CN109918048B

CN109918048B - Target object extraction method, device and system and computer readable storage medium

Info

Publication number: CN109918048B
Application number: CN201811614035.9A
Authority: CN
Inventors: 姜丹薇
Original assignee: Beijing QIYI Century Science and Technology Co Ltd
Current assignee: Beijing QIYI Century Science and Technology Co Ltd
Priority date: 2018-12-27
Filing date: 2018-12-27
Publication date: 2022-09-06
Anticipated expiration: 2038-12-27
Also published as: CN109918048A

Abstract

The invention provides a target object extraction method, a device and a system and a computer readable storage medium, and belongs to the technical field of computers. The terminal can display a preset interface comprising a candidate object type and a candidate feature extraction option, then, the selection operation of a user on the candidate object type and the candidate feature extraction option can be detected, feature configuration information of a target object is generated according to the selected candidate object type and the selected candidate feature extraction option, finally, the feature configuration information is sent to the server, and the server can extract a matched object according to the feature configuration information. Therefore, when an object meeting certain characteristics needs to be extracted, a user only needs to select the type of the object needing to be extracted and the characteristic factors which the object needs to have in a preset interface, and compared with a mode of developing corresponding implementation codes aiming at different characteristic customization modes in the prior art, the implementation process of object extraction is simplified, and the implementation cost is reduced.

Description

Target object extraction method, device and system and computer readable storage medium

Technical Field

The present invention relates to the field of computer technologies, and in particular, to a method, an apparatus, a system, and a computer-readable storage medium for extracting a target object.

Background

At present, in security wind control and recommendation systems, it is necessary to analyze User behaviors, extract objects conforming to different characteristics, for example, User Identities (UIDs) conforming to abnormal login characteristics, and use the objects for detecting fraud, identifying illegal users, performing personalized recommendation, and the like.

In the prior art, when an object meeting a certain characteristic needs to be extracted, a corresponding implementation code is customized and developed aiming at the characteristic that the object needs to meet, and then object capture is realized. However, in the prior art, the method for realizing the code through customized development consumes higher cost, and has more complicated realization process and lower convenience.

Disclosure of Invention

The invention provides a target object extraction method, a device, a system and a computer readable storage medium, which are used for solving the problems of high cost and complex implementation process of extracting a target object.

According to a first aspect of the present invention, there is provided a target object extraction method, which may be applied to a system including a terminal and a server, the method including:

the terminal displays a preset interface; the preset interface comprises candidate object categories and candidate feature extraction options;

the terminal detects the selection operation of the user on the candidate object category and the candidate feature extraction option;

the terminal generates feature configuration information of the target object according to the selected candidate object category and the selected candidate feature extraction option; the feature configuration information at least defines the category of the target object and the features required by the target object;

the terminal sends the feature configuration information to a server;

and the server extracts the target object according to the category of the target object and the characteristics required by the target object.

According to a second aspect of the present invention, there is provided a target object extraction method, which can be applied to a terminal, and the method can include:

displaying a preset interface; the preset interface comprises candidate object categories and candidate feature extraction options;

detecting the selection operation of the user on the candidate object category and the candidate feature extraction option;

generating feature configuration information of the target object according to the selected candidate object category and the selected candidate feature extraction option; the feature configuration information at least defines the category of the target object and the features required by the target object;

and sending the feature configuration information to a server.

Optionally, different candidate feature extraction options correspond to different feature extraction factors;

generating feature configuration information of the target object according to the selected candidate object category and the selected candidate feature extraction option, including:

determining the selected candidate object category as a category of the target object;

and combining the feature extraction factors corresponding to each selected candidate feature extraction option and the category of the target object according to a preset format to obtain feature configuration information.

According to a third aspect of the present invention, there is provided a target object extraction method, which may be applied to a server, the method including:

receiving feature configuration information sent by a terminal; the feature configuration information at least defines the category of the target object and the features required by the target object;

and extracting the target object according to the category of the target object and the required characteristics of the target object.

Optionally, the required characteristics of the target object at least include a target time period;

the extracting the target object according to the category of the target object and the required features of the target object includes:

if the target time period in the features required by the target object falls into the time range of the real-time data, extracting the target object from the real-time data; or,

if the target time period in the features required by the target object falls into the time range of the off-line data, extracting the target object from the off-line data; or,

and if one part of the target time period in the characteristics of the target object falls into the time range of the real-time data and the other part of the target time period falls into the time range of the off-line data, extracting the target object from the real-time data and the off-line data.

Optionally, the extracting the target object from the real-time data includes:

and extracting an object with the characteristics required by the target object from the real-time data by using a preset real-time calculation engine to obtain the target object.

Optionally, the features required by the target object further include attributes of the target operation; the extracting the target object from the offline data comprises the following steps:

selecting a target data source from a plurality of preset data sources according to the type of the target operation in the characteristics required by the target object; the different data sources include offline data for different types of operations;

screening the data in the target data source according to a target time period included in the characteristics required by the target object to obtain offline data to be analyzed;

and extracting an object with the characteristics required by the target object from the offline data to be analyzed by using a preset offline calculation engine to obtain the target object.

Optionally, the extracting a target object from the real-time data and the offline data includes:

extracting an object with characteristics required by the target object from the real-time data by using a preset real-time computing engine to obtain a first target object;

screening the data in the target data source according to a target time period, a target operation type and attributes of target operation which are included in the characteristics required by the target object to obtain offline data to be analyzed;

extracting an object with characteristics required by the target object from the offline data to be analyzed by using a preset offline calculation engine to obtain a second target object;

and taking the first target object and the second target object as the target objects.

Optionally, after extracting the target object according to the category of the target object and the feature required by the target object, the method further includes:

and storing the target object and the characteristics required by the target object into a specified database.

According to a fourth aspect of the present invention, there is provided a target object extraction system that can be applied to a system including a terminal and a server;

the terminal is used for displaying a preset interface; the preset interface comprises candidate object categories and candidate feature extraction options;

the terminal is further used for detecting the selection operation of the user on the candidate object category and the candidate feature extraction option;

the terminal is further used for generating feature configuration information of the target object according to the selected candidate object category and the selected candidate feature extraction option; the feature configuration information at least defines the category of the target object and the features required by the target object;

the terminal is also used for sending the feature configuration information to a server;

and the server is also used for extracting the target object according to the category of the target object and the characteristics required by the target object.

According to a fifth aspect of the present invention, there is provided a target object extraction apparatus, which can be applied to a terminal, the apparatus comprising:

the display module is used for displaying a preset interface; the preset interface comprises candidate object categories and candidate feature extraction options;

the detection module is used for detecting the selection operation of the user on the candidate object category and the candidate feature extraction option;

the generating module is used for generating the feature configuration information of the target object according to the selected candidate object category and the selected candidate feature extraction option; the feature configuration information at least defines the category of the target object and the features required by the target object;

and the sending module is used for sending the feature configuration information to a server.

the generation module is configured to:

determining the selected candidate object category as the category of the target object;

According to a sixth aspect of the present invention, there is provided a target object extraction apparatus, which can be applied to a terminal, the apparatus may include:

the receiving module is used for receiving the characteristic configuration information sent by the terminal; the feature configuration information at least defines the category of the target object and the features required by the target object;

and the extraction module is used for extracting the target object according to the category of the target object and the characteristics required by the target object.

the extraction module comprises:

the first extraction submodule is used for extracting the target object from the real-time data if the target time period in the characteristics required by the target object falls into the time range of the real-time data; or,

the second extraction submodule is used for extracting the target object from the offline data if the target time period in the characteristics required by the target object falls into the time range of the offline data; or,

and the third extraction submodule is used for extracting the target object from the real-time data and the off-line data if one part of the target time period in the characteristics of the target object falls into the time range of the real-time data and the other part of the target time period falls into the time range of the off-line data.

Optionally, the first extraction sub-module is configured to:

Optionally, the features required by the target object further include attributes of the target operation; the second extraction submodule is configured to:

Optionally, the third extraction sub-module is configured to:

extracting an object with characteristics required by the target object from the real-time data by using a preset real-time calculation engine to obtain a first target object;

screening the data in the target data source according to the target time period, the target operation type and the attribute of the target operation included in the characteristics required by the target object to obtain offline data to be analyzed;

Optionally, the apparatus further comprises:

and the storage module is used for storing the target object and the characteristics required by the target object into a specified database.

According to a seventh aspect of the present invention, there is provided a computer-readable storage medium on which a computer program is stored, the computer program, when executed by a processor, implementing the target object extraction method as described in the first, second and third aspects.

Aiming at the prior art, the invention has the following advantages: the method comprises the steps that a terminal displays a preset interface comprising a candidate object category and a candidate feature extraction option, then, the selection operation of a user on the candidate object category and the candidate feature extraction option in the preset interface can be detected, feature configuration information of a target object is generated according to the selected candidate object category and the selected candidate feature extraction option, wherein at least the category of the target object and features required by the target object are defined in the feature configuration information, finally, the feature configuration information is sent to a server, and the server can extract matched objects according to the feature configuration information. Therefore, when an object meeting certain characteristics needs to be extracted, a user only needs to select the type of the object needing to be extracted and the characteristic factors which the object needs to have in the preset interface, and compared with the mode of developing corresponding implementation codes in the prior art aiming at different characteristic customization modes, the implementation process of object extraction is simplified, and the implementation cost is reduced.

The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:

fig. 1 is a flowchart illustrating steps of a target object extraction method according to an embodiment of the present invention;

FIG. 2 is a flowchart illustrating steps of another method for extracting a target object according to an embodiment of the present invention;

FIG. 3 is a flowchart illustrating steps of a further method for extracting a target object according to an embodiment of the present invention;

FIG. 4-1 is a flowchart illustrating steps of a further method for extracting a target object according to an embodiment of the present invention;

FIG. 4-2 is a schematic diagram of a user interface provided by an embodiment of the invention;

4-3 are schematic diagrams of a data screening interface provided by an embodiment of the invention;

fig. 4-4 are schematic diagrams of an application of a target feature extraction method provided by an embodiment of the present invention;

FIG. 5 is a block diagram of a target object extraction system provided by an embodiment of the present invention;

fig. 6 is a block diagram of a target object extraction apparatus according to an embodiment of the present invention;

fig. 7 is a block diagram of another target object extraction apparatus according to an embodiment of the present invention.

Detailed Description

Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

In practical application scenarios, for example, in a security-controlled scenario and an item recommendation scenario, it is often necessary to analyze the behavior of the user, and determine the user with high risk behavior based on the analysis result, or determine an item that may be interested in the user or an item that is not interested in the user, and so on. Further, when the behavior of the user is analyzed, the object with the corresponding feature is often extracted according to actual requirements, for example, when it is required to determine whether the user has a high-risk behavior, the UID with the high-risk behavior feature needs to be extracted, and when an object which the user may be interested in needs to be recommended to the user, the IP address of the object with the high-frequency access feature needs to be extracted.

Therefore, the embodiment of the present invention provides a target object extraction method, and in the method, a corresponding solution idea is provided for solving the problems of complicated operation and high cost in the prior art: the method comprises the steps that a preset interface is displayed by a terminal, the preset interface can be developed in advance, the interface can comprise preset candidate object types and candidate feature extraction options, the terminal can detect selection operation of a user on the candidate object types and the candidate feature extraction options, feature configuration information of a target object is generated according to the candidate object types and the candidate feature extraction options selected by the user, then the feature configuration information is sent to a server, the server can extract matched objects according to the feature configuration information, therefore, the user can select in the preset interface according to own extraction requirements, the objects with corresponding features can be extracted through the server, the operation process is simplified, and the implementation cost is reduced.

The above-mentioned target object extraction method is specifically described below.

Fig. 1 is a flowchart of steps of a target object extraction method provided in an embodiment of the present invention, which is applied to a system including a terminal and a server, and as shown in fig. 1, the method may include:

step 101, the terminal displays a preset interface; the preset interface comprises candidate object categories and candidate feature extraction options.

In this embodiment of the present invention, the preset interface may be developed in advance by a developer, and different candidate object categories and different candidate feature extraction options may be defined in the preset interface, where the candidate object categories defined in the preset interface indicate different types of objects, and for example, the object categories may be User Identities (UIDs), fingerprints, IP addresses of web pages, and the like. Further, different candidate feature extraction options may correspond to different feature extraction factors, and the feature extraction factors may serve as part of the content in the features to be extracted. Further, in practical application, all selectable contents of all feature extraction factors may be displayed in a preset interface for a user to select, and certainly, definition input boxes corresponding to all feature extraction factors may also be displayed in the preset interface, and the user may manually input a required content, which is not limited in the embodiment of the present invention.

And 102, detecting the selection operation of the candidate object category and the candidate feature extraction option by the terminal.

In practical application, when a user performs a selection operation, the user often performs the selection according to the actual needs of the user, and therefore, in this step, the terminal may detect the selection operation of the user on the candidate object type and the candidate feature extraction option in the preset interface, so as to determine what feature the user needs to extract the object.

103, the terminal generates feature configuration information of the target object according to the selected candidate object category and the selected candidate feature extraction option; the feature configuration information defines at least a category of the target object and a feature required by the target object.

Correspondingly, in the embodiment of the present invention, the terminal may determine the category of the target object according to the selected candidate object category, determine the feature required by the target object according to the selected candidate feature extraction option, and finally generate the feature configuration information defining the category of the target object and the required feature.

And step 104, the terminal sends the feature configuration information to a server.

In the embodiment of the present invention, since the feature configuration information defines the type of the target object and the feature configuration information of the required feature, the terminal may send the feature configuration information to the server, and the server may extract the target object having the required feature according to the feature configuration information.

Step 105, the server extracts the target object according to the category of the target object and the characteristics required by the target object.

In this embodiment of the present invention, the server may receive the feature configuration information, and then obtain a category of the target object and features required by the target object from the feature configuration information, where the category of the target object may indicate what kind of object needs to be extracted, and the features required by the target object may indicate features required by the extracted object, and then extract an object having the features required by the target object from the network system to obtain the target object.

In summary, in the target object extraction method provided in the embodiment of the present invention, the terminal may display a preset interface including a candidate object category and a candidate feature extraction option, then, may detect a selection operation of the user on the candidate object category and the candidate feature extraction option, and then generate feature configuration information of the target object according to the selected candidate object category and the selected candidate feature extraction option, where at least the category of the target object and features required by the target object are defined in the feature configuration information, and finally, the feature configuration information is sent to the server, and the server may extract a matched object according to the feature configuration information. Therefore, when an object meeting certain characteristics needs to be extracted, a user only needs to select the type of the object needing to be extracted and the characteristic factors which the object needs to have in a preset interface, and compared with a mode of developing corresponding implementation codes aiming at different characteristic customization modes in the prior art, the implementation process of object extraction is simplified, and the implementation cost is reduced.

Fig. 2 is a flowchart of steps of another target object extraction method provided in an embodiment of the present invention, which is applied to a terminal, and as shown in fig. 2, the method may include:

step 201, displaying a preset interface; the preset interface comprises candidate object categories and candidate feature extraction options.

Specifically, the implementation manner of this step may refer to step 101, and details of the embodiment of the present invention are not described herein.

Step 202, detecting the selection operation of the candidate object category and the candidate feature extraction option by the user.

Specifically, the implementation manner of this step may refer to step 102, which is not described herein again in this embodiment of the present invention.

Step 203, generating feature configuration information of the target object according to the selected candidate object category and the selected candidate feature extraction option; the feature configuration information defines at least a category of the target object and a feature required by the target object.

Specifically, the implementation manner of this step may refer to step 103, which is not described herein again in this embodiment of the present invention.

And step 204, sending the feature configuration information to a server so that the server extracts a matched object according to the feature configuration information.

Specifically, the implementation manner of this step may refer to step 104, and details of this embodiment of the present invention are not described herein.

In summary, in the target object extraction method provided in the embodiment of the present invention, the terminal may display a preset interface including a candidate object category and a candidate feature extraction option, then, may detect a selection operation of the user on the candidate object category and the candidate feature extraction option, and then generate feature configuration information of the target object according to the selected candidate object category and the selected candidate feature extraction option, where the feature configuration information at least defines a category of the target object and a feature required by the target object, and finally, send the feature configuration information to the server, so that the server may extract a matched object according to the feature configuration information. Therefore, when an object meeting certain characteristics needs to be extracted, a user only needs to select the type of the object needing to be extracted and the characteristic factors which the object needs to have in a preset interface, and compared with a mode of developing corresponding implementation codes aiming at different characteristic customization modes in the prior art, the implementation process of object extraction is simplified, and the implementation cost is reduced.

Fig. 3 is a flowchart of steps of another target object extraction method provided in an embodiment of the present invention, which is applied to a server, and as shown in the drawing, the method may include:

step 301, receiving feature configuration information sent by a terminal; the feature configuration information is generated by the terminal according to the selection operation of the user on a preset interface, and at least defines the category of the target object and the features required by the target object.

Specifically, the implementation manner of this step may refer to step 105, which is not described herein again in this embodiment of the present invention.

Step 302, extracting the target object according to the category of the target object and the characteristics required by the target object.

Specifically, the implementation manner of this step may refer to step 105, and details of the embodiment of the present invention are not described herein.

In summary, in the target object extraction method provided in the embodiments of the present invention, the server may receive feature configuration information sent by the terminal, where the feature configuration information is generated by the terminal according to a selection operation of a user on a preset interface, and at least a category of the target object and features required by the target object are defined in the feature configuration information, and then the target object is extracted according to the category of the target object and the features required by the target object in the feature configuration information. Therefore, when an object meeting certain characteristics needs to be extracted, a user only needs to select the type of the object needing to be extracted and the characteristic factors which the object needs to have in a preset interface of the terminal, the terminal can generate characteristic configuration information based on the selection of the user and send the characteristic configuration information to the server for object extraction, and compared with the mode of developing corresponding implementation codes in a customized mode aiming at different characteristics in the prior art, the implementation process of object extraction is simplified, and the implementation cost is reduced.

Fig. 4-1 is a flowchart illustrating steps of a further method for extracting a target object according to an embodiment of the present invention, and as shown in fig. 4-1, the method may include:

step 401, displaying a preset interface by a terminal; the preset interface comprises candidate object categories and candidate feature extraction options.

In this step, different candidate feature extraction options may correspond to different feature extraction factors, where the feature extraction factors may include a time range, an attribute of operation, a comparator, a comparison value, and so on. The time range may be unlimited time, or may be a fixed time period, for example, from 10 days in 11 months to 20 days in 11 months, or may be a sliding time period, that is, the length of the time period is fixed, but the starting and ending time points are rolling forward all the time, for example, within 2 hours from the current time point, further, the attribute of the operation may be the actual number of operations, the maximum number of times in unit time, the minimum number of times in unit time, the latest number of times in unit time, the number of times of a deduplication COUNT (DISTINCT COUNT), the duration of the operation, or the like, further, the comparator may include one of greater than, equal to, less than, equal to, or equal to, and the like, and the comparison value may be any value.

For example, fig. 4-2 is a schematic diagram of a user interface provided by an embodiment of the present invention, as shown in fig. 4-2, an attribute of an operation is represented by a "feature pattern" in fig. 4-2, and specifically, the attribute of the operation selected by the user is taken as "the latest value number per unit time" in fig. 4-2 as an example to illustrate. Further, in practical applications, a user may select multiple candidate object categories, that is, there may be multiple categories of target objects, so the candidate object category selected by the user is represented by "dimension combination" in fig. 4-2, and specifically, the candidate object category selected by the user is exemplified by "IP" and "UID" in fig. 4-2.

Further, the preset interface may further include a "deduplication dimension" option, and the user may use any one of the selected candidate object categories as the deduplication dimension to control the server to perform object extraction according to other candidate object categories except the candidate object category as the deduplication dimension, which is illustrated in fig. 4-2 by taking the deduplication dimension as "IP" as an example. Further, in an actual application, the characteristics required for the target object may include content indicating the entity object, for example, the number of login accounts corresponding to the login operation may be greater than 3 for the characteristics required for the target object, and then, the login account is the content indicating the entity object, so the preset interface may further include an "add" option and a "clear" option, and the user may increase a "sinking dimension" by selecting the "add" option, where the sinking dimension may be set to the entity object included in the characteristics required for the target object, for example, the login account, and thus, by setting the sinking dimension, the server may be controlled to display the entity object included in the extracted characteristics corresponding to the target object. Specifically, the lower sinking dimension in fig. 4-2 is "login account", for example, to illustrate. Further, the interface defines a time range by a "time window", the time range is taken as an example in fig. 4-2 as a sliding time period, the time range is set to be 1 minute to 10 minutes from the current time point, the interface further includes a "threshold value", that is, a comparison value, and the threshold value is taken as an example in fig. 4-2 as 5 for schematic illustration. Of course, in practical applications, other contents may also be included in the interface, for example, a selection area of the comparator, and the like, which is not limited in the embodiment of the present invention.

Step 402, the terminal detects the selection operation of the user on the candidate object category and the candidate feature extraction option.

Step 403, the terminal generates feature configuration information of the target object according to the selected candidate object category and the selected candidate feature extraction option; the feature configuration information defines at least a category of the target object and a feature required by the target object.

In this step, the terminal can be realized by the following substeps (1) to (2):

substep (1): the selected candidate object category is determined as the category of the target object.

For example, assuming that the candidate object class selected by the user is the UID, the terminal may determine that the class of the target object is the UID.

Substep (2): and combining the feature extraction factors corresponding to each selected candidate feature extraction option and the category of the target object according to a preset format to obtain feature configuration information.

In this step, the features required by the target object are the features required by the object to be extracted, and further, the preset format may be predefined by a developer, which is not limited in the embodiment of the present invention. For example, the preset format may be "category of target object + attribute of target operation + comparator + comparison value". Accordingly, the terminal may combine the category of the target object and the feature extraction factors selected by the user according to the category of the target object and the sequence of each feature extraction factor in the preset format, thereby obtaining feature configuration information. For example, assuming that the category of the target object selected by the user is UID, and the feature extraction factor corresponding to the selected feature extraction option is 1 minute, the number of login operations is greater than 5, the feature configuration information obtained by combining the features is: UID +1 minute + number of login operations + greater than +5, where the part "1 minute + number of login operations + greater than + 5" that the feature extraction factor constitutes is used to represent the feature required by the target, and the feature configuration information may be used to instruct the server to extract a UID whose number of login operations within 1 minute is greater than 5.

And step 404, the terminal sends the feature configuration information to a server.

Specifically, the implementation manner of this step may refer to step 104, which is not described herein again in this embodiment of the present invention.

Step 405, the server receives the feature configuration information sent by the terminal.

Step 406, the server extracts the target object according to the category of the target object and the required characteristics of the target object.

In this step, the features required by the target object may include at least a target time period, which is a time range included in the feature extraction factors used when the feature configuration information is generated. Further, the data in the network system includes real-time data and offline data, where the real-time data is real-time data received by the server within a preset time from the current time, and the preset time is set according to an actual situation, for example, the preset time may be 10 minutes, and the offline data is historical data received by the server within a time that exceeds the preset time from the current time.

Accordingly, if the target time period in the features required by the target object falls within the time range of the real-time data, the server may extract the target object from the real-time data. In the embodiment of the invention, the target object is extracted from the real-time data by the target time period falling into the time range of the real-time data in the characteristics required by the target object, so that the extraction range can be narrowed, and the extraction efficiency is improved.

Specifically, the server may implement the step of extracting the target object from the real-time data by the following substep (1):

substep (1): and extracting an object with the characteristics required by the target object from the real-time data by using a preset real-time calculation engine to obtain the target object.

In this step, the real-time computing engine may be an engine, which is deployed in advance on a server, and is used to extract an object from real-time data, where the real-time data may be composed of a plurality of message queues, each message queue may include data sent to the server, and the data may be a log.

Specifically, when extracting the target object, each piece of data in the real-time data may be analyzed to determine an object indicated by each piece of data, an operation performed on the object, and an operation time, and then, counting the analysis result, determining the specific value of the attribute of the target operation corresponding to the object with the same category as the target object in the target time period, and finally, it is determined whether it satisfies the numerical relationship represented by the comparator and the comparison value in the feature configuration information, for example, the login times of the UID1 in 1 minute from the current time point are 3, the login times of the UID2 in 1 minute from the current time point are 7, the numerical relation represented by the comparator and the comparison value in the feature configuration information is more than 5, since the UID1 does not satisfy the numerical relationship and the UID2 satisfies the numerical relationship, the UID2 can be determined as the target object.

Further, if the target time period in the features required by the target object falls within the time range of the offline data, the server may extract the target object from the offline data, where the time range of the offline data is the time beyond the preset time from the current time.

Specifically, the server may implement the step of extracting the target object from the offline data by the following substeps (1) to (3):

substep (1): selecting a target data source from a plurality of preset data sources according to the type of the target operation in the characteristics required by the target object; the different data sources include offline data for different types of operations.

In practical applications, in order to facilitate management of offline data, the offline data is often classified and stored to different locations according to different data dimensions, and therefore, multiple data sources exist. Taking data dimension as the type of the operation corresponding to the data as an example, the preset multiple data sources may store offline data for different types of operations, where addresses and adopted data formats of each data source are different.

Correspondingly, in this step, the stored offline data can be selected from the preset multiple data sources as the data source of the type for the target operation, and the data source is used as the target data source, so that the data range of the extraction object is narrowed, and the efficiency of the extraction operation is improved. Wherein the type of the target operation is used to indicate what the target operation is specifically. For example, assuming the type of target operation is a login operation, the server may select the stored offline data as the data source for the login operation as the target data source.

Substep (2): and screening the data in the target data source according to a target time period included in the characteristics required by the target object to obtain the offline data to be analyzed.

For example, assuming that the target time period is from 11 month 10 to 11 month 20, the server performs screening according to the time point of each piece of offline data in the target data source, and specifically, the offline data whose time point is from 11 month 10 to 11 month 20 may be determined as the offline data to be analyzed. Of course, as the requirements for object extraction are different, the features required by the target object may further include other information, for example, a service source of the data, and accordingly, when the screening is performed, the screening may be performed according to the service source, and when a plurality of screening conditions are provided, each condition may be satisfied as the screening criterion, or any one of the conditions may be satisfied as the screening criterion, which is not limited in the embodiment of the present invention. In the embodiment of the invention, the offline data in the target data source is screened, so that the data range of the extracted object can be further reduced, and the efficiency of the extraction operation is further improved.

Further, in order to improve flexibility of data screening, in the embodiment of the present invention, a user may set a data screening condition, and accordingly, the server may perform a corresponding screening operation according to a content set by the user. For example, fig. 4-3 are schematic diagrams of a data filtering interface provided in an embodiment of the present invention, specifically, a server may display the interface through an external display device, for example, through a terminal connected to the server, and a user may set data filtering conditions on the interface, as shown in fig. 4-3, the interface includes two filtering mode options: "all of the following conditions are satisfied" and "any of the following conditions are satisfied", specifically, fig. 4-3 schematically illustrates, by taking as an example that the user selects "all of the following conditions are satisfied", and accordingly, if the user selects the option "all of the following conditions are satisfied", the server may use each of the conditions as the screening criteria, and if the user selects the option "any of the following conditions is satisfied", the server may use any of the conditions as the screening criteria, further, the interface further includes an "add" option and a "clear" option, the user may add the screening conditions by clicking the "add" option, delete the added screening conditions by clicking the clear "option, and fig. 4-3 adds 3 screening conditions by the user, and these 3 screening conditions are respectively: the "service name is equal to security _ slide _ captcha", "Level is equal to 3", and "sliding verification code sliding verification result is equal to true" are taken as examples, which are schematically illustrated.

Substep (3): and extracting an object with the characteristics required by the target object from the offline data to be analyzed by using a preset offline calculation engine to obtain the target object.

In this step, the offline computation engine may be an engine that is deployed in advance on a server and is used to extract objects from offline data. Specifically, when the target object is extracted, each piece of offline data to be analyzed in the offline data to be analyzed may be analyzed first, an object indicated by each piece of offline data to be analyzed, an operation performed on the object, and an operation time are determined, then, the analysis result is counted, the number of times of the attribute of the target operation corresponding to the object having the same category as the target object in the target time period is determined, and finally, whether the number satisfies a numerical relationship represented by the comparator and the comparison value in the feature configuration information is determined.

Further, if a part of the target time period in the features required by the target object falls within the time range of the real-time data and another part of the target time period falls within the time range of the off-line data, the target object is extracted from the real-time data and the off-line data. Specifically, the server may implement the step of extracting the target object from the real-time data by the following substep (1):

substep (1): and extracting an object with the characteristics required by the target object from the real-time data by using a preset real-time calculation engine to obtain a first target object.

For example, assuming that the target time period in the feature required by the target object is one minute, the server may count, from the real-time data, a specific value of an attribute of the corresponding target operation within one minute of the object having the same category as the target object, for example, a specific value of the login number corresponding to the UID within 1 minute, finally, determine whether the value relationship represented by the comparator and the comparison value in the feature configuration information is satisfied, and if the value relationship is satisfied, determine that the value is the first target object.

Substep (2): selecting a target data source from a plurality of preset data sources according to the type of the target operation in the characteristics required by the target object; the different data sources include offline data for different types of operations.

Specifically, the implementation manner of this step may refer to the foregoing substeps, and details are not described herein in this embodiment of the present invention.

And (3) screening the data in the target data source according to a target time period included in the characteristics required by the target object to obtain the offline data to be analyzed.

Specifically, the implementation manner of this step may refer to the foregoing substeps, and details are not described herein in this embodiment of the present invention. It should be noted that, in practical applications, in order to improve the analysis efficiency of the real-time data, the real-time data may be first filtered, and finally, the target object is extracted from the filtered real-time data, so as to improve the efficiency of the extraction operation.

Substep (4): and extracting an object with the characteristics required by the target object from the offline data to be analyzed by using a preset offline calculation engine to obtain a second target object.

For example, the server may use a preset offline calculation engine to count, from the offline data to be analyzed, specific values of attributes of corresponding target operations of objects having the same category as the target object within one minute, then determine whether the specific values satisfy a numerical relationship represented by the comparator and the comparison value in the feature configuration information, and if the specific values satisfy the numerical relationship, determine that the specific values are the second target object. In the embodiment of the invention, different calculation engines are respectively arranged for the real-time data and the off-line data, so that the object can be simultaneously extracted from the real-time data and the off-line data, and the efficiency of extracting the object is further ensured.

Substep (5): and taking the first target object and the second target object as target objects.

For example, the server may determine all objects in the set of the first target object and the second target object as the target objects.

It should be noted that, in practical applications, when extracting a target object, third-party data may also be referred to, for example, logs provided by other network systems, so as to improve the representativeness of the extracted target object, for example, fig. 4 to 4 are application schematic diagrams of a target feature extraction method provided in an embodiment of the present invention, and as shown in fig. 4 to 4, real-time data may include a plurality of message queues: message queue 1, message queue X, offline data may include multiple data sources: the data warehouse 1, the data warehouse Y and the server may process the real-time data and the offline data by using a real-time computing engine and an offline computing engine, specifically, the data may be first screened, and then the target object may be extracted from the screened data based on the characteristics required by the target object.

Further, in order to facilitate the subsequent process of utilizing the target object according to the features of the target object, in the embodiment of the present invention, after the server extracts the target object according to the category of the target object and the features required by the target object, the server may store the target object and the features required by the target object into the specified database, so as to facilitate the utilization of other operations. For example, the target object and the features required by the target object may be used as model training samples for training a model, or, according to the target object and the features required by the target object, an access rule may be set for the client, for example, if the features required by the target object are greater than 10 times of login operation in one minute, the access rule may be set to prohibit access to the target object having the features required by the target object, so as to improve the security of the client.

In summary, in the target object extraction method provided in the embodiment of the present invention, the terminal may display a preset interface including a candidate object category and a candidate feature extraction option, then, may detect a selection operation of the user on the candidate object category and the candidate feature extraction option, and then generate feature configuration information of the target object according to the selected candidate object category and the selected candidate feature extraction option, where at least the category of the target object and features required by the target object are defined in the feature configuration information, and finally, the feature configuration information is sent to the server, and the server may extract a matched object according to the feature configuration information. Therefore, when an object meeting certain characteristics needs to be extracted, a user only needs to select the type of the object needing to be extracted and the characteristic factors which the object needs to have in the preset interface, and compared with the mode of developing corresponding implementation codes in the prior art aiming at different characteristic customization modes, the implementation process of object extraction is simplified, and the implementation cost is reduced.

Fig. 5 is a block diagram of a target object extraction system according to an embodiment of the present invention, and as shown in fig. 5, the system 50 may include: a terminal 501 and a server 502;

the terminal 501 is configured to display a preset interface; the preset interface comprises candidate object categories and candidate feature extraction options;

the terminal 501 is further configured to detect a selection operation of the user on the candidate object category and the candidate feature extraction option;

the terminal 501 is further configured to generate feature configuration information of the target object according to the selected candidate object category and the selected candidate feature extraction option; the feature configuration information at least defines the category of the target object and the features required by the target object;

the terminal 501 is further configured to send the feature configuration information to a server 502;

the server 502 is configured to extract the target object according to the category of the target object and the feature required by the target object.

In summary, in the target object extraction system provided in the embodiment of the present invention, the terminal may display a preset interface including a candidate object category and a candidate feature extraction option, then, may detect a selection operation of the user on the candidate object category and the candidate feature extraction option, and then generate feature configuration information of the target object according to the selected candidate object category and the selected candidate feature extraction option, where at least the category of the target object and features required by the target object are defined in the feature configuration information, and finally, the feature configuration information is sent to the server, and the server may extract a matched object according to the feature configuration information. Therefore, when an object meeting certain characteristics needs to be extracted, a user only needs to select the object type needing to be extracted and the characteristic factors needing to be possessed by the object in the preset interface, and compared with the mode of developing corresponding implementation codes aiming at different characteristic customization in the prior art, the implementation process of object extraction is simplified, and the implementation cost is reduced.

Fig. 6 is a block diagram of an apparatus for extracting a target object according to an embodiment of the present invention, and as shown in fig. 6, the apparatus 60 may include:

the display module 601 is configured to display a preset interface; the preset interface comprises candidate object categories and candidate feature extraction options;

a detection module 602, configured to detect a selection operation of the candidate object category and the candidate feature extraction option by a user;

a generating module 603, configured to generate feature configuration information of the target object according to the selected candidate object category and the selected candidate feature extraction option; the feature configuration information at least defines the category of the target object and the features required by the target object;

a sending module 604, configured to send the feature configuration information to a server, so that the server extracts a matched object according to the feature configuration information.

the generating module 603 is configured to:

In summary, in an embodiment of the target object extraction apparatus provided by the invention, the display module may display a preset interface including a candidate object category and a candidate feature extraction option, the detection module may detect a selection operation of a user on the candidate object category and the candidate feature extraction option in the preset interface, the generation module may generate feature configuration information of the target object according to the selected candidate object category and the selected candidate feature extraction option, where the feature configuration information at least defines a category of the target object and a feature required by the target object, and finally the sending module may send the feature configuration information to the server, so that the server may extract a matched object according to the feature configuration information. Therefore, when an object meeting certain characteristics needs to be extracted, a user only needs to select the object type needing to be extracted and the characteristic factors needing to be possessed by the object in the preset interface, and compared with the mode of developing corresponding implementation codes aiming at different characteristic customization in the prior art, the implementation process of object extraction is simplified, and the implementation cost is reduced.

Fig. 7 is a block diagram of another target object extracting apparatus according to an embodiment of the present invention, and as shown in fig. 7, the apparatus 70 may include:

a receiving module 701, configured to receive feature configuration information sent by a terminal; the characteristic configuration information is generated by the terminal according to the selection operation of a user on a preset interface, and at least defines the category of a target object and the characteristics required by the target object;

an extracting module 702, configured to extract a target object according to the category of the target object and the feature required by the target object.

the extracting module 702 includes:

a third extraction submodule, configured to extract a target object from the real-time data and the offline data if a part of a target time period in the features of the target object falls within a time range of the real-time data and another part of the target time period falls within a time range of the offline data

Optionally, the first extraction sub-module is configured to:

Optionally, the third extraction sub-module is configured to:

and taking the first target object and the second target object as target objects.

Optionally, the apparatus 70 further comprises:

In summary, in the target object extraction apparatus provided in the embodiment of the present invention, the receiving module may receive feature configuration information sent by the terminal, where the feature configuration information is generated by the terminal according to a selection operation of a user on a preset interface, and at least a category of the target object and a feature required by the target object are defined in the feature configuration information, and then the extracting module may extract the target object according to the category of the target object and the feature required by the target object in the feature configuration information. Therefore, when an object meeting certain characteristics needs to be extracted, a user only needs to select the object type needing to be extracted and the characteristic factors needing to be possessed by the object in a preset interface of the terminal, the terminal can generate characteristic configuration information based on the selection of the user and sends the characteristic configuration information to the server for object extraction, and compared with the mode of developing corresponding implementation codes in a customized mode aiming at different characteristics in the prior art, the implementation process of object extraction is simplified, and the implementation cost is reduced.

For the above device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for the relevant points, refer to the partial description of the method embodiment.

Preferably, an embodiment of the present invention further provides a mobile terminal, which includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor, where the computer program, when executed by the processor, implements each process of the above-mentioned target object extraction method embodiment, and can achieve the same technical effect, and details are not repeated here to avoid repetition.

The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements each process of the above target object extraction method embodiment, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here. The computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.

The embodiments in the present specification are all described in a progressive manner, and each embodiment focuses on differences from other embodiments, and portions that are the same and similar between the embodiments may be referred to each other.

As is readily imaginable to the person skilled in the art: any combination of the above embodiments is possible, and thus any combination between the above embodiments is an embodiment of the present invention, but the present disclosure is not necessarily detailed herein for reasons of space.

The target object extraction methods provided herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems may also be used with the teachings herein. The structure required to construct a system embodying aspects of the present invention will be apparent from the above description. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.

In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed to reflect the intent: rather, the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components in the embodiments may be combined into one module or unit or component, and furthermore, may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Moreover, those skilled in the art will appreciate that although some embodiments described herein include some features included in other embodiments, not others, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the claims, any of the claimed embodiments may be used in any combination.

The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components of the target object extraction method according to embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website, or provided on a carrier signal, or provided in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.

Claims

1. A target object extraction method is applied to a system comprising a terminal and a server, and comprises the following steps:

the terminal displays a preset interface; the preset interface comprises candidate object categories, candidate feature extraction options and sinking dimension options;

the terminal generates feature configuration information of the target object according to the selected candidate object category, the selected candidate feature extraction option and the selected sinking dimension option; the feature configuration information at least defines the category of the target object and the features required by the target object; the sinking dimension option is used for controlling the server to display entity objects contained in the extracted features corresponding to the target objects;

the terminal sends the feature configuration information to a server;

the server extracts a target object according to the category of the target object and the characteristics required by the target object; different candidate feature extraction options correspond to different feature extraction factors;

and combining the feature extraction factors corresponding to each selected candidate feature extraction option and the category of the target object according to the category of the target object and the sequence of each feature extraction factor in a preset format to obtain feature configuration information.

2. A target object extraction method is applied to a terminal, and comprises the following steps:

displaying a preset interface; the preset interface comprises candidate object categories, candidate feature extraction options and sinking dimension options;

detecting the selection operation of the user on the candidate object category and the candidate characteristic extraction option;

generating feature configuration information of the target object according to the selected candidate object category and the selected candidate feature extraction option and sinking dimension option; the feature configuration information at least defines the category of the target object and the features required by the target object; the sinking dimension option is used for controlling the server to display the entity objects contained in the extracted features corresponding to the target objects;

sending the feature configuration information to the server; different candidate feature extraction options correspond to different feature extraction factors;

3. A target object extraction method is applied to a server, and comprises the following steps:

receiving feature configuration information sent by a terminal; the feature configuration information at least defines the category of the target object, the features required by the target object and entity objects contained in the features required by the target object;

extracting a target object according to the category of the target object and the characteristics required by the target object; the required characteristics of the target object comprise at least a target time period;

displaying entity objects contained in the extracted features corresponding to the target objects;

4. The method of claim 3, wherein extracting the target object from the real-time data comprises:

and extracting an object with the characteristics required by the target object from the real-time data by using a preset real-time computing engine to obtain the target object.

5. The method of claim 3, wherein the desired characteristics of the target object further include attributes of the target operation; the extracting the target object from the offline data comprises the following steps:

6. The method of claim 3, wherein extracting the target object from the real-time data and the offline data comprises:

7. The method according to claim 3, wherein after extracting the target object according to the category of the target object and the required features of the target object, the method further comprises:

8. A target object extraction system is characterized by comprising a terminal and a server;

the terminal is used for displaying a preset interface; the preset interface comprises candidate object categories, candidate feature extraction options and sinking dimension options;

the terminal is further used for generating feature configuration information of the target object according to the selected candidate object category, the selected candidate feature extraction option and the selected sinking dimension option; the feature configuration information at least defines the category of the target object and the features required by the target object; the sinking dimension option is used for controlling the server to display entity objects contained in the extracted features corresponding to the target objects;

the server is used for extracting the target object according to the category of the target object and the characteristics required by the target object; different candidate feature extraction options correspond to different feature extraction factors;

the terminal is specifically used for determining the selected candidate object type as the type of the target object; and combining the feature extraction factors corresponding to each selected candidate feature extraction option and the category of the target object according to the category of the target object in a preset format and the sequence of each feature extraction factor to obtain feature configuration information.

9. An object extraction device, applied to a terminal, the device comprising:

the display module is used for displaying a preset interface; the preset interface comprises candidate object categories, candidate feature extraction options and sinking dimension options;

the generating module is used for generating feature configuration information of the target object according to the selected candidate object category and the selected candidate feature extraction option and sinking dimension option; the feature configuration information at least defines the category of the target object and the features required by the target object; the sinking dimension option is used for controlling the server to display the entity objects contained in the extracted features corresponding to the target objects;

a sending module, configured to send the feature configuration information to the server;

different candidate feature extraction options correspond to different feature extraction factors;

the generation module is configured to:

determining the selected candidate object category as a category of the target object; and combining the feature extraction factors corresponding to each selected candidate feature extraction option and the category of the target object according to the category of the target object in a preset format and the sequence of each feature extraction factor to obtain feature configuration information.

10. A target object extraction device applied to a server, the device comprising:

the receiving module is used for receiving the characteristic configuration information sent by the terminal; the feature configuration information at least defines the category of the target object, the features required by the target object and entity objects contained in the features required by the target object;

the extraction module is used for extracting the target object according to the category of the target object and the characteristics required by the target object; the characteristics required by the target object comprise at least a target time period;

the device is also used for displaying entity objects contained in the extracted features corresponding to the target objects;

the extraction module comprises:

the second extraction submodule is used for extracting the target object from the off-line data if the target time period in the characteristics required by the target object falls into the time range of the off-line data; or,

11. The apparatus of claim 10, wherein the first extraction sub-module is configured to:

12. The apparatus of claim 10, wherein the desired characteristics of the target object further include attributes of a target operation; the second extraction submodule is configured to:

13. The apparatus of claim 10, wherein the third extraction sub-module is configured to:

14. The apparatus of claim 10, further comprising:

15. A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, implements a target object extraction method according to any one of claims 1 to 7.