include, but are not limited to, basic information such as the data transfer object's name, age, gender, and document address. The transfer data characteristics can include, but are not limited to, transaction amount, transaction time, and transaction frequency. The transfer data characteristics can be characteristics within a preset time period, such as one week or one month from the current time.

[0047] In this embodiment of the application, the first description information is used to describe the characteristics of the data transfer object. For example, when the data transfer object characteristic is that the object is 60 years old, the first description information can be that the object is older. The second description information is used to describe the characteristics of the transferred data. For example, when the data transfer characteristic is that the customer's transaction time is between 2 am and 3 am within a week, the second description information can be that the customer frequently makes transactions late at night and in the early morning.

[0048] In this embodiment of the application, when there are multiple data transfer object features and multiple transfer data features in the data transfer record, these features may include normal features and abnormal features; and the description information in the initial review message may all be description information corresponding to abnormal features. There may be cases where there is no corresponding description information for a feature in the data transfer record. If such a case exists for the transfer data feature, the feature is directly recorded in the review message to remind the user to review it.

[0049] S203: Based on the matching result between the above-mentioned data transfer object features and the above-mentioned first description information, determine the first review description information of the above-mentioned data transfer object features.

[0050] In this embodiment of the application, when reviewing the characteristics of the data transfer object, the characteristics of the data transfer object can be matched with the first description information described above to obtain the corresponding review conclusion.

[0051] In this embodiment of the application, the above method further includes:

[0052] Determine whether the characteristics of the data transfer object match the first descriptive information.

[0053] In the embodiments of this application, such as Figure 3 As shown, the first review description information for determining the characteristics of the data transfer object based on the matching result between the characteristics of the data transfer object and the first description information includes:

[0054] S2031: If the data transfer object characteristics do not match the first description information, update the first description information based on the data transfer object characteristics, and set the first identifier information of the updated first description information;

[0055] In this application embodiment, the updated first identification information of the first description information may include, but is not limited to, modifying the font color of the first description information, adding underlines, or dynamically displaying it, so as to distinguish it from other description information, thereby attracting the attention of review users and improving review efficiency and accuracy.

[0056] S2033: Based on the updated first description information and the aforementioned first identification information, determine the aforementioned first review description information.

[0057] In this embodiment of the application, the above method further includes:

[0058] If the characteristics of the data transfer object match the first description information, the first description information is determined as the first review description information.

[0059] In this embodiment, "the data transfer object characteristics matching the first descriptive information" means that the first descriptive information accurately describes the data transfer object characteristics. In this case, the first descriptive information is directly determined as the first review descriptive information, thus retaining the conclusion of the initial review.

[0060] For example, if the data transfer target's characteristic is an age of 70, and the first description information is an older age (greater than 60 years old), then the data transfer target's characteristic is determined to match the first description information. If the first description information is a younger age (greater than 18 years old), then the data transfer target's characteristic is determined not to match the first description information. For example, if the data transfer target's characteristic is the name Zhang San, and the first description information is Zhang San, then the data transfer target's characteristic is determined to match the first description information.

[0061] S205: Determine at least two candidate anomaly indicator descriptions corresponding to the above-mentioned transfer data characteristics.

[0062] In this embodiment, at least two candidate anomaly indicator descriptions (e.g., m conditions) corresponding to the transferred data features can be pre-set. When there are multiple transferred data features, the same or different number of candidate anomaly indicator descriptions can be set for each transferred data feature; the candidate anomaly indicator descriptions are used to describe the abnormal transferred data features. Multiple anomaly values ​​can be pre-set for the transferred data features, and each anomaly value corresponds to one candidate anomaly indicator description.

[0063] In some embodiments, if the transfer data characteristic is transaction amount, the following candidate anomaly indicator description information can be set based on the transfer data characteristics within a preset time period:

[0064] Condition 1: The number of transactions with a single transaction amount that is a multiple of ten yuan or one hundred yuan accounts for more than 50%;

[0065] Condition 2: The number of transactions with a single transaction amount that is a multiple of ten yuan or one hundred yuan accounts for more than 30%;

[0066] Condition m: The percentage of transactions with a single transaction amount that is a multiple of ten or one hundred yuan exceeds X%.

[0067] In this embodiment of the application, after determining at least two candidate anomaly indicator descriptions, the method further includes:

[0068] Determine the priority of the descriptive information for each candidate anomaly indicator.

[0069] S207: The candidate anomaly indicator description information that matches the above-mentioned transfer data features is determined as the anomaly indicator description information of the above-mentioned transfer data features.

[0070] In this embodiment of the application, the candidate anomaly indicator description information that matches the above-mentioned transfer data features refers to information that is consistent with the feature value description in the transfer data features; for example, if the transfer data feature is that the number of transactions with a single transaction amount of 1000 accounts for 35% within a preset time period, then the above condition 1 (candidate anomaly indicator description information) corresponds to the following: the number of transactions with a single transaction amount of ten yuan or a multiple of one hundred yuan accounts for more than 30%.

