CN111241284B - Article content identification method, apparatus and computer storage medium - Google Patents
Article content identification method, apparatus and computer storage medium Download PDFInfo
- Publication number
- CN111241284B CN111241284B CN202010041427.1A CN202010041427A CN111241284B CN 111241284 B CN111241284 B CN 111241284B CN 202010041427 A CN202010041427 A CN 202010041427A CN 111241284 B CN111241284 B CN 111241284B
- Authority
- CN
- China
- Prior art keywords
- article content
- timeliness
- article
- content
- mode
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000004044 response Effects 0.000 claims abstract description 51
- 230000036962 time dependent Effects 0.000 claims abstract description 15
- 238000013145 classification model Methods 0.000 claims description 26
- 230000002123 temporal effect Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 abstract description 20
- 238000004891 communication Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 6
- 238000013135 deep learning Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 238000007726 management method Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 229910044991 metal oxide Inorganic materials 0.000 description 2
- 150000004706 metal oxides Chemical class 0.000 description 2
- 238000012797 qualification Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 241000264060 Lethrinus Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009954 braiding Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000003337 fertilizer Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 235000014347 soups Nutrition 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001550 time effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
Abstract
The disclosure relates to a method and a device for identifying article content and a computer storage medium, belonging to the technical field of data processing; the article content identification method comprises the following steps: acquiring article content; carrying out semantic recognition on the article content to obtain a time-dependent recognition result of the article content; in response to determining that the timeliness recognition result is of a first type, performing pattern matching on the article content, and re-determining the timeliness recognition result of the article content according to the pattern matching condition; by adopting the technical scheme disclosed by the disclosure, the accuracy of time-efficient identification of the article content can be improved.
Description
Technical Field
The disclosure relates to the technical field of data processing, and in particular relates to an article content identification method, an article content identification device and a computer storage medium.
Background
In the field of information, various information applications have become an important tool for users to acquire news information, and news recommending functions customized for the users according to their behavior preferences become one of the necessary functions. The news recommendation has the characteristics of strong timeliness, high updating speed and the like, and the news which is liked and not too long is recommended to the user to become extremely important. In general, news perceived by 'outdated news' is called outdated news, a recommendation system needs to identify information timely, filter outdated news, and avoid outdated news from appearing in an information flow recommendation list of a user, so that bad experience is brought to the user. However, the existing identification method has low accuracy in time-efficient identification.
Disclosure of Invention
The present disclosure provides a method, apparatus and computer storage medium for article content recognition.
According to a first aspect of an embodiment of the present disclosure, there is provided an article content identifying method, including:
acquiring article content;
carrying out semantic recognition on the article content to obtain a time-dependent recognition result of the article content;
and in response to determining that the timeliness recognition result is of a first type, performing pattern matching on the article content, and re-determining the timeliness recognition result of the article content according to the pattern matching condition.
In the above scheme, the performing semantic recognition on the article content to obtain a time-efficient recognition result of the article content includes:
carrying out semantic recognition on the article content by using the trained classification model to obtain a first probability that the article content belongs to a first type of timeliness and a second probability that the article content belongs to a second type of timeliness;
and determining that the timeliness identification result is of a first type of timeliness in response to the first probability being greater than a first preset threshold or the second probability being less than a second preset threshold.
In the above scheme, the pattern includes a first pattern, performing pattern matching on the article content, and redetermining a time-efficient recognition result of the article content according to a pattern matching condition, including: matching the article content with the first mode, and redetermining a timeliness recognition result of the article content according to the mode matching condition; or alternatively
The pattern includes a second pattern, the performing pattern matching on the article content, and redefining a timeliness recognition result of the article content according to the pattern matching condition, including: matching the article content with the second mode, and redetermining a timeliness recognition result of the article content according to the mode matching condition; or alternatively
The patterns comprise a first pattern and a second pattern, the pattern matching is carried out on the article content, and the timeliness recognition result of the article content is redetermined according to the pattern matching condition, and the method comprises the following steps: matching the article content with the first pattern; responding to the fact that the article content cannot be matched with the first mode, matching the article content with the second mode, and re-determining a time-based identification result of the article content according to the mode matching condition; or matching the article content with the second pattern; and responding to the fact that the article content cannot be matched with the second mode, matching the article content with the first mode, and re-determining a time-based identification result of the article content according to the mode matching condition.
In the above scheme, the matching the article content with the first pattern, and redefining the timeliness recognition result of the article content according to the pattern matching condition includes:
determining whether the article content contains at least one preset keyword in the first mode;
responding to the fact that the article content contains at least one preset keyword, determining that the article content can be matched with the first mode, and determining that the timeliness class of the article content is second timeliness;
determining that the article content cannot be matched with the first mode in response to the article content not containing the preset keywords, and determining that the timeliness class of the article content is the timeliness of the first class;
the matching of the article content with the second pattern, and the redetermining of the time-dependent identification result of the article content according to the pattern matching condition, includes:
determining whether the article content contains at least one word in date and/or time format in a second mode;
determining that the article content can be matched with the second mode in response to the article content containing at least one word in the date and/or time format, and determining that the timeliness class of the article content is of a second class timeliness;
And in response to the article content not containing the words in the date and/or time format, determining that the article content cannot be matched with the second pattern, and determining that the timeliness class of the article content is the timeliness of the first class.
In the above scheme, the method further comprises:
setting a first expiration time for the article content in response to the determined timeliness recognition result of the article content being still of the first type of timeliness; or (b)
And setting a second expiration time for the article content in response to determining that the timeliness recognition result is of a second type of timeliness or that the timeliness recognition result of the article content is of the second type of timeliness after being redetermined.
In the above scheme, the method further comprises:
and setting an expiration time for the article content in combination with the time word appearing in the article content and the release time of the article content, wherein the expiration time comprises a second expiration time and a first expiration time.
