CN113468424A - Monitoring method and device for abnormal attribute label, electronic equipment and storage medium - Google Patents
Monitoring method and device for abnormal attribute label, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113468424A CN113468424A CN202110733643.7A CN202110733643A CN113468424A CN 113468424 A CN113468424 A CN 113468424A CN 202110733643 A CN202110733643 A CN 202110733643A CN 113468424 A CN113468424 A CN 113468424A
- Authority
- CN
- China
- Prior art keywords
- tag
- value
- distribution
- label
- difference data
- 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.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 96
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 34
- 238000009826 distribution Methods 0.000 claims abstract description 207
- 238000012545 processing Methods 0.000 claims description 34
- 238000004590 computer program Methods 0.000 claims description 9
- 230000005856 abnormality Effects 0.000 claims description 6
- 230000002547 anomalous effect Effects 0.000 claims description 2
- 238000010606 normalization Methods 0.000 description 15
- 238000010586 diagram Methods 0.000 description 9
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Transfer Between Computers (AREA)
- Alarm Systems (AREA)
Abstract
The disclosure relates to a monitoring method and device for an abnormal attribute label, an electronic device and a storage medium, wherein the monitoring method for the abnormal attribute label comprises the following steps: acquiring a tag value of a target attribute tag corresponding to each media content in a media content set to obtain a first tag value set of the target attribute tag in a current monitoring period; determining first label value distribution of the target attribute label in the current monitoring period according to the first label value set; determining distribution difference data according to the first label value distribution and a second label value distribution of the target attribute label in the last monitoring period; and when the distribution difference data meets the preset condition, determining that the target attribute label is abnormal. The attribute tag with quality problems can be quickly and efficiently found, and the overall quality of the attribute tag in the media content recommendation system and the accuracy of the media content recommended based on the attribute tag are improved.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a method and an apparatus for monitoring an abnormal attribute tag, an electronic device, and a storage medium.
Background
With the development of internet technology, recommendation of media content to a user through a terminal device has become one of common popularization methods, such as recommendation of advertisements.
Currently, recommendations are generally made based on attribute tags of media content, and therefore the quality of the attribute tags directly affects the accuracy of the recommendations. However, the related art cannot quickly and efficiently identify the attribute tags having quality problems, thereby reducing the accuracy of media content recommended based on the attribute tags of the media content.
Disclosure of Invention
The present disclosure provides a method and an apparatus for monitoring an abnormal attribute tag, an electronic device, and a storage medium, so as to at least solve the problem that an attribute tag having a quality problem cannot be identified quickly and efficiently in the related art. The technical scheme of the disclosure is as follows:
according to a first aspect of the embodiments of the present disclosure, a method for monitoring an abnormal attribute tag is provided, including:
acquiring a tag value of a target attribute tag corresponding to each media content in a media content set to obtain a first tag value set of the target attribute tag in a current monitoring period;
determining first label value distribution of the target attribute label in the current monitoring period according to the first label value set;
determining distribution difference data according to the first label value distribution and a second label value distribution of the target attribute label in the last monitoring period;
and when the distribution difference data meets the preset condition, determining that the target attribute label is abnormal.
In an exemplary embodiment, the determining, according to the first tag value set, a first tag value distribution of the target attribute tag in a current monitoring period includes:
normalizing each label value in the first label value set to obtain a normalized label value corresponding to each label value;
respectively corresponding each normalized tag value to a plurality of numerical value sub-ranges of a preset numerical value range;
and obtaining a first label value distribution of the target attribute label in the current monitoring period according to the normalized label values contained in each numerical value sub-range.
In an exemplary embodiment, the determining distribution difference data according to the first tag value distribution and the second tag value distribution of the target attribute tag in the last monitoring period includes:
for each numerical sub-range in the plurality of numerical sub-ranges, determining sub-distribution difference data corresponding to the numerical sub-range according to the normalized tag value included in the first tag value distribution and the normalized tag value included in the second tag value distribution of the numerical sub-range;
and obtaining the distribution difference data according to the sub-distribution difference data corresponding to each numerical value sub-range.
In an exemplary embodiment, the method further comprises:
judging whether target sub-distribution difference data exceeding a preset difference threshold exist in each sub-distribution difference data or not;
and when the judgment result is yes, determining that the distribution difference data meets a preset condition.
In an exemplary embodiment, before determining that the distribution difference data satisfies a preset condition, the method further includes:
determining a distribution change trend according to the target sub-distribution difference data;
and when the distribution variation trend is a preset distribution variation trend, executing the step of determining that the distribution difference data meets a preset condition.