[0071] In some embodiments, such as Figure 4 As shown, the above-mentioned candidate anomaly indicator description information that matches the above-mentioned transfer data features, and the anomaly indicator description information that is determined as the above-mentioned transfer data features, includes:

[0072] S2071: Determine at least two candidate anomaly indicator descriptions that match the above-mentioned transfer data features as target anomaly indicator descriptions;

[0073] S2073: Sort at least two target anomaly indicator descriptions based on the priority of each target anomaly indicator description;

[0074] S2075: Based on the ranking results of the description information of the abnormal indicators of each target, determine the description information of the abnormal indicators of the above-mentioned transferred data features.

[0075] In this embodiment, priority information for each target anomaly indicator description can be pre-set. When a data transfer feature matches multiple target anomaly indicator descriptions, the target anomaly indicator description with the highest priority can be determined as the anomaly indicator description of the transferred data feature. For example, condition 1 can be set as the highest priority, condition 2 as the second priority, and condition m as the lowest priority. If the data transfer feature matches multiple conditions 1, 2, and m simultaneously, then condition 1 with the highest priority can be determined as the anomaly indicator description of the transferred data feature.

[0076] In some embodiments, such as Figure 5 As shown, the above sorting of at least two target anomaly indicator descriptions based on the priority of each target anomaly indicator description information includes:

[0077] S20731: Determine the priority of the descriptive information for each target anomaly indicator;

[0078] S20733: Sort the description information of at least two target anomaly indicators in descending order of priority.

[0079] In some embodiments, the anomaly indicator description information used to determine the characteristics of the transferred data based on the sorting results of the anomaly indicator description information of each target may include:

[0080] S20751: The description information of the target anomaly indicator ranked first is determined as the description information of the anomaly indicator of the above-mentioned transferred data characteristics.

[0081] In this embodiment, the priority of each candidate abnormal indicator description information can be preset. For example, indicators that are of high concern or have a high degree of abnormality can be given a higher priority. If there are multiple target abnormal indicator description information that match the transfer data feature, the target abnormal indicator description information is sorted according to the priority of each target abnormal indicator description information, and the target abnormal indicator description information with the highest priority is determined as the abnormal indicator description information of the transfer data feature. This allows the output of the highest priority abnormal indicator description information corresponding to the transfer data feature, thereby improving the accuracy of the review.

[0082] In this embodiment of the application, the aforementioned transferred data features are at least two, and the method further includes:

[0083] The transfer data features that match words in the preset vocabulary in the above data transfer records are identified as target transfer data features; the preset vocabulary is used to store words whose error frequency is greater than a preset frequency threshold in historical periods.

[0084] The above-mentioned description information of at least two candidate anomaly indicators corresponding to the above-mentioned transferred data characteristics includes:

[0085] Identify at least two candidate anomaly indicators corresponding to the aforementioned target transfer data characteristics.

[0086] In this embodiment, words or fields with an error frequency greater than a preset frequency threshold can be identified based on historical data transfer records, historical initial review messages, and historical secondary review messages; that is, error-prone words are pre-determined, such as transaction amount, transaction time, etc. During the secondary review, these features can be the focus of the review. Transfer data features that match words in the preset thesaurus refer to transfer data features that include any one or more words from the preset thesaurus. When target transfer data features are identified, these key features can be reviewed multiple times, thereby improving the accuracy of the secondary review.

[0087] S209: Based on the matching result between the abnormal indicator description information of the above-mentioned transfer data characteristics and the above-mentioned second description information, determine the second review description information of the above-mentioned transfer data characteristics.

[0088] In this embodiment, the matching result between the anomaly indicator description information of the transferred data features and the aforementioned second description information includes two results: matching and non-matching. Matching means that the text similarity between the two is greater than a preset threshold, i.e., the two express the same meaning. Non-matching means that the text similarity between the two is less than or equal to the preset threshold, i.e., the two express different meanings.

[0089] In this embodiment of the application, the above method further includes:

[0090] Determine whether the description information of the abnormal indicators of the transferred data characteristics matches the second description information mentioned above.

[0091] In this embodiment of the application, the second review description information of the transfer data characteristics is determined by matching the above-mentioned abnormal indicator description information based on the above-mentioned transfer data characteristics with the above-mentioned second description information, including:

[0092] If the abnormal indicator description information of the above-mentioned transferred data features does not match the above-mentioned second description information, determine the second identification information of the above-mentioned abnormal indicator description information;

[0093] Based on the abnormal indicator description information of the above-mentioned transfer data characteristics and the above-mentioned second identification information, the above-mentioned second review description information is determined.

