CN115049446A - Merchant identification method and device, electronic equipment and computer readable medium - Google Patents
Merchant identification method and device, electronic equipment and computer readable medium Download PDFInfo
- Publication number
- CN115049446A CN115049446A CN202110256483.1A CN202110256483A CN115049446A CN 115049446 A CN115049446 A CN 115049446A CN 202110256483 A CN202110256483 A CN 202110256483A CN 115049446 A CN115049446 A CN 115049446A
- Authority
- CN
- China
- Prior art keywords
- target
- merchant
- similarity
- vector representation
- name
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Finance (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Accounting & Taxation (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the disclosure provides a merchant identification method, a merchant identification device, electronic equipment and a computer readable medium. The method comprises the following steps: acquiring a target merchant name registered by a target merchant; processing the target business name to obtain a target business vector representation of the target business name; calculating the similarity of the target merchant vector representation and the set center vector representation of the history set; establishing a new set according to the similarity as a target set corresponding to the target merchant name; and determining the target merchant as a target type merchant according to the target set information of the target set, wherein the target type merchant refers to merchants performing abnormal transactions by using a first number of merchant names registered in a preset time range, and the similarity between any two merchant names in the first number of merchant names is smaller than a preset threshold value. The technical scheme provided by the embodiment of the disclosure can improve the accuracy of target type merchant identification and continuously mine online to obtain a newly added target type merchant set.
Description
Technical Field
The disclosure relates to the technical field of computer application, and in particular to a merchant identification method, a merchant identification device, electronic equipment and a computer readable medium.
Background
In the ecology of online payment, a lot of phenomena of abnormal transaction behaviors of merchants registered in batch in a short time appear, and very large economic loss is caused. Although the merchant names registered in batches are not exactly the same but are highly similar, and the merchant in the batch can be abandoned after several transactions are carried out, if the merchant is detected by relying on transaction behaviors, the merchant is difficult to find in time by wind control and is in a passive situation. Therefore, how to efficiently identify the abnormal merchants registered in the batch is a considerable problem.
Therefore, a new merchant identification method, apparatus, electronic device and computer readable medium are needed.
It is to be noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the present disclosure, and thus may include information that does not constitute prior art known to those of ordinary skill in the art.
Disclosure of Invention
The embodiment of the disclosure provides a merchant identification method, a merchant identification device, electronic equipment and a computer readable medium, so that the accuracy of target type merchant identification is improved at least to a certain extent, and a newly added target type merchant set is obtained by online continuous mining.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows, or in part will be obvious from the description, or may be learned by practice of the disclosure.
The embodiment of the disclosure provides a merchant identification method, which includes: acquiring a target merchant name registered by a target merchant; processing the target business name to obtain a target business vector representation of the target business name; calculating the similarity of the target merchant vector representation and the set center vector representation of the history set; creating a new set according to the similarity as a target set corresponding to the target merchant name; and determining the target merchant as a target type merchant according to the target set information of the target set, wherein the target type merchant refers to a merchant performing abnormal transaction by using a first number of merchant names registered in a preset time range, and the similarity between any two of the first number of merchant names is smaller than a preset threshold.
The embodiment of the present disclosure provides a merchant identification apparatus, including: the business account name acquisition module is configured to acquire a target business account name registered by a target business; the vector representation module is configured to process the target business name to obtain target business vector representation of the target business name; a similarity calculation module configured to calculate a similarity of the target merchant vector representation and a set center vector representation of a history set; a target set determining module configured to create a new set according to the similarity as a target set corresponding to the target merchant name; and the target type merchant identification module is configured to determine the target merchant as a target type merchant according to the target set information of the target set, wherein the target type merchant refers to a merchant which performs abnormal transaction by using a first number of merchant names registered in a preset time range, and the similarity between any two of the first number of merchant names is smaller than a preset threshold value.
In an exemplary embodiment of the present disclosure, the target set determination module includes: a first target set determining unit, configured to, if a maximum value in the similarity is smaller than a similarity threshold, create a new added set as a target set corresponding to the target business name; a second target set determining unit configured to determine, if a maximum value of the similarities is greater than or equal to a similarity threshold, a history set having the largest similarity as the target set.
In an exemplary embodiment of the present disclosure, the target set information is an identifier indicating that the target set is a target type merchant set, and the target type merchant identifying module includes: the first target type merchant identification unit is configured to determine a newly added set corresponding to the newly added set within a time range from creation time to current time after the newly added set is newly established as a target set corresponding to the target merchant name if the maximum value of the similarity is smaller than a similarity threshold; when the newly added set is determined to be a target type merchant set according to the transaction information of the new merchant account name and the target merchant account name, determining the target merchant to be a target type merchant; and a second target type merchant identification unit configured to determine that the target merchant is a target type merchant if a maximum value of the similarity is greater than or equal to a similarity threshold and when the target set is determined to be a target type merchant set according to target set information of the target set.
In an exemplary embodiment of the disclosure, the merchant identifying apparatus further comprises a set center vector updating module configured to update a set center vector representation of the target set according to the target merchant vector representation.
In an exemplary embodiment of the disclosure, the set center vector updating module includes a first set center vector updating unit configured to determine the target merchant vector representation as the set center vector representation of the newly added set if a maximum value of the similarities is less than a similarity threshold; the second set center vector updating unit is configured to determine the number of target merchants corresponding to the history set with the maximum similarity if the maximum value of the similarities is greater than or equal to a similarity threshold; determining a first weight and a second weight according to the number of the target commercial tenants; and performing weighted summation calculation on the aggregate center vector representation of the history set and the target merchant vector representation according to the first weight and the second weight so as to update the aggregate center vector representation of the target set according to a weighted summation calculation result.
In an exemplary embodiment of the present disclosure, the merchant identifying device further includes: a first set identifier determining module configured to obtain a set identifier of the history set if a maximum value of the similarity is smaller than a similarity threshold; sorting the set identifications of the history set to obtain the largest set identification; and determining the set identifier of the newly added set according to the increment calculation of the maximum set identifier. And the second set identifier determining module is configured to determine the set identifier of the history set with the maximum similarity as the set identifier of the target set if the maximum value of the similarities is greater than or equal to a similarity threshold.
In an exemplary embodiment of the present disclosure, the vector representation module includes: the stop word unit is configured to stop words for the target business name; the word segmentation unit is configured to segment the target business name without the stop word to obtain the segmentation of the target business name and the part-of-speech information of the segmentation; the first segmentation weight unit is configured to set first segmentation weights for the segmentation of the place name by the part of speech information; the second word segmentation weight unit is configured to set a second word segmentation weight for a word with a preset length, and the first word segmentation weight is greater than the second word segmentation weight; the third word segmentation weight unit is configured to set a third word segmentation weight for the word segmentation with the part-of-speech information not being the place name and the word length being greater than the preset length; and the vector representation unit is configured to perform weighted calculation on the participles according to the first participle weight, the second participle weight and the third participle weight to obtain vector representation of the target business name.
An embodiment of the present disclosure provides an electronic device, including: at least one processor; a storage device for storing at least one program which, when executed by the at least one processor, causes the at least one processor to implement the merchant identification method as described in the above embodiments.
The embodiments of the present disclosure provide a computer-readable medium, on which a computer program is stored, which when executed by a processor implements the merchant identification method as described in the above embodiments.
In the technical solutions provided by some embodiments of the present disclosure, when a target merchant registers through a target merchant name, vector representation is performed on the target merchant name, and similarity between the target merchant vector representation and set center vector representation of each history set is calculated; and a new set is created according to the similarity and is used as a target set corresponding to the target merchant name, and the continuously added target merchant names can be clustered incrementally, so that the accuracy of set division is improved, the existing history set is not influenced, and the resource waste caused by repeated offline calculation of the existing history set can be avoided. Meanwhile, based on the newly-created added set as a target set, the target merchant can be determined as the target type merchant according to the target set information of the target set, and the newly-created target type merchant set can be obtained through online continuous mining.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure. It is to be understood that the drawings in the following description are merely exemplary of the disclosure, and that other drawings may be derived from those drawings by one of ordinary skill in the art without the exercise of inventive faculty. In the drawings:
fig. 1 shows a schematic diagram of an exemplary system architecture to which a merchant identification method or apparatus of an embodiment of the present disclosure may be applied.
FIG. 2 schematically shows a flow diagram of a merchant identification method according to one embodiment of the present disclosure.
FIG. 3 schematically shows a flow diagram of a merchant identification method according to one embodiment of the present disclosure.
FIG. 4 schematically shows a flow diagram of a merchant identification method according to one embodiment of the present disclosure.
FIG. 5 schematically illustrates a process flow diagram for a target business name after a stop word.
FIG. 6 schematically illustrates a process flow diagram for a target business name after a stop word.
Fig. 7 schematically illustrates a flow chart of a merchant identification method according to one embodiment of the present disclosure.
Fig. 8 schematically illustrates a block diagram of a merchant identification arrangement according to an embodiment of the present disclosure.
FIG. 9 shows a schematic structural diagram of an electronic device suitable for use in implementing embodiments of the present disclosure.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the embodiments of the disclosure can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and the like. In other instances, well-known methods, devices, implementations, or operations have not been shown or described in detail to avoid obscuring aspects of the disclosure.
The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in at least one hardware module or integrated circuit, or in different networks and/or processor means and/or microcontroller means.
The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
In a traditional service scenario, according to a traditional Clustering method such as a K-means Clustering algorithm (Kmeans), a Density-Based Clustering algorithm (Density-Based Clustering of Applications with Noise, DBSCAN), etc., the method obtains aggregate information through offline Clustering, and puts the offline aggregate information on line for use, thereby achieving the purpose of classifying newly registered merchants into existing aggregates according to registered merchant names.
However, the above-described method has the following disadvantages.
(1) The scheme needs to use a large amount of data for off-line training, the calculation complexity is generally O (K x N ^2), the training is time-consuming, even if the method is applied to on-line reasoning, the calculation complexity of a single sample is still O (K x N), and the requirement of on-line calculation real-time performance cannot be met.
(2) When the scheme is applied to the online, only the newly added merchant names can be classified into the set obtained by offline training, and the newly added set in the newly registered merchants cannot be effectively mined, so that the accuracy of classifying the registered merchant names into the set is greatly reduced, and the capability of discovering a new target type merchant set is limited.
(3) The scheme has the problem that the set identification is unstable, and if the set information is obtained by on-line retraining, the problem that the set identification after retraining and the set identification obtained by previous training cannot correspond to each other occurs, so that historical results cannot be compatible. If the degree of maliciousness of the set is re-evaluated based on the total amount of historical data, a great deal of resource waste will be brought.
Therefore, a new merchant identification method, apparatus, electronic device and computer readable medium are needed.
Fig. 1 shows a schematic diagram of an exemplary system architecture 100 to which the merchant identification method or apparatus of embodiments of the present disclosure may be applied.
As shown in fig. 1, the system architecture 100 may include one or more of terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation. For example, server 105 may be a server cluster comprised of multiple servers, or the like.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablets, portable computers, desktop computers, wearable devices, virtual reality devices, smart homes, and so forth.
The server 105 may be a server that provides various services. For example, terminal device 103 (which may also be terminal device 101 or 102) uploads the target merchant name of the target merchant registration to server 105. The server 105 may obtain a name of a target merchant registered by the target merchant; processing the target business name to obtain a target business vector representation of the target business name; calculating the similarity of the target merchant vector representation and the set center vector representation of the history set; creating a new set as a target set corresponding to the target merchant name according to the similarity; and determining the target merchant as a target type merchant according to the target set information of the target set, wherein the target type merchant refers to merchants which use a first number of merchant names registered in a preset time range to conduct abnormal transactions, and the similarity between any two of the first number of merchant names is smaller than a preset threshold value. And feeds back the identification result that the target merchant is the merchant of the target type to the terminal device 103.
FIG. 2 schematically shows a flow diagram of a merchant identification method according to one embodiment of the present disclosure. The method provided in the embodiment of the present disclosure may be processed by any electronic device with computing processing capability, for example, the server 105 and/or the terminal devices 102 and 103 in the embodiment of fig. 1 described above, and in the following embodiment, the server 105 is taken as an example for illustration, but the present disclosure is not limited thereto.
As shown in fig. 2, a merchant identification method provided by an embodiment of the present disclosure may include the following steps.
In step S202, a target merchant name registered by the target merchant is acquired.
In the embodiment of the present disclosure, the target merchant may be a user using the terminal device 102 or 103, and the user generates a registered target merchant name through an operation on the terminal device and sends the registered target merchant name to the server 105 through the terminal device, so that the server obtains the registered target merchant name of the target merchant.
In step S204, the target merchant name is processed to obtain a target merchant vector representation of the target merchant name.
In the embodiment of the disclosure, the target business name can be represented as a multidimensional vector containing semantic information according to processes of stop-word, word segmentation, vector representation and the like.
In step S206, the similarity of the target merchant vector representation and the set center vector representation of the history set is calculated.
In the embodiment of the present disclosure, the history set may be a set of multiple merchant names obtained by performing offline training in advance according to the merchant names registered in history to cluster the merchant names registered in history. A set-center vector representation for each history set may be determined from merchant vector representations of historically registered merchant names included in each history set. In step S206, the similarity may be obtained by calculating the cosine distance between the target merchant name and the similarity represented by the set center vector of each history set. The calculation formula of the similarity can be expressed as follows.
Wherein, V sim Is a K-dimensional vector representing K similarities between the target merchant vector representation and the K history sets, V mch For target merchant vector representation, V centers Set center vector, V, for all (K in this embodiment) history sets center_k Is a set center vector for the kth history set (e.g. K history set center vectors 501 shown in figure 5),
for the ith element in the set center vector of the kth history set,
is the ith element in the target merchant vector representation, and n is the dimension of the target merchant vector representation. In this example n is 200, see FIGS. 5 andfig. 6 embodiment).
In step S208, a new added set is created as a target set corresponding to the target merchant name according to the similarity.
In the embodiment of the disclosure, the maximum value of the similarity can be determined
And establishing a new set as a target set corresponding to the target merchant name. Maximum value in similarity
Can be expressed as
Wherein each merchant name may belong to a different set of merchants. The similarity between any two business names in a certain business set is smaller than a preset set threshold value.
If the maximum value in the similarity is smaller than the similarity threshold, a newly-added set can be created as the target set corresponding to the target business name. In this embodiment, when the maximum value of the similarity is smaller than the similarity threshold, it may be considered that the target merchant name is not similar to the historical set, and therefore, by creating a new added set directly as the target set corresponding to the target merchant name, the target merchant names that are continuously added may be incrementally clustered, which is beneficial to subsequent mining of target type merchants directly on line.
In an exemplary embodiment, if the maximum value of the similarities is greater than or equal to a similarity threshold, the history set having the largest similarity is determined as the target set.
In step S210, a target merchant is determined as a target type merchant according to target set information of a target set, where the target type merchant is a merchant that performs an abnormal transaction by using a first number of merchant names registered in a preset time range, and a similarity between any two of the first number of merchant names is smaller than a preset threshold.
In the embodiment of the present disclosure, the target set information is an identifier indicating that the target set is a target-type merchant set. When the target set is the target type merchant set, the target merchant can be confirmed to be the target type merchant. For a given target set, target set information may be determined based on historical transaction behavior for merchant names (including target merchant names) included in the target set. The target type merchant may be a malicious merchant type. The types to which each set of target merchants may belong may include: a benevolent merchant type and a malicious merchant type.
According to the merchant identification method provided by the embodiment of the disclosure, when a target merchant registers through a target merchant name, vector representation is carried out on the target merchant name, and the similarity between the vector representation of the target merchant and the vector representation of the set center of each historical set is calculated; and a new set is created according to the similarity and is used as a target set corresponding to the target merchant name, and the continuously added target merchant names can be clustered incrementally, so that the accuracy of set division is improved, the existing history set is not influenced, and the resource waste caused by repeated offline calculation of the existing history set can be avoided. Meanwhile, based on the newly-created added set as a target set, the target merchant can be determined as the target type merchant according to the target set information of the target set, and the newly-created target type merchant set can be obtained through online continuous mining.
In an exemplary embodiment, when the target business name is processed to obtain the vector representation of the target business name, the following steps may be included.
Removing stop words from the target business name; segmenting the target business name without the stop word to obtain the segmentation of the target business name and the part-of-speech information of the segmentation; setting first word segmentation weight for the word segmentation of the place name by using the part of speech information; setting a second participle weight for the participles with the word length being a preset length, wherein the first participle weight is greater than the second participle weight; setting third participles with part-of-speech information not being place names and word length being greater than preset length; and performing weighted calculation on the participles according to the first participle weight, the second participle weight and the third participle weight to obtain the vector representation of the target business name.
When the stop word is removed from the target business username, the meaningless special symbols and the like in the target business username can be removed firstly, so that the influence of the meaningless special symbols and the like on the subsequent semantic representation is avoided. Secondly, words with high frequency in historical merchant names can be counted to obtain a merchant name deactivation word list such as 'limited company', the words are contained in most merchant names, useless information in the target merchant names can be reduced by deleting the words, and words with more distinctiveness are reserved.
Fig. 5 and 6 schematically show the above-mentioned process flow of the target merchant name after the stop word is removed by way of example. As shown in fig. 5 and fig. 6, the participle of the target house name "internet retail store an ancient type of spoon internet grocery bar of koroqin, avenue" after the stop word is removed may be expressed as: "Tongliao city, ns", "Korlin region, ns", "Korlin, ns", "street, ns", "Fan, d", "Bar, y", "Bir, n", "Internet, n", "retail store, n". Wherein ns represents that the part of speech information is a place name, d represents an adverb, y represents a word of a mood, and n represents a noun. In this case, each participle may be subjected to word vector mapping, so as to obtain a participle vector representation of each participle, for example, a 200-dimensional vector representation in fig. 5 and 6. And different weights are set according to the part of speech of each participle. For example, in fig. 5, the first weight set for the participle of the place name (for example, the participle: "tongliao city", "koreans", "aven") is 1.2, and the second weight set for the participle of the word length being a preset length (the preset length being 1 in the example of fig. 5) (for example, the participle: "fan", "bar", "an ancient type of spoon") is 0.5. The third weight is set to 1 for the participle whose part-of-speech information is not a place name and whose word length is greater than a preset length (e.g., participle: "internet", "retail store"). The resulting vector representation of the target merchant name may be shown, for example, at 504 in fig. 5 or at 610 in fig. 6. Vector representation V of target business name mch The calculation method of (c) is as follows:
wherein, V word_l And representing the word segmentation vector obtained by mapping the ith word segmentation word, wherein L is the total number of the word segmentations included by the target merchant name.
In this embodiment, since the place nouns in the target-type merchants registered in batch contain more semantic information, different weights are assigned to the participles according to the part-of-speech information and the word length, a higher weight is assigned to the nouns of the place names, and a lower weight is assigned to the participles of the single words. The weight of the place name participle can be increased to more accurately classify the target place name into the correct set. Meanwhile, some randomly generated words exist in the merchant names which are registered in batch, the words can be divided into a plurality of single words, and the interference of meaningless words in the target merchant names to semantic representation can be avoided by reducing the weight of the single words.
FIG. 3 schematically shows a flow diagram of a merchant identification method according to one embodiment of the present disclosure.
As shown in fig. 3, a merchant identification method provided by the embodiment of the present disclosure may include the following steps.
In step S302, a target merchant name registered by the target merchant is acquired.
In the embodiment of the present disclosure, the step may be similar to step S202, and is not described herein again.
In step S304, the target merchant name is processed to obtain a target merchant vector representation of the target merchant name.
In the embodiment of the present disclosure, the step may be similar to step S204, and is not described herein again.
In step S306, the similarity of the target merchant vector representation and the set center vector representation of the history set is calculated.
In the embodiment of the present disclosure, the step may be similar to step S206, and is not described herein again.
In step S308, if the maximum value of the similarity is smaller than the similarity threshold, a new added set is created as a target set corresponding to the target merchant name.
In the embodiment of the present disclosure, the newly added set may be provided with a corresponding set identifier.
In step S310, if the maximum value of the similarity is smaller than the similarity threshold, after a new added set is created as a target set corresponding to the target merchant name, a new merchant name corresponding to the new added set in a time range from the creation time to the current time of the new added set is determined.
In the disclosed embodiment, for example, when 14 is given at 2/10/2021: at 00, according to the target house name ' Keerqin Koerqin Dajie Van bar an ancient type of spoon Internet retail store ' in Keerqin district, Tongliao city in figure 5 ' (hereinafter, a is called) 1 ) When a new added set a is newly created as a target set corresponding to a target merchant name, the new creation time (i.e., creation time) 14 of the new added set a may be: the time range from 00 hours to the current time is divided into the business account names (a) in the set A 2 To a m And m is an integer greater than 2) is determined as a new increased user name.
In step S312, when the added set is determined to be the target type merchant set according to the transaction information of the added account name and the target account name, the target merchant is determined to be the target type merchant.
In the embodiment of the present disclosure, can be according to a 1 、a 2 ，…，a m Determines the target set information for the new added set (i.e., the target set). The transaction information is an identifier indicating that a merchant corresponding to the merchant name has abnormal transaction behavior. Wherein a in a preset time range can be obtained according to the statistics of the transaction information 1 、a 2 ，…，a m When the ratio of the number of the merchants to m is larger than the target type merchant proportion threshold, the target set information of the newly added set is considered as follows: is a target type merchant set. The target-type merchant proportion threshold may be set to a value between 0 and 1 according to actual situations, and this is not particularly limited in the embodiment of the present disclosure. When the target set information is 'the target type merchant set', the newly added set is confirmed to be the target type merchant set, and the target merchant is confirmed to be the target type merchant, so that the target type merchant is identified on line.
In an exemplary embodiment, it may further include: updating a set-center vector representation of the target set according to the target merchant vector representation. For example, the target merchant vector representation may be determined as a set-center vector representation of the newly added set.
In an exemplary embodiment, it may further include: acquiring a set identifier of the history set; sorting the set identifications of the history set to obtain the largest set identification; and determining the set identifier of the newly added set according to the increment calculation of the maximum set identifier. In the embodiment of the present disclosure, the set identifier of the history set may be obtained by numbering the history set when the history set is obtained by training on line. For example, when 100 history sets are obtained from offline training, the 100 history sets may be numbered sequentially as 1, 2, 3, …, 100. With the largest set identified as 100. The incremental calculation may be, for example, an add 1 operation, and the set of the newly added set is identified as 101.
For another example, the 100 history sets are numbered sequentially as 2, 4, 6, …, 200. With the largest set identified as 200. If the increment is plus 2, the set id of the newly added set is 202.
Fig. 4 schematically illustrates a flow chart of a merchant identification method according to one embodiment of the present disclosure.
As shown in fig. 4, a merchant identification method provided by the embodiment of the present disclosure may include the following steps.
In step S402, a target merchant name registered by the target merchant is acquired.
In the embodiment of the present disclosure, the step may be similar to step S202, and is not described herein again.
In step S404, the target merchant name is processed to obtain a target merchant vector representation of the target merchant name.
In the embodiment of the present disclosure, the step may be similar to step S204, and is not described herein again.
In step S406, a similarity of the target merchant vector representation and a set center vector representation of the history set is calculated.
In the embodiment of the present disclosure, the steps may be similar to step S206, and are not described herein again.
In step S408, if the maximum value of the similarities is greater than or equal to the similarity threshold, the history set having the largest similarity is determined as the target set.
In step S410, when the target set is determined to be the target type merchant set according to the target set information of the target set, the target merchant is determined to be the target type merchant.
In the embodiment of the present disclosure, the determination manner of the target type merchant set may be described in relation to step S312 in fig. 3, and is not described herein again.
In an exemplary embodiment, it may further include: updating a set-center vector representation of the target set according to the target merchant vector representation. For example, the number of target merchants corresponding to the history set with the largest similarity may be determined; determining a first weight and a second weight according to the number of the target commercial tenants; and performing weighted summation calculation on the set center vector representation of the history set and the target merchant vector representation according to the first weight and the second weight so as to update the set center vector representation of the target set according to the weighted summation calculation result.
Wherein, when the number of target merchants is m, the first weight can be expressed as
The second weight can be expressed as
The weighted sum calculation result can be expressed as:
wherein, V center_k1 For the set-centered vector representation of the updated set of targets, V center_k Is a set center vector representation of the target set. The updated set center vector 502 may be schematically illustrated as 502 in FIG. 5.
In an exemplary embodiment, it may further include: and determining the set identifier of the history set with the maximum similarity as the set identifier of the target set. Such as set identifier 503 shown in fig. 5.
FIG. 7 schematically shows a flow diagram of a merchant identification method according to one embodiment of the present disclosure.
As shown in fig. 7, a merchant identification method provided by the embodiment of the present disclosure may include the following steps.
In step S702, cosine similarity is calculated from the target merchant vector representation and the set center vector representation of the history set.
In step S704, it is determined whether the maximum cosine similarity is greater than a similarity threshold.
In step S706, if the maximum cosine similarity is greater than the similarity threshold, the history set with the maximum cosine similarity is determined as the target set corresponding to the target merchant name, and the set center vector representation of the target set is updated according to the target merchant vector representation.
In step S708, if the maximum cosine similarity is less than or equal to the similarity threshold, a new added set is added, and the target merchant vector representation is determined as the set center vector representation of the new added set. Exemplary diagrams of the disclosed embodiments can be seen in fig. 5 and 6. In FIG. 5, the input is a set center vector representation of the target merchant name and the history set. And outputting the set identification of the set to which the target merchant belongs and the updated set center vector representation.
The method and the device effectively solve the problem that the existing clustering technology cannot find a newly-added set in real time, simultaneously avoid the work of repeatedly examining and verifying a malicious commercial tenant set caused by unstable set identification, and also represent the name of the commercial tenant by using the commercial tenant vector containing semantic information, thereby greatly improving the clustering accuracy and simultaneously reducing the calculation complexity.
From the practical application perspective, the scheme is applied to the group-gang mining service of target type merchants (such as malicious merchants), more than 200 malicious groups are found at present, more than 5000 newly registered target type merchants are found, the gain reaches 100% compared with the manual auditing mark amount, and the daily accumulated transaction amount of the target type merchants mined in 8 months reaches 2000 ten thousand.
In the embodiment, the computation complexity of a single sample is reduced to O (K) by an incremental clustering scheme, and compared with the prior art, the computation complexity is reduced by several orders of magnitude, so that the timeliness requirement of low computation amount required on the line can be met. The scheme design based on incremental clustering can effectively discover a new group on line, and when a newly added merchant does not belong to the current existing history set, the newly added merchant is set as a new added set, so that the problem that the newly added merchant name set cannot be effectively discovered in the prior art can be effectively solved. Meanwhile, the method and the device can ensure that the set identification is self-increased, ensure the uniqueness and the stability of the set identification, and avoid the defect that the stability and the uniqueness of the set identification cannot be ensured due to multiple times of training in the prior art.
The merchant identification method provided by the embodiment of the application has the advantages that the calculation complexity is low, the requirement of online real-time calculation can be met, the capability of discovering a new set in real time is realized, the accuracy of model division set is improved, and meanwhile, a new target type merchant set can be effectively mined. In the aspect of expansibility, the scheme can be used for not only mining target type merchant group but also detecting information such as abnormal personal account numbers, abnormal WeChat groups and the like.
Embodiments of the apparatus of the present disclosure are described below, which may be used to perform the above-mentioned merchant identification method of the present disclosure. For details that are not disclosed in the embodiments of the device of the present disclosure, please refer to the embodiments of the merchant identification method described above in the present disclosure.
Fig. 8 schematically illustrates a block diagram of a merchant identification arrangement according to an embodiment of the present disclosure.
Referring to fig. 8, a merchant identification apparatus 800 according to an embodiment of the present disclosure may include: a merchant name obtaining module 810, a vector representing module 820, a similarity calculating module 830, a target set determining module 840, and a target type merchant identifying module 850.
The merchant name acquisition module 810 may be configured to acquire a target merchant name registered by a target merchant.
The vector representation module 820 may be configured to process the target merchant name to obtain a target merchant vector representation of the target merchant name.
The similarity calculation module 830 may be configured to calculate the similarity of the target merchant vector representation and the collective center vector representation of the history collection.
The target set determining module 840 may be configured to create a new set according to the similarity as the target set corresponding to the target business name.
The target-type merchant identification module 850 may be configured to determine the target merchant as a target-type merchant according to the target set information of the target set, where the target-type merchant is a merchant that performs an abnormal transaction by using a first number of merchant names registered within a preset time range, and a similarity between any two of the first number of merchant names is smaller than a preset threshold.
According to the merchant identification method provided by the embodiment of the disclosure, when a target merchant registers through a target merchant name, vector representation is carried out on the target merchant name, and the similarity between the vector representation of the target merchant and the vector representation of the set center of each historical set is calculated; and a new set is created according to the similarity and is used as a target set corresponding to the target merchant name, and the continuously added target merchant names can be clustered incrementally, so that the accuracy of set division is improved, the existing history set is not influenced, and the resource waste caused by repeated offline calculation of the existing history set can be avoided. Meanwhile, based on the newly-created added set as a target set, the target merchant can be determined as the target type merchant according to the target set information of the target set, and the newly-created target type merchant set can be obtained through online continuous mining.
In an exemplary embodiment, the target set determination module 840 may include: a first target set determining unit, configured to, if a maximum value of the similarities is smaller than a similarity threshold, create a new set as a target set corresponding to the target business name; a second target set determining unit, configured to determine a history set having a maximum similarity as the target set if a maximum value of the similarities is greater than or equal to a similarity threshold.
In an exemplary embodiment, the target set information is an identifier indicating that the target set is a target type merchant set, and the target type merchant identifying module 850 may include: the first target type merchant identification unit can be configured to determine a newly added merchant name corresponding to a newly added set in a time range from creation time to current time after the newly added set is newly established as a target set corresponding to the target merchant name if the maximum value in the similarity is smaller than a similarity threshold value; when the newly-added set is determined to be a target type merchant set according to the transaction information of the new merchant account name and the target merchant account name, determining that the target merchant is a target type merchant; and a second target type merchant identification unit, which may be configured to determine that the target merchant is a target type merchant if the maximum value of the similarity is greater than or equal to a similarity threshold and the target set is determined to be a target type merchant set according to the target set information of the target set.
In an exemplary embodiment, the merchant identifying apparatus 800 may further comprise a set center vector update module configurable to update the set center vector representation of the target set according to the target merchant vector representation.
In an exemplary embodiment, the set center vector updating module may include a first set center vector updating unit, which may be configured to determine the target merchant vector representation as the set center vector representation of the newly added set if a maximum value of the similarities is less than a similarity threshold; a second set center vector updating unit, configured to determine the number of target merchants corresponding to the history set with the maximum similarity if the maximum value of the similarities is greater than or equal to a similarity threshold; determining a first weight and a second weight according to the number of the target commercial tenants; and performing weighted summation calculation on the set center vector representation of the history set and the target merchant vector representation according to the first weight and the second weight so as to update the set center vector representation of the target set according to the weighted summation calculation result.
In an exemplary embodiment, the merchant identifying apparatus 800 may further include: a first set identifier determining module, configured to obtain a set identifier of the history set if a maximum value of the similarity is smaller than a similarity threshold; sorting the set identifications of the history set to obtain the largest set identification; and determining the set identifier of the newly added set according to the increment calculation of the maximum set identifier. And the second set identifier determining module may be configured to determine, if the maximum value of the similarities is greater than or equal to a similarity threshold, the set identifier of the history set having the largest similarity as the set identifier of the target set.
In an exemplary embodiment, the vector representation module 820 may include: the stop word unit can be configured to stop words for the target business name; the word segmentation unit can be configured to segment the target business name without the stop word to obtain the segmentation of the target business name and the part-of-speech information of the segmentation; a first word segmentation weight unit configured to set a first word segmentation weight for a word segmentation of the part of speech information for the place name; the second participle weight unit can be configured to set a second participle weight for the participle with the word length being a preset length, wherein the first participle weight is greater than the second participle weight; a third participle weight unit which can be configured to set a third participle weight for the participle of which the part-of-speech information is not a place name and the word length is greater than the preset length; and the vector representation unit can be configured to perform weighted calculation on the participles according to the first participle weight, the second participle weight and the third participle weight to obtain the vector representation of the target business name.
FIG. 9 shows a schematic structural diagram of an electronic device suitable for use in implementing embodiments of the present disclosure. It should be noted that the electronic device 900 shown in fig. 9 is only an example, and should not bring any limitation to the functions and the application scope of the embodiment of the present disclosure.
As shown in fig. 9, the electronic apparatus 900 includes a Central Processing Unit (CPU)901 that can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)902 or a program loaded from a storage portion 908 into a Random Access Memory (RAM) 903. In the RAM903, various programs and data necessary for system operation are also stored. The CPU 901, ROM 902, and RAM903 are connected to each other via a bus 904. An input/output (I/O) interface 905 is also connected to bus 904.
The following components are connected to the I/O interface 905: an input portion 906 including a keyboard, a mouse, and the like; an output section 907 including components such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 908 including a hard disk and the like; and a communication section 909 including a network interface card such as a LAN card, a modem, or the like. The communication section 909 performs communication processing via a network such as the internet. A drive 910 is also connected to the I/O interface 905 as needed. A removable medium 911 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 910 as necessary so that a computer program read out therefrom is mounted into the storage section 908 as necessary.
In particular, the processes described below with reference to the flowcharts may be implemented as computer software programs, according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication section 909 and/or installed from the removable medium 911. The computer program executes various functions defined in the system of the present application when executed by a Central Processing Unit (CPU) 901.
It should be noted that the computer readable media shown in the present disclosure may be computer readable signal media or computer readable storage media or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having at least one wire, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer-readable signal medium may include a propagated data signal with computer-readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises at least one executable instruction for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules and/or units described in the embodiments of the present disclosure may be implemented by software, or by hardware, and the described modules and/or units may also be disposed in a processor. Wherein the names of such modules and/or units do not in some way constitute a limitation on the modules and/or units themselves.
As another aspect, the present application also provides a computer-readable medium, which may be contained in the electronic device described in the above embodiments; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by one of the electronic devices, cause the electronic device to implement the method as described in the embodiments below. For example, the electronic device may implement the steps shown in fig. 2 or fig. 3 or fig. 4 or fig. 7.
It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice in the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (10)
1. A merchant identification method, comprising:
acquiring a target merchant name registered by a target merchant;
processing the target business name to obtain a target business vector representation of the target business name;
calculating the similarity of the target merchant vector representation and the set center vector representation of the history set;
creating a new set according to the similarity as a target set corresponding to the target merchant name;
and determining the target merchant as a target type merchant according to the target set information of the target set, wherein the target type merchant refers to a merchant performing abnormal transaction by using a first number of merchant names registered in a preset time range, and the similarity between any two of the first number of merchant names is smaller than a preset threshold.
2. The method of claim 1, wherein creating a new added set according to the similarity as the target set corresponding to the target merchant name comprises:
if the maximum value in the similarity is smaller than a similarity threshold value, a new added set is created as a target set corresponding to the target merchant name;
and if the maximum value in the similarity is greater than or equal to the similarity threshold, determining the history set with the maximum similarity as the target set.
3. The method of claim 2, wherein the target collection information is an identification indicating that the target collection is a target type merchant collection; wherein determining the target merchant as a target type merchant according to the target set information of the target set comprises:
if the maximum value in the similarity is smaller than the similarity threshold, determining a new provider account name corresponding to a new set in a time range from creation time to current time after the new set is newly created as a target set corresponding to the target merchant name; when the newly added set is determined to be a target type merchant set according to the transaction information of the new merchant account name and the target merchant account name, determining the target merchant to be a target type merchant;
and if the maximum value in the similarity is greater than or equal to the similarity threshold value, and when the target set is determined to be the target type merchant set according to the target set information of the target set, determining that the target merchant is the target type merchant.
4. The method of claim 2, further comprising:
updating a set center vector representation of the target set according to the target merchant vector representation.
5. The method of claim 4, wherein updating the set-center vector representation of the target set according to the target merchant vector representation comprises:
if the maximum value in the similarity is smaller than the similarity threshold value, determining the target merchant vector representation as a set center vector representation of the newly-added set;
if the maximum value in the similarity is larger than or equal to the similarity threshold, determining the number of target merchants corresponding to the history set with the maximum similarity; determining a first weight and a second weight according to the number of the target commercial tenants; and performing weighted summation calculation on the set center vector representation of the history set and the target merchant vector representation according to the first weight and the second weight so as to update the set center vector representation of the target set according to the weighted summation calculation result.
6. The method of claim 2, further comprising:
if the maximum value in the similarity is smaller than the similarity threshold value, acquiring a set identifier of the history set; sorting the set identifications of the history set to obtain the largest set identification; determining the set identifier of the newly added set according to the increment calculation of the maximum set identifier;
and if the maximum value in the similarity is greater than or equal to the similarity threshold value, determining the set identifier of the history set with the maximum similarity as the set identifier of the target set.
7. The method of claim 1, wherein processing the target username to obtain the vector representation of the target username comprises:
removing stop words from the target business name;
segmenting the target business name without the stop word to obtain the segmentation of the target business name and the part-of-speech information of the segmentation;
setting first segmentation weight for the segmentation of the place name according to the part of speech information;
setting a second participle weight for the participles with the word length being a preset length, wherein the first participle weight is greater than the second participle weight;
setting third participles with part-of-speech information not being place names and word length being greater than preset length;
and performing weighted calculation on the participles according to the first participle weight, the second participle weight and the third participle weight to obtain the vector representation of the target business name.
8. A merchant identification arrangement, comprising:
the merchant name acquisition module is configured to acquire a target merchant name registered by a target merchant;
the vector representation module is configured to process the target business name to obtain target business vector representation of the target business name;
a similarity calculation module configured to calculate a similarity of the target merchant vector representation and a set center vector representation of a history set;
a target set determining module configured to create a new set according to the similarity as a target set corresponding to the target merchant name;
and the target type merchant identification module is configured to determine the target merchant as a target type merchant according to the target set information of the target set, wherein the target type merchant refers to a merchant which performs abnormal transaction by using a first number of merchant names registered in a preset time range, and the similarity between any two of the first number of merchant names is smaller than a preset threshold value.
9. An electronic device, comprising:
at least one processor;
storage means for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement the method of any one of claims 1-7.
10. A computer-readable medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110256483.1A CN115049446A (en) | 2021-03-09 | 2021-03-09 | Merchant identification method and device, electronic equipment and computer readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110256483.1A CN115049446A (en) | 2021-03-09 | 2021-03-09 | Merchant identification method and device, electronic equipment and computer readable medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115049446A true CN115049446A (en) | 2022-09-13 |
Family
ID=83156537
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110256483.1A Pending CN115049446A (en) | 2021-03-09 | 2021-03-09 | Merchant identification method and device, electronic equipment and computer readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115049446A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117112628A (en) * | 2023-09-08 | 2023-11-24 | 廊坊丛林科技有限公司 | Logistics data updating method and system |
| CN117172792A (en) * | 2023-11-02 | 2023-12-05 | 赞塔(杭州)科技有限公司 | Customer information management method and device |
-
2021
- 2021-03-09 CN CN202110256483.1A patent/CN115049446A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117112628A (en) * | 2023-09-08 | 2023-11-24 | 廊坊丛林科技有限公司 | Logistics data updating method and system |
| CN117172792A (en) * | 2023-11-02 | 2023-12-05 | 赞塔(杭州)科技有限公司 | Customer information management method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112148987B (en) | Message pushing method based on target object activity and related equipment | |
| CN106651057B (en) | Mobile terminal user age prediction method based on installation package sequence list | |
| CN112528025A (en) | Text clustering method, device and equipment based on density and storage medium | |
| CN111371858B (en) | Group control equipment identification method, device, medium and electronic equipment | |
| CN110909222B (en) | User portrait establishing method and device based on clustering, medium and electronic equipment | |
| CN107886241B (en) | Resource analysis method, device, medium, and electronic apparatus | |
| CN114444619B (en) | Sample generation method, training method, data processing method and electronic device | |
| CN115049446A (en) | Merchant identification method and device, electronic equipment and computer readable medium | |
| CN114186626A (en) | Abnormity detection method and device, electronic equipment and computer readable medium | |
| CN110110213A (en) | Excavate method, apparatus, computer readable storage medium and the terminal device of user's occupation | |
| CN111582645B (en) | APP risk assessment method and device based on factoring machine and electronic equipment | |
| CN112035449A (en) | Data processing method and device, computer equipment and storage medium | |
| CN115632874A (en) | Method, device, equipment and storage medium for detecting threat of entity object | |
| CN111667018B (en) | Object clustering method and device, computer readable medium and electronic equipment | |
| CN112950359A (en) | User identification method and device | |
| CN111245815B (en) | Data processing method and device, storage medium and electronic equipment | |
| CN115545753A (en) | Partner prediction method based on Bayesian algorithm and related equipment | |
| CN115099875A (en) | Data classification method based on decision tree model and related equipment | |
| CN113591881A (en) | Intention recognition method and device based on model fusion, electronic equipment and medium | |
| CN113961797A (en) | Resource recommendation method and device, electronic equipment and readable storage medium | |
| CN113869904A (en) | Suspicious data identification method, device, electronic equipment, medium and computer program | |
| CN112084408A (en) | List data screening method and device, computer equipment and storage medium | |
| CN110895564A (en) | Potential customer data processing method and device | |
| CN114547448B (en) | Data processing method, model training method, device, equipment, storage medium and program | |
| CN114065074A (en) | Audience group acquisition method, and training method and device of user object matching model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40074007 Country of ref document: HK |