In an exemplary embodiment, the normalizing each tag value in the first tag value set to obtain a normalized tag value corresponding to each tag value includes:
determining a type of each tag value in the first set of tag values;
when the type is a numerical value type, carrying out logarithm taking processing on the label value of the numerical value type, and taking the result of the logarithm taking processing as the normalized label value of the corresponding label value;
and when the type is the text type, determining a hash value corresponding to the label value of the text type, carrying out logarithm processing on the hash value, and taking the result of the logarithm processing as the normalized label value of the corresponding label value.
According to a second aspect of the embodiments of the present disclosure, there is provided a monitoring apparatus for an abnormal attribute tag, including:
the system comprises a tag value acquisition unit, a tag value acquisition unit and a monitoring unit, wherein the tag value acquisition unit is configured to execute the acquisition of a tag value of a target attribute tag corresponding to each media content in a media content set to obtain a first tag value set of the target attribute tag in a current monitoring period;
a tag value distribution determining unit configured to perform determining a first tag value distribution of the target attribute tag in a current monitoring period according to the first tag value set;
a distribution difference data determination unit configured to perform determination of distribution difference data according to the first tag value distribution and a second tag value distribution of the target attribute tag in a last monitoring period;
an attribute tag abnormality determination unit configured to perform determination that the target attribute tag is abnormal when the distribution difference data satisfies a preset condition.
In an exemplary embodiment, the tag value distribution determining unit includes:
the normalization processing unit is configured to perform normalization processing on each label value in the first label value set to obtain a normalized label value corresponding to each label value;
a numerical value sub-range corresponding unit configured to perform a plurality of numerical value sub-ranges respectively corresponding the respective normalized tag values to a preset numerical value range;
and the first determining subunit is configured to execute a first label value distribution of the target attribute label in the current monitoring period according to the normalized label values included in the numerical value sub-ranges.
In an exemplary embodiment, the distribution difference data determining unit includes:
a sub-distribution difference data determination unit configured to perform, for each of the plurality of numerical value sub-ranges, determining sub-distribution difference data corresponding to the numerical value sub-range according to a normalized tag value included in the first tag value distribution and a normalized tag value included in the second tag value distribution of the numerical value sub-range;
and the second determining subunit is configured to execute sub-distribution difference data corresponding to each numerical value sub-range to obtain the distribution difference data.
In an exemplary embodiment, the apparatus further comprises:
a judging unit configured to perform judgment of whether there is target sub-distribution difference data exceeding a preset difference threshold in each of the sub-distribution difference data;
a preset condition determination unit configured to perform, when the result of the judgment by the judgment unit is yes, determination that the distribution difference data satisfies a preset condition.
In an exemplary embodiment, the apparatus further comprises:
a distribution change trend determination unit configured to perform determination of a distribution change trend from the target sub-distribution difference data;
an execution unit configured to execute the step of determining that the distribution difference data satisfies a preset condition when the distribution variation tendency is a preset distribution variation tendency.
In an exemplary embodiment, the normalization processing unit includes:
a tag type determination unit configured to perform determining a type of each tag value in the first set of tag values;
the first normalization unit is configured to perform logarithm processing on the tag value of the numerical value type when the type is the numerical value type, and taking the result of the logarithm processing as the normalized tag value of the corresponding tag value;
and the second normalization unit is configured to determine a hash value corresponding to the label value of the text type when the type is the text type, perform logarithm processing on the hash value, and use the result of the logarithm processing as the normalized label value of the corresponding label value.
According to a third aspect of the embodiments of the present disclosure, there is provided an electronic apparatus including:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the monitoring method of the exception attribute tag of the first aspect.
According to a fourth aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium, wherein instructions of the computer-readable storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the monitoring method for the abnormal attribute tag of the first aspect.
According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method for monitoring an anomaly property tag of the first aspect.
The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:
the method comprises the steps of obtaining a first label value set of a target attribute label corresponding to each media content in a media content set in a current monitoring period, determining first label value distribution of the target attribute label in the current monitoring period according to the first label value set, determining distribution difference data according to the first label value distribution and second label value distribution of the target attribute label in a last monitoring period, and determining that the target attribute label is abnormal when the distribution difference data meets a preset condition, so that the attribute label with a quality problem can be found quickly and efficiently, and the overall quality of the attribute label in a media content recommendation system and the accuracy of the media content recommended based on the attribute label are improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.
FIG. 1 is a schematic diagram illustrating an application environment of a method for monitoring an exception attribute tag in accordance with an illustrative embodiment;
FIG. 2 is a flow diagram illustrating a method for monitoring an exception attribute tag in accordance with an exemplary embodiment;
FIG. 3 is a flow diagram illustrating another method of monitoring exception attribute tags in accordance with an exemplary embodiment;
FIG. 4 is a flow diagram illustrating another method of monitoring exception attribute tags in accordance with an exemplary embodiment;
FIG. 5 is a block diagram illustrating an anomalous attribute tag monitoring arrangement in accordance with an illustrative embodiment;
FIG. 6 is a block diagram illustrating an electronic device in accordance with an example embodiment.
Detailed Description
In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
Referring to fig. 1, a schematic diagram of an application environment of a monitoring method for an abnormal attribute tag is shown, where the application environment may include a terminal 110 and a server 120, and the terminal 110 and the server 120 may be connected through a wired network or a wireless network.
The terminal 110 may be, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, and the like. The server 120 may be a server providing a background service for the terminal 110, and specifically, the server 120 may provide a media content recommendation service for the terminal 110, and the terminal 110 may present the media content recommended by the server 120.
The server 120 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a network service, cloud communication, middleware service, a domain name service, a security service, a CDN, a big data and artificial intelligence platform, and the like.
In a specific application scenario, the server 120 determines the recommended media content based on the attribute tags of the media content, and the server 120 may monitor the attribute tags related to the media content set to determine abnormal attribute tags. The attribute tag is used to indicate attributes corresponding to media content, and may include, for example, an industry attribute, an exposure attribute, a duration attribute, and the like, where the specific attributes may be set according to actual needs. Each attribute tag corresponds to a plurality of tag values, and the tag values are used to indicate specific attribute contents of the media content under the corresponding attribute, for example, an industry attribute may include education, games, news, and the like, and the tag values corresponding to the industry attribute tags may include education, games, news, and the like.
Fig. 2 is a flowchart illustrating a monitoring method for an abnormal attribute tag according to an exemplary embodiment, where as shown in fig. 2, taking the monitoring method for an abnormal attribute tag as an example applied to the server in fig. 1, the method includes the following steps:
in step S201, a tag value of a target attribute tag corresponding to each media content in a media content set is obtained, so as to obtain a first tag value set of the target attribute tag in a current monitoring period.
The target attribute tag refers to an attribute tag to be monitored currently.
In an exemplary embodiment, the quality of each attribute tag related to the media content set may be monitored according to a preset monitoring period, where the preset monitoring period may be set according to actual needs, and may be, for example, 1 day, 3 days, and so on. In a specific implementation, a corresponding monitoring timer may be set for each attribute tag, and when the timing duration of the monitoring timer reaches a preset monitoring period, monitoring of the corresponding target attribute tag is automatically triggered, so as to obtain a tag value of each media content in the media content set corresponding to the target attribute tag, and obtain a first tag value set of the target attribute tag in the current monitoring period.
In step S203, a first tag value distribution of the target attribute tag in the current monitoring period is determined according to the first tag value set.
And the first label value distribution represents the distribution condition of the label values in the first label value set.
In step S205, distribution difference data is determined according to the first tag value distribution and the second tag value distribution of the target attribute tag in the previous monitoring period.
Specifically, the first tag value distribution and the second tag value distribution of the target attribute tag in the previous monitoring period may be compared to obtain a difference change therebetween, and distribution difference data may be obtained based on the difference change.
In practical applications, each monitoring cycle may include a plurality of time periods, and correspondingly, the tag value distribution corresponding to each monitoring cycle may include sub-tag value distributions corresponding to the time periods in the monitoring cycle, so that when comparing the tag value distributions corresponding to different monitoring cycles, the sub-tag value distributions corresponding to the same time period in different monitoring cycles may be compared, thereby obtaining distribution difference data.
In step S207, when the distribution difference data satisfies a preset condition, it is determined that the target attribute tag is abnormal.
The preset condition may be that the distribution difference data exceeds a certain set threshold, and the threshold may be set according to an actual situation.
The method and the device for determining the distribution difference data can quickly and efficiently find the attribute tags with quality problems by acquiring the tag values of the target attribute tags corresponding to the media contents in the media content set to obtain the first tag value set of the target attribute tags in the current monitoring period, determining the first tag value distribution of the target attribute tags in the current monitoring period according to the first tag value set, determining the distribution difference data according to the first tag value distribution and the second tag value distribution of the target attribute tags in the last monitoring period, and determining the abnormality of the target attribute tags under the condition that the distribution difference data meets the preset conditions, thereby being beneficial to improving the overall quality of the attribute tags in the media content recommendation system and the accuracy of the media contents recommended based on the attribute tags.
In an exemplary embodiment, in order to improve the monitoring efficiency, the above step S203 may adopt the method in fig. 3 when determining the first tag value distribution of the target attribute tag in the current monitoring period according to the first tag value set, and includes the following steps:
in step S2031, normalization processing is performed on each tag value in the first tag value set to obtain a normalized tag value corresponding to each tag value.
The normalized tag value can be a value between 0 and 1.
In practical applications, the tag types of the tag values may include a numerical type, such as 0 or 1, and may also include a text type, such as education and game, and then the normalization process for each tag value in the first set of tag values may include:
determining the type of each label value in the first label value set;
when the type is a numerical value type, carrying out logarithm taking processing on the label value of the numerical value type, and taking the result of the logarithm taking processing as the normalized label value of the corresponding label value;
and when the type is the text type, determining a hash value corresponding to the label value of the text type, carrying out logarithm processing on the hash value, and taking the result of the logarithm processing as the normalized label value of the corresponding label value.
The logarithm processing may be a base-10 logarithm function conversion, i.e., y-log10(x) X denotes a label value and y denotes a normalized label value.
The hash value is also referred to as a hash code, and a hash algorithm may be used to determine the hash value corresponding to the tag value of each text type, where the hash algorithm may be a division hash algorithm, a multiplication hash algorithm, and the like, which is not specifically limited in this disclosure.
According to the embodiment of the disclosure, normalization processing is performed on the label values of both the text type and the numerical value type by determining the type of each label value in the first label value set and further adopting different normalization processing modes for different types.
In step S2033, each normalized tag value is respectively corresponding to a plurality of numerical value sub-ranges of a preset numerical value range.
The preset value range can be a value range of 0-1, and a plurality of value sub-ranges of the preset value range can be obtained by dividing the preset value range according to actual needs, for example, the preset value range can be divided into 5 value sub-ranges, namely (0-0.2), (0.2-0.4), (0.4-0.6), (0.6-0.8) and (0.8-1.0), so that the value sub-ranges in which the normalized tag values respectively fall can be determined.
In step S2035, a first label value distribution of the target attribute label in the current monitoring period is obtained according to the normalized label values included in each of the numerical value sub-ranges.
In an exemplary scenario, for each numerical value sub-range, the number of normalized tag values falling into the numerical value sub-range may be counted, so as to obtain the number of normalized tag values corresponding to each numerical value sub-range, where the number of normalized tag values corresponding to a plurality of numerical value sub-ranges reflects the first tag value distribution of the target attribute tag in the current monitoring period.
It can be understood that the number of the normalized tag values corresponding to the plurality of numerical value sub-ranges is only one form of the tag value distribution representing the target attribute tag, and in practical applications, the tag value distribution of the target attribute tag may also be represented in other forms as needed, for example, in a scenario where the tag value is an exposure amount, the total exposure amount corresponding to each numerical value sub-range may be determined according to the normalized tag value included in each numerical value sub-range, so that the tag value distribution of the exposure attribute tag in the current monitoring period is represented by the total exposure amount corresponding to each numerical value sub-range.
According to the embodiment of the disclosure, each tag value in the first tag value set is subjected to normalization processing, and each normalized tag value is respectively corresponding to a plurality of numerical value sub-ranges of the preset numerical value range, so that first tag value distribution of the target attribute tag in the current monitoring period is obtained according to the normalized tag values contained in each numerical value sub-range, the efficiency of obtaining the tag value distribution is improved, and the monitoring efficiency of the attribute tag is further improved.
In an exemplary embodiment, with continued reference to fig. 3, the step S205 may include the following steps when determining distribution difference data according to the first tag value distribution and the second tag value distribution of the target attribute tag in the last monitoring period:
in step S2051, for each of the plurality of numerical value sub-ranges, the sub-distribution difference data corresponding to the numerical value sub-range is determined according to the normalized tag value included in the first tag value distribution and the normalized tag value included in the second tag value distribution of the numerical value sub-range.
In step S2053, the distribution difference data is obtained according to the sub-distribution difference data corresponding to each of the numerical value sub-ranges.
Taking the case that the label value distribution adopts the number of the normalized label values corresponding to a plurality of numerical value sub-ranges as an example, for each numerical value sub-range, the difference value between the number of the numerical value sub-range corresponding to the first label value distribution and the number of the numerical value sub-range corresponding to the second label value distribution can be determined, the difference value is the sub-distribution difference data corresponding to the numerical value sub-range, and the sub-distribution difference data corresponding to each numerical value sub-range constitutes the distribution difference data.
According to the embodiment of the disclosure, the sub-distribution difference data corresponding to the numerical value sub-range is determined for each numerical value sub-range in the plurality of numerical value sub-ranges, and then the distribution difference data is obtained based on each sub-distribution difference data, so that the calculation speed of the distribution difference data is increased, and the monitoring efficiency of the attribute label is favorably improved.
In an exemplary embodiment, referring to fig. 4, before step S207, the method may further include:
in step S209, it is determined whether there is target sub-distribution difference data exceeding a preset difference threshold in each of the sub-distribution difference data.
Specifically, each sub-distribution difference data is compared with a preset difference threshold, and if there is target sub-distribution difference data exceeding the preset difference threshold, step S211 may be executed; and if the sub-distribution difference data do not exceed the preset difference threshold, indicating that the target attribute label is a non-abnormal attribute label. The preset difference threshold is matched with the representation form of the sub-distribution difference data, and the specific numerical value of the preset difference threshold can be set according to actual experience.
In step S211, it is determined that the distribution difference data satisfies a preset condition.
According to the embodiment of the disclosure, when any one of the sub-distribution difference data exceeds the preset difference threshold, the distribution difference data is determined to meet the preset condition, so that the accuracy of judging the distribution difference data is improved, and the accuracy of monitoring the attribute label is further improved.
In an exemplary embodiment, to further improve the accuracy of monitoring the attribute tag, with continuing reference to fig. 4, before determining that the distribution difference data satisfies the preset condition in step S211, the method may further include:
in step S213, a distribution variation trend is determined according to the target sub-distribution difference data.
In step S215, determining whether the distribution variation trend is a preset distribution variation trend, if so, performing the step S211 to determine that the distribution difference data meets a preset condition; on the contrary, if the distribution variation trend is not the preset distribution variation trend, it is indicated that the distribution difference data does not meet the preset condition, and the target attribute tag is not the abnormal attribute tag.
The distribution trend may include a positive distribution trend and a negative distribution trend, where the positive distribution trend indicates a change in an increasing direction and the negative distribution trend indicates a change in a decreasing direction. The preset distribution change trend can be determined according to the actual situation of the target attribute label, when the positive change of the target attribute label is a normal change situation, the preset distribution change trend is a negative distribution change trend, and when the negative change of the target attribute label is a normal change situation, the preset distribution change trend is a positive distribution change trend. In practical applications, the distribution change trend may be determined based on the positive and negative of the target sub-distribution difference data, and when the target sub-distribution difference data is positive, the distribution change trend is determined as a positive distribution change trend, and when the target sub-distribution difference data is negative, the distribution change trend is determined as a negative distribution change trend.
According to the embodiment of the disclosure, the distribution variation trend is determined according to the target sub-distribution difference data, and when the distribution variation trend is the preset distribution variation trend, the distribution difference data is determined to meet the preset condition, so that the accuracy of monitoring the attribute label is further improved.
Fig. 5 is a block diagram illustrating an apparatus for monitoring an abnormal attribute tag in accordance with an exemplary embodiment. Referring to fig. 5, the apparatus 500 for monitoring an abnormal attribute tag includes a tag value obtaining unit 510, a tag value distribution determining unit 520, a distribution difference data determining unit 530, and an attribute tag abnormality determining unit 540, wherein:
a tag value obtaining unit 510, configured to perform obtaining a tag value of a target attribute tag corresponding to each media content in a media content set, to obtain a first tag value set of the target attribute tag in a current monitoring period;
a tag value distribution determining unit 520 configured to perform determining a first tag value distribution of the target attribute tag in a current monitoring period according to the first tag value set;
a distribution difference data determining unit 530 configured to perform determining distribution difference data according to the first tag value distribution and a second tag value distribution of the target attribute tag in a last monitoring period;
an attribute tag abnormality determining unit 540 configured to determine that the target attribute tag is abnormal when the distribution difference data satisfies a preset condition.