[0094] In this application embodiment, the second identification information may include, but is not limited to, setting the font color, underlining, or dynamic display, so as to distinguish the abnormal indicator description information from other description information, thereby attracting the attention of the review user and improving the review efficiency and accuracy.

[0095] In this embodiment of the application, the second review description information of the transfer data characteristics is determined by matching the above-mentioned abnormal indicator description information based on the above-mentioned transfer data characteristics with the above-mentioned second description information, including:

[0096] If the abnormal indicator description information of the above-mentioned transfer data features matches the above-mentioned second description information, determine the first data interval corresponding to the above-mentioned abnormal indicator description information and the second data interval corresponding to the above-mentioned second description information.

[0097] Based on the first data interval and the second data interval mentioned above, the second review description information of the aforementioned transferred data characteristics is determined.

[0098] In this embodiment of the application, the second review description information for determining the transfer data characteristics based on the first data interval and the second data interval includes:

[0099] If the first data interval is smaller than the second data interval, the abnormal indicator description information of the transferred data characteristics will be determined as the second review description information.

[0100] In this embodiment of the application, the second review description information of the transferred data feature can be determined by the size of the data range corresponding to different abnormal indicator description information; for example, if the first data range is 30-50 and the second data range is 20-60, then the abnormal indicator description information corresponding to the first data range is determined as the second review description information; thereby improving the accuracy of the second review description information.

[0101] In this embodiment of the application, the second review description information of the transfer data characteristics is determined by matching the above-mentioned abnormal indicator description information based on the above-mentioned transfer data characteristics with the above-mentioned second description information, including:

[0102] Based on at least two matching results between the anomaly indicator description information of the above-mentioned target transfer data characteristics and the above-mentioned second description information, the second review description information of the above-mentioned transfer data characteristics is determined.

[0103] In this embodiment of the application, the aforementioned preliminary examination message includes second descriptive information of abnormal data transfer characteristics. The second review descriptive information of the aforementioned transfer data characteristics is determined based on the matching result between the abnormal indicator descriptive information of the aforementioned transfer data characteristics and the aforementioned second descriptive information, including:

[0104] Determine whether there is second descriptive information in the aforementioned preliminary review message that matches the characteristics of the aforementioned target transfer data;

[0105] If it does not exist, the abnormal indicator description information of the above target transfer data characteristics shall be determined as the above second review description information.

[0106] If it exists, the matching result between the abnormal indicator description information based on the above-mentioned transfer data characteristics and the above-mentioned second description information is executed to determine the second review description information of the above-mentioned transfer data characteristics.

[0107] In this embodiment of the application, after determining the abnormal indicator description information of the target transfer data characteristics, it is matched with the preliminary review message. However, there is a situation where the abnormal indicator is not found during the preliminary review. In this case, there is no corresponding second description information in the preliminary review message, and the abnormal indicator description information obtained from the review is directly used as the second review description information.

[0108] In some embodiments, for abnormal features not found in the initial review message, specific identification information can be set in the corresponding second review description information to distinguish it from other information, and remarks can be added to prompt the review user to pay attention.

[0109] S2011: Generate a review message based on the first review description information and the second review description information described above.

[0110] In this embodiment of the application, generating a review message based on the first review description information and the second review description information may include:

[0111] Based on the above-mentioned first review description information and the above-mentioned second review description information, the review conclusion is obtained;

[0112] Based on the first review description information, the second review description information, and the aforementioned review conclusions, a review message is generated.

[0113] In this embodiment, the influence of the first and second review description information on the review conclusion can be set. For example, the first review description information can be set to "serious reminder," and the second review description information can be set to "minor reminder." If "serious reminder" information exists, the review rejection conclusion can be directly determined. If only "minor reminder" information exists, the review can be directly determined to be passed, and the minor reminder information can be retained. Alternatively, the review conclusion can be determined after manual review. In addition, besides manually setting indicators in advance, the "minor reminder" also needs to refer to indicators with lower review selection rates in the "serious reminder" section, and convert indicators with lower usage rates into "minor reminders" for relatively low-risk warnings that require review attention.

[0114] In this application embodiment, the review message may include conclusions drawn based on the first review description information and the second review description information.

[0115] In this embodiment of the application, the generation of a review message based on the first review description information and the second review description information includes:

[0116] Determine the first issue type corresponding to the aforementioned first review description information and the second issue type corresponding to the aforementioned second review description information;

[0117] Based on the first review description information, the first issue type, the second review description information, and the second issue type mentioned above, a review message is generated.

[0118] In this embodiment of the application, a first problem type corresponding to the first review description information and a second problem type corresponding to the second review description information can be determined based on the first review description information and the second review description information. The problem type may include, but is not limited to, objective description problems, language logic problems, insufficient evidence problems, final conclusion problems, and systemic problems. Specifically, the review description information can be determined based on the fields in the first review description information and the second review description information; for example, if the review description information includes "typos," then its problem type is determined to be an objective description problem; if the review description information includes "incoherent sentences," then its problem type is determined to be a language logic problem.

[0119] In this embodiment of the application, after generating the review message based on the first review description information and the second review description information, the method further includes:

[0120] Send the aforementioned review message to the target terminal so that the target terminal displays the aforementioned review message on the target page; and in response to an operation instruction triggered by the issue type display control on the target page, display at least two issue type selection controls; and in response to an operation instruction triggered by any issue type selection control, display the target issue type selection control and the review description information corresponding to the target issue type selection control.

[0121] In this embodiment of the application, the target terminal can be used to display the review message, and the user can select the content displayed in the review message and determine the final review conclusion.

[0122] In some embodiments, the target terminal may include a target application for reviewing the initial review message. In this target application, for example, when a user clicks to select the initial review message, the corresponding review message can be retrieved from the server and displayed. Figure 6 As shown, the review message can be displayed as a pop-up window on the target application's page. The displayed review message can include three parts: Part 1 (03), Part 2 (04), and Part 3 (05). Part 1 (03) displays review conclusion selection controls, including "Agree" and "Reject" controls. Part 2 (04) is descriptive information, characterizing the abnormal features; also known as anomaly alert information. Based on the severity of the anomaly, i.e., its impact on the review conclusion, it is divided into severe and minor alerts. Each alert has a corresponding selection control, allowing the review user to subjectively select the appropriate option, thereby generating the final review message. Part 3 (05) presents the basis for the review conclusion; different information can be displayed based on the selected review conclusion. For example... Figure 7 As shown, Figure 7This is a schematic diagram of a review message indicating a review rejection after user confirmation. The review user clicks the selection control corresponding to section 07 in the reminder information section; the selected control displays a "√" mark. Then, the user selects the "Reject" control in section 06 of the review conclusion selection control to confirm the review rejection conclusion. After selecting the reminder information, the selection control for displaying the reminder information in section 08 of the processing basis section initially displays one type of problem and its description. Multiple problem types can be displayed by triggering section 09 of the problem type selection control; and one type of problem and its corresponding description will be displayed based on the user's selection. For example... Figure 8 As shown, Figure 8 This is a schematic diagram of a review message that has not been rejected after being confirmed by the reviewing user. If there is no description of abnormal features in the review message or the reviewing user has not selected any reminder information, the "Agree" option in the review conclusion selection control 010 can be selected. The corresponding processing basis 011 section will display "Agree to report" or "Agree to continue monitoring". Specifically, the content output can be based on the conclusion of the review message. If the message conclusion is "report", "Agree to report" will be displayed. If the message conclusion is "not to report", "Agree to continue monitoring" will be displayed.

[0123] In one specific embodiment, in an anti-money laundering system, such as Figure 9 As shown, the method for generating review messages includes:

[0124] S901: During the initial review process, an initial review message is generated based on customer information and customer transaction records; the initial review message includes basic customer information, transaction characteristics, and due diligence information.

[0125] S903: The anti-money laundering system backend obtains the initial review message, customer information, and customer transaction records; matches the customer transaction records with a preset set of abnormal indicator description information to obtain the abnormal indicator description information corresponding to each feature in the transaction records, and matches it with the corresponding information in the initial review message to obtain the matching result; matches the customer information with the corresponding description information in the initial review message (e.g., field matching) to obtain the matching result; the matching result includes important reminder information and minor reminder information.

[0126] In some embodiments, the system backend extracts the customer's age field and matches it against the "older than average age" field in the initial review message. If the match fails, the system needs to output the problem and display it in the reminder. The system extracts the customer's gender and the gender field in the initial review message. If the match fails, it automatically outputs "gender description is incorrect". The system extracts the customer's name and matches it against the corresponding field in the initial review message. If the match succeeds, it automatically outputs "the message outputs the correct name".

[0127] In some embodiments, a dictionary of easily confused words collected manually in the early stage can also be used. The system extracts all fields from the dictionary and matches them with all fields in the initial review message. If a match is successful, the corresponding field is output to prompt the review user to conduct the review.

[0128] In some embodiments, the light reminder will subdivide the transaction characteristics into n characteristics, set abnormal characteristic indicators such as transaction amount, transaction time, and region, and assign m conditions to each characteristic value. Each condition will be given a priority. The system will match the transaction data in the case according to the above indicators. If the match is successful, the corresponding condition content will be automatically output. If multiple conditions are matched at the same time, the condition with the highest priority will be automatically output according to the priority.

[0129] like Figure 10 As shown, the flowchart of the matching method is as follows, including the steps:

[0130] S1001: Extract customer transaction data;

[0131] S1003: Extract n customer transaction features and set m conditions for each transaction feature;

[0132] In some embodiments, m conditions can be set for each transaction feature, or different numbers of conditions can be set for different transaction features.

[0133] S1005: Match each transaction feature with its corresponding condition to obtain the matching condition; if there are multiple matching conditions, retain the matching condition with the highest priority.

[0134] S1007: Send the matching results to the terminal for display.

[0135] In a specific embodiment, the matching logic for different transaction characteristics is as follows:

[0136] a. Transaction Amount: (The system prioritizes the percentage and number of single transactions in the transaction log, and matches them with pre-set abnormal transaction amount indicators. If any one indicator matches, the corresponding condition content is output. If multiple indicators match, condition 1 (the highest priority condition) is output first, and so on.)

[0137] Condition 1: The number of transactions with a single transaction amount that is a multiple of ten yuan or one hundred yuan accounts for more than 50%;

[0138] Condition 2: The number of transactions with a single transaction amount that is a multiple of ten yuan or one hundred yuan accounts for more than 30%;

[0139] Condition m: XXX.

[0140] b. Trading Time: (The system pre-defines the terms "late night", "early morning", and "daytime". It matches the percentage of late night, early morning, or daytime with pre-defined criteria for abnormal times. If any one of these criteria is matched, the corresponding condition is output. If multiple criteria are matched, condition 1 is output first, and so on.)

[0141] Condition 1: The number of transactions occurring late at night or in the early morning accounts for more than 30% (late at night and early morning are defined as 10 PM to 6 AM).

[0142] Condition 2: The number of transactions occurring in the early morning hours accounts for more than 30% (early morning is defined as 10 PM to 12 AM).

[0143] Condition m: YYY.

[0144] S905: Generate a review message based on the important reminder information and the minor reminder information.

[0145] In some embodiments, the content of the alert is matched with the initial review message. Content not reflected in the initial review message can be highlighted in red, while content already reflected in the initial review message is not displayed on the front end. Alternatively, the alert can be displayed directly on the front end without matching it with the initial review message to indicate risks.

[0146] In the existing technology, message review relies entirely on manual review without any technical assistance. Each review takes an average of 3 minutes, and nearly 100 cases need to be processed every day. This is time-consuming and prone to omissions and errors. Using the method of this application, the time for each message can be controlled within 2 minutes, improving efficiency by 30%.

[0147] This application utilizes data aggregation and organization, rather than human experience-based judgment, making it more accurate and comprehensive than manual analysis. It also assists in reviewing and controlling risk points, avoiding omissions and misjudgments. In summary, this embodiment improves the efficiency of reviewers while ensuring the accuracy of case characterization, and also saves manpower.

[0148] In the embodiments described in this specification, the above method may further include:

[0149] The blockchain system stores data transfer records and preliminary review messages. The blockchain system includes multiple nodes, which form a peer-to-peer network.

[0150] In some embodiments, the blockchain system can be Figure 13The structure shown depicts a peer-to-peer (P2P) network formed by multiple nodes. The P2P protocol is an application layer protocol that runs on top of the Transmission Control Protocol (TCP). In a blockchain system, any machine, such as a server or terminal, can join and become a node. A node comprises a hardware layer, a middleware layer, an operating system layer, and an application layer.

[0151] Figure 13 The functions of each node in the blockchain system shown include:

[0152] 1) Routing: A basic function of nodes used to support communication between nodes.

[0153] In addition to routing capabilities, nodes can also have the following functions:

[0154] 2) Applications are deployed in the blockchain to implement specific business needs. They record data related to the implementation of functions to form record data, carry digital signatures in the record data to indicate the source of the task data, and send the record data to other nodes in the blockchain system. When other nodes successfully verify the source and integrity of the record data, they add the record data to a temporary block.

[0155] 3) A blockchain consists of a series of blocks that are sequentially generated. Once a new block is added to the blockchain, it will not be removed. The blocks contain the data submitted by the nodes in the blockchain system.

[0156] In some embodiments, the block structure can be Figure 14 The structure shown includes a hash value for each block containing the transaction records stored in that block (the hash value of this block) and the hash value of the previous block. These blocks are linked together to form the blockchain. Additionally, blocks may include information such as a timestamp when they were generated. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains relevant information used to verify the validity of the information (anti-counterfeiting) and to generate the next block.

[0157] As can be seen from the technical solutions provided by the above embodiments of this application, the embodiments of this application obtain data transfer records and preliminary review messages; the data transfer records include data transfer object characteristics and transferred data characteristics; the preliminary review messages include first description information of the data transfer object characteristics and second description information of the transferred data characteristics; based on the matching result of the data transfer object characteristics and the first description information, first review description information of the data transfer object characteristics is determined; thereby realizing rapid review of the description information of the data transfer object characteristics in the preliminary review messages; determining at least two candidate abnormal indicator description information corresponding to the transferred data characteristics; and comparing the transferred data with the first description information. Based on the candidate anomaly indicator description information of feature matching, the anomaly indicator description information of the transferred data feature is determined; thus, the description information corresponding to the transferred data feature can be quickly determined according to the pre-set anomaly indicator description information; then, based on the matching result of the anomaly indicator description information of the transferred data feature and the second description information, the second review description information of the transferred data feature is determined; thereby realizing the rapid review of the description information of the transferred data feature in the initial review message; finally, based on the first review description information and the second review description information, a review message is generated; thereby improving the generation efficiency and accuracy of the review message and reducing labor costs.

[0158] It is understood that in the specific implementation of this application, user information such as data transfer records and other related data are involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0159] This application also provides a review message generation device, such as... Figure 11 As shown, the device includes:

[0160] The information acquisition module 1110 is used to acquire data transfer records and preliminary review messages; the data transfer records include data transfer object characteristics and transferred data characteristics; the preliminary review messages include first descriptive information of the data transfer object characteristics and second descriptive information of the transferred data characteristics.

[0161] The first review description information determination module 1120 is used to determine the first review description information of the data transfer object features based on the matching result between the data transfer object features and the first description information.

[0162] The candidate anomaly indicator description information determination module 1130 is used to determine at least two candidate anomaly indicator description information corresponding to the above-mentioned transferred data features.

[0163] The abnormal indicator description information determination module 1140 is used to determine the candidate abnormal indicator description information that matches the above-mentioned transfer data features as the abnormal indicator description information of the above-mentioned transfer data features.

[0164] The second review description information determination module 1150 is used to determine the second review description information of the above-mentioned transfer data features based on the matching result of the abnormal indicator description information of the above-mentioned transfer data features and the above-mentioned second description information.

[0165] The review message generation module 1160 is used to generate a review message based on the first review description information and the second review description information mentioned above.

[0166] In some embodiments, the first review description information determination module may include:

[0167] The first identification information setting unit is used to update the first description information based on the data transfer object characteristics and set the first identification information of the updated first description information if the data transfer object characteristics do not match the first description information.

[0168] The first review description information determination unit is used to determine the first review description information based on the updated first description information and the first identification information.

[0169] In some embodiments, the second review description information determination module may include:

[0170] The second identification information determination unit is used to determine the second identification information of the above-mentioned abnormal indicator description information if the above-mentioned abnormal indicator description information of the above-mentioned transferred data features does not match the above-mentioned second description information.

[0171] The first information determining unit is used to determine the second review description information based on the abnormal indicator description information of the above-mentioned transfer data characteristics and the above-mentioned second identification information.

[0172] In some embodiments, the second review description information determination module may include:

[0173] The data interval determination unit is used to determine the first data interval corresponding to the above-mentioned abnormal indicator description information and the second data interval corresponding to the above-mentioned second description information if the above-mentioned abnormal indicator description information matches the above-mentioned second description information.

[0174] The second information determining unit is used to determine the second review description information of the transferred data characteristics based on the first data interval and the second data interval.

[0175] In some embodiments, the data range determination unit may include:

[0176] The second review description information determination subunit is used to determine the abnormal indicator description information of the transferred data characteristics as the second review description information if the first data interval is smaller than the second data interval.

[0177] In some embodiments, the apparatus may further include:

[0178] The priority determination module is used to determine the priority of the description information of each candidate anomaly indicator.

[0179] In some embodiments, the abnormal indicator description information determination module may include:

[0180] The target anomaly indicator description information determination unit is used to determine at least two candidate anomaly indicator description information that match the above-mentioned transfer data features as the target anomaly indicator description information.

[0181] The sorting unit is used to sort at least two target anomaly indicator descriptions based on the priority of each target anomaly indicator description.

[0182] The abnormal indicator description information determination unit is used to determine the abnormal indicator description information of the above-mentioned transferred data features based on the sorting results of the abnormal indicator description information of each target.

[0183] In some embodiments, the above-mentioned transfer data features are at least two, and the apparatus may further include:

[0184] The target transfer data feature determination module is used to determine the transfer data features that match words in the above data transfer records as target transfer data features; the above-mentioned preset vocabulary is used to store words whose error frequency is greater than a preset frequency threshold in historical periods.

[0185] In some embodiments, the candidate anomaly indicator description information determination module may include:

[0186] The candidate anomaly information determination unit is used to determine at least two candidate anomaly indicator descriptions based on the aforementioned target transfer data characteristics.

[0187] In some embodiments, the second review description information determination module may include:

[0188] The information matching unit is used to determine the second review description information of the above-mentioned transfer data features based on at least two matching results between the abnormal indicator description information of the above-mentioned target transfer data features and the above-mentioned second description information.

[0189] In some embodiments, the review message generation module may include:

[0190] The problem type determination unit is used to determine the first problem type corresponding to the first review description information and the second problem type corresponding to the second review description information.

[0191] The review message generation unit is used to generate a review message based on the first review description information, the first issue type, the second review description information, and the second issue type.

[0192] In some embodiments, the apparatus may further include:

[0193] The review message sending module is used to send the review message to the target terminal so that the target terminal displays the review message on the target page; and in response to an operation instruction triggered by the problem type display control on the target page, to display at least two problem type selection controls; and in response to an operation instruction triggered by any problem type selection control, to display the target problem type selection control and the review description information corresponding to the target problem type selection control.

[0194] The apparatus and method embodiments described herein are based on the same inventive concept.

[0195] This application provides a review message generation device, which includes a processor and a memory. The memory stores at least one instruction or at least one program, which is loaded and executed by the processor to implement the review message generation method provided in the above method embodiments.

[0196] The embodiments of this application also provide a computer storage medium, which can be disposed in a terminal to store at least one instruction or at least one program related to implementing a review message generation method in the method embodiments. The at least one instruction or at least one program is loaded and executed by the processor to implement the review message generation method provided in the above method embodiments.

[0197] Embodiments of this application also provide a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the review message generation method provided in the above-described method embodiments.

[0198] Optionally, in this embodiment, the storage medium may be located at at least one of the multiple network servers in a computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0199] The memory described in this application embodiment can be used to store software programs and modules. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, applications required for the functions, etc.; the data storage area may store data created according to the use of the device, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory may also include a memory controller to provide the processor with access to the memory.

[0200] The review message generation method provided in this application can be executed on a mobile terminal, computer terminal, server, or similar computing device. Taking running on a server as an example... Figure 12 This is a hardware structure block diagram of a server for a review message generation method provided in an embodiment of this application. For example... Figure 12As shown, the server 1200 can vary significantly due to different configurations or performance. It may include one or more Central Processing Units (CPUs) 1210 (CPUs 1210 may include, but are not limited to, microprocessors (MCUs) or programmable logic devices (FPGAs), a memory 1230 for storing data, and one or more storage media 1220 (e.g., one or more mass storage devices) for storing application programs 1223 or data 1222. The memory 1230 and storage media 1220 may be temporary or persistent storage. The program stored in the storage media 1220 may include one or more modules, each module may include a series of instruction operations on the server. Furthermore, the CPU 1210 may be configured to communicate with the storage media 1220 and execute the series of instruction operations stored in the storage media 1220 on the server 1200. Server 1200 may also include one or more power supplies 1260, one or more wired or wireless network interfaces 1250, one or more input / output interfaces 1240, and / or one or more operating systems 1221, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0201] The input / output interface 1240 can be used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of server 1200. In one example, the input / output interface 1240 includes a network interface controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the input / output interface 1240 may be a radio frequency (RF) module for wireless communication with the Internet.

[0202] Those skilled in the art will understand that Figure 12 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, server 1200 may also include... Figure 12 The more or fewer components shown, or having the same Figure 12 The different configurations shown.

[0203] As can be seen from the embodiments of the review message generation method, apparatus, device, or storage medium provided in this application above, this application obtains data transfer records and preliminary review messages; the data transfer records include data transfer object characteristics and transferred data characteristics; the preliminary review message includes first descriptive information of the data transfer object characteristics and second descriptive information of the transferred data characteristics; based on the matching result of the data transfer object characteristics and the first descriptive information, the first review description information of the data transfer object characteristics is determined; thereby realizing rapid review of the description information of the data transfer object characteristics in the preliminary review message; determining at least two candidate abnormal indicator description information corresponding to the transferred data characteristics; and... Candidate anomaly indicator description information matching the transferred data feature is determined as the anomaly indicator description information of the transferred data feature; thus, the description information corresponding to the transferred data feature can be quickly determined based on the pre-set anomaly indicator description information; then, based on the matching result between the anomaly indicator description information of the transferred data feature and the second description information, the second review description information of the transferred data feature is determined; thereby realizing rapid review of the description information of the transferred data feature in the initial review message; finally, based on the first review description information and the second review description information, a review message is generated; thereby improving the generation efficiency and accuracy of the review message and reducing labor costs.

[0204] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, specific embodiments have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0205] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0206] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer storage medium, such as a read-only memory, a disk, or an optical disk.

[0207] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for generating a review message, characterized in that, The method includes: Acquire data transfer records and preliminary review messages; the data transfer records include data transfer object characteristics and transferred data characteristics; the preliminary review messages include first descriptive information of the data transfer object characteristics and second descriptive information of the transferred data characteristics. Based on the matching result between the data transfer object features and the first description information, the first review description information of the data transfer object features is determined; Determine at least two candidate anomaly indicator descriptions corresponding to the transferred data features; Candidate anomaly indicator description information that matches the transferred data features is determined as the anomaly indicator description information of the transferred data features. Based on the matching result between the anomaly indicator description information of the transferred data features and the second description information, the second review description information of the transferred data features is determined; A review message is generated based on the first review description information and the second review description information.

2. The method according to claim 1, characterized in that, The step of determining the first review description information of the data transfer object features based on the matching result between the data transfer object features and the first description information includes: If the data transfer object features do not match the first description information, update the first description information based on the data transfer object features, and set the first identifier information of the updated first description information; The first review description information is determined based on the updated first description information and the first identification information.

3. The method according to claim 1, characterized in that, The matching result between the anomaly indicator description information based on the transfer data features and the second description information determines the second review description information of the transfer data features, including: If the abnormal indicator description information of the transferred data features does not match the second description information, determine the second identification information of the abnormal indicator description information; Based on the anomaly indicator description information of the transferred data characteristics and the second identification information, the second review description information is determined.

4. The method according to claim 1, characterized in that, The matching result between the anomaly indicator description information based on the transfer data features and the second description information determines the second review description information of the transfer data features, including: If the abnormal indicator description information of the transferred data features matches the second description information, determine the first data interval corresponding to the abnormal indicator description information and the second data interval corresponding to the second description information; Based on the first data interval and the second data interval, a second review description information for the transferred data characteristics is determined.

5. The method according to claim 4, characterized in that, The second review description information for determining the characteristics of the transferred data based on the first data interval and the second data interval includes: If the first data interval is smaller than the second data interval, the abnormal indicator description information of the transferred data feature is determined as the second review description information.

6. The method according to any one of claims 1-5, characterized in that, After determining at least two candidate anomaly indicator descriptions, the method further includes: Determine the priority of the descriptive information for each candidate anomaly indicator; The step of determining the candidate anomaly indicator description information that matches the transferred data features as the anomaly indicator description information of the transferred data features includes: The description information of at least two candidate anomaly indicators that match the characteristics of the transferred data is determined as the target anomaly indicator description information. Based on the priority of each target anomaly indicator description information, sort at least two target anomaly indicator description information. Based on the sorting results of the anomaly indicator description information of each target, the anomaly indicator description information of the transferred data features is determined.

7. The method according to any one of claims 1-5, characterized in that, The transferred data features are at least two, and the method further includes: The transfer data features that match words in the preset vocabulary in the data transfer record are identified as target transfer data features; the preset vocabulary is used to store words whose error frequency is greater than a preset frequency threshold in historical time periods. The determination of at least two candidate anomaly indicator descriptions corresponding to the transferred data features includes: Based on the characteristics of the target transfer data, at least two candidate anomaly indicator descriptions are determined; The matching result between the anomaly indicator description information based on the transfer data features and the second description information determines the second review description information of the transfer data features, including: Based on at least two matching results between the anomaly indicator description information of the target transfer data feature and the second description information, the second review description information of the transfer data feature is determined.

8. The method according to any one of claims 1-5, characterized in that, The step of generating a review message based on the first review description information and the second review description information includes: Determine the first issue type corresponding to the first review description information and the second issue type corresponding to the second review description information; Based on the first review description information, the first issue type, the second review description information, and the second issue type, a review message is generated; After generating the review message based on the first review description information and the second review description information, the method further includes: Send the review message to the target terminal so that the target terminal displays the review message on the target page; and in response to an operation instruction triggered by the issue type display control on the target page, display at least two issue type selection controls; and in response to an operation instruction triggered by any issue type selection control, display the target issue type selection control and the review description information corresponding to the target issue type selection control.

9. A device for generating a review message, characterized in that, The device includes: The information acquisition module is used to acquire data transfer records and preliminary review messages; the data transfer records include data transfer object characteristics and transferred data characteristics; the preliminary review messages include first descriptive information of the data transfer object characteristics and second descriptive information of the transferred data characteristics. The first review description information determination module is used to determine the first review description information of the data transfer object feature based on the matching result between the data transfer object feature and the first description information; The candidate anomaly indicator description information determination module is used to determine at least two candidate anomaly indicator description information corresponding to the transferred data features. An abnormal indicator description information determination module is used to determine the candidate abnormal indicator description information that matches the characteristics of the transferred data as the abnormal indicator description information of the characteristics of the transferred data. The second review description information determination module is used to determine the second review description information of the transfer data feature based on the matching result between the abnormal indicator description information of the transfer data feature and the second description information; The review message generation module is used to generate a review message based on the first review description information and the second review description information.

10. A computer storage medium, characterized in that, The computer storage medium stores at least one instruction or at least one program, which is loaded and executed by a processor to implement the review message generation method as described in any one of claims 1-8.

11. A computer program product comprising computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the review message generation method as described in any one of claims 1-8.

Images