CN110706026A - Abnormal user identification method, identification device and readable storage medium - Google Patents
Abnormal user identification method, identification device and readable storage medium Download PDFInfo
- Publication number
- CN110706026A CN110706026A CN201910908839.8A CN201910908839A CN110706026A CN 110706026 A CN110706026 A CN 110706026A CN 201910908839 A CN201910908839 A CN 201910908839A CN 110706026 A CN110706026 A CN 110706026A
- Authority
- CN
- China
- Prior art keywords
- comment
- dimension
- abnormal
- comment data
- detection
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0282—Rating or review of business operators or products
-
- 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]
- G06Q30/0609—Buyer or seller confidence or verification
Abstract
The application provides an identification method, an identification device and a readable storage medium of an abnormal user, wherein the identification method comprises the following steps: the method comprises the steps of obtaining a comment data set of a target user on a sharing platform within a preset statistical time period, and detecting whether comment data in the comment data set are abnormal comment data in each detection dimension; when the comment data are abnormal comment data in any detection dimension, dividing the corresponding detection dimension into a detection dimension data set; and adding the weight coefficient corresponding to each detection dimension in the detection dimension data set, and determining that the target user is an abnormal user when the total weight of the target user is greater than a preset threshold value. Therefore, the detection dimensionality needing to be added with the weight coefficient is determined according to the detection result of the comment data of the user on each detection dimensionality, the characteristic value of each detection dimensionality does not need to be added, multi-dimensional detection can be achieved, the weight coefficient of the detection dimensionality with abnormal data only needs to be added, and the detection efficiency and the detection accuracy are improved.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to an identification method, an identification device, and a readable storage medium for an abnormal user.
Background
With the rapid development of computer technology, users begin to rely more and more on terminal applications to purchase daily living goods, in view of the above, each large brand also popularizes the brand products of its own to various terminal applications, the users can refer to corresponding comments under the products to determine the quality of the products, and the brands themselves can analyze the popularity of the products according to the comments under the products themselves, but some abnormal users who brush comments exist in the comments, thereby influencing the estimation of the users and the brands themselves on the real effects of the products, and therefore, the method is very important for the identification of the comment users.
At present, the judgment of the abnormal user is directly carried out based on a single judgment rule, even when the judgment is carried out by integrating all detection rules, a large amount of judgment needs to be carried out on each detection rule through the rule, the judgment logic is complex, the calculation amount is large, and the judgment result is inaccurate.
Disclosure of Invention
In view of this, an object of the present application is to provide an identification method, an identification apparatus, and a readable storage medium for an abnormal user, which can perform detection on each detection dimension through comment data of a target user, add weight coefficients of the detection dimensions where data abnormality is detected, and determine that the target user is an abnormal user if a sum of the weight coefficients is greater than a preset threshold, so that a detection dimension that needs to be added with the weight coefficients is determined according to a detection result of the comment data of the user on each detection dimension, and without performing complicated discrimination on each detection dimension and adding a feature value of each detection dimension, multi-dimensional detection can be performed and only the weight coefficients of the detection dimensions where abnormal data exists need to be added, thereby facilitating improvement of detection efficiency and accuracy.
The embodiment of the application provides an identification method of an abnormal user, which comprises the following steps:
the method comprises the steps of obtaining a comment data set of a target user on a sharing platform within a preset statistical time period, and detecting whether comment data in the comment data set are abnormal comment data in each detection dimension;
when the comment data are abnormal comment data in any detection dimension, dividing the corresponding detection dimension into a detection dimension data set;
adding a weight coefficient corresponding to each detection dimension in the detection dimension data set to determine the total weight of the target user;
and when the total weight is greater than a preset threshold value, determining that the target user is an abnormal user.
Further, the detection dimension comprises at least one of a comment amount dimension, a comment density dimension, a comment content repetition degree dimension, a comment original label repetition degree dimension and a comment content contradiction dimension.
Further, when the detection dimension includes a comment amount dimension, it is determined that the comment data is abnormal comment data in the comment amount dimension by:
determining the total amount of the comment information of the target user from the comment data, and calculating the daily average comment amount of the target user within a preset statistical time period;
detecting whether the daily average evaluation quantity is larger than a preset threshold value;
and if the average daily comment amount is larger than a preset threshold value, determining that the comment data is abnormal comment data in the comment amount dimension.
Further, when the detection dimension includes a comment density dimension, it is determined that the comment data is abnormal comment data in the comment density dimension by:
acquiring a plurality of pieces of comment information of the target user within a preset time interval and a comment original label of a comment corresponding to each piece of comment information;
if the number of the comments of the target user under the comment post in a preset time interval is larger than a preset threshold value, determining that the comments of the target user are abnormal comments;
detecting whether the occurrence frequency of the abnormal comments in a preset statistical time period is greater than a preset threshold value or not;
and if the occurrence frequency of the abnormal comment in a preset statistical time period is greater than a preset threshold value, determining that the comment data is abnormal comment data in a comment density dimension.
Further, when the detection dimension includes a comment content repetition degree dimension, the comment data is determined to be abnormal comment data in the comment content repetition degree dimension by:
obtaining comment contents of the target user in different comment original posts within a preset statistical time period;
detecting whether the number of comments of the target user originally attached to comments with the same comment content is larger than a preset threshold value or not;
and if the number of the comments of the target user originally posted in the comment with the same comment content is larger than a preset threshold value, determining that the comment data is abnormal comment data in the dimension of the comment content repeatability.
Further, when the detection dimension comprises a comment original duplicate dimension, determining that the comment data is abnormal comment data in the comment original duplicate dimension by the following steps:
obtaining a plurality of original comment posts corresponding to the comment data and original post keywords corresponding to each original comment post;
detecting whether the number of the comments originally posted by the comments with the same original posting keyword in a preset time interval is greater than a preset threshold value;
and if the number of the comments originally posted by the comments with the same original posting keywords in a preset time interval is larger than a preset threshold value, determining that the comment data is abnormal comment data in the dimension of the original posting repetition degree of the comments.
Further, when the detection dimension comprises a comment content contradiction dimension, determining that the comment data is abnormal comment data in the comment content contradiction dimension by the following steps:
obtaining comment contents of the target user in different original posts within a preset statistical time period;
detecting whether the evaluation of the target user for the same keyword in different originally posted comment contents is inconsistent;
and if the evaluation of the target user for the same keyword in the comment contents originally posted is inconsistent, determining that the comment data is abnormal comment data in the comment content contradiction dimension.
The embodiment of the present application further provides an identification apparatus for an abnormal user, where the identification apparatus includes:
the processing module is used for acquiring a comment data set of a target user on a sharing platform within a preset statistical time period and detecting whether comment data in the comment data set are abnormal comment data in each detection dimension;
the dividing module is used for dividing the corresponding detection dimension into a detection dimension data set when the comment data is abnormal comment data in any detection dimension;
the first determining module is used for adding a weight coefficient corresponding to each detection dimension in the detection dimension data set divided by the dividing module and determining the total weight of the target user;
and the second determining module is used for determining that the target user is an abnormal user when the total weight determined by the first determining module is greater than a preset threshold.
Further, the detection dimension comprises at least one of a comment amount dimension, a comment density dimension, a comment content repetition degree dimension, a comment original label repetition degree dimension and a comment content contradiction dimension.
Further, when the detection dimension includes a comment amount dimension, the processing module, when determining that the comment data is abnormal comment data in the comment amount dimension, is configured to:
determining the total amount of the comment data of the target user from the comment data, and calculating the daily average comment amount of the target user within a preset statistical time period;
detecting whether the daily average evaluation quantity is larger than a preset threshold value;
and if the average daily comment amount is larger than a preset threshold value, determining that the comment data is abnormal comment data in the comment amount dimension.
Further, when the detection dimension includes a comment density dimension, the processing module, when determining that the comment data is abnormal comment data in the comment density dimension, is configured to:
acquiring a plurality of pieces of comment information of the target user within a preset time interval and a comment original label of a comment corresponding to each piece of comment information;
if the number of the comments of the target user under the comment post in a preset time interval is larger than a preset threshold value, determining that the comments of the target user are abnormal comments;
detecting whether the occurrence frequency of the abnormal comments in a preset statistical time period is greater than a preset threshold value or not;
and if the occurrence frequency of the abnormal comment in a preset statistical time period is greater than a preset threshold value, determining that the comment data is abnormal comment data in a comment density dimension.
Further, when the detection dimension includes a comment content repetition degree dimension, the processing module, when determining that the comment data is abnormal comment data in the comment content repetition degree dimension, is configured to:
obtaining comment contents of the target user in different comment original posts within a preset statistical time period;
detecting whether the number of comments of the target user originally attached to comments with the same comment content is larger than a preset threshold value or not;
and if the number of the comments of the target user originally posted in the comment with the same comment content is larger than a preset threshold value, determining that the comment data is abnormal comment data in the dimension of the comment content repeatability.
Further, when the detection dimension includes a comment original duplicate dimension, the processing module is configured to, when determining that the comment data is abnormal comment data in the comment original duplicate dimension through the following steps:
obtaining a plurality of original comment posts corresponding to the comment data and original post keywords corresponding to each original comment post;
detecting whether the number of the comments originally posted by the comments with the same original posting keyword in a preset time interval is greater than a preset threshold value;
and if the number of the comments originally posted by the comments with the same original posting keywords in a preset time interval is larger than a preset threshold value, determining that the comment data is abnormal comment data in the dimension of the original posting repetition degree of the comments.
Further, when the detection dimension includes a comment content contradiction dimension, the dividing module is configured to, when determining that the comment data is abnormal comment data in the comment content contradiction dimension:
obtaining comment contents of the target user in different original posts within a preset statistical time period;
detecting whether the evaluation of the target user for the same keyword in different originally posted comment contents is inconsistent;
and if the evaluation of the target user for the same keyword in the comment contents originally posted is inconsistent, determining that the comment data is abnormal comment data in the comment content contradiction dimension.
An embodiment of the present application further provides an electronic device, including: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating via the bus when the electronic device is running, the machine-readable instructions being executable by the processor to perform the steps of the method for identifying an abnormal user as described above.
The embodiment of the present application 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 steps of the method for identifying an abnormal user as described above are performed.
According to the identification method, the identification device and the readable storage medium for the abnormal users, a comment data set of a target user on a sharing platform in a preset statistical time period is obtained, and whether comment data in the comment data set are abnormal comment data in each detection dimension is detected; when the comment data are abnormal comment data in any detection dimension, dividing the corresponding detection dimension into a detection dimension data set; adding a weight coefficient corresponding to each detection dimension in the detection dimension data set to determine the total weight of the target user; and when the total weight is greater than a preset threshold value, determining that the target user is an abnormal user.
Therefore, a comment data set of a target user on a sharing platform is obtained, whether comment data are abnormal comment data in each detection dimension is detected according to the comment data in the comment data set, the weight coefficients of the detection dimensions for determining that the comment data are abnormal comment data are added to obtain the total weight, if the total weight is larger than a preset threshold value, the target user is determined to be an abnormal user, complex judgment is not needed to be carried out in each detection dimension, the characteristic value of each detection dimension is not needed to be added, multi-dimensional detection can be achieved, and only the weight coefficient of the detection dimension with the abnormal data needs to be added, and detection efficiency and accuracy are improved.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
FIG. 1 is a block diagram of a possible application scenario;
fig. 2 is a flowchart of an abnormal user identification method according to an embodiment of the present application;
FIG. 3 is a flow chart of a method of determining the review data as anomalous review data in a review volume dimension;
fig. 4 is a schematic structural diagram of an apparatus for identifying an abnormal user according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. Every other embodiment that can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present application falls within the protection scope of the present application.
First, an application scenario to which the present application is applicable will be described. The method and the device can be applied to the technical field of data processing, whether the obtained comment data set of the target user on the sharing platform is abnormal comment data or not in each detection dimension is detected, the total weight of the target user is obtained by adding the weight coefficients of the detection dimensions of the comment data set determined to be abnormal comment data, and if the weight coefficients are larger than a preset threshold value, the target user is determined to be an abnormal user. Therefore, the coefficient of each detection dimension with abnormality can be integrated, on the premise of reducing the calculation amount, whether the target user is an abnormal user can be detected more comprehensively and accurately, the efficiency and the accuracy rate of abnormal user detection can be improved, please refer to fig. 1, fig. 1 is a system structure diagram under a possible application scene, as shown in fig. 1, the system comprises a comment data storage device and an abnormal user identification device, the comment data storage device stores all comment data sharing on a platform in a preset statistical time period, the abnormal user identification device screens out a comment data set of the target user after receiving all comment data, and based on a detection result of the comment data set on each detection dimension, whether the target user is an abnormal user can be determined.
Research shows that at present, the judgment of abnormal users is directly carried out on the basis of a single judgment rule, even when the judgment is carried out by integrating all detection rules, a large amount of judgment needs to be carried out on each detection rule through the rule, the judgment logic is complex, the calculation amount is large, and the judgment result is inaccurate.
Based on this, the embodiment of the application provides an identification method for an abnormal user, which determines a detection dimension needing to be added with a weight coefficient according to a detection result of comment data of the user in each detection dimension, does not need to perform complex discrimination in each detection dimension and add a characteristic value of each detection dimension, can perform multi-dimensional detection and only needs to add the weight coefficient of the detection dimension with abnormal data, and is beneficial to improving detection efficiency and accuracy.
Referring to fig. 2, fig. 2 is a flowchart illustrating an abnormal user identification method according to an embodiment of the present application. As shown in fig. 2, the method for identifying an abnormal user provided in the embodiment of the present application includes:
In the step, all comment data on a sharing platform are divided according to the unique code ID (identity document) of each comment user within a preset statistical time period to obtain a comment data set of a target user, wherein the comment data set of the target user comprises at least one piece of comment data of the target user, and whether the comment data of the comment data set of the target user are abnormal comment data in each detection dimension is determined according to the comment data of the comment data set of the target user.
Wherein detecting the dimension may include: the comment volume dimension, the comment density dimension, the comment content repetition degree dimension, the comment original label repetition degree dimension and the comment content contradiction dimension.
Here, the comment volume dimension refers to the total number of the comment data of the target user within a preset statistical time period; the comment density dimension refers to the time interval between two comments issued by a target user; the comment content repeatability dimension refers to the similarity of comment contents of target users in different comment posts; the comment original posting repetition degree dimension refers to the content similarity of different comment posts of the target user comment; the comment content contradiction dimension refers to the comment content which is contradictory to the target user in different comment data.
The preset statistical time period can determine the number of the acquired comment data, and generally one month is used as a division node.
In this step, for the detection result of the comment data in the comment data set of the target user in each detection dimension, the detection dimension determining that the comment data in the comment data set is abnormal comment data is divided into a detection dimension data set in step 201.
Wherein the number of detection dimensions in the detection dimension dataset is less than or equal to the total number of detection dimensions.
For example, the comment data is detected to be abnormal comment data in any detection dimension in a comment quantity dimension, a comment content repeatability dimension and a comment content contradiction dimension, and the comment quantity dimension, the comment content repeatability dimension and the comment content contradiction dimension are divided into a detection dimension data set.
And 203, adding a weight coefficient corresponding to each detection dimension in the detection dimension data set, and determining the total weight of the target user.
In the step, a weight coefficient corresponding to each detection dimension in the detection dimension data set is obtained, and each weight coefficient is added to obtain a total weight corresponding to the target user.
For example, whether the user is an abnormal user is judged accurately according to the total number of comments of the user in a preset statistical time period, and the weight coefficient corresponding to the comment quantity dimension can be adjusted up when the weight is set; the weight of each dimension may also be determined according to measures to avoid abnormal users when the sharing platform is designed, for example, when the sharing platform is designed, for a user who reviews repeatedly within a period of time, the system has taken measures to frequently review and prohibit review again, and in this embodiment, the weight of the review content repetition degree dimension is set to be lower; a scheme of setting the weight of each detection dimension is given, the weight of the comment quantity dimension is set to be 0.8, and the weight of the comment density dimension is set to be 0.8; the weight of the comment content repetition degree dimension is set to 0.3; the weight of the dimension of the repeatability of the original comment is set to be 0.5; the weight of the contradiction dimension of the comment content is set to 0.3; it follows that the sum of the weight coefficients for each dimension may not be 1.
Corresponding to the above embodiment, the weighting coefficients 0.8, 0.3, and 0.3 corresponding to the comment amount dimension, the comment content repetition degree dimension, and the comment content contradiction dimension are added, resulting in a total weighting of 1.4.
And 204, when the total weight is greater than a preset threshold value, determining that the target user is an abnormal user.
In this step, after the calculation in step 203, the total weight number corresponding to the target user is obtained, and the total weight number is compared with a preset threshold, and when the total weight number is greater than the preset threshold, the corresponding target user may be an abnormal user.
Corresponding to the above embodiment, the total weight is 1.4, the preset threshold is 0.8, and the total weight is greater than the preset threshold, so that the target user is determined to be an abnormal user.
Here, the preset threshold may be preset according to historical detection data, may be set to about 1, or may be a preset threshold that is a weight coefficient of a detection dimension with the highest reliability of judgment of an abnormal user in all detection dimensions.
According to the identification method of the abnormal user, a comment data set of a target user on a sharing platform in a preset statistical time period is obtained, and whether comment data in the comment data set are abnormal comment data in each detection dimension is detected; when the comment data are abnormal comment data in any detection dimension, dividing the corresponding detection dimension into a detection dimension data set; adding a weight coefficient corresponding to each detection dimension in the detection dimension data set to determine the total weight of the target user; and when the total weight is greater than a preset threshold value, determining that the target user is an abnormal user.
Therefore, a comment data set of a target user on a sharing platform is obtained, whether comment data are abnormal comment data in each detection dimension is detected according to the comment data in the comment data set, the weight coefficients of the detection dimensions for determining that the comment data are abnormal comment data are added to obtain the total weight, if the total weight is larger than a preset threshold value, the target user is determined to be an abnormal user, complex judgment is not needed to be carried out in each detection dimension, the characteristic value of each detection dimension is not needed to be added, multi-dimensional detection can be achieved, and only the weight coefficient of the detection dimension with the abnormal data needs to be added, and detection efficiency and accuracy are improved.
Referring to fig. 3, fig. 3 is a flowchart of a method for determining that the comment data is abnormal comment data in the comment volume dimension. As shown in fig. 3, when the detection dimension is the comment amount dimension, it is determined that the comment data is abnormal data in the comment amount dimension by:
step 301, determining the total amount of the comment information of the target user from the comment data, and calculating the daily average comment amount of the target user within a preset statistical time period.
In this step, the total number of the comments in the comment data set of the target user in the current statistical time period is obtained, and the daily average comment amount for each day in the statistical time period is obtained.
For example, the statistical time period is 30 days a month, the total number of the comment data in the statistical time period is 450, and in the month, assuming that the target user gives comments every day, the daily average comment amount corresponding to the target user is 15.
And 302, detecting whether the daily average evaluation quantity is larger than a preset threshold value.
In this step, it is detected whether the average amount per day is greater than a preset threshold, where the preset threshold may be set according to historical statistical data, for example, in a normal user in a one-month statistical period, the average number of comments per day does not exceed 10, and then 10 may be used as a preset threshold for detecting the average amount per day.
Step 303, if the average daily comment amount is larger than a preset threshold, determining that the comment data is abnormal comment data in the comment amount dimension.
In this step, after the detection in step 302, if the average comment amount per day is greater than the preset threshold, in the comment amount dimension, the comment data in the comment data set corresponding to the target user is the abnormal comment data.
For example, corresponding to the above embodiment, it is counted that the average daily comment amount of the user is 15, the preset threshold is 10, and it can be known that the average daily comment amount of the target user is 15 and is greater than the preset threshold 10, so that the comment data in the comment data set of the target user is the abnormal comment data in the comment amount dimension.
Further, in the comment amount detection dimension, the judgment on the abnormal comment data may also use the comment amount of the target user every day in a preset statistical time period as a judgment standard, and when the number of the comment data of the target user in a single day is greater than a preset threshold, it is determined that the comment data is the abnormal comment data in the comment amount dimension.
For example, the total number of comment information of a certain target user in a preset statistical time period is obtained, the number of comments of the target user in each day is divided according to the time of the comments of the target user, and if the number of comments of the target user in a certain day or even a certain day is more than 40 and is greater than a preset threshold value of 30 within the statistical time of one month, it is determined that the comment data in the comment data set of the target user is abnormal comment data in the comment quantity dimension.
Further, when the detection dimension comprises comment dimension density, the comment data is determined to be abnormal comment data in comment density by the following steps: acquiring a plurality of pieces of comment information of the target user within a preset time interval and a comment original label of a comment corresponding to each piece of comment information; if the number of the comments of the target user under the comment post in a preset time interval is larger than a preset threshold value, determining that the comments of the target user are abnormal comments; detecting whether the occurrence frequency of the abnormal comments in a preset statistical time period is greater than a preset threshold value or not; and if the occurrence frequency of the abnormal comment in a preset statistical time period is greater than a preset threshold value, determining that the comment data is abnormal comment data in a comment density dimension.
In the step, the number of a plurality of pieces of comment data of a target user in a preset time interval and a comment original sticker corresponding to each piece of comment data are obtained, namely the number of comments of the target user in a period of time interval and the original sticker of the comment of the target user in the period of time are obtained, in the preset time interval, the number of comments of the target user in different original stickers is larger than a preset threshold value, the abnormal comment situation of the target user is shown, the frequency of the abnormal comment situation of the target user is recorded, in a preset counting time period, the frequency of the abnormal comment situation of the target user is larger than the preset threshold value, and then the comment data in the comment data set of the target user are abnormal comment data in a comment density dimension.
The preset time interval can be set according to the time of normally browsing a post, and the possibility that a user commenting under the condition that the post cannot be browsed is an abnormal user exists.
For example, if the time for normally seeing one original sticker is 1 minute, 1 minute is set as a preset time interval, within 1 minute, the number of comments of a target user on different original stickers exceeds 3, the target user can be considered to have abnormal comment, and within a time period of 30 days in one month of a statistical time period, the abnormal comment of the target user occurs for more than 3 times, and the comment data of the target user is considered to be abnormal comment data in a comment density dimension.
Further, when the detection dimension includes a comment content repetition degree dimension, the comment data is determined to be abnormal comment data in the comment content repetition degree dimension or the comment original label repetition degree dimension through the following steps: obtaining comment contents of the target user in different comment original posts within a preset statistical time period; detecting whether the number of comments of the target user originally attached to comments with the same comment content is larger than a preset threshold value or not; and if the number of the comments of the target user originally posted in the comment with the same comment content is larger than a preset threshold value, determining that the comment data is abnormal comment data in the dimension of the comment content repeatability.
In the step, comment contents of target users under different original posts in a preset statistical time period are obtained, whether the comment contents of the target users under different original posts are the same or not is detected, particularly whether the comment contents of the target users are the same or not is detected under the condition that the original posts are greatly different, and the number of comment data of the target users under different original posts in the preset statistical time period is counted; if the number of the comment data with the same comment content under different original posts is larger than a preset threshold value, determining that the comment data is abnormal comment data in the dimension of the comment content repeatability.
For example, if the comments of the target users in the posts of different bloggers are similar contents such as "where they can buy", "look", "strongly recommend" and the like within one month of the statistical time, and the comment contents of the target users and the like exceed 30 pieces within one month, it is determined that the comment data is abnormal comment data in the comment content repetition dimension.
Further, when the detection dimension comprises a comment original duplicate dimension, determining that the comment data is abnormal comment data in the comment original duplicate dimension by the following steps: obtaining a plurality of original comment posts corresponding to the comment data and original post keywords corresponding to each set of original comment posts; detecting whether the number of the comments originally posted by the comments with the same original posting keyword in a preset time interval is greater than a preset threshold value; and if the number of the comments originally posted by the comments with the same original posting keywords in a preset time interval is larger than a preset threshold value, determining that the comment data is abnormal comment data in the dimension of the original posting repetition degree of the comments.
In the step, keywords of original comments corresponding to comment data comments of the target user are obtained, the number of original comments with the same keywords of the original comments is counted within a preset counting time period, and if the number of original comments with the same keywords of the original comments is larger than a preset threshold value, the comment data are determined to be abnormal comment data in the dimension of the repeatability of the original comments.
Wherein, the keyword of the original label can be the name and efficacy of the article introduced in the original label; the scenic and special features of the introduced tourist attractions can express words in the center of the original main introduction content.
Here, the preset statistical time period for counting the original post may be a time interval for issuing the original post.
For example, the target user evaluates the brand a skin care product within 1-2 days, and if the number of comments of the target comment brand a skin care product exceeds 5 within 2 days, it can be determined that the comment data is abnormal comment data in the comment original copy repetition dimension.
Further, when the detection dimension comprises a comment content contradiction dimension, determining that the comment data is abnormal comment data in the comment content contradiction dimension by the following steps: obtaining comment contents of the target user in different original posts within a preset statistical time period; detecting whether the evaluation of the comment contents of the target user under different original posts is inconsistent for the same keyword; and if the evaluation of the target user for the same keyword in the comment contents originally posted is inconsistent, determining that the comment data is abnormal comment data in the comment content contradiction dimension.
In the step, comment contents of target users under different original posts are obtained within a preset statistical time period, keywords in the comment contents are obtained, whether evaluations of the target users on the same keyword in different comments are consistent or not is detected, and if the evaluations on the same keyword are inconsistent, the comment data are determined to be abnormal comment data in the comment content contradiction dimension.
The keyword of the comment content is selected according to historical comment data, and can be a brand article, a tourist attraction name or a comment for evaluating the user according to the content of the original sticker.
For example, for brand a skin care product, the efficacy of brand a skin care product is oil control, and the target user's comment on the original sticker of brand a skin care product is "i is oily skin, one can try to use it"; the skin care product of the brand B has the effects of moisturizing, and the comment of the target user on the original sticker of the skin care product of the brand B is that the target user is dry skin and has good effect after being used. In the description of the skin characteristics, the descriptions of the target users in different comments are obviously contradictory, the comment authenticity is in doubt, and the comment data can be determined to be abnormal comment data in the comment content contradiction dimension.
According to the method for determining the comment data as the abnormal comment data in the comment quantity dimension, the total quantity of the comment information of the target user is determined from the comment data, and the daily average comment quantity of the target user in a preset statistical time period is calculated; detecting whether the daily average evaluation quantity is larger than a preset threshold value; and if the average daily comment amount is larger than a preset threshold value, determining that the comment data is abnormal comment data in the comment amount dimension.
Therefore, under the comment quantity dimension, whether the comment data of the target user in the comment quantity dimension is abnormal comment data or not can be judged according to the daily average comment quantity of the target user in the preset statistical time period, whether the abnormality exists in the dimension or not can be conveniently and quickly determined according to the comment quantity, and the efficiency of judging the abnormal comment data is improved.
Fig. 4 is a schematic structural diagram of an apparatus for identifying an abnormal user according to an embodiment of the present application, and as shown in fig. 4, the apparatus 400 includes:
the processing module 410 is configured to acquire a comment data set of a target user on a sharing platform within a statistical time period, and detect whether comment data in the comment data set is abnormal comment data in each detection dimension.
The dividing module 420 is configured to, when the comment data is abnormal comment data in any detection dimension, divide the corresponding detection dimension into a detection dimension data set.
A first determining module 430, configured to add a weight coefficient corresponding to each detection dimension in the detection dimension data set divided by the dividing module 420, and determine a total weight of the target user.
A second determining module 440, configured to determine that the target user is an abnormal user when the total number of weights determined by the first determining module 430 is greater than a preset threshold.
Further, the detection dimension comprises at least one of a comment amount dimension, a comment density dimension, a comment content repetition degree dimension, a comment original label repetition degree dimension and a comment content contradiction dimension.
Further, when the detection dimension includes a comment amount dimension, the processing module 410, when determining that the comment data is abnormal comment data in the comment amount dimension, is configured to:
determining the total amount of the comment data of the target user from the comment data, and determining the daily average comment amount of the target user within a preset statistical time period;
detecting whether the daily average evaluation quantity is larger than a preset threshold value;
and if the average daily comment amount is larger than a preset threshold value, determining that the comment data is abnormal comment data in the comment amount dimension.
Further, when the detection dimension includes a comment density dimension, the processing module 410, when determining that the comment data is abnormal comment data in the comment density dimension, is configured to:
acquiring a plurality of pieces of comment information of the target user within a preset time interval and a comment original label of a comment corresponding to each piece of comment information;
if the number of the comments of the target user under the comment post in a preset time interval is larger than a preset threshold value, determining that the comments of the target user are abnormal comments;
detecting whether the occurrence frequency of the abnormal comments in a preset statistical time period is greater than a preset threshold value or not;
and if the occurrence frequency of the abnormal comment in a preset statistical time period is greater than a preset threshold value, determining that the comment data is abnormal comment data in a comment density dimension.
Further, when the detection dimension includes a comment content repetition dimension, the processing module 410, when determining that the comment data is abnormal comment data in the comment content repetition dimension, is configured to:
obtaining comment contents of the target user in different comment original posts within a preset statistical time period;
detecting whether the number of comments of the target user originally attached to comments with the same comment content is larger than a preset threshold value or not;
and if the number of the comments of the target user originally posted in the comment with the same comment content is larger than a preset threshold value, determining that the comment data is abnormal comment data in the dimension of the comment content repeatability.
Further, when the detection dimension includes a comment original posting repetition degree dimension, the processing module 410 is configured to, when it is determined that the comment data is abnormal comment data in the comment original posting repetition degree dimension through the following steps:
obtaining a plurality of original comment posts corresponding to the comment data and original post keywords corresponding to each original comment post;
detecting whether the number of the comments originally posted by the comments with the same original posting keyword in a preset time interval is greater than a preset threshold value;
and if the number of the comments originally posted by the comments with the same original posting keywords in a preset time interval is larger than a preset threshold value, determining that the comment data is abnormal comment data in the dimension of the original posting repetition degree of the comments.
Further, when the detection dimension includes a comment content contradiction dimension, the processing module 410, when determining that the comment data is abnormal comment data in the comment content contradiction dimension, is configured to:
obtaining comment contents of the target user in different original posts within a preset statistical time period;
detecting whether the evaluation of the target user for the same keyword in different originally posted comment contents is inconsistent;
and if the evaluation of the target user for the same keyword in the comment contents originally posted is inconsistent, determining that the comment data is abnormal comment data in the comment content contradiction dimension.
The identification device for the abnormal users, provided by the embodiment of the application, acquires the comment data set of the target user on the sharing platform within a preset statistical time period, and detects whether the comment data in the comment data set are abnormal comment data in each detection dimension; when the comment data are abnormal comment data in any detection dimension, dividing the corresponding detection dimension into a detection dimension data set; adding a weight coefficient corresponding to each detection dimension in the detection dimension data set to determine the total weight of the target user; and when the total weight is greater than a preset threshold value, determining that the target user is an abnormal user.
Therefore, a comment data set of a target user on a sharing platform is obtained, whether comment data are abnormal comment data in each detection dimension is detected according to the comment data in the comment data set, the weight coefficients of the detection dimensions for determining that the comment data are abnormal comment data are added to obtain the total weight, if the total weight is larger than a preset threshold value, the target user is determined to be an abnormal user, complex judgment is not needed to be carried out in each detection dimension, the characteristic value of each detection dimension is not needed to be added, multi-dimensional detection can be achieved, and only the weight coefficient of the detection dimension with the abnormal data needs to be added, and detection efficiency and accuracy are improved.
Referring to fig. 5, fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. As shown in fig. 5, the electronic device 500 includes a processor 510, a memory 520, and a bus 530.
The memory 520 stores machine-readable instructions executable by the processor 510, when the electronic device 500 runs, the processor 510 communicates with the memory 520 through the bus 530, and when the machine-readable instructions are executed by the processor 510, the steps of the method for identifying an abnormal user in the method embodiments shown in fig. 2 and fig. 3 may be executed.
An embodiment of the present application 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 step of the method for identifying an abnormal user in the method embodiments shown in fig. 2 and fig. 3 may be executed.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present application, and are used for illustrating the technical solutions of the present application, but not limiting the same, and the scope of the present application is not limited thereto, and although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope disclosed in the present application; such modifications, changes or substitutions do not depart from the spirit and scope of the exemplary embodiments of the present application, and are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. An identification method for an abnormal user, the identification method comprising:
the method comprises the steps of obtaining a comment data set of a target user on a sharing platform within a preset statistical time period, and detecting whether comment data in the comment data set are abnormal comment data in each detection dimension;
when the comment data are abnormal comment data in any detection dimension, dividing the corresponding detection dimension into a detection dimension data set;
adding a weight coefficient corresponding to each detection dimension in the detection dimension data set to determine the total weight of the target user;
and when the total weight is greater than a preset threshold value, determining that the target user is an abnormal user.
2. The identification method according to claim 1, wherein the detection dimension comprises at least one of a comment amount dimension, a comment density dimension, a comment content repetition dimension, a comment original label repetition dimension and a comment content contradiction dimension.
3. The identification method according to claim 2, wherein when the detection dimension includes a comment amount dimension, it is determined that the comment data is abnormal comment data in the comment amount dimension by:
determining the total amount of the comment information of the target user from the comment data, and calculating the daily average comment amount of the target user within a preset statistical time period;
detecting whether the daily average evaluation quantity is larger than a preset threshold value;
and if the average daily comment amount is larger than a preset threshold value, determining that the comment data is abnormal comment data in the comment amount dimension.
4. The identification method according to claim 2, wherein when the detection dimension includes a comment density dimension, it is determined that the comment data is abnormal comment data in the comment density dimension by:
acquiring a plurality of pieces of comment information of the target user within a preset time interval and a comment original label of a comment corresponding to each piece of comment information;
if the number of the comments of the target user under the comment post in a preset time interval is larger than a preset threshold value, determining that the comments of the target user are abnormal comments;
detecting whether the occurrence frequency of the abnormal comments in a preset statistical time period is greater than a preset threshold value or not;
and if the occurrence frequency of the abnormal comment in a preset statistical time period is greater than a preset threshold value, determining that the comment data is abnormal comment data in a comment density dimension.
5. The identification method according to claim 2, wherein when the detection dimension includes a comment content duplication dimension, it is determined that the comment data is abnormal comment data in the comment content duplication dimension by:
obtaining comment contents of the target user in different comment original posts within a preset statistical time period;
detecting whether the number of comments of the target user originally attached to comments with the same comment content is larger than a preset threshold value or not;
and if the number of the comments of the target user originally posted in the comment with the same comment content is larger than a preset threshold value, determining that the comment data is abnormal comment data in the dimension of the comment content repeatability.
6. The identification method according to claim 2, wherein when the detection dimension includes a comment original posting repetition dimension, it is determined that the comment data is abnormal comment data in the comment original posting repetition dimension by:
obtaining a plurality of original comment posts corresponding to the comment data and original post keywords corresponding to each original comment post;
detecting whether the number of the comments originally posted by the comments with the same original posting keyword in a preset time interval is greater than a preset threshold value;
and if the number of the comments originally posted by the comments with the same original posting keywords in a preset time interval is larger than a preset threshold value, determining that the comment data is abnormal comment data in the dimension of the original posting repetition degree of the comments.
7. The identification method according to claim 2, wherein when the detection dimension includes a comment content contradiction dimension, it is determined that the comment data is abnormal comment data in the comment content contradiction dimension by:
obtaining comment contents of the target user in different original posts within a preset statistical time period;
detecting whether the evaluation of the target user for the same keyword in different originally posted comment contents is inconsistent;
and if the evaluation of the target user for the same keyword in the comment contents originally posted is inconsistent, determining that the comment data is abnormal comment data in the comment content contradiction dimension.
8. An apparatus for identifying an abnormal user, the apparatus comprising:
the processing module is used for acquiring a comment data set of a target user on a sharing platform within a preset statistical time period and detecting whether comment data in the comment data set are abnormal comment data in each detection dimension;
the dividing module is used for dividing the corresponding detection dimension into a detection dimension data set when the comment data is abnormal comment data in any detection dimension;
the first determining module is used for adding a weight coefficient corresponding to each detection dimension in the detection dimension data set divided by the dividing module and determining the total weight of the target user;
and the second determining module is used for determining that the target user is an abnormal user when the total weight determined by the first determining module is greater than a preset threshold.
9. An electronic device, comprising: processor, memory and bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating over the bus when the electronic device is running, the machine-readable instructions when executed by the processor performing the steps of the method for identification of an anomalous user as claimed in any one of the claims 1 to 7.
10. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, performs the steps of the method for identification of an anomalous user as claimed in any one of the claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910908839.8A CN110706026A (en) | 2019-09-25 | 2019-09-25 | Abnormal user identification method, identification device and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910908839.8A CN110706026A (en) | 2019-09-25 | 2019-09-25 | Abnormal user identification method, identification device and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110706026A true CN110706026A (en) | 2020-01-17 |
Family
ID=69195007
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910908839.8A Pending CN110706026A (en) | 2019-09-25 | 2019-09-25 | Abnormal user identification method, identification device and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110706026A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111339436A (en) * | 2020-02-11 | 2020-06-26 | 腾讯科技（深圳）有限公司 | Data identification method, device, equipment and readable storage medium |
| CN111865941A (en) * | 2020-07-03 | 2020-10-30 | 北京天空卫士网络安全技术有限公司 | Abnormal behavior identification method and device |
| CN111966978A (en) * | 2020-08-20 | 2020-11-20 | 咪咕文化科技有限公司 | Abnormal user determination method, electronic device and storage medium |
| CN112000711A (en) * | 2020-07-21 | 2020-11-27 | 微梦创科网络科技（中国）有限公司 | Method and system for determining evaluation user based on Spark |
| CN112148947A (en) * | 2020-09-28 | 2020-12-29 | 微梦创科网络科技（中国）有限公司 | Method and system for mining and reviewing users in batches |
| CN112395556A (en) * | 2020-09-30 | 2021-02-23 | 广州市百果园网络科技有限公司 | Abnormal user detection model training method, abnormal user auditing method and device |
| CN112511372A (en) * | 2020-11-06 | 2021-03-16 | 新华三技术有限公司 | Anomaly detection method, device and equipment |
| CN113449170A (en) * | 2020-03-24 | 2021-09-28 | 北京沃东天骏信息技术有限公司 | Abnormal account identification method and device, storage medium and electronic equipment |
| CN113743103A (en) * | 2021-08-20 | 2021-12-03 | 南京星云数字技术有限公司 | Comment user identity identification method and device, computer equipment and storage medium |
| CN116015979A (en) * | 2023-02-23 | 2023-04-25 | 网思科技股份有限公司 | Intelligent security situation awareness method, system and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105630801A (en) * | 2014-10-30 | 2016-06-01 | 国际商业机器公司 | Method and apparatus for detecting deviated user |
| CN107093085A (en) * | 2016-08-19 | 2017-08-25 | 北京小度信息科技有限公司 | Abnormal user recognition methods and device |
| CN108009220A (en) * | 2017-11-22 | 2018-05-08 | 中国电子科技集团公司第二十八研究所 | A kind of method for being detected in network hotspot public sentiment event and positioning abnormal user |
| CN110019954A (en) * | 2017-12-13 | 2019-07-16 | 优酷网络技术（北京）有限公司 | A kind of recognition methods and system of the user that practises fraud |
| CN110175851A (en) * | 2019-02-28 | 2019-08-27 | 腾讯科技（深圳）有限公司 | A kind of cheating detection method and device |
-
2019
- 2019-09-25 CN CN201910908839.8A patent/CN110706026A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105630801A (en) * | 2014-10-30 | 2016-06-01 | 国际商业机器公司 | Method and apparatus for detecting deviated user |
| CN107093085A (en) * | 2016-08-19 | 2017-08-25 | 北京小度信息科技有限公司 | Abnormal user recognition methods and device |
| CN108009220A (en) * | 2017-11-22 | 2018-05-08 | 中国电子科技集团公司第二十八研究所 | A kind of method for being detected in network hotspot public sentiment event and positioning abnormal user |
| CN110019954A (en) * | 2017-12-13 | 2019-07-16 | 优酷网络技术（北京）有限公司 | A kind of recognition methods and system of the user that practises fraud |
| CN110175851A (en) * | 2019-02-28 | 2019-08-27 | 腾讯科技（深圳）有限公司 | A kind of cheating detection method and device |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111339436A (en) * | 2020-02-11 | 2020-06-26 | 腾讯科技（深圳）有限公司 | Data identification method, device, equipment and readable storage medium |
| CN111339436B (en) * | 2020-02-11 | 2021-05-28 | 腾讯科技（深圳）有限公司 | Data identification method, device, equipment and readable storage medium |
| CN113449170A (en) * | 2020-03-24 | 2021-09-28 | 北京沃东天骏信息技术有限公司 | Abnormal account identification method and device, storage medium and electronic equipment |
| CN111865941B (en) * | 2020-07-03 | 2022-12-27 | 北京天空卫士网络安全技术有限公司 | Abnormal behavior identification method and device |
| CN111865941A (en) * | 2020-07-03 | 2020-10-30 | 北京天空卫士网络安全技术有限公司 | Abnormal behavior identification method and device |
| CN112000711A (en) * | 2020-07-21 | 2020-11-27 | 微梦创科网络科技（中国）有限公司 | Method and system for determining evaluation user based on Spark |
| CN111966978A (en) * | 2020-08-20 | 2020-11-20 | 咪咕文化科技有限公司 | Abnormal user determination method, electronic device and storage medium |
| CN112148947A (en) * | 2020-09-28 | 2020-12-29 | 微梦创科网络科技（中国）有限公司 | Method and system for mining and reviewing users in batches |
| CN112148947B (en) * | 2020-09-28 | 2024-03-22 | 微梦创科网络科技（中国）有限公司 | Method and system for excavating and brushing users in batches |
| CN112395556A (en) * | 2020-09-30 | 2021-02-23 | 广州市百果园网络科技有限公司 | Abnormal user detection model training method, abnormal user auditing method and device |
| CN112511372A (en) * | 2020-11-06 | 2021-03-16 | 新华三技术有限公司 | Anomaly detection method, device and equipment |
| CN113743103A (en) * | 2021-08-20 | 2021-12-03 | 南京星云数字技术有限公司 | Comment user identity identification method and device, computer equipment and storage medium |
| CN116015979A (en) * | 2023-02-23 | 2023-04-25 | 网思科技股份有限公司 | Intelligent security situation awareness method, system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110706026A (en) | Abnormal user identification method, identification device and readable storage medium | |
| CN105808639B (en) | Network access behavior identification method and device | |
| CN103905532B (en) | The recognition methods of microblogging marketing account and system | |
| CN106022900B (en) | User risk data mining method and device | |
| CN110390584B (en) | Abnormal user identification method, identification device and readable storage medium | |
| CN106919611B (en) | Product information pushing method and device | |
| CN110413870B (en) | Commodity recommendation method and device and server | |
| CN109360089B (en) | Loan risk prediction method and device | |
| CN109033200A (en) | Method, apparatus, equipment and the computer-readable medium of event extraction | |
| CN112000747B (en) | Data multidimensional analysis method, device and system | |
| CN108764705A (en) | A kind of data quality accessment platform and method | |
| CN107423613A (en) | The method, apparatus and server of device-fingerprint are determined according to similarity | |
| CN106327230B (en) | Abnormal user detection method and equipment | |
| CN108829769B (en) | Suspicious group discovery method and device | |
| CN109697454B (en) | Cross-device individual identification method and device based on privacy protection | |
| CN109918678B (en) | Method and device for identifying field meaning | |
| CN106301979B (en) | Method and system for detecting abnormal channel | |
| CN113934937A (en) | Intelligent content recommendation method and device, terminal and storage medium | |
| CN107305615B (en) | Data table identification method and system | |
| CN112214663A (en) | Method, system, device, storage medium and mobile terminal for obtaining public opinion volume | |
| CN105809488B (en) | Information processing method and electronic equipment | |
| CN110334936B (en) | Method, device and equipment for constructing credit qualification scoring model | |
| CN110009056B (en) | Method and device for classifying social account numbers | |
| KR20210029006A (en) | Product Evolution Mining Method And Apparatus Thereof | |
| CN115146729A (en) | Abnormal shop identification method and device, computer equipment and storage medium |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201222 Address after: A108, 1st floor, curling hall, winter training center, 68 Shijingshan Road, Shijingshan District, Beijing Applicant after: Beijing second hand Artificial Intelligence Technology Co.,Ltd. Address before: Room 9014, 9 / F, building 3, yard 30, Shixing street, Shijingshan District, Beijing Applicant before: ADMASTER TECHNOLOGY (BEIJING) Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200117 |