According to a second aspect of the embodiments of the present disclosure, there is provided an article content recognition apparatus, including:
the acquisition module is configured to acquire article content;
the first identification module is configured to perform semantic identification on the article content to obtain a timeliness identification result of the article content;
And the second identification module is configured to respond to the fact that the timeliness identification result is of the first type, perform pattern matching on the article content, and redetermine the timeliness identification result of the article content according to the pattern matching condition.
In the above aspect, the first identifying module is configured to:
carrying out semantic recognition on the article content by using the trained classification model to obtain a first probability that the article content belongs to a first type of timeliness and a second probability that the article content belongs to a second type of timeliness;
and determining that the timeliness identification result is of a first type of timeliness in response to the first probability being greater than a first preset threshold or the second probability being less than a second preset threshold.
In the above aspect, the mode includes a first mode, and the second identifying module is configured to:
determining whether the article content contains at least one preset keyword in the first mode;
responding to the fact that the article content contains at least one preset keyword, determining that the article content can be matched with the first mode, and determining that the timeliness class of the article content is second timeliness;
And determining that the article content cannot be matched with the first mode in response to the article content not containing the preset keywords, and determining that the timeliness class of the article content is the timeliness of the first class.
In the above aspect, the mode includes a first mode, and the second identifying module is configured to:
matching the article content with the first mode, and redetermining a timeliness recognition result of the article content according to the mode matching condition; or alternatively
The modes include a second mode, the second identification module configured to: matching the article content with the second mode, and redetermining a timeliness recognition result of the article content according to the mode matching condition; or alternatively
The modes include a first mode and a second mode, the second identification module configured to: matching the article content with the first pattern; responding to the fact that the article content cannot be matched with the first mode, matching the article content with the second mode, and re-determining a time-based identification result of the article content according to the mode matching condition; or matching the article content with the second pattern; and responding to the fact that the article content cannot be matched with the second mode, matching the article content with the first mode, and re-determining a time-based identification result of the article content according to the mode matching condition.
In the above aspect, the mode includes a second mode, and the second identifying module is configured to:
determining whether the article content contains at least one word in date and/or time format in a second mode;
determining that the article content can be matched with the second mode in response to the article content containing at least one word in the date and/or time format, and determining that the timeliness class of the article content is of a second class timeliness;
and in response to the article content not containing the words in the date and/or time format, determining that the article content cannot be matched with the second pattern, and determining that the timeliness class of the article content is the timeliness of the first class.
In the above scheme, the device further includes:
a setting module configured to:
setting a first expiration time for the article content in response to the determined timeliness recognition result of the article content being still of the first type of timeliness; or (b)
And setting a second expiration time for the article content in response to determining that the timeliness recognition result is of a second type of timeliness or that the timeliness recognition result of the article content is of the second type of timeliness after being redetermined.
In the above aspect, the setting module is configured to:
and setting an expiration time for the article content in combination with the time word appearing in the article content and the release time of the article content, wherein the expiration time comprises a second expiration time and a first expiration time.
According to a third aspect of the embodiments of the present disclosure, there is provided an article content recognition apparatus, including:
a processor;
a memory for storing executable instructions;
wherein the processor is configured to: the executable instructions when executed implement the article content recognition method according to any one of the foregoing aspects of the embodiments of the present disclosure.
According to a fourth aspect of the embodiments of the present disclosure, there is provided a computer storage medium having stored therein executable instructions, which when executed by a processor, cause the processor to perform the article content identification method according to any one of the foregoing aspects of the embodiments of the present disclosure.
The technical scheme provided by the embodiment of the disclosure can comprise the following beneficial effects:
acquiring article content; carrying out semantic recognition on the article content to obtain a time-dependent recognition result of the article content; in response to determining that the timeliness recognition result is of a first type, performing pattern matching on the article content, and re-determining the timeliness recognition result of the article content according to the pattern matching condition; thus, the accuracy of time-based identification of the content of the article can be 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 invention and together with the description, serve to explain the principles of the invention.
FIG. 1 is a flow diagram illustrating a method of article content recognition according to an exemplary embodiment;
FIG. 2 is a schematic diagram illustrating a time-dependent identification process according to an exemplary embodiment;
FIG. 3 is a block diagram of an article content recognition device, according to an example embodiment;
FIG. 4 is a block diagram illustrating an apparatus 800 for enabling article content recognition according to an example embodiment;
fig. 5 is a block diagram illustrating an apparatus 900 for enabling article content identification according to an example embodiment.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the embodiments of the present application. Rather, they are merely examples of apparatus and methods consistent with aspects of embodiments of the present application as detailed in the accompanying claims.
The terminology used in the embodiments of the disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the embodiments of the disclosure. As used in this disclosure and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, third, etc. may be used in embodiments of the present disclosure to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, the first information may also be referred to as second information, and similarly, the second information may also be referred to as first information, without departing from the scope of embodiments of the present disclosure. The words "if" and "if" as used herein may be interpreted as "at … …" or "at … …" or "in response to a determination", depending on the context.
Example 1
FIG. 1 is a flowchart illustrating an article content recognition method according to an exemplary embodiment, as shown in FIG. 1, which may be applied to various electronic devices including, but not limited to, stationary devices and/or mobile devices, such as, but not limited to: personal computers (Personal Computer, PCs), or servers, which may be cloud servers or general servers. The mobile device includes, but is not limited to: a cell phone or tablet computer, etc. As shown in fig. 1, the method mainly comprises the following steps:
In step S11, acquiring article contents;
in step S12, performing semantic recognition on the article content to obtain a time-efficient recognition result of the article content;
in step S13, in response to determining that the timeliness recognition result is the first type of timeliness, performing pattern matching on the article content, and redetermining the timeliness recognition result of the article content according to the pattern matching condition.
In embodiments of the present disclosure, the article may include one or more of the following:
news; drama; a novel; scientific paper; narrative, treatises, descriptions, application, etc.