In an exemplary embodiment, the tag value distribution determining unit 520 includes:
the normalization processing unit is configured to perform normalization processing on each label value in the first label value set to obtain a normalized label value corresponding to each label value;
a numerical value sub-range corresponding unit configured to perform a plurality of numerical value sub-ranges respectively corresponding the respective normalized tag values to a preset numerical value range;
and the first determining subunit is configured to execute a first label value distribution of the target attribute label in the current monitoring period according to the normalized label values included in the numerical value sub-ranges.
In an exemplary embodiment, the distribution difference data determining unit 530 includes:
a sub-distribution difference data determination unit configured to perform, for each of the plurality of numerical value sub-ranges, determining sub-distribution difference data corresponding to the numerical value sub-range according to a normalized tag value included in the first tag value distribution and a normalized tag value included in the second tag value distribution of the numerical value sub-range;
and the second determining subunit is configured to execute sub-distribution difference data corresponding to each numerical value sub-range to obtain the distribution difference data.
In an exemplary embodiment, the apparatus 500 further comprises:
a judging unit configured to perform judgment of whether there is target sub-distribution difference data exceeding a preset difference threshold in each of the sub-distribution difference data;
a preset condition determination unit configured to perform, when the result of the judgment by the judgment unit is yes, determination that the distribution difference data satisfies a preset condition.
In an exemplary embodiment, the apparatus 500 further comprises:
a distribution change trend determination unit configured to perform determination of a distribution change trend from the target sub-distribution difference data;
an execution unit configured to execute the step of determining that the distribution difference data satisfies a preset condition when the distribution variation tendency is a preset distribution variation tendency.
In an exemplary embodiment, the normalization processing unit includes:
a tag type determination unit configured to perform determining a type of each tag value in the first set of tag values;
the first normalization unit is configured to perform logarithm processing on the tag value of the numerical value type when the type is the numerical value type, and taking the result of the logarithm processing as the normalized tag value of the corresponding tag value;
and the second normalization unit is configured to determine a hash value corresponding to the label value of the text type when the type is the text type, perform logarithm processing on the hash value, and use the result of the logarithm processing as the normalized label value of the corresponding label value.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
In one exemplary embodiment, there is also provided an electronic device, comprising a processor; a memory for storing processor-executable instructions; when the processor is configured to execute the instructions stored in the memory, the method for monitoring the abnormal attribute tag provided in the embodiment of the present disclosure is implemented.
The memory may be used to store software programs and modules, and the processor may execute various functional applications and data processing by operating the software programs and modules stored in the memory. The memory can mainly comprise a program storage area and a data storage area, wherein the program storage area can store an operating system, application programs needed by functions and the like; the storage data area may store data created according to use of the apparatus, and the like. Further, the memory may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory may also include a memory controller to provide the processor access to the memory.
The electronic device may be a terminal, a server, or a similar computing device, taking the electronic device as a server as an example, fig. 6 is a block diagram of an electronic device for monitoring an abnormal attribute tag according to an exemplary embodiment, and as shown in fig. 6, the server 600 may generate a relatively large difference due to different configurations or performances, and may include one or more Central Processing Units (CPUs) 610 (the processor 610 may include but is not limited to a Processing device such as a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 630 for storing data, and one or more storage media 620 (e.g., one or more mass storage devices) for storing an application program 623 or data 622. Memory 630 and storage medium 620 may be, among other things, transient or persistent storage. The program stored on the storage medium 620 may include one or more modules, each of which may include a series of instruction operations for the server. Still further, the central processor 610 may be configured to communicate with the storage medium 620 to execute a series of instruction operations in the storage medium 620 on the server 600. The server 600 may also include one or more power supplies 660, one or more wired or wireless network interfaces 650, one or more input-output interfaces 640, and/or one or more operating systems 621, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, and so forth.
The input/output interface 640 may be used to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the server 600. In one example, i/o Interface 640 includes a Network adapter (NIC) that may be coupled to other Network devices via a base station to communicate with the internet. In one example, the input/output interface 640 may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
It will be understood by those skilled in the art that the structure shown in fig. 6 is only an illustration and is not intended to limit the structure of the electronic device. For example, server 600 may also include more or fewer components than shown in FIG. 6, or have a different configuration than shown in FIG. 6.
In an exemplary embodiment, a computer-readable storage medium comprising instructions, such as the memory 630 comprising instructions, executable by the processor 610 of the apparatus 500 to perform the method described above is also provided. Alternatively, the computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
In an exemplary embodiment, a computer program product is further provided, which includes a computer program, and when the computer program is executed by a processor, the computer program implements the monitoring method for the abnormal attribute tag provided in the embodiment of the present disclosure.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (10)
1. A monitoring method of an abnormal attribute label is characterized by comprising the following steps:
acquiring a tag value of a target attribute tag corresponding to each media content in a media content set to obtain a first tag value set of the target attribute tag in a current monitoring period;
determining first label value distribution of the target attribute label in the current monitoring period according to the first label value set;
determining distribution difference data according to the first label value distribution and a second label value distribution of the target attribute label in the last monitoring period;
and when the distribution difference data meets the preset condition, determining that the target attribute label is abnormal.
2. The method for monitoring an abnormal attribute tag according to claim 1, wherein the determining a first tag value distribution of the target attribute tag in a current monitoring period according to the first tag value set comprises:
normalizing each label value in the first label value set to obtain a normalized label value corresponding to each label value;
respectively corresponding each normalized tag value to a plurality of numerical value sub-ranges of a preset numerical value range;
and obtaining a first label value distribution of the target attribute label in the current monitoring period according to the normalized label values contained in each numerical value sub-range.
3. The method for monitoring an abnormal attribute tag according to claim 2, wherein the determining distribution difference data according to the first tag value distribution and the second tag value distribution of the target attribute tag in the previous monitoring period comprises:
for each numerical sub-range in the plurality of numerical sub-ranges, determining sub-distribution difference data corresponding to the numerical sub-range according to the normalized tag value included in the first tag value distribution and the normalized tag value included in the second tag value distribution of the numerical sub-range;
and obtaining the distribution difference data according to the sub-distribution difference data corresponding to each numerical value sub-range.
4. The method for monitoring an abnormal attribute tag of claim 3, further comprising:
judging whether target sub-distribution difference data exceeding a preset difference threshold exist in each sub-distribution difference data or not;
and when the judgment result is yes, determining that the distribution difference data meets a preset condition.
5. The method for monitoring an abnormal attribute tag of claim 4, wherein before determining that the distribution difference data meets a preset condition, the method further comprises:
determining a distribution change trend according to the target sub-distribution difference data;
and when the distribution variation trend is a preset distribution variation trend, executing the step of determining that the distribution difference data meets a preset condition.
6. The method for monitoring an abnormal attribute tag according to claim 2, wherein the normalizing each tag value in the first tag value set to obtain a normalized tag value corresponding to each tag value comprises:
determining a type of each tag value in the first set of tag values;
when the type is a numerical value type, carrying out logarithm taking processing on the label value of the numerical value type, and taking the result of the logarithm taking processing as the normalized label value of the corresponding label value;
and when the type is the text type, determining a hash value corresponding to the label value of the text type, carrying out logarithm processing on the hash value, and taking the result of the logarithm processing as the normalized label value of the corresponding label value.
7. An apparatus for monitoring an anomalous property label, comprising:
the system comprises a tag value acquisition unit, a tag value acquisition unit and a monitoring unit, wherein the tag value acquisition unit is configured to execute the acquisition of a tag value of a target attribute tag corresponding to each media content in a media content set to obtain a first tag value set of the target attribute tag in a current monitoring period;
a tag value distribution determining unit configured to perform determining a first tag value distribution of the target attribute tag in a current monitoring period according to the first tag value set;
a distribution difference data determination unit configured to perform determination of distribution difference data according to the first tag value distribution and a second tag value distribution of the target attribute tag in a last monitoring period;
an attribute tag abnormality determination unit configured to perform determination that the target attribute tag is abnormal when the distribution difference data satisfies a preset condition.
8. An electronic device, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the method of monitoring an exception attribute tag of any of claims 1 to 6.
9. A computer readable storage medium, instructions in which, when executed by a processor of an electronic device, enable the electronic device to perform a method of monitoring an anomaly property tag as claimed in any one of claims 1 to 6.
10. A computer program product comprising computer programs/instructions, characterized in that the computer programs/instructions, when executed by a processor, implement the method of monitoring an abnormality attribute tag of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110733643.7A CN113468424B (en) | 2021-06-30 | 2021-06-30 | Monitoring method and device for abnormal attribute tags, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110733643.7A CN113468424B (en) | 2021-06-30 | 2021-06-30 | Monitoring method and device for abnormal attribute tags, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113468424A true CN113468424A (en) | 2021-10-01 |
| CN113468424B CN113468424B (en) | 2023-10-31 |
Family
ID=77874224
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110733643.7A Active CN113468424B (en) | 2021-06-30 | 2021-06-30 | Monitoring method and device for abnormal attribute tags, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113468424B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104123466A (en) * | 2014-07-24 | 2014-10-29 | 中国软件与技术服务股份有限公司 | Big data situation analysis early warning method and system based on normal modes |
| US20190272470A1 (en) * | 2018-03-05 | 2019-09-05 | Microsoft Technology Licensing, Llc | Rule-Based Classification for Detected Anomalies |
| CN111881175A (en) * | 2020-07-07 | 2020-11-03 | 腾讯科技（深圳）有限公司 | Label model verification method, device and equipment |
| CN112508615A (en) * | 2020-12-10 | 2021-03-16 | 深圳市欢太科技有限公司 | Feature extraction method, feature extraction device, storage medium, and electronic apparatus |
| CN112561636A (en) * | 2020-12-14 | 2021-03-26 | 深圳市傲天科技股份有限公司 | Recommendation method, recommendation device, terminal equipment and medium |
| CN112579738A (en) * | 2020-12-23 | 2021-03-30 | 广州博冠信息科技有限公司 | Target object label processing method, device, equipment and storage medium |
-
2021
- 2021-06-30 CN CN202110733643.7A patent/CN113468424B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104123466A (en) * | 2014-07-24 | 2014-10-29 | 中国软件与技术服务股份有限公司 | Big data situation analysis early warning method and system based on normal modes |
| US20190272470A1 (en) * | 2018-03-05 | 2019-09-05 | Microsoft Technology Licensing, Llc | Rule-Based Classification for Detected Anomalies |
| CN111881175A (en) * | 2020-07-07 | 2020-11-03 | 腾讯科技（深圳）有限公司 | Label model verification method, device and equipment |
| CN112508615A (en) * | 2020-12-10 | 2021-03-16 | 深圳市欢太科技有限公司 | Feature extraction method, feature extraction device, storage medium, and electronic apparatus |
| CN112561636A (en) * | 2020-12-14 | 2021-03-26 | 深圳市傲天科技股份有限公司 | Recommendation method, recommendation device, terminal equipment and medium |
| CN112579738A (en) * | 2020-12-23 | 2021-03-30 | 广州博冠信息科技有限公司 | Target object label processing method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113468424B (en) | 2023-10-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112052151B (en) | Fault root cause analysis method, device, equipment and storage medium | |
| CN104038908B (en) | Push message sending method and device | |
| CN111835760B (en) | Alarm information processing method and device, computer storage medium and electronic equipment | |
| CN109815406B (en) | Data processing and information recommendation method and device | |
| CN110532152A (en) | A kind of monitoring alarm processing method and system based on Kapacitor computing engines | |
| CN115277566B (en) | Load balancing method and device for data access, computer equipment and medium | |
| CN111400126B (en) | Network service abnormal data detection method, device, equipment and medium | |
| CN114095567B (en) | Data access request processing method and device, computer equipment and medium | |
| CN113946590B (en) | Integral data updating method, device, equipment and storage medium | |
| CN107819745B (en) | Method and device for defending against abnormal traffic | |
| CN111200517B (en) | Service data early warning control method, device, equipment and storage medium | |
| CN112835921B (en) | Slow query processing method and device, electronic equipment and storage medium | |
| CN112948223A (en) | Method and device for monitoring operation condition | |
| CN117557214A (en) | Approval aging early warning method and device for approval process information and storage medium | |
| CN113468424B (en) | Monitoring method and device for abnormal attribute tags, electronic equipment and storage medium | |
| CN117093627A (en) | Information mining method, device, electronic equipment and storage medium | |
| CN113760666A (en) | System exception processing method, device and storage medium | |
| CN111414395A (en) | Data processing method, system and computer equipment | |
| CN113672453B (en) | Monitoring method and device for display page, electronic equipment and storage medium | |
| CN113010759B (en) | Cluster set processing method and device, computer readable medium and electronic equipment | |
| CN115022171A (en) | Optimization method and device for updating interface, electronic equipment and readable storage medium | |
| CN114282940A (en) | Method and apparatus for intention recognition, storage medium, and electronic device | |
| CN113873003A (en) | Data transmission control method and system between storage end and communication end in Internet of things | |
| CN113420236A (en) | List data display method and device, electronic equipment and storage medium | |
| CN112433891A (en) | Data processing method and device and server |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |