Abnormal medium determination method, device, system and equipment and medium

Abstract

The invention relates to the technical field of data processing, in particular to an abnormal medium determination method and device, equipment and a medium, and is used for solving the problem of low calculation efficiency in the prior art. The method comprises the following steps: acquiring first transaction detail data of an account in a preset period; for each piece of first transaction detail data of the account, obtaining target transaction content contained in a transaction abstract in the first transaction detail data, and determining a target behavior type corresponding to the first transaction detail data according to the target transaction content and a stored corresponding relationship between the transaction content and the behavior type; determining a target transaction medium type corresponding to the first transaction detail data according to a corresponding relationship between a stored behavior type and a transaction medium type; and determining an abnormal transaction medium set of the account according to the target transaction medium type corresponding to each piece of first transaction detail data. The abnormal transaction medium set of the customer is determined based on the target transaction content, a large amount of useless transaction information is removed, and the calculation efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an abnormal medium determination method, device, system, equipment and medium. Background Art

[0002] With the advent of the big data and information age, transaction media such as the Internet Protocol (IP) and Multiple Access Channel (MAC), as the only identifier for connecting to the Internet, occupy a very important position in the field of network security and risk control.

[0003] The transaction medium contains the geographic location information of the device or user. In financial transactions, by analyzing the behavior patterns and network characteristics of the transaction medium, abnormal activities can be identified, fraud can be prevented, and the security of the entire financial system can be improved. In scenarios such as anti-money laundering and anti-fraud, rapid analysis and identification of users' abnormal transaction media can effectively identify the relationship between users and abnormal transaction media, and use abnormal transaction media as a bridge to dig out abnormal transaction gangs.

[0004] However, in the current related technologies, all transaction information of the customer including the transaction medium is usually retained, and the relationship between the customer and the transaction information is established. Subsequently, the customer's transaction medium is determined based on the customer's transaction information. This method can ensure that all the customer's transaction medium information is obtained, but the amount of data is too large when applied, which affects the computing efficiency. Summary of the invention

[0005] The embodiments of the present application provide a method, device, equipment and medium for determining an abnormal medium, so as to solve the problem of low computing efficiency existing in the prior art.

[0006] In a first aspect, the present application provides a method for determining an abnormal medium, the method comprising:

[0007] Obtaining the first transaction details of the account within a preset period;

[0008] For each first transaction detail data of the account, the target transaction content included in the transaction summary in the first transaction detail data is obtained, and the target behavior type corresponding to the first transaction detail data is determined according to the target transaction content and the correspondence between the transaction content and the behavior type saved in advance; and the target transaction medium type corresponding to the first transaction detail data is determined according to the correspondence between the behavior type and the transaction medium type saved in advance;

[0009] According to the target transaction medium type corresponding to each first transaction detail data, the abnormal transaction medium set of the account is determined.

[0010] Through the above method, the target transaction content contained in the transaction summary in the first transaction detail data of the account is obtained, and a large amount of useless transaction information is removed, so that the customer's abnormal transaction medium set is determined based on the target transaction content, which can improve calculation efficiency.

[0011] In a possible implementation manner, obtaining the target transaction content included in the transaction summary in the first transaction detail data includes:

[0012] Get the historical transaction content in the saved historical content collection;

[0013] Determine whether the transaction summary in the first transaction detail data contains all the word segments corresponding to any historical transaction content. If so, determine the historical transaction content as the target transaction content included in the first transaction detail data.

[0014] In a possible implementation manner, if the transaction summary in the first transaction detail data does not include all the word segments corresponding to any historical transaction content, obtaining the target transaction content included in the transaction summary in the first transaction detail data includes:

[0015] The transaction summary in the first transaction detail data is segmented, and according to the sentence component to which each segmented word belongs, the segmented words of the preset sentence components are spliced ​​to obtain the target transaction content.

[0016] In a possible implementation, the method further includes:

[0017] The target transaction content is added to the historical content collection.

[0018] In a possible implementation manner, the process of determining the historical transaction content includes:

[0019] Obtain a historical transaction summary of a preset number of historical transaction detail data within a period, segment the historical transaction summary, and according to the sentence component to which each segmented word belongs, concatenate the segmented words of the preset sentence components to obtain the historical transaction content, and add the historical transaction content to the historical content collection.

[0020] In a possible implementation, after acquiring the historical transaction summaries of the historical transaction detail data within a preset number of periods and before segmenting the historical transaction summaries, the method further includes:

[0021] Selecting part of the historical transaction detail data and performing subsequent operations on the part of the historical transaction detail data;

[0022] After adding the historical transaction content to the historical content collection, the method further includes:

[0023] Filtering other historical transaction detail data including the historical transaction content in the remaining part of the historical transaction detail data to obtain filtered second transaction detail data;

[0024] Repeat the step of selecting part of the historical transaction detail data for the second transaction detail data until there is no filtered second transaction detail data after filtering other historical transaction detail data containing the historical transaction content.

[0025] In a possible implementation manner, determining the abnormal transaction medium set of the account according to the target transaction medium type corresponding to each first transaction detail data includes:

[0026] Determine, among all first transaction detail data, that the target transaction medium type is specific transaction detail data of a specific transaction medium type;

[0027] Acquire the specific transaction medium included in the specific transaction detail data;

[0028] It is determined whether other first transaction detail data except the specific transaction detail data include the specific transaction medium; if not, the specific transaction medium is determined to be an abnormal transaction medium in the abnormal transaction medium set.

[0029] In a possible implementation manner, before determining whether other first transaction detail data other than the specific transaction detail data includes the specific transaction medium, the method further includes:

[0030] Acquire daily transaction media included in other first transaction detail data except the specific transaction detail data;

[0031] The determining whether other first transaction detail data other than the specific transaction detail data contains the specific transaction medium comprises:

[0032] It is determined whether the specific transaction medium is located in the daily transaction medium.

[0033] In a second aspect, the present application provides an abnormal medium determination device, the device comprising:

[0034] An acquisition module, used to acquire the first transaction detail data of an account within a preset period;

[0035] a processing module, configured to obtain, for each first transaction detail data of the account, a target transaction content included in a transaction summary in the first transaction detail data, and determine a target behavior type corresponding to the first transaction detail data according to the target transaction content and a pre-saved correspondence between the transaction content and the behavior type; and determine a target transaction medium type corresponding to the first transaction detail data according to a saved correspondence between the behavior type and the transaction medium type;

[0036] The determination module is used to determine the abnormal transaction medium set of the account according to the target transaction medium type corresponding to each first transaction detail data.

[0037] In a possible implementation, the processing module is specifically used to obtain historical transaction content in a saved historical content set; determine whether the transaction summary in the first transaction detail data contains all the word segments corresponding to any historical transaction content, and if so, determine the historical transaction content as the target transaction content contained in the first transaction detail data.

[0038] In a possible implementation, the processing module is specifically used to segment the transaction summary in the first transaction detail data if the transaction summary in the first transaction detail data does not contain all the segmented words corresponding to any historical transaction content, and to concatenate the segmented words of the preset sentence components according to the sentence component to which each segmented word belongs to obtain the target transaction content.

[0039] In a possible implementation manner, the processing module is further configured to add the target transaction content to a historical content collection.

[0040] In a possible implementation, the processing module is specifically used to obtain a historical transaction summary of historical transaction detail data within a preset number of periods, segment the historical transaction summary, and according to the sentence component to which each segmented word belongs, concatenate the segmented words of the preset sentence components to obtain the historical transaction content, and add the historical transaction content to a historical content collection.

[0041] In a possible implementation, the processing module is further configured to, after acquiring the historical transaction summaries of the historical transaction detail data within a preset number of periods, select part of the historical transaction detail data before segmenting the historical transaction summaries, and perform subsequent operations on the part of the historical transaction detail data;

[0042] The processing module is also used to, after adding the historical transaction content to the historical content collection, filter other historical transaction detail data containing the historical transaction content in the remaining part of the historical transaction detail data to obtain filtered second transaction detail data; repeat the step of selecting part of the historical transaction detail data for the second transaction detail data until the filtered second transaction detail data does not exist after filtering other historical transaction detail data containing the historical transaction content.

[0043] In a possible implementation, the determination module is specifically used to determine, among all first transaction detail data, specific transaction detail data in which the target transaction medium type is a specific transaction medium type; obtain the specific transaction medium contained in the specific transaction detail data; and determine whether other first transaction detail data except the specific transaction detail data contain the specific transaction medium, and if not, determine that the specific transaction medium is an abnormal transaction medium in the abnormal transaction medium set.

[0044] In a possible implementation manner, the determination module is further configured to obtain daily transaction media included in other first transaction detail data except the specific transaction detail data before determining whether other first transaction detail data except the specific transaction detail data includes the specific transaction medium;

[0045] The determination module is specifically used to determine whether the specific transaction medium is located in the daily transaction medium.

[0046] In a third aspect, the present application provides an electronic device, which includes at least a processor and a memory, and the processor is used to implement the steps of any method described in the first aspect when executing a computer program stored in the memory.

[0047] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of any method described in the first aspect.

[0048] In a fifth aspect, the present application provides a computer program product, comprising: a computer program code, when the computer program code is run on a computer, the computer executes the steps of any method described in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 A schematic diagram of an abnormal medium determination process provided in an embodiment of the present application;

[0051] Figure 2 A schematic diagram of an abnormal medium determination device provided in an embodiment of the present application;

[0052] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solutions and advantages of this application clearer, this application will be further described in detail below in conjunction with the accompanying drawings. Obviously, the embodiments described in this application are only part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0054] It should be noted that the brief description of terms in this application is only for the convenience of understanding the embodiments described below, and is not intended to limit the embodiments of this application. Unless otherwise specified, these terms should be understood according to their common and usual meanings.

[0055] The terms "first", "second", "third", etc. in the specification and claims of this application and the above drawings are used to distinguish similar or similar objects or entities, and do not necessarily mean to limit a specific order or sequence, unless otherwise noted. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances.

[0056] The terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover but not exclude inclusion, for example, a product or device comprising a list of components is not necessarily limited to all the components expressly listed but may include other components not expressly listed or inherent to such product or device.

[0057] The term "module" refers to any known or later developed hardware, software, firmware, artificial intelligence, fuzzy logic, or combination of hardware and / or software code that is capable of performing the functions associated with that element.

[0058] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0059] The following is a description of exemplary embodiments of the present application in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description. It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, which should be considered as exemplary, and their purpose is only to illustrate the feasibility of the implementation of the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0060] In the technical solution of this application, the acquisition, transmission, storage, and use of data are in compliance with the requirements of relevant national laws and regulations.

[0061] Before introducing the abnormal medium determination method provided in the embodiment of the present application, in order to facilitate understanding, the technical background of the embodiment of the present application is first introduced.

[0062] In related technologies, all transaction information of a customer including transaction media is usually retained, and a relationship between the customer and the transaction information is established. Subsequently, the customer's transaction media is determined based on the customer's transaction information. This method can ensure that all transaction media information of the customer is obtained, but the amount of data is too large when applied, which affects the computing efficiency.

[0063] In view of this, in order to improve the calculation efficiency, the embodiments of the present application propose an abnormal medium determination method, device, equipment and medium. Some preferred embodiments of the present application are described below in conjunction with the drawings of the specification.

[0064] Embodiment 1:

[0065] Figure 1 A schematic diagram of an abnormal medium determination process provided in an embodiment of the present application, the process includes:

[0066] S101: Obtain the first transaction details data of an account within a preset period.

[0067] The abnormal medium determination method provided in the embodiment of the present application is applied to an electronic device, which may be a personal computer (PC), a server, etc.

[0068] In an embodiment of the present application, the electronic device obtains first transaction detail data generated by an account within a preset period.

[0069] For example, the preset period may be one day, one week, or one month, etc., and is not specifically limited here.

[0070] Specifically, the first transaction details data includes information such as customer information, counterparty information, specific transaction content, and transaction record information.

[0071] Among them, customer information includes but is not limited to customer number, customer name, customer ID, etc.

[0072] Counterparty information includes but is not limited to counterparty customer number, counterparty customer name, counterparty customer identification, etc.

[0073] The specific contents of the transaction include but are not limited to the transaction amount, transaction date, transaction direction, transaction time, transaction method, etc.

[0074] Transaction record information includes but is not limited to transaction summary, transaction medium code, etc. The transaction summary contains a brief description of the transaction process, usually within 20 words.

[0075] It can be understood that in order to reduce the situation of processing invalid first transaction details data, after obtaining the first transaction details data of the account within the preset period, for each first transaction details data, it is determined whether there is transaction medium information (i.e. the above-mentioned transaction medium code) in the first transaction details data. If not, that is, if the transaction medium information in the first transaction details data is empty, the first transaction details data is filtered out and no further processing is performed on the first transaction details data; and it is determined whether the transaction method contained in the first transaction details data is an online transaction. If not, the first transaction details data is filtered out and no further processing is performed on the first transaction details data.

[0076] S102: For each first transaction detail data of the account, obtain the target transaction content included in the transaction summary in the first transaction detail data, and determine the target behavior type corresponding to the first transaction detail data based on the target transaction content and the pre-saved correspondence between the transaction content and the behavior type; determine the target transaction medium type corresponding to the first transaction detail data based on the saved correspondence between the behavior type and the transaction medium type.

[0077] For each first transaction detail data of the account, the target transaction content contained in the transaction summary in the first transaction detail data is obtained, wherein the target transaction content can be obtained by segmenting the transaction summary, determining multiple target segmentations in the segmentations of the transaction summary, and splicing the multiple target segmentations according to the arrangement order of preset sentence components.

[0078] Since the correspondence between transaction content and behavior type is stored in the electronic device, the target behavior type corresponding to the first transaction detail data is determined based on the target transaction content contained in the transaction summary in the first transaction detail data and the pre-stored correspondence between transaction content and behavior type.

[0079] Among them, the types of behaviors include but are not limited to the customer's autonomous daily behaviors, customer's autonomous special behaviors and other behaviors. For example, the customer's autonomous daily behaviors include but are not limited to online shopping for private customers (such as Meituan takeout, Ele.me takeout, Taobao shopping, JD shopping, etc.), water and electricity bills for corporate customers, etc.; the customer's autonomous special behaviors include but are not limited to transfers for private customers, transfers for corporate customers, etc.; other behaviors include but are not limited to automatic deductions for private customers, account collection for corporate customers, and SMS fees charged by banks, etc.

[0080] After determining the target behavior type corresponding to the first transaction detail data, the target transaction medium type corresponding to the first transaction detail data is determined based on the target behavior type corresponding to the first transaction detail data and the correspondence between the behavior type and the transaction medium type stored in the electronic device itself.

[0081] Among them, the correspondence between the behavior type and the transaction medium type includes that if the behavior type is a daily behavior of the customer, the transaction medium type corresponding to the behavior type is a daily transaction medium type; if the behavior type is a special behavior of the customer, the transaction medium type corresponding to the behavior type is a specific transaction medium type; if the behavior type is other behavior, the transaction medium type corresponding to the behavior type is other transaction medium type.

[0082] S103: Determine an abnormal transaction medium set of the account according to the target transaction medium type corresponding to each first transaction detail data.

[0083] After determining the target transaction medium type corresponding to each first transaction detail data, based on the target transaction medium type corresponding to each first transaction detail data, determine the specific transaction detail data whose target transaction medium type is a specific transaction medium type among all the first transaction detail data, and determine the specific transaction medium contained in each specific transaction detail data.

[0084] For each specific transaction medium, determine whether the specific transaction medium is included in other first transaction detail data except the specific transaction detail data, if not, determine that the specific transaction medium is an abnormal transaction medium. According to all abnormal transaction media, determine the abnormal transaction medium set of the account.

[0085] In an embodiment of the present application, the target transaction content contained in the transaction summary in the first transaction detail data of the account is obtained, and a large amount of useless transaction information is removed, so that the customer's abnormal transaction media set is determined based on the target transaction content, which can improve computing efficiency.

[0086] Embodiment 2:

[0087] In order to further improve the calculation efficiency, based on the above embodiment, in the embodiment of the present application, obtaining the target transaction content contained in the transaction summary in the first transaction detail data includes:

[0088] Get the historical transaction content in the saved historical content collection;

[0089] Determine whether the transaction summary in the first transaction detail data contains all the word segments corresponding to any historical transaction content. If so, determine the historical transaction content as the target transaction content included in the first transaction detail data.

[0090] In the embodiment of the present application, a preset number of historical content sets within a period are stored in the electronic device, and the historical content set includes multiple and non-repeating historical transaction contents; the electronic device obtains all historical transaction contents in the historical content set stored by itself. Among them, any historical transaction content can be a short sentence included in the historical transaction summary in the historical detailed data, and the short sentence (i.e., the historical transaction content) contains multiple participles.

[0091] Match the transaction summary in the first transaction details data with the historical transaction content in the historical content set. Specifically, when matching, for any historical transaction content, determine whether the transaction summary in the first transaction details data contains all the words corresponding to the historical transaction content. If so, determine whether the order in which all the words corresponding to the historical transaction content appear in the historical transaction content is consistent with the order in which they appear in the first transaction details data. If so, determine the historical transaction content as the target transaction content contained in the first transaction details data.

[0092] In an embodiment of the present application, the transaction summary in the first transaction detail data is matched with the historical transaction content in the historical content set to determine the target transaction content contained in the first transaction detail data, and a large amount of useless information in the first transaction detail data is eliminated, thereby further improving the computing efficiency.

[0093] Embodiment 3:

[0094] On the basis of the above embodiments, in an embodiment of the present application, if the transaction summary in the first transaction detail data does not include all the word segments corresponding to any historical transaction content, obtaining the target transaction content included in the transaction summary in the first transaction detail data includes:

[0095] The transaction summary in the first transaction detail data is segmented, and according to the sentence component to which each segmented word belongs, the segmented words of the preset sentence components are spliced ​​to obtain the target transaction content.

[0096] If the transaction summary in the first transaction detail data does not contain all the word segments corresponding to any historical transaction content, it is determined that the historical content set does not contain the target transaction content contained in the first transaction detail data, and the transaction summary in the first transaction detail data is segmented, and the sentence component to which each word segment belongs in the transaction summary is determined, and the sentence component of each word segment of the transaction summary is marked using a part-of-speech tagging tool. Among them, the process of determining the sentence component to which each word segment belongs in the transaction summary is a prior art and is not repeated here.

[0097] According to the sentence component to which each segment of the transaction summary in the first transaction detail data belongs, a segment of a sentence component is determined in the transaction summary as a preset sentence component. The preset sentence component may be a subject, a predicate, an object, etc. For example, the predicate and the object are usually taken as the preset sentence components.

[0098] After obtaining the word segmentation of the preset sentence components in the transaction summary in the first transaction details data, the word segmentation of the preset sentence components in the transaction summary in the first transaction details data is spliced ​​according to the saved arrangement order of the preset sentence components to obtain the target short sentence corresponding to the first transaction details data, and the target short sentence is determined as the target transaction content contained in the first transaction details data.

[0099] For example, if the preset sentence components are subject, predicate, and object, the arrangement order of the preset sentence components from front to back is subject, predicate, and object.

[0100] As another example, if the preset sentence components are subject and predicate, the arrangement order of the preset sentence components from front to back is subject and predicate.

[0101] As another example, if the preset sentence components are predicate and object, the arrangement order of the preset sentence components from front to back is predicate, object.

[0102] In order to ensure the effectiveness of the abnormal medium determination process, based on the above embodiments, in the embodiment of the present application, the method further includes:

[0103] Add the target transaction content to the historical content collection.

[0104] If the transaction summary in the first transaction detail data does not contain all the words corresponding to any historical transaction content, then after obtaining the target transaction content contained in the first transaction detail data, the target transaction content is added to the historical content set to complete the update and improvement of the historical content set, thereby ensuring the effectiveness of the subsequent abnormal medium determination process and facilitating the subsequent monitoring of whether the transaction detail data has changed.

[0105] Embodiment 4:

[0106] In order to improve the robustness of determining the historical content set, based on the above embodiments, in the embodiment of the present application, the process of determining the historical transaction content includes:

[0107] Obtain the historical transaction summary of the historical transaction detail data within a preset number of periods, segment the historical transaction summary, and according to the sentence component to which each segmented word belongs, concatenate the segmented words of the preset sentence components to obtain the historical transaction content, and add the historical transaction content to the historical content collection.

[0108] The electronic device obtains a historical transaction summary of a preset number of historical transaction details within a period stored in the electronic device, wherein the preset number is a positive integer and the specific value is not limited here.

[0109] In a possible implementation, for each cycle in a preset number of cycles and for any historical transaction detail data within the cycle, a historical transaction summary of the historical transaction detail data is segmented, the sentence component to which each segmented word in the historical transaction summary belongs is determined, and the sentence component of each segmented word is annotated using a part-of-speech tagging tool; based on the sentence component to which each segmented word in the historical transaction summary belongs, a segmented word whose sentence component is a preset sentence component is determined in the historical transaction summary, and based on the arrangement order of the saved preset sentence components, the segmented words of the preset sentence components in the historical transaction summary are spliced ​​to obtain a historical short sentence corresponding to the historical transaction detail data, and the historical short sentence is determined as the historical transaction content corresponding to the historical transaction detail data.

[0110] The historical transaction content corresponding to each historical transaction detail data in the period is added to the historical content subset, and duplicates are removed to obtain the target historical content subset corresponding to the period.

[0111] According to the target historical content subset corresponding to each period in the preset number of periods, the non-repetitive historical transaction content in each target historical content subset is added to the historical content set.

[0112] In another possible implementation, for any historical transaction detail data within a preset number of periods, the historical transaction summary of the historical transaction detail data is segmented, the sentence component to which each segmented word in the historical transaction summary belongs is determined, and the sentence component of each segmented word is annotated using a part-of-speech tagging tool; based on the sentence component to which each segmented word in the historical transaction summary belongs, the segmented words whose sentence components are preset sentence components are determined in the historical transaction summary, and based on the arrangement order of the saved preset sentence components, the segmented words of the preset sentence components in the historical transaction summary are spliced ​​to obtain the historical short sentence corresponding to the historical transaction detail data, and the historical short sentence is determined as the historical transaction content corresponding to the historical transaction detail data.

[0113] The historical transaction content corresponding to each historical transaction detail data within the preset number of periods is added to the candidate historical content subset, and duplicates are removed to obtain a historical content set.

[0114] In the embodiment of the present application, by simultaneously spanning multiple periods, a stable set of historical content corresponding to multiple periods is obtained, thereby improving the robustness of determining the historical content set, achieving a comprehensive consideration of transaction summaries of multiple periods, and ensuring the stability of the abnormal medium determination process.

[0115] Embodiment 5:

[0116] In order to further improve the calculation efficiency, based on the above embodiments, in the embodiment of the present application, after obtaining the historical transaction summaries of the historical transaction detail data within a preset number of periods, and before segmenting the historical transaction summaries, the method further includes:

[0117] Select some historical transaction details data and perform subsequent operations on some historical transaction details data;

[0118] After adding the historical transaction content to the historical content collection, the method further includes:

[0119] Filtering other historical transaction detail data containing historical transaction content in the remaining part of the historical transaction detail data to obtain filtered second transaction detail data;

[0120] Repeat the step of selecting part of the historical transaction detail data for the second transaction detail data until the filtered second transaction detail data does not exist after filtering other historical transaction detail data containing historical transaction content.

[0121] Considering that the amount of transaction details data within a period is relatively large, in the embodiment of the present application, after obtaining a preset number of historical transaction summaries of historical transaction details data within a period, a portion of historical transaction details data is randomly extracted from all historical transaction details data (hereinafter referred to as the first portion of historical transaction details data for ease of description). For example, the number of partial historical transaction details data may be k, where k is a positive integer.

[0122] For the extracted first part of historical transaction details data, subsequent word segmentation is performed on the historical transaction summaries in each first part of historical transaction details data, and according to the sentence component to which each participle belongs, the participles of preset sentence components are concatenated to obtain the historical transaction content, and the historical transaction content corresponding to the first part of historical transaction details data is added to a historical content set (referred to as the first part of historical content set hereinafter for ease of description).

[0123] After the historical transaction content corresponding to the first part of the historical transaction detail data is added to the first historical content set, the remaining part of the historical transaction detail data except the above-mentioned first part of the historical transaction detail data (referred to as the second part of the historical transaction detail data hereinafter for the convenience of description) is determined; for each second part of the historical transaction detail data, it is determined whether the historical transaction summary of the second part of the historical transaction detail data contains all the words corresponding to any historical transaction content in the first historical content set; if so, it is determined that the second part of the historical transaction detail data contains historical transaction content; in the second part of the historical transaction detail data, all other historical transaction detail data containing historical transaction content are filtered to obtain the filtered second transaction detail data.

[0124] If the number of historical transaction details data contained in the filtered second transaction details data is greater than k, the above-mentioned step of randomly selecting a part (such as k items) of the historical transaction details data is repeated for the second transaction details data until there is no filtered second transaction details data after filtering other historical transaction details data containing historical transaction content.

[0125] If the number of historical transaction details data contained in the filtered second transaction details data is less than k, there is no need to perform random selection, and all the filtered second transaction details data can be directly subjected to subsequent word segmentation and other operations until there is no filtered second transaction details data after filtering other historical transaction details containing historical transaction content.

[0126] In an embodiment of the present application, each time a portion of historical transaction detail data is selected and the historical content set corresponding to the portion of historical transaction detail data is determined, other historical transaction detail data containing historical transaction content are filtered out from the remaining portion of historical transaction detail data, and then the selection steps are repeated. There is no need to directly process the transaction detail data within the period at one time, thereby further improving the computing efficiency.

[0127] Embodiment 6:

[0128] On the basis of the above embodiments, in the embodiment of the present application, determining the abnormal transaction medium set of the account according to the target transaction medium type corresponding to each first transaction detail data includes:

[0129] Determine, among all first transaction detail data, specific transaction detail data whose target transaction medium type is a specific transaction medium type;

[0130] Obtaining specific transaction media contained in specific transaction details;

[0131] It is determined whether other first transaction detail data except the specific transaction detail data include the specific transaction medium; if not, the specific transaction medium is determined to be an abnormal transaction medium in the abnormal transaction medium set.

[0132] In the embodiment of the present application, after determining the target transaction medium type corresponding to each first transaction detail data, the specific transaction detail data whose target transaction medium type is a specific transaction medium type is determined in all the first transaction detail data. Since each first transaction detail data contains a transaction medium code, the transaction medium code is a code corresponding to the transaction medium, and the transaction medium code uniquely identifies the transaction medium. Therefore, based on the transaction medium code in each specific transaction detail data, the specific transaction medium contained in each specific transaction detail data is obtained. Among them, in a possible implementation, the transaction medium corresponding to the transaction medium code in each specific transaction detail data is directly determined as the specific transaction medium.

[0133] Since any normal customer will not frequently change the transaction medium for transaction in each cycle, this property can be used in the embodiment of the present application to distinguish the specific transaction medium to determine the specific transaction medium in which the customer may have abnormal transaction behavior in addition to the normal transaction medium (such as daily transaction medium). Therefore, in the embodiment of the present application, for each specific transaction medium, according to the transaction medium included in other first transaction detail data except the specific transaction detail data, it is determined whether the other first transaction detail data contains the specific transaction medium. If so, the specific transaction medium is determined to be a normal transaction medium; if not, the specific transaction medium is determined to be an abnormal transaction medium.

[0134] Embodiment 7:

[0135] On the basis of the above embodiments, in the embodiment of the present application, before determining whether other first transaction detail data other than the specific transaction detail data contains the specific transaction medium, the method further includes:

[0136] Acquiring daily transaction media included in other first transaction detail data except for the specific transaction detail data;

[0137] Determining whether other first transaction detail data other than the specific transaction detail data contains the specific transaction medium includes:

[0138] Determine whether a specific transaction medium is located in the daily transaction medium.

[0139] In the embodiment of the present application, after determining the target transaction medium type corresponding to each first transaction detail data, according to the first transaction detail data whose target transaction medium type is the daily transaction medium type and the specific transaction detail data, the daily transaction detail data contained in the other first transaction detail data except the specific transaction detail data is determined among all the first transaction detail data. Since each first transaction detail data contains a transaction medium code, the daily transaction medium contained in each daily transaction detail data is obtained based on the transaction medium code in each daily transaction detail data. In one possible implementation, the transaction medium code in each daily transaction detail data is directly determined as the specific transaction medium contained in the daily transaction detail data.

[0140] In a possible implementation, for each specific transaction medium, it is determined whether the specific transaction medium is located in the daily transaction medium, that is, it is determined whether the specific transaction medium is the same as any daily transaction medium. If so, the specific transaction medium is determined to be a normal transaction medium. If not, the specific transaction medium is determined to be a collective abnormal transaction medium in the abnormal transaction medium.

[0141] In another possible implementation, based on all specific transaction media, a specific transaction medium set including all specific transaction media is determined; based on all daily transaction media, a daily transaction medium set including all daily transaction media is determined; the intersection of the specific transaction medium set and the daily transaction medium set is determined, and the specific transaction medium set is subtracted from the intersection to determine a difference set between the specific transaction medium set and the intersection, and the characteristic transaction media included in the difference set are determined as a set of abnormal transaction media in the abnormal transaction media.

[0142] Embodiment 8:

[0143] Based on the same inventive concept, on the basis of the above embodiments, the present application provides an abnormal medium determination device, see Figure 2 , Figure 2A schematic diagram of an abnormal medium determination device provided by some embodiments is shown, the device comprising:

[0144] The acquisition module 201 is used to acquire the first transaction details data of the account within a preset period;

[0145] The processing module 202 is used to obtain, for each first transaction detail data of the account, the target transaction content contained in the transaction summary in the first transaction detail data, and determine the target behavior type corresponding to the first transaction detail data according to the target transaction content and the pre-stored correspondence between the transaction content and the behavior type; and determine the target transaction medium type corresponding to the first transaction detail data according to the stored correspondence between the behavior type and the transaction medium type;

[0146] The determination module 203 is configured to determine the abnormal transaction medium set of the account according to the target transaction medium type corresponding to each first transaction detail data.

[0147] In a possible implementation, the processing module 202 is specifically used to obtain historical transaction content in a saved historical content set; determine whether the transaction summary in the first transaction detail data contains all the word segments corresponding to any historical transaction content, and if so, determine the historical transaction content as the target transaction content contained in the first transaction detail data.

[0148] In a possible implementation, the processing module 202 is specifically used to segment the transaction summary in the first transaction detail data if the transaction summary in the first transaction detail data does not contain all the segmented words corresponding to any historical transaction content, and to concatenate the segmented words of the preset sentence components according to the sentence component to which each segmented word belongs to obtain the target transaction content.

[0149] In a possible implementation manner, the processing module 202 is further configured to add the target transaction content to a historical content collection.

[0150] In a possible implementation, the processing module 202 is specifically used to obtain a historical transaction summary of historical transaction detail data within a preset number of periods, segment the historical transaction summary, and according to the sentence component to which each segmented word belongs, concatenate the segmented words of the preset sentence components to obtain the historical transaction content, and add the historical transaction content to the historical content collection.

[0151] In a possible implementation, the processing module 202 is further configured to, after acquiring the historical transaction summaries of the historical transaction detail data within a preset number of periods, select part of the historical transaction detail data before segmenting the historical transaction summaries, and perform subsequent operations on the part of the historical transaction detail data;

[0152] The processing module 202 is further used to filter other historical transaction detail data containing the historical transaction content in the remaining part of the historical transaction detail data after adding the historical transaction content to the historical content collection, so as to obtain filtered second transaction detail data; and repeatedly perform the step of selecting part of the historical transaction detail data on the second transaction detail data until the filtered second transaction detail data does not exist after filtering other historical transaction detail data containing the historical transaction content.

[0153] In a possible implementation, the determination module 203 is specifically used to determine, among all first transaction detail data, specific transaction detail data in which the target transaction medium type is a specific transaction medium type; obtain the specific transaction medium contained in the specific transaction detail data; and determine whether other first transaction detail data except the specific transaction detail data contain the specific transaction medium, and if not, determine that the specific transaction medium is an abnormal transaction medium in the abnormal transaction medium set.

[0154] In a possible implementation manner, the determination module 203 is further configured to obtain daily transaction media included in other first transaction detail data except the specific transaction detail data before determining whether other first transaction detail data except the specific transaction detail data includes the specific transaction medium;

[0155] The determination module 203 is specifically configured to determine whether the specific transaction medium is located in the daily transaction medium.

[0156] Embodiment 9:

[0157] Based on the same inventive concept, on the basis of the above embodiments, the present application embodiment further provides an electronic device, which can realize the function of the abnormal medium determination device discussed above, please refer to Figure 3 , Figure 3 A schematic diagram of the structure of an electronic device provided in some embodiments is shown, the electronic device comprising: a processor 301, a communication interface 302, a memory 303 and a communication bus 304, wherein the processor 301, the communication interface 302, and the memory 303 communicate with each other through the communication bus 304;

[0158] The memory 303 stores a computer program. When the program is executed by the processor 301, the processor 301 performs the following steps:

[0159] Obtaining the first transaction details of the account within a preset period;

[0160] For each first transaction detail data of the account, the target transaction content included in the transaction summary in the first transaction detail data is obtained, and the target behavior type corresponding to the first transaction detail data is determined according to the target transaction content and the correspondence between the transaction content and the behavior type saved in advance; and the target transaction medium type corresponding to the first transaction detail data is determined according to the correspondence between the behavior type and the transaction medium type saved in advance;

[0161] According to the target transaction medium type corresponding to each first transaction detail data, the abnormal transaction medium set of the account is determined.

[0162] In one possible implementation, the processor 301 is specifically used to obtain historical transaction content in a saved historical content set; determine whether the transaction summary in the first transaction detail data contains all the word segments corresponding to any historical transaction content, and if so, determine the historical transaction content as the target transaction content contained in the first transaction detail data.

[0163] In a possible implementation, the processor 301 is specifically used to segment the transaction summary in the first transaction detail data if the transaction summary in the first transaction detail data does not contain all the segmented words corresponding to any historical transaction content, and according to the sentence component to which each segmented word belongs, the segmented words of the preset sentence components are spliced ​​to obtain the target transaction content.

[0164] In a possible implementation manner, the processor 301 is further configured to add the target transaction content to a historical content set.

[0165] In a possible implementation, the processor 301 is specifically used to obtain a historical transaction summary of historical transaction detail data within a preset number of periods, segment the historical transaction summary, and according to the sentence component to which each segmented word belongs, concatenate the segmented words of the preset sentence components to obtain the historical transaction content, and add the historical transaction content to a historical content collection.

[0166] In a possible implementation, the processor 301 is further used to obtain historical transaction summaries of historical transaction detail data within a preset number of saved periods, select part of the historical transaction detail data before segmenting the historical transaction summaries, and perform subsequent operations on the part of the historical transaction detail data.

[0167] In a possible implementation, the processor 301 is further used to, after adding the historical transaction content to the historical content collection, filter other historical transaction detail data containing the historical transaction content in the remaining part of the historical transaction detail data to obtain filtered second transaction detail data; and repeat the step of selecting part of the historical transaction detail data for the second transaction detail data until the filtered second transaction detail data does not exist after filtering other historical transaction detail data containing the historical transaction content.

[0168] In a possible implementation, the processor 301 is specifically used to determine, among all first transaction detail data, specific transaction detail data in which the target transaction medium type is a specific transaction medium type; obtain the specific transaction medium contained in the specific transaction detail data; and determine whether other first transaction detail data except the specific transaction detail data contain the specific transaction medium, and if not, determine that the specific transaction medium is an abnormal transaction medium in the abnormal transaction medium set.

[0169] In a possible implementation, the processor 301 is further configured to obtain daily transaction media included in other first transaction detail data except the specific transaction detail data before determining whether other first transaction detail data except the specific transaction detail data includes the specific transaction medium.

[0170] In a possible implementation, the processor 301 is specifically configured to determine whether the specific transaction medium is located in the daily transaction medium.

[0171] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0172] The communication interface 302 is used for communication between the electronic device and other devices.

[0173] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0174] The above-mentioned processor can be a general-purpose processor, including a central processing unit, a network processor (Network Processor, NP), etc.; it can also be a digital signal processing processor (Digital Signal Processing, DSP), an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc.

[0175] Based on the same inventive concept, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a computer, the computer executes the following steps:

[0176] Obtaining the first transaction details of the account within a preset period;

[0177] For each first transaction detail data of the account, the target transaction content included in the transaction summary in the first transaction detail data is obtained, and the target behavior type corresponding to the first transaction detail data is determined according to the target transaction content and the correspondence between the transaction content and the behavior type saved in advance; and the target transaction medium type corresponding to the first transaction detail data is determined according to the correspondence between the behavior type and the transaction medium type saved in advance;

[0178] According to the target transaction medium type corresponding to each first transaction detail data, the abnormal transaction medium set of the account is determined.

[0179] In a possible implementation manner, obtaining the target transaction content included in the transaction summary in the first transaction detail data includes:

[0180] Get the historical transaction content in the saved historical content collection;

[0181] Determine whether the transaction summary in the first transaction detail data contains all the word segments corresponding to any historical transaction content. If so, determine the historical transaction content as the target transaction content included in the first transaction detail data.

[0182] In a possible implementation manner, if the transaction summary in the first transaction detail data does not include all the word segments corresponding to any historical transaction content, obtaining the target transaction content included in the transaction summary in the first transaction detail data includes:

[0183] The transaction summary in the first transaction detail data is segmented, and according to the sentence component to which each segmented word belongs, the segmented words of the preset sentence components are spliced ​​to obtain the target transaction content.

[0184] In a possible implementation, the method further includes:

[0185] The target transaction content is added to the historical content collection.

[0186] In a possible implementation manner, the process of determining the historical transaction content includes:

[0187] Obtain a historical transaction summary of a preset number of historical transaction detail data within a period, segment the historical transaction summary, and according to the sentence component to which each segmented word belongs, concatenate the segmented words of the preset sentence components to obtain the historical transaction content, and add the historical transaction content to the historical content collection.

[0188] In a possible implementation, after acquiring the historical transaction summaries of the historical transaction detail data within a preset number of periods and before segmenting the historical transaction summaries, the method further includes:

[0189] Selecting part of the historical transaction detail data and performing subsequent operations on the part of the historical transaction detail data;

[0190] After adding the historical transaction content to the historical content collection, the method further includes:

[0191] Filtering other historical transaction detail data including the historical transaction content in the remaining part of the historical transaction detail data to obtain filtered second transaction detail data;

[0192] Repeat the step of selecting part of the historical transaction detail data for the second transaction detail data until there is no filtered second transaction detail data after filtering other historical transaction detail data containing the historical transaction content.

[0193] In a possible implementation manner, determining the abnormal transaction medium set of the account according to the target transaction medium type corresponding to each first transaction detail data includes:

[0194] Determine, among all first transaction detail data, that the target transaction medium type is specific transaction detail data of a specific transaction medium type;

[0195] Acquire the specific transaction medium included in the specific transaction detail data;

[0196] It is determined whether other first transaction detail data except the specific transaction detail data include the specific transaction medium; if not, the specific transaction medium is determined to be an abnormal transaction medium in the abnormal transaction medium set.

[0197] In a possible implementation manner, before determining whether other first transaction detail data other than the specific transaction detail data includes the specific transaction medium, the method further includes:

[0198] Acquire daily transaction media included in other first transaction detail data except the specific transaction detail data;

[0199] The determining whether other first transaction detail data other than the specific transaction detail data contains the specific transaction medium comprises:

[0200] It is determined whether the specific transaction medium is located in the daily transaction medium.

[0201] The above-mentioned computer-readable storage medium can be any available medium or data storage device that can be accessed by the processor in the electronic device, including but not limited to magnetic storage such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc., optical storage such as CD, DVD, BD, HVD, etc., and semiconductor storage such as ROM, EPROM, EEPROM.

[0202] Based on the same inventive concept, the embodiment of the present application also provides a computer program product, which includes: computer program code, when the computer program code is run on a computer, the computer executes any of the abnormal medium determination methods discussed above. Since the principle of solving the problem by the above computer program product is similar to that of the abnormal medium determination method, the implementation of the above computer program product can refer to the implementation of the method, and the repeated parts will not be repeated.

[0203] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0204] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0205] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0206] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0207] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for determining abnormal media, It is characterized in that The method comprises: Obtaining the first transaction details of the account within a preset period; For each first transaction detail data of the account, the target transaction content included in the transaction summary in the first transaction detail data is obtained, and the target behavior type corresponding to the first transaction detail data is determined according to the target transaction content and the correspondence between the transaction content and the behavior type saved in advance; and the target transaction medium type corresponding to the first transaction detail data is determined according to the correspondence between the behavior type and the transaction medium type saved in advance; According to the target transaction medium type corresponding to each first transaction detail data, the abnormal transaction medium set of the account is determined.

2. The method according to claim 1, It is characterized in that The step of obtaining the target transaction content contained in the transaction summary in the first transaction detail data includes: Get the historical transaction content in the saved historical content collection; Determine whether the transaction summary in the first transaction detail data contains all the word segments corresponding to any historical transaction content. If so, determine the historical transaction content as the target transaction content included in the first transaction detail data.

3. The method according to claim 2, It is characterized in that If the transaction summary in the first transaction detail data does not include all the word segments corresponding to any historical transaction content, the step of obtaining the target transaction content included in the transaction summary in the first transaction detail data includes: The transaction summary in the first transaction detail data is segmented, and according to the sentence component to which each segmented word belongs, the segmented words of the preset sentence components are spliced ​​to obtain the target transaction content.

4. The method according to claim 3, It is characterized in that The method further comprises: The target transaction content is added to the historical content collection.

5. The method according to claim 2, It is characterized in that The process of determining the historical transaction content includes: Obtain a historical transaction summary of a preset number of historical transaction detail data within a period, segment the historical transaction summary, and according to the sentence component to which each segment belongs, concatenate the segmentations of the preset sentence components to obtain historical transaction content, and add the historical transaction content to a historical content collection.

6. The method according to claim 5, It is characterized in that After acquiring the historical transaction summaries of the historical transaction detail data within a preset number of periods and before segmenting the historical transaction summaries, the method further includes: Selecting part of the historical transaction detail data and performing subsequent operations on the part of the historical transaction detail data; After adding the historical transaction content to the historical content collection, the method further includes: Filtering other historical transaction detail data including the historical transaction content in the remaining part of the historical transaction detail data to obtain filtered second transaction detail data; Repeat the step of selecting part of the historical transaction detail data for the second transaction detail data until there is no filtered second transaction detail data after filtering other historical transaction detail data containing the historical transaction content.

7. The method according to claim 1, It is characterized in that The determining, according to the target transaction medium type corresponding to each first transaction detail data, the abnormal transaction medium set of the account includes: Determine, among all first transaction detail data, that the target transaction medium type is specific transaction detail data of a specific transaction medium type; Acquire the specific transaction medium included in the specific transaction detail data; It is determined whether other first transaction detail data except the specific transaction detail data include the specific transaction medium; if not, the specific transaction medium is determined to be an abnormal transaction medium in the abnormal transaction medium set.

8. The method according to claim 7, It is characterized in that Before determining whether other first transaction detail data other than the specific transaction detail data includes the specific transaction medium, the method further includes: Acquire daily transaction media included in other first transaction detail data except the specific transaction detail data; The determining whether other first transaction detail data other than the specific transaction detail data contains the specific transaction medium comprises: It is determined whether the specific transaction medium is located in the daily transaction medium.

9. An abnormal medium determination device, It is characterized in that The device comprises: An acquisition module, used to acquire the first transaction detail data of an account within a preset period; a processing module, configured to obtain, for each first transaction detail data of the account, a target transaction content included in a transaction summary in the first transaction detail data, and determine a target behavior type corresponding to the first transaction detail data according to the target transaction content and a pre-saved correspondence between the transaction content and the behavior type; and determine a target transaction medium type corresponding to the first transaction detail data according to a saved correspondence between the behavior type and the transaction medium type; The determination module is used to determine the abnormal transaction medium set of the account according to the target transaction medium type corresponding to each first transaction detail data.

10. The device according to claim 9, It is characterized in that The processing module is specifically used to obtain historical transaction content in the saved historical content set; determine whether the transaction summary in the first transaction detail data contains all the word segments corresponding to any historical transaction content, and if so, determine the historical transaction content as the target transaction content contained in the first transaction detail data.

11. The device according to claim 10, It is characterized in that The processing module is specifically used to segment the transaction summary in the first transaction detail data if the transaction summary in the first transaction detail data does not contain all the segmented words corresponding to any historical transaction content, and to splice the segmented words of the preset sentence components according to the sentence component to which each segmented word belongs to obtain the target transaction content.

12. The device according to claim 11, It is characterized in that The processing module is further configured to add the target transaction content to a historical content collection.

13. The device according to claim 10, It is characterized in that The processing module is specifically used to obtain a historical transaction summary of historical transaction detail data within a preset number of periods, segment the historical transaction summary, and according to the sentence component to which each segment belongs, concatenate the segmentations of the preset sentence components to obtain the historical transaction content, and add the historical transaction content to the historical content collection.

14. The device according to claim 13, It is characterized in that The processing module is further configured to, after obtaining the historical transaction summaries of the historical transaction detail data within a preset number of periods, select part of the historical transaction detail data before segmenting the historical transaction summaries, and perform subsequent operations on the part of the historical transaction detail data; The processing module is also used to, after adding the historical transaction content to the historical content collection, filter other historical transaction detail data containing the historical transaction content in the remaining part of the historical transaction detail data to obtain filtered second transaction detail data; repeat the step of selecting part of the historical transaction detail data for the second transaction detail data until the filtered second transaction detail data does not exist after filtering other historical transaction detail data containing the historical transaction content.

15. The device according to claim 9, It is characterized in that The determination module is specifically used to determine, among all first transaction detail data, specific transaction detail data in which the target transaction medium type is a specific transaction medium type; obtain the specific transaction medium contained in the specific transaction detail data; and determine whether other first transaction detail data except the specific transaction detail data contain the specific transaction medium. If not, determine that the specific transaction medium is an abnormal transaction medium in the abnormal transaction medium set.

16. The device according to claim 15, It is characterized in that The determination module is further configured to obtain daily transaction media included in other first transaction detail data except the specific transaction detail data before determining whether the specific transaction medium is included in other first transaction detail data except the specific transaction detail data; The determination module is specifically used to determine whether the specific transaction medium is located in the daily transaction medium.

17. An electronic device, It is characterized in that include: A memory for storing program instructions; A processor is used to call the program instructions stored in the memory, and execute the steps included in any one of the methods of claims 1-8 according to the obtained program instructions.

18. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a computer, the computer executes the method according to any one of claims 1 to 8.

19. A computer program product, It is characterized in that The computer program product comprises: a computer program code, and when the computer program code is run on a computer, the computer is enabled to execute the method according to any one of claims 1 to 8.

Images