In an embodiment of the present disclosure, the time-efficient identification result includes:
timeliness of the first type; the second category is timeliness. Wherein the timeliness of the first class of timeliness is lower than the timeliness of the second class of timeliness.
In an embodiment of the disclosure, the modes include:
a first mode and a second mode.
The first mode and the second mode can be used for matching the strong timeliness articles which cannot be identified by the currently trained classification model.
Wherein the first pattern is a semantic ambiguity free keyword pattern. Illustratively, the first mode includes a plurality of preset keywords, and each preset keyword can embody that the article content is a strong timeliness content. For example, the preset keyword is "i.e. start day", or "count down XX day", etc.
Wherein the second mode is a temporal mode having a temporal meaning. The second mode includes a plurality of words in a date and/or time format, each word in the date and/or time format being capable of representing the article content as a highly time-efficient content. For example, the words of the date and/or time format are "XXXX year XX month XX day (number)", "XX month XX day (number)", and the like.
According to the technical scheme, article content is acquired; carrying out semantic recognition on the article content to obtain a time-dependent recognition result of the article content; in response to determining that the timeliness recognition result is of a first type, performing pattern matching on the article content, and re-determining the timeliness recognition result of the article content according to the pattern matching condition; thus, the accuracy of time-based identification of the content of the article can be improved.
In some embodiments, performing semantic recognition on the article content to obtain a time-efficient recognition result of the article content, including:
carrying out semantic recognition on the article content by using the trained classification model to obtain a first probability that the article content belongs to a first type of timeliness and a second probability that the article content belongs to a second type of timeliness;
And determining that the timeliness identification result is of a first type of timeliness in response to the first probability being greater than a first preset threshold or the second probability being less than a second preset threshold.
For example, the sum of the first probability and the second probability is 1.
The classification model is a classification model in deep learning, such as BERT, semantic recognition is performed by using the classification model based on article content, and articles with strong timeliness can be accurately identified by using context information.
It should be noted that, the first preset threshold value and the second threshold value may be set or adjusted according to actual situations, such as detection accuracy.
Therefore, semantic understanding is carried out on the context content of the article based on the classification model in the deep learning, so that the timeliness recognition of the article is realized, the problem that the recognition accuracy is low due to possible ambiguity only through pattern matching recognition is solved, and in the timeliness recognition, the semantic recognition can be obviously improved compared with the pattern matching recognition accuracy and recall rate.
In some embodiments, the pattern includes a first pattern, the performing pattern matching on the article content, and redefining a time-efficient recognition result of the article content according to a pattern matching condition includes:
Step S13a, determining whether the article content contains at least one preset keyword in the first mode; responding to the fact that the article content contains at least one preset keyword, determining that the article content can be matched with the first mode, and determining that the timeliness class of the article content is second timeliness; and determining that the article content cannot be matched with the first mode in response to the article content not containing the preset keywords, and determining that the timeliness class of the article content is the timeliness of the first class.
Therefore, after semantic understanding is carried out on the context content of the articles based on the classification model in the deep learning to realize timeliness recognition of the articles, the timeliness recognition result output by the classification model in the first mode is adopted to further recognize the article content in the first type timeliness, and the timeliness recognition accuracy is further improved.
In some embodiments, the pattern includes a second pattern, the performing pattern matching on the article content, and redefining a time-efficient recognition result of the article content according to a pattern matching condition includes:
step S13b, determining whether the article content contains at least one word in a date and/or time format in a second mode; determining that the article content can be matched with the second mode in response to the article content containing at least one word in the date and/or time format, and determining that the timeliness class of the article content is of a second class timeliness; and in response to the article content not containing the words in the date and/or time format, determining that the article content cannot be matched with the second pattern, and determining that the timeliness class of the article content is the timeliness of the first class.
Therefore, after semantic understanding is carried out on the context content of the articles based on the classification model in the deep learning to realize the timeliness recognition of the articles, the timeliness recognition result output by the classification model in the second mode is adopted to further recognize the article content in the first class timeliness, the timeliness meaning of the rule is fully utilized, and the timeliness recognition accuracy is further improved.
In some embodiments, the modes include a first mode and a second mode, the performing mode matching on the article content, and redefining a time-dependent recognition result of the article content according to a mode matching condition includes:
step S13c, matching the article content with the first mode; responding to the fact that the article content cannot be matched with the first mode, matching the article content with the second mode, and re-determining a time-based identification result of the article content according to the mode matching condition; or matching the article content with the second pattern; and responding to the fact that the article content cannot be matched with the second mode, matching the article content with the first mode, and re-determining a time-based identification result of the article content according to the mode matching condition.
Therefore, after semantic understanding is carried out on the context content of the articles based on the classification model in deep learning to realize timeliness recognition of the articles, the timeliness recognition result output by the classification model is used for further recognizing the article content of the first class timeliness by adopting the matching of the first mode and the second mode, the timeliness meaning of the rule is fully utilized, and the timeliness recognition accuracy is further improved. In the above scheme, the method further comprises:
setting a first expiration time for the article content in response to the determined timeliness recognition result of the article content being still of the first type of timeliness; or (b)
And setting a second expiration time for the article content in response to determining that the timeliness recognition result is of a second type of timeliness or that the timeliness recognition result of the article content is of the second type of timeliness after being redetermined.
Therefore, different expiration times are set for the article contents with different timeliness categories, and before articles are recommended to the user terminal, articles with expiration times smaller than the current time are filtered, so that the expired articles can be effectively prevented from appearing in the information flow list of the user.
In some embodiments, the expiration time is set for the article content in the following manner:
And setting an expiration time for the article content in combination with the time word appearing in the article content and the release time of the article content, wherein the expiration time comprises a second expiration time and a first expiration time.
In this way, the first expiration time and the second expiration time set for the article content are made more accurate.
The following list of 4 articles analyzes how each article is set to an expiration time according to the time-dependent identification method.
[ example 1 ]
Title: the commercial and the Hangzhou high-speed rail commercial hills start to test operation at present to the fertilizer mixing section
Text: today, the Shanghon Hangzhou high-speed rail north section serving as the second largest channel of China formally enters a test operation stage. During the test operation, the parameter test of the train operation diagram, the project test of emergency exercise and the like are mainly carried out, and scientific basis is provided for formally opening operation.
Release time: 2019-10-24 15:20:01
Through step S12, the trained classification model predicts a label category of 1 for the article, which represents that the article is a strongly time-efficient content, and sets the expiration time to "2019-10-25-00:00:00".
[ example 2 ]
Title: the teacher qualification counts down for 8 days, and this set of composition scoring criteria hopes you to win the high score composition
Text: as is well known, the composition of the comprehensive diathesis in the teacher qualification takes up the half-wall Jiangshan, and the composition is happy, and is comprehensive; the composition and the check are synthesized; the small plaiting is a set of composition scoring criteria.
Release time: 2019-10-24 14:47:01
Step S12, the trained classification model predicts that the label class of the article is 0, and the representative model recognizes the article as an aging content; step S13a is entered, the article content is matched with the patterns in the word stock, the article is matched with the patterns in the word stock in the countdown XX days, the article is identified as the strongly aged content by representing the rule matching, and the expiration time is set to be '2019-10-25 00:00:00'.
[ example 3 ]
Title: beijing college entrance examination registration flow detailed description
Text: what is the college entrance procedure when the beijing college entrance is started on 1 day 11 months 2020? What important time nodes the examinee needs to pay attention to? Let us look together at the bar-!
Release time: 2019-10-24 20:51:27
Step S12, predicting the category label of the article to be 0 by the trained classification model; step S13a is entered, the content of the article is matched with the mode in the word stock, and the article is not matched with any rule in the word stock; proceeding to step S13b, the article content is subjected to date rule matching, and "11 months 1 day" is matched, and the time is 10 months 24 days after the release time, so that the expiration time of the article is set as "2019-11-01-00:00:00".
[ example 4 ]
Title: after the Yao dies of the year, the left book has 8 words written by someone, and is right to see the broken ends
Text: the year of the soup Yao is a great minister who makes the emperors particularly lean in the early Qing dynasty, and from an officer just beginning to a martial arts later, he can be said to finish a particularly great turn.
Release time: 2019-10-25 13:34:07
After S12, S13a and S13b, the article is identified as non-aging content, and the expiration time is set to seven days after the release time, namely "2019-11-01:13:34:07".
The technical schemes described in the embodiments of the present disclosure may be arbitrarily combined without any conflict.
According to the technical scheme, article content is acquired; carrying out semantic recognition on the article content to obtain a time-dependent recognition result of the article content; in response to determining that the timeliness recognition result is of a first type, performing pattern matching on the article content, and re-determining the timeliness recognition result of the article content according to the pattern matching condition; therefore, the timeliness accurate judgment of the article content is realized by combining the semantic recognition and the pattern matching, and the accuracy and recall rate of the timeliness recognition are remarkably improved.
Example two
FIG. 2 is a schematic diagram illustrating a time-dependent identification process, as shown in FIG. 2, according to an exemplary embodiment, the process comprising:
step 201: labeling sample data;
step 202: training and parameter adjustment are carried out on the model;
step 203: judging whether the generalization capability of the model meets the preset requirement, and if not, returning to the step 201; if yes, go to step 204;
step 204: exporting a model, and deploying;
step 205: generating a classification model;
step 206: inputting news content into a classification model;
step 207: determining from the classification model whether the news content is strongly aged content, and if so, executing step 210; if not, go to step 208;
step 208: judging whether the news content can be matched with the first mode, if so, executing step 210; if not, go to step 209;
step 209: judging whether the news content can be matched with the second mode, if so, executing step 210; if not, step 211 is performed.
Step 210: setting a first expiration time for the news content;
step 211: a second expiration time is set for the news content.
The method for manually labeling all articles in the current sample set to be labeled comprises the following steps: samples determined to be strongly time-efficient content, manually labeled 1 (noted as positive samples); samples determined to be weakly time-efficient content are artificially marked 0 (noted as negative samples). If an article is pushed to the user terminal the next day of news release, the user can generate the perception of 'outdated content', and the article can be judged as the strong timeliness content; conversely, the article will be judged as a less time-efficient content. And training a classification model by using a known label sample set with class labels, and classifying a large number of articles without class labels after the accuracy and recall rate of the training model for identifying the strongly aged content and the weakly aged content meet the requirements.
As can be seen from fig. 2, when the trained classification model is used to identify the article content, the main process is divided into three steps A, B, C:
and A, step A: for an article without a category label, using a pre-trained model, inputting the text content of the article as the model, enabling the model to output the probability that the article belongs to each category, setting a threshold value, and selecting the category with the probability exceeding the threshold value as the article category label. If the category label of an article is predicted to be 1, setting the expiration time of the article to be 0 in the morning of the release time on the next day; otherwise, the category label of the article is predicted to be 0, and the step B is entered;
and (B) step (B): a batch of time-efficient but unambiguous patterns are arranged to form word banks, such as "i.e. day up", "countdown XX day" and the like, by analyzing the strongly time-efficient content that cannot be identified by the trained patterns. For an article with a model identified as the weak time-efficient content, if the article is matched with any mode in the word stock, the article is represented as the strong time-efficient content, and the expiration time of the article is set to be 0 in the next morning of the release time; otherwise, enter step C;
step C: for an article identified as weakly time-efficient after passing through steps a-B, date pattern matching is used, such as "XXXX year XX month XX day (number)", "XX month XX day (number)", etc. If the content of an article matches the time mode, comparing the matched time word in the article content with the article release time, and setting the expiration time of the article according to the comparison result, wherein an interval is set, for example, the matched time word in the article content must be within 3 months before and after the article release time (the size of the interval can be adjusted); otherwise, the expiration time of the article is set to seven days after the article release time. If the earliest time of the appearance time word in the article content is after the release time, judging that the event described by the article belongs to the impending but not happening yet, and setting the expiration time of the article as the earliest time of the appearance time word in the article content, namely 0 early morning; otherwise, judging that the event described by the article occurs in the past, and setting the expiration time of the article as 0 in the next morning of the release time.
2600 articles are randomly extracted, the articles are identified in time effect by using the current scheme pattern matching method and the method proposed by the present disclosure (only using step A), and the evaluation results are as follows: the accuracy of the semantic recognition method for recognizing the strong timeliness content (sample class 1) is improved by 38%, and the recall rate is improved by 4%; the accuracy of identifying the weak time-efficient content (sample class 0) is improved by 53%, and the recall rate is improved by 80%. The steps B-C of the timeliness recognition scheme are improved based on the semantic recognition method (step A), and accuracy and recall rate can be further improved.
Example III
Fig. 3 is a block diagram illustrating an article content recognition device according to an exemplary embodiment. Referring to fig. 3, the apparatus includes an acquisition module 10, a first identification module 20, and a second identification module 30.
An acquisition module 10 configured to acquire article content;
the first recognition module 20 is configured to perform semantic recognition on the article content to obtain a time-based recognition result of the article content;
and the second identifying module 30 is configured to perform pattern matching on the article content in response to determining that the timeliness identifying result is of the first type, and redetermine the timeliness identifying result of the article content according to the pattern matching condition.
In some embodiments, the first identification module 20 is configured to:
carrying out semantic recognition on the article content by using the trained classification model to obtain a first probability that the article content belongs to a first type of timeliness and a second probability that the article content belongs to a second type of timeliness;
and determining that the timeliness identification result is of a first type of timeliness in response to the first probability being greater than a first preset threshold or the second probability being less than a second preset threshold.
In some embodiments, the pattern comprises a first pattern, and the second identification module 30 is configured to:
determining whether the article content contains at least one preset keyword in the first mode;
responding to the fact that the article content contains at least one preset keyword, determining that the article content can be matched with the first mode, and determining that the timeliness class of the article content is second timeliness;
and determining that the article content cannot be matched with the first mode in response to the article content not containing the preset keywords, and determining that the timeliness class of the article content is the timeliness of the first class.
In some embodiments, the pattern comprises a first pattern, and the second identification module 30 is configured to:
Matching the article content with the first mode, and redetermining a timeliness recognition result of the article content according to the mode matching condition; or alternatively
The modes include a second mode, the second identification module 30 configured to: matching the article content with the second mode, and redetermining a timeliness recognition result of the article content according to the mode matching condition; or alternatively
The modes include a first mode and a second mode, the second identification module 30 being configured to: matching the article content with the first pattern; responding to the fact that the article content cannot be matched with the first mode, matching the article content with the second mode, and re-determining a time-based identification result of the article content according to the mode matching condition; or matching the article content with the second pattern; and responding to the fact that the article content cannot be matched with the second mode, matching the article content with the first mode, and re-determining a time-based identification result of the article content according to the mode matching condition.
In some embodiments, the modes include a second mode, the second identification module 30 configured to:
Determining whether the article content contains at least one word in date and/or time format in a second mode;
determining that the article content can be matched with the second mode in response to the article content containing at least one word in the date and/or time format, and determining that the timeliness class of the article content is of a second class timeliness;
and in response to the article content not containing the words in the date and/or time format, determining that the article content cannot be matched with the second pattern, and determining that the timeliness class of the article content is the timeliness of the first class.
In the above scheme, the device further includes:
a setup module 40 (not shown in fig. 3) configured to:
setting a first expiration time for the article content in response to the determined timeliness recognition result of the article content being still of the first type of timeliness; or (b)
And setting a second expiration time for the article content in response to determining that the timeliness recognition result is of a second type of timeliness or when the timeliness recognition result of the article content is of the second type of timeliness after being re-determined.
In some embodiments, the setup module 40 is configured to:
And setting an expiration time for the article content in combination with the time word appearing in the article content and the release time of the article content, wherein the expiration time comprises a second expiration time and a first expiration time.
The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.
In practical applications, the specific structures of the acquiring module 10, the first identifying module 20 and the second identifying module 30 may be implemented by a central processing unit (CPU, central Processing Unit), a microprocessor (MCU, micro Controller Unit), a digital signal processor (DSP, digital Signal Processing) or a programmable logic device (PLC, programmable Logic Controller) in the article content identifying device or an electronic device to which the article content identifying device belongs.
It should be understood by those skilled in the art that the functions of each processing module in the article content recognition device according to the embodiments of the present disclosure may be understood with reference to the foregoing description of the article content recognition method applied to the vehicle side, and each processing module in the article content recognition device according to the embodiments of the present disclosure may be implemented by an analog circuit implementing the functions described in the embodiments of the present disclosure, or may be implemented by running software that performs the functions described in the embodiments of the present disclosure on an electronic device.
The article content identification device disclosed by the embodiment of the invention can improve the accuracy rate and recall rate of identifying the validity of the article content.
The embodiment of the disclosure also discloses an article content identification device, which comprises: the article content identification method provided by the technical scheme applied to the electronic equipment is realized by the processor when the processor executes the program.
As an embodiment, the processor implements:
acquiring article content;
carrying out semantic recognition on the article content to obtain a time-dependent recognition result of the article content;
and in response to determining that the timeliness recognition result is of a first type, performing pattern matching on the article content, and re-determining the timeliness recognition result of the article content according to the pattern matching condition.
As an embodiment, the processor implements:
carrying out semantic recognition on the article content by using the trained classification model to obtain a first probability that the article content belongs to a first type of timeliness and a second probability that the article content belongs to a second type of timeliness;
And determining that the timeliness identification result is of a first type of timeliness in response to the first probability being greater than a first preset threshold or the second probability being less than a second preset threshold.
As an embodiment, the processor implements:
determining whether the article content contains at least one preset keyword in the first mode;
responding to the fact that the article content contains at least one preset keyword, determining that the article content can be matched with the first mode, and determining that the timeliness class of the article content is second timeliness;
and determining that the article content cannot be matched with the first mode in response to the article content not containing the preset keywords, and determining that the timeliness class of the article content is the timeliness of the first class.
As an embodiment, the processor implements: the pattern includes a first pattern, the performing pattern matching on the article content, and redetermining a time-lapse recognition result of the article content according to a pattern matching condition, including: matching the article content with the first mode, and redetermining a timeliness recognition result of the article content according to the mode matching condition; or alternatively
The pattern includes a second pattern, the performing pattern matching on the article content, and redefining a timeliness recognition result of the article content according to the pattern matching condition, including: matching the article content with the second mode, and redetermining a timeliness recognition result of the article content according to the mode matching condition; or alternatively
The patterns comprise a first pattern and a second pattern, the pattern matching is carried out on the article content, and the timeliness recognition result of the article content is redetermined according to the pattern matching condition, and the method comprises the following steps: matching the article content with the first pattern; responding to the fact that the article content cannot be matched with the first mode, matching the article content with the second mode, and re-determining a time-based identification result of the article content according to the mode matching condition; or matching the article content with the second pattern; and responding to the fact that the article content cannot be matched with the second mode, matching the article content with the first mode, and re-determining a time-based identification result of the article content according to the mode matching condition.
As an embodiment, the processor implements:
determining whether the article content contains at least one word in date and/or time format in a second mode;
determining that the article content can be matched with the second pattern in response to the article content containing at least one word in the date and/or time format, and determining that the timeliness class of the article content is of a second class timeliness;
and in response to the article content not containing the words in the date and/or time format, determining that the article content cannot be matched with the second pattern, and determining that the timeliness class of the article content is the timeliness of the first class.
As an embodiment, the processor implements:
setting a first expiration time for the article content in response to the determined timeliness recognition result of the article content being still of the first type of timeliness; or (b)
And setting a second expiration time for the article content in response to determining that the timeliness recognition result is of a second type of timeliness or when the timeliness recognition result of the article content is of the second type of timeliness after being re-determined.
As an embodiment, the processor implements:
and setting an expiration time for the article content in combination with the time word appearing in the article content and the release time of the article content, wherein the expiration time comprises a second expiration time and a first expiration time.
The article content identification device provided by the embodiment of the application can improve the accuracy rate and recall rate of identifying the validity of the article content.
The embodiments of the present application also describe a computer storage medium having stored therein computer executable instructions for performing the article content identification method described in the foregoing embodiments. That is, the computer executable instructions, when executed by the processor, implement the article content recognition method provided by any one of the foregoing technical solutions.
It should be understood by those skilled in the art that the functions of each program in the computer storage medium of the present embodiment can be understood with reference to the description of the article content recognition method described in the foregoing embodiments.
Example IV
Fig. 4 is a block diagram illustrating an apparatus 800 for enabling article content recognition according to an example embodiment. For example, apparatus 800 may be a mobile phone, computer, digital broadcast terminal, messaging device, game console, tablet device, medical device, exercise device, personal digital assistant, or the like.
Referring to fig. 4, apparatus 800 may include one or more of the following components: a processing component 802, a memory 804, a power component 806, a multimedia component 808, an audio component 810, an Input/Output (I/O) interface 812, a sensor component 814, and a communication component 816.
The processing component 802 generally controls overall operation of the apparatus 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interactions between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.
The memory 804 is configured to store various types of data to support operations at the apparatus 800. Examples of such data include instructions for any application or method operating on the device 800, contact data, phonebook data, messages, pictures, videos, and the like. The Memory 804 may be implemented by any type or combination of volatile or non-volatile Memory devices, such as Static Random-Access Memory (SRAM), electrically erasable programmable Read-Only Memory (EEPROM), erasable programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), read Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk, or optical disk.
The power component 806 provides power to the various components of the device 800. The power components 806 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the device 800.
The multimedia component 808 includes a screen between the device 800 and the user that provides an output interface. In some embodiments, the screen may include a liquid crystal display (Liquid Crystal Display, LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or slide action, but also the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and/or a rear camera. The front camera and/or the rear camera may receive external multimedia data when the apparatus 800 is in an operational mode, such as a photographing mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.
The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 further includes a speaker for outputting audio signals.
The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be a keyboard, click wheel, buttons, etc. These buttons may include, but are not limited to: homepage button, volume button, start button, and lock button.
The sensor assembly 814 includes one or more sensors for providing status assessment of various aspects of the apparatus 800. For example, the sensor assembly 814 may detect an on/off state of the device 800, a relative positioning of the components, such as a display and keypad of the device 800, the sensor assembly 814 may also detect a change in position of the device 800 or a component of the device 800, the presence or absence of user contact with the device 800, an orientation or acceleration/deceleration of the device 800, and a change in temperature of the device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include a light sensor, such as a complementary metal oxide semiconductor (Complementary Metal Oxide Semiconductor, CMOS) or Charge-coupled Device (CCD) image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
The communication component 816 is configured to facilitate communication between the apparatus 800 and other devices, either in a wired or wireless manner. The device 800 may access a wireless network based on a communication standard, such as Wi-Fi,2G, or 3G, or a combination thereof. In one exemplary embodiment, the communication component 816 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component 816 further includes a near field communication (Near Field Communication, NFC) module to facilitate short range communications. For example, the NFC module may be implemented based on radio frequency identification (Radio Frequency Identification, RFID) technology, infrared data association (Infrared Data Association, irDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.
In an exemplary embodiment, the apparatus 800 can be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuit, ASIC), digital signal processor (Digital Signal Processor, DSP), digital signal processing device (Digital Signal Processing Device, DSPD), programmable logic device (Programmable Logic Device, PLD), field programmable gate array (Field Programmable Gate Array, FPGA), controller, microcontroller, microprocessor, or other electronic element for performing the article content identification method described above.
In an exemplary embodiment, a non-transitory computer storage medium is also provided, such as memory 804 including executable instructions executable by processor 820 of apparatus 800 to perform the above-described method. For example, the non-transitory computer storage medium may be ROM, random access memory (Random Access Memory, RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.
Example five
Fig. 5 is a block diagram illustrating an apparatus 900 for enabling article content identification according to an example embodiment. For example, apparatus 900 may be provided as a server. Referring to FIG. 5, apparatus 900 includes a processing component 922 that further includes one or more processors, and memory resources represented by memory 932, for storing instructions, such as applications, executable by processing component 922. The application programs stored in memory 932 may include one or more modules that each correspond to a set of instructions. Further, the processing component 922 is configured to execute instructions to perform the article content identification method described above.
The apparatus 900 may also include a power component 926 configured to perform power management of the apparatus 900, a wired or wireless network interface 950 configured to connect the apparatus 900 to a network, and an input output (I/O) interface 958. The device 900 may operate based on an operating system stored in memory 932, such as Windows Server, mac OS XTM, unixTM, linuxTM, freeBSDTM, or the like.
The technical schemes described in the embodiments of the present disclosure may be arbitrarily combined without any conflict.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.
It is to be understood that the invention is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the invention is limited only by the appended claims.
Claims (14)
1. A method for identifying content of an article, comprising:
acquiring article content;
carrying out semantic recognition on the article content to obtain a time-dependent recognition result of the article content; wherein, the time-lapse recognition result includes: a first type of timeliness and a second type of timeliness, the timeliness of the first type of timeliness being lower than the timeliness of the second type of timeliness;
And responding to the fact that the timeliness recognition result is of a first type, carrying out mode matching on the article content and a first mode and/or a second mode, wherein the first mode is a keyword mode without semantic ambiguity, the second mode is a time mode with timeliness meaning, and the timeliness recognition result of the article content is redetermined according to the mode matching condition.
2. The method for identifying content of an article according to claim 1, wherein the performing semantic identification on the content of the article to obtain a time-dependent identification result of the content of the article comprises:
carrying out semantic recognition on the article content by using the trained classification model to obtain a first probability that the article content belongs to a first type of timeliness and a second probability that the article content belongs to a second type of timeliness;
and determining that the timeliness identification result is of a first type of timeliness in response to the first probability being greater than a first preset threshold or the second probability being less than a second preset threshold.
3. The method of claim 1, wherein responsive to determining that the temporal identification result is of a first type, performing pattern matching on the article content with a first pattern and a second pattern, and redefining the temporal identification result of the article content according to the pattern matching condition, comprises:
Matching the article content with the first pattern; responding to the fact that the article content cannot be matched with the first mode, matching the article content with the second mode, and re-determining a time-based identification result of the article content according to the mode matching condition; or matching the article content with the second pattern; and responding to the fact that the article content cannot be matched with the second mode, matching the article content with the first mode, and re-determining a time-based identification result of the article content according to the mode matching condition.
4. The method for identifying content of an article according to claim 1, wherein said matching the content of the article with the first pattern, redefining a time-dependent identification result of the content of the article according to a pattern matching condition, comprises:
determining whether the article content contains at least one preset keyword in the first mode;
responding to the fact that the article content contains at least one preset keyword, determining that the article content can be matched with the first mode, and determining that the timeliness class of the article content is second timeliness;
Determining that the article content cannot be matched with the first mode in response to the article content not containing the preset keywords, and determining that the timeliness class of the article content is the timeliness of the first class;
the matching of the article content and the second pattern, and the redetermining of the time-dependent identification result of the article content according to the pattern matching condition, includes:
determining whether the article content contains at least one word in date and/or time format in a second mode;
determining that the article content can be matched with the second mode in response to the article content containing at least one word in the date and/or time format, and determining that the timeliness class of the article content is of a second class timeliness;
and in response to the article content not containing the words in the date and/or time format, determining that the article content cannot be matched with the second pattern, and determining that the timeliness class of the article content is the timeliness of the first class.
5. The article content recognition method of any one of claims 1 to 4, further comprising:
setting a first expiration time for the article content in response to the determined timeliness recognition result of the article content being still of the first type of timeliness; or (b)
And setting a second expiration time for the article content in response to determining that the timeliness recognition result is of a second type of timeliness or that the timeliness recognition result of the article content is of the second type of timeliness after being redetermined.
6. The article content identification method of claim 5, wherein the expiration time is set for the article content by:
and setting an expiration time for the article content in combination with the time word appearing in the article content and the release time of the article content, wherein the expiration time comprises a second expiration time and a first expiration time.
7. An article content recognition device, comprising:
the acquisition module is configured to acquire article content;
the first identification module is configured to perform semantic identification on the article content to obtain a timeliness identification result of the article content; wherein, the time-lapse recognition result includes: a first type of timeliness and a second type of timeliness, the timeliness of the first type of timeliness being lower than the timeliness of the second type of timeliness;
the second recognition module is configured to respond to the fact that the timeliness recognition result is of a first type, perform pattern matching on the article content and a first pattern and/or a second pattern, wherein the first pattern is a keyword pattern without semantic ambiguity, the second pattern is a time pattern with timeliness meaning, and the timeliness recognition result of the article content is redetermined according to the pattern matching condition.
8. The article content recognition device of claim 7, wherein the first recognition module is configured to:
carrying out semantic recognition on the article content by using the trained classification model to obtain a first probability that the article content belongs to a first type of timeliness and a second probability that the article content belongs to a second type of timeliness;
and determining that the timeliness identification result is of a first type of timeliness in response to the first probability being greater than a first preset threshold or the second probability being less than a second preset threshold.
9. The article content recognition device of claim 7, wherein the second recognition module is configured to: matching the article content with the first pattern; responding to the fact that the article content cannot be matched with the first mode, matching the article content with the second mode, and re-determining a time-based identification result of the article content according to the mode matching condition; or matching the article content with the second pattern; and responding to the fact that the article content cannot be matched with the second mode, matching the article content with the first mode, and re-determining a time-based identification result of the article content according to the mode matching condition.
10. The article content recognition device of claim 7, wherein the second recognition module is configured to:
determining whether the article content contains at least one preset keyword in the first mode;
responding to the fact that the article content contains at least one preset keyword, determining that the article content can be matched with the first mode, and determining that the timeliness class of the article content is second timeliness;
determining that the article content cannot be matched with the first mode in response to the article content not containing the preset keywords, and determining that the timeliness class of the article content is the timeliness of the first class;
the second identification module is configured to:
determining whether the article content contains at least one word in date and/or time format in a second mode;
determining that the article content can be matched with the second mode in response to the article content containing at least one word in the date and/or time format, and determining that the timeliness class of the article content is of a second class timeliness;
and in response to the article content not containing the words in the date and/or time format, determining that the article content cannot be matched with the second pattern, and determining that the timeliness class of the article content is the timeliness of the first class.
11. The article content recognition device of any one of claims 7 to 10, further comprising:
a setting module configured to:
setting a first expiration time for the article content in response to the determined timeliness recognition result of the article content being still of the first type of timeliness; or (b)
And setting a second expiration time for the article content in response to determining that the timeliness recognition result is of a second type of timeliness or that the timeliness recognition result of the article content is of the second type of timeliness after being redetermined.
12. The article content recognition device of claim 11, wherein the setup module is configured to:
and setting an expiration time for the article content in combination with the time word appearing in the article content and the release time of the article content, wherein the expiration time comprises a second expiration time and a first expiration time.
13. An article content recognition device, comprising:
a processor;
a memory for storing executable instructions;
wherein the processor is configured to: execution of the executable instructions to implement the article content recognition method of any one of claims 1 to 6.
14. A computer storage medium having stored therein executable instructions which, when executed by a processor, cause the processor to perform the article content identification method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010041427.1A CN111241284B (en) | 2020-01-15 | 2020-01-15 | Article content identification method, apparatus and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010041427.1A CN111241284B (en) | 2020-01-15 | 2020-01-15 | Article content identification method, apparatus and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111241284A CN111241284A (en) | 2020-06-05 |
| CN111241284B true CN111241284B (en) | 2024-04-02 |
Family
ID=70864057
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010041427.1A Active CN111241284B (en) | 2020-01-15 | 2020-01-15 | Article content identification method, apparatus and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111241284B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112232075A (en) * | 2020-12-14 | 2021-01-15 | 北京智慧星光信息技术有限公司 | Article release time identification method based on time format and webpage element characteristics |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108090201A (en) * | 2017-12-20 | 2018-05-29 | 珠海市君天电子科技有限公司 | A kind of method, apparatus and electronic equipment of article content classification |
| WO2019153551A1 (en) * | 2018-02-12 | 2019-08-15 | 平安科技（深圳）有限公司 | Article classification method and apparatus, computer device and storage medium |
-
2020
- 2020-01-15 CN CN202010041427.1A patent/CN111241284B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108090201A (en) * | 2017-12-20 | 2018-05-29 | 珠海市君天电子科技有限公司 | A kind of method, apparatus and electronic equipment of article content classification |
| WO2019153551A1 (en) * | 2018-02-12 | 2019-08-15 | 平安科技（深圳）有限公司 | Article classification method and apparatus, computer device and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 陈燕方 ; 周晓英 ; 张璐 ; .基于语义共现匹配的在线食品安全谣言相关文档识别方法研究.情报理论与实践.2017,(06),全文. * |
| 麦林 ; 俞能海 ; .多特征融合的博客文章分类方法.小型微型计算机系统.2010,(06),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111241284A (en) | 2020-06-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| RU2649294C2 (en) | Template construction method and apparatus and information recognition method and apparatus | |
| CN111539443B (en) | Image recognition model training method and device and storage medium | |
| CN105955618B (en) | Information display method and device | |
| CN108227950B (en) | Input method and device | |
| CN104735243B (en) | Contact list displaying method and device | |
| CN106777016B (en) | Method and device for information recommendation based on instant messaging | |
| CN105975540A (en) | Information display method and device | |
| CN112508612B (en) | Method for training advertisement creative generation model and generating advertisement creative and related device | |
| CN106919629A (en) | The method and device of information sifting is realized in group chat | |
| CN111580773B (en) | Information processing method, device and storage medium | |
| CN112291614A (en) | Video generation method and device | |
| CN109002184A (en) | A kind of association method and device of input method candidate word | |
| US10244367B2 (en) | Short message identification method and device, and storage medium | |
| CN111241284B (en) | Article content identification method, apparatus and computer storage medium | |
| CN113849723A (en) | Search method and search device | |
| CN111831132A (en) | Information recommendation method and device and electronic equipment | |
| CN112784151A (en) | Method and related device for determining recommendation information | |
| WO2019095812A1 (en) | Interface presenting method and device | |
| CN107122801B (en) | Image classification method and device | |
| CN105260088A (en) | Information classify-displaying method and device | |
| CN107846347B (en) | Communication content processing method and device and electronic equipment | |
| CN112000840B (en) | Business object display method and device | |
| CN110020117B (en) | Interest information acquisition method and device and electronic equipment | |
| CN109145151B (en) | Video emotion classification acquisition method and device | |
| CN110213062B (en) | Method and device for processing message |
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 | ||
| CB02 | Change of applicant information |
Address after: 100085 unit C, building C, lin66, Zhufang Road, Qinghe, Haidian District, Beijing Applicant after: Beijing Xiaomi pinecone Electronic Co.,Ltd. Address before: 100085 unit C, building C, lin66, Zhufang Road, Qinghe, Haidian District, Beijing Applicant before: BEIJING PINECONE ELECTRONICS Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |