CN110929018A - Text processing method and device, storage medium and electronic equipment - Google Patents
Text processing method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN110929018A CN110929018A CN201911229978.4A CN201911229978A CN110929018A CN 110929018 A CN110929018 A CN 110929018A CN 201911229978 A CN201911229978 A CN 201911229978A CN 110929018 A CN110929018 A CN 110929018A
- Authority
- CN
- China
- Prior art keywords
- time
- target text
- text
- target
- candidate
- 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
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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- 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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3334—Selection or weighting of terms from queries, including natural language queries
-
- 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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3335—Syntactic pre-processing, e.g. stopword elimination, stemming
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The embodiment of the application discloses a text processing method, a text processing device, a storage medium and electronic equipment, wherein a target text needing to be subjected to timeliness analysis is obtained, a plurality of timeliness analysis strategies with different preset dimensions are obtained, the obtained timeliness analysis strategies are used for respectively carrying out timeliness analysis on the target text, a plurality of candidate failure times corresponding to the target text are correspondingly obtained, and finally the obtained candidate failure times are fused to obtain the target failure time of the target text. Therefore, the timeliness of the text is analyzed in different dimensions, a plurality of analysis results are correspondingly obtained, and finally a final result is obtained by fusing the plurality of analysis results, wherein the final result contains timeliness characteristics of the text in different dimensions, and the timeliness of the text can be accurately reflected.
Description
Technical Field
The present application relates to the field of text processing technologies, and in particular, to a text processing method and apparatus, a storage medium, and an electronic device.
Background
In the content distribution service, information stream texts such as hot news, maximum events, current day reports, weather news and the like have certain timeliness. Timeliness refers to the property that information is valuable only for a certain period of time, the magnitude of its value being closely related to time. Accurate time efficiency analysis of the text is beneficial to more accurate text pushing, and therefore, how to accurately perform time efficiency analysis on the text becomes crucial.
Disclosure of Invention
The embodiment of the application provides a text processing method and device, a storage medium and electronic equipment, which can accurately analyze the timeliness of a text.
In a first aspect, an embodiment of the present application provides a text processing method, including:
acquiring a target text needing to be subjected to timeliness analysis;
acquiring a plurality of timeliness analysis strategies with preset different dimensions;
respectively carrying out timeliness analysis on the target text according to the timeliness analysis strategies to obtain a plurality of candidate failure times corresponding to the target text;
and according to a preset time fusion strategy, fusing the candidate dead times into a target dead time of the target text.
In a second aspect, an embodiment of the present application provides a text processing apparatus, including:
the text acquisition module is used for acquiring a target text which needs to be subjected to timeliness analysis;
the strategy acquisition module is used for acquiring a plurality of timeliness analysis strategies with different preset dimensions;
the time effectiveness analysis module is used for respectively carrying out time effectiveness analysis on the target text according to the time effectiveness analysis strategies to obtain a plurality of candidate failure times corresponding to the target text;
and the time determining module is used for fusing the candidate dead times into the target dead time of the target text according to a preset time fusion strategy.
In a third aspect, embodiments of the present application provide a storage medium having a computer program stored thereon, which, when called by a processor, causes the processor to execute a text processing method as provided by embodiments of the present application.
In a fourth aspect, an embodiment of the present application provides an electronic device, which includes a processor and a memory, where the memory stores a computer program, and the processor is configured to execute the text processing method according to the embodiment of the present application by calling the computer program.
According to the method and the device, timeliness analysis is carried out on the text in different dimensions, a plurality of analysis results are obtained correspondingly, a plurality of analysis results are finally fused to obtain a final result, the final result contains timeliness characteristics of the text in different dimensions, and timeliness of the text can be accurately reflected.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a text processing method according to an embodiment of the present application.
Fig. 2 is an exemplary diagram of a time effectiveness analysis interface provided in an embodiment of the present application.
FIG. 3 is an exemplary diagram of a selection sub-interface provided in an embodiment of the present application.
Fig. 4 is another schematic flowchart of a text processing method according to an embodiment of the present application.
Fig. 5 is a schematic structural diagram of a text processing apparatus according to an embodiment of the present application.
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Fig. 7 is another schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
It is to be appreciated that the principles of the present application are illustrated as being implemented in a suitable computing environment. The following description is based on illustrated embodiments of the application and should not be taken as limiting the application with respect to other embodiments that are not detailed herein.
At present, in a content distribution service, an information stream text has timeliness characteristics under many conditions, such as hot news, major events, current-day reports, weather news and the like. Such a text with a time-efficient feature is easily liked and clicked by the user if pushed within the validity period, but may become invalid information if the time-efficient feature is exceeded, and at this time, the pushing again may even have an adverse effect.
In the embodiment of the application, the timeliness mark is given to the text to be pushed, which is an extremely important link for the information flow service. The method and the device can assist in accurate personalized pushing and can avoid adverse effects of overdue pushing, so that the method and the device for accurately analyzing the timeliness of the text become very important.
Therefore, the embodiment of the application provides a text processing method, a text processing device, a storage medium and an electronic device, wherein the text is subjected to timeliness analysis in multiple different dimensions, and finally analysis results of the dimensions are integrated to obtain a final analysis result. An execution main body of the text processing method may be the text processing apparatus provided in the embodiment of the present application, or an electronic device integrated with the text processing apparatus, where the text processing apparatus may be implemented in a hardware or software manner, the electronic device may be a server for providing an information streaming text push service, and the information streaming text includes, but is not limited to, various types of news texts, articles, and the like.
Referring to fig. 1, fig. 1 is a schematic flow chart of a text processing method according to an embodiment of the present application, where the flow of the text processing method may be as follows:
in 101, a target text which needs to be subjected to timeliness analysis is acquired.
It should be noted that, in the embodiment of the present application, a timeliness analysis trigger mechanism is configured in advance in the electronic device, and the electronic device is triggered to perform timeliness analysis through the timeliness analysis trigger mechanism.
For example, when the electronic device reaches a preset timeliness analysis period, the electronic device automatically triggers to perform timeliness analysis, and a text to be pushed received in the timeliness analysis period is used as a target text which needs to be subjected to timeliness analysis. The text to be pushed can be provided to the electronic device by a content provider and/or from media, etc., and pushed to the user by the electronic device.
For another example, the electronic device may also trigger to perform timeliness analysis according to a timeliness analysis request input by a user, and acquire a target text that needs to be subjected to timeliness analysis according to the timeliness analysis request.
For example, the electronic device may receive an input time-based analysis request through a time-based analysis interface including a request input interface, as shown in fig. 2, where the request input interface may be in the form of an input box, and a user may enter identification information of a text to be time-based analyzed into the request input interface in the form of the input box and enter confirmation information (e.g., directly pressing an enter key of a keyboard) to input the time-based analysis request, where the time-based analysis request carries the identification information of the text to be time-based analyzed. Correspondingly, the electronic equipment can determine the target text needing to be subjected to timeliness analysis according to the identification information in the received timeliness analysis request.
For another example, the timeliness analysis interface shown in fig. 2 further includes an "open" control, on one hand, when the electronic device detects that the open control is triggered, a selection sub-interface (as shown in fig. 3) is displayed on the timeliness analysis interface in an overlapping manner, and the selection sub-interface provides an icon of a text that can be subjected to timeliness analysis, such as an icon of a text a, a text B, a text C, a text D, a text E, a text F, and the like, for the user to search for and select an icon of a text that needs to be subjected to timeliness analysis; on the other hand, after the icon of the text needing time efficiency analysis is selected, the user can trigger a confirmation control provided by the selection sub-interface to input a time efficiency analysis request to the electronic equipment, wherein the time efficiency analysis request is associated with the icon of the text chosen by the user and instructs the electronic equipment to use the text chosen by the user as the text needing time efficiency analysis.
In addition, other ways not mentioned in the embodiment of the present application may also be adopted to trigger the electronic device to perform the timeliness analysis, which is not specifically limited in the embodiment of the present application.
At 102, a plurality of timeliness analysis strategies of preset different dimensions are obtained.
It should be noted that, in the embodiment of the present application, a plurality of timeliness analysis strategies with different dimensions are also preset, and the timeliness analysis strategies are used for analyzing timeliness of a text in different dimensions to obtain a failure time thereof.
Correspondingly, after the electronic equipment is triggered to perform timeliness analysis and acquires the target text needing to be subjected to timeliness analysis, a plurality of timeliness analysis strategies with different preset dimensions are further acquired so as to perform timeliness analysis on the acquired target text.
For a text, the text is considered valuable when its expiration time is not reached, and beyond, the text is considered to be no longer valuable.
In 103, the target text is subjected to timeliness analysis according to a plurality of timeliness analysis strategies, so as to obtain a plurality of candidate failure times corresponding to the target text.
For example, four timeliness analysis strategies, namely a timeliness analysis strategy a, a timeliness analysis strategy B, a timeliness analysis strategy C and a timeliness analysis strategy D, are configured in advance on the electronic device, after the four timeliness analysis strategies are obtained, the electronic device respectively performs timeliness analysis on the target text according to the obtained timeliness analysis strategies, wherein candidate failure time a corresponding to the target text is obtained according to the timeliness analysis strategy a, candidate failure time B corresponding to the target text is obtained according to the timeliness analysis strategy B, candidate failure time C corresponding to the target text is obtained according to the timeliness analysis strategy C, and candidate failure time D corresponding to the target text is obtained according to the timeliness analysis strategy D.
At 104, according to a preset time fusion strategy, fusing the candidate dead times into a target dead time of the target text.
The electronic equipment respectively analyzes the timeliness of the target text according to the acquired timeliness analysis strategies, correspondingly obtains a plurality of failure times, and further fuses a plurality of candidate failure times obtained through analysis into a time length according to a preset time fusion strategy to serve as the target failure time of the target text.
As can be seen from the above, in the embodiment of the application, by acquiring the target text to be subjected to the timeliness analysis, acquiring the multiple timeliness analysis strategies with different preset dimensions, respectively performing timeliness analysis on the target text by using the multiple acquired timeliness analysis strategies, correspondingly obtaining multiple candidate failure times corresponding to the target text, and finally fusing the multiple candidate failure times obtained through analysis to obtain the target failure time of the target text. Therefore, the timeliness of the text is analyzed in different dimensions, a plurality of analysis results are correspondingly obtained, and finally a final result is obtained by fusing the plurality of analysis results, wherein the final result contains timeliness characteristics of the text in different dimensions, and the timeliness of the text can be accurately reflected.
In an embodiment, the time effectiveness analysis is respectively performed on a target text according to a plurality of time effectiveness analysis strategies to obtain a plurality of candidate failure times corresponding to the target text, and the method includes:
(1) generating a regular expression of the time character string, matching the target text according to the regular expression, and if the matching is successful, allocating first candidate failure time to the target text;
(2) traversing the target text, and when time words in the target text are traversed, allocating second candidate failure time to the target text;
(3) identifying the text type of the target text, and distributing third candidate failure time to the target text according to the text type;
(4) and identifying keywords in the target text, and if the identified keywords comprise preset time-efficiency keywords, allocating fourth candidate failure time to the target text.
By way of example, in the embodiment of the application, the target text is subjected to timeliness analysis in four dimensions.
Firstly, the electronic equipment generates a regular expression of a time character string, and performs regular matching on a target according to the regular expression, when the matching is successful (that is, a time character string exists in a target text), and the difference between the matched time character string and the current actual time does not reach a preset duration (which can be set by a person skilled in the art according to actual needs, for example, can be set to 24 hours), the electronic equipment judges that the target text has strong timeliness, and allocates candidate failure time to the target text according to a preset failure time allocation rule of the corresponding time character string, which is recorded as first candidate failure time.
The time character strings have various forms, which can be defined by those skilled in the art according to actual needs, including but not limited to 'beijing time year, month, and day' form, 'month and day' form, full digital expression time form, and the like, such as "beijing time 2019 year 11 month 13 day", "11 month 13 day", and "2019-11-13", and the like. In addition, the expiration time allocation rule corresponding to the time string may be set by a person of ordinary skill in the art according to actual needs, for example, in the embodiment of the present application, the expiration time allocation rule corresponding to the time string is configured as:
if the minimum time of the time character string reaches the day, taking 24 hours of the day as the candidate failure time;
if the minimum time of the time string reaches month, 24 hours on the last day of the month is taken as the candidate expiration time.
Secondly, the electronic equipment can traverse the full target text, when the time words in the time word set exist in the target text, the electronic equipment judges that the target text has strong timeliness, and distributes candidate failure time for the target text according to a preset failure time distribution rule corresponding to the time words, and the candidate failure time is recorded as second candidate failure time.
The time word is a word representing time, and the form of the time word is also various, and can be defined by a person skilled in the art according to experience, and a time word set comprising a plurality of time words is formed. For example, temporal words include, but are not limited to, 'morning', 'noon', 'afternoon', 'just', 'tomorrow', 'yesterday', 'today', 'tonight', 'morning', etc. In addition, the expiration time allocation rule corresponding to the time word may be set by a person of ordinary skill in the art according to actual needs, for example, in the embodiment of the present application, the expiration time allocation rule corresponding to the time character string is configured as:
and on the basis of the publishing time of the target text, adding 24 hours to the publishing time of the target text to serve as candidate failure time of the target text.
Thirdly, some abstract categories corresponding to the text are time-efficient, such as "fashion" and "sports", and can be calibrated by those skilled in the art according to experience. Correspondingly, the electronic equipment can identify the text type of the target text, if the target text is the text type which is calibrated in advance and has timeliness, the target text is judged to have stronger timeliness, and further candidate failure time is distributed to the target text according to a preset failure time distribution rule corresponding to the text type and is recorded as third candidate failure time.
For example, the sports category can be subdivided into subcategories of "football", "basketball", "badminton", and the like, and the subcategories have different timeliness. Accordingly, the aforementioned large category is designated as the primary text category, and its further subdivided sub-categories are designated as the secondary text categories.
In order to realize the identification of the target text category, in the embodiment of the application, a primary text classification model for primary category classification and a secondary text classification model for secondary category classification are trained in advance in a machine learning manner.
The machine learning is a multi-field cross subject, relates to multiple subjects such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and the like, and generally comprises technologies such as neural network, belief network, reinforcement learning, transfer learning, inductive learning and the like.
Illustratively, when the text category of the target text is identified, the electronic device first calls a pre-trained primary text classification model to perform primary classification on the target text to obtain a primary text category of the target text, when the primary text category of the target text is a pre-calibrated primary text category with timeliness, the electronic device further calls a secondary text classification model corresponding to the primary text category to perform secondary classification on the target text to obtain a secondary text category of the target text, and candidate failure time is allocated to the target text according to a preset failure time allocation rule corresponding to the secondary text category. In addition, the expiration time allocation rule corresponding to the secondary text category may be set by a person of ordinary skill in the art according to actual needs, for example, taking the primary text category "sports" as an example, in the embodiment of the present application, the expiration time allocation rule corresponding to the secondary text category is configured as:
if the secondary text category of the target text is football, taking 24 days of the day as candidate failure time;
if the secondary text category of the target text is basketball, taking 24 hours of the next day as candidate failure time;
if the second-level text type of the target text is "badminton", 24 hours on the last day of the week is used as the candidate expiration time.
Fourthly, the electronic equipment can firstly identify keywords in the target text (the keywords can be keywords in the full text of the target text, and can also be keywords in the text part of the target text), then further identify whether preset timeliness keywords exist in the keywords, if yes, the target text is judged to have stronger timeliness, candidate failure time is distributed to the target text according to a preset failure time distribution rule corresponding to the timeliness keywords, and the candidate failure time is recorded as fourth candidate failure time.
The timeliness keywords may be all contents capable of reflecting timeliness, such as current hot words, for example, "bad weather," "typhoon," and the like. In addition, the expiration time allocation rule corresponding to the time-efficient keyword may be set by a person of ordinary skill in the art according to actual needs, for example, in the embodiment of the present application, the expiration time allocation rule corresponding to the time-efficient keyword is configured as:
the next day 24 is taken as the candidate expiration time of the target text.
In one embodiment, fusing a plurality of candidate expiration times into a target expiration time of a target text according to a preset time fusion policy includes:
(1) determining candidate failure time far away from the current time in the first candidate failure time and the second candidate failure time, and correcting the candidate failure time according to preset correction time to obtain corrected candidate failure time;
(2) and determining the third candidate failure time, the fourth candidate failure time and the candidate failure time which is closest to the current time in the corrected candidate failure times as the target failure time of the target text.
As an optional implementation manner, in the embodiment of the present application, on one hand, in consideration of the pushing Time and the exposure Time of the text to be guaranteed, for the strong timeliness result obtained by matching, that is, the first candidate failure Time and the second candidate failure Time, the candidate failure Time farther from the current Time in the two candidate failure times is taken, and a preset correction Time length is added thereto (an empirical value may be taken by a person skilled in the art according to actual needs, for example, set to 18 hours), so as to obtain a corrected candidate failure Time, which is denoted as Limit _ Time 1; on the other hand, considering that the probability that the text is pushed by mistake after failure is reduced, for the results with stronger timeliness obtained by matching, namely the third candidate failure Time and the fourth candidate failure Time, the candidate failure Time which is closer to the current Time in the two candidate times is taken as Limit _ Time 2; finally, the candidate failure Time closer to the current Time (i.e., the third candidate failure Time, the fourth candidate failure Time, and the candidate failure Time closest to the current Time in the corrected candidate failure times) in the Limit _ Time1 and the Limit _ Time2 is taken as the target failure Time of the target text, and may be represented as:
Limit_Time＝min(Limit_Time1，Limit_Time2)。
in addition, it should be further noted that, when any one of the above four dimensions fails to be matched, the electronic device determines that the target text is weakly valid in the dimension, and directly marks the candidate failure time of the dimension as a preset failure time, where the preset failure time is a large-span time and can be set by a person having ordinary skill in the art according to actual needs, such as the end of each month, the end of each quarter, or the end of each year.
In one embodiment, fusing a plurality of candidate expiration times into a target expiration time of a target text according to a preset time fusion policy includes:
(1) obtaining the effective duration corresponding to each candidate failure time;
(2) carrying out weighted summation according to the preset weight corresponding to each effective time length to obtain weighted time length;
(3) and determining the target failure time of the target text according to the weighted duration.
As another optional implementation manner, when multiple candidate expiration times are fused into a target expiration time of a target text according to a preset time fusion policy, for each candidate expiration time from a first candidate expiration time to a fourth candidate expiration time, the electronic device calculates a time length difference between the candidate expiration time and a current time as an effective time length of the candidate expiration time, then performs weighted summation according to preset weights corresponding to the effective time lengths to obtain a corresponding weighted time length, and finally determines the target expiration time of the target text according to the weighted time length, for example, directly increasing the weighted time length based on the current time as the target expiration time of the target text.
For example, in the embodiment of the present application, the preset weight is assigned to the valid duration corresponding to the first candidate failure time to be "0.4", the preset weight is assigned to the valid duration corresponding to the second candidate failure time to be "0.3", the preset weight is assigned to the valid duration corresponding to the third candidate failure time to be "0.2", and the preset weight is assigned to the valid duration corresponding to the fourth candidate failure time to be "0.1".
In one embodiment, identifying keywords in the target text comprises:
(1) performing word segmentation operation on the target text to obtain a word segmentation set;
(2) deleting preset stop words in the segmentation set, and identifying keywords from the segmentation set after the preset stop words are deleted according to a preset keyword identification strategy.
When the electronic equipment identifies the keywords in the target text, firstly, a word segmentation tool is adopted to perform word segmentation operation on the target text to obtain a word segmentation set consisting of a plurality of words; matching the participles in the participle set with preset stop words in a preset stop word lexicon, and deleting the preset stop words in the participle set; and finally, identifying the keywords from the word segmentation set after the preset stop words are deleted according to a preset keyword identification strategy.
For example, the electronic device may perform a word segmentation operation on the target text by using a crust word segmentation tool, so as to obtain a word segmentation set composed of a plurality of words; then, the electronic equipment deletes stop words in the participle set according to the ending stop word lexicon; and finally, the electronic equipment identifies the key words from the word segmentation set after the stop words are deleted by adopting a word frequency-reverse file frequency (TF-IDF) algorithm.
In an embodiment, before performing the timeliness analysis on the target text according to the plurality of timeliness analysis policies, the method further includes:
(1) deleting invalid characters in the target text to obtain the target text after deleting the invalid characters;
respectively carrying out timeliness analysis on the target text according to a plurality of timeliness analysis strategies, wherein the timeliness analysis comprises the following steps:
(2) and respectively carrying out timeliness analysis on the target text after the invalid characters are deleted according to a plurality of timeliness analysis strategies.
The invalid character may be a semantically meaningless character, and may be defined empirically by a person having ordinary skill in the art.
In the embodiment of the application, the electronic device deletes the invalid character in the target text at first, and then performs time efficiency analysis on the target text after deleting the invalid character, so as to achieve the purpose of improving the time efficiency analysis efficiency.
In an embodiment, fusing the candidate expiration times into a target expiration time of the target text according to a preset time fusion policy, further includes:
and pushing the target text according to the target failure time.
For example, the electronic device determines a push policy for the target text according to a preset push rule and the target expiration time of the target text, and then pushes the target text according to the push policy. Wherein the push policy may include a push time indicating when the target text is to be pushed, and a drop time when the target text is to be dropped. In addition, the pushing rule can be set by a person of ordinary skill in the art according to actual needs, which is not specifically limited in the embodiments of the present application.
For example, the electronic device may use the current time as the push time of the target text and the target expiration time as the off-shelf time of the target text.
Referring to fig. 4, a flow of the text processing method provided in the embodiment of the present application may further be:
in 201, the electronic device acquires a target text which needs to be subjected to time-based analysis.
It should be noted that, in the embodiment of the present application, a timeliness analysis trigger mechanism is configured in advance in the electronic device, and the electronic device is triggered to perform timeliness analysis through the timeliness analysis trigger mechanism.
For example, when the electronic device reaches a preset timeliness analysis period, the electronic device automatically triggers to perform timeliness analysis, and a text to be pushed received in the timeliness analysis period is used as a target text which needs to be subjected to timeliness analysis. The text to be pushed can be provided to the electronic device by a content provider and/or from media, etc., and pushed to the user by the electronic device.
For another example, the electronic device may also trigger to perform timeliness analysis according to a timeliness analysis request input by a user, and acquire a target text that needs to be subjected to timeliness analysis according to the timeliness analysis request.
In addition, other ways not mentioned in the embodiment of the present application may also be adopted to trigger the electronic device to perform the timeliness analysis, which is not specifically limited in the embodiment of the present application.
At 202, the electronic device deletes invalid characters in the target text.
The invalid character may be a character whose semantic meaning is meaningless, and may be defined empirically by a person having ordinary skill in the art.
In the embodiment of the application, the electronic device deletes the invalid character in the target text at first to reduce the data volume for subsequent time-based analysis, so as to achieve the purpose of improving the time-based analysis efficiency.
In 203, the electronic device generates a regular expression of the time character string, matches the target text according to the regular expression, and allocates a first candidate expiration time to the target text if matching is successful.
The electronic equipment generates a regular expression of a time character string, performs regular matching on a target according to the regular expression, determines that the target text has strong timeliness when the matching is successful (namely, the time character string exists in the target text) and the difference between the matched time character string and the current actual time does not reach a preset duration (which can be set by a person skilled in the art according to actual needs, for example, can be set to 24 hours), and allocates candidate failure time for the target text according to a preset failure time allocation rule of the corresponding time character string, and records the candidate failure time as a first candidate failure time.
The time character strings have various forms, which can be defined by those skilled in the art according to actual needs, including but not limited to 'beijing time year, month, and day' form, 'month and day' form, full digital expression time form, and the like, such as "beijing time 2019 year 11 month 13 day", "11 month 13 day", and "2019-11-13", and the like. In addition, the expiration time allocation rule corresponding to the time string may be set by a person of ordinary skill in the art according to actual needs, for example, in the embodiment of the present application, the expiration time allocation rule corresponding to the time string is configured as:
if the minimum time of the time character string reaches the day, taking 24 hours of the day as the candidate failure time;
if the minimum time of the time string reaches month, 24 hours on the last day of the month is taken as the candidate expiration time.
At 204, the electronic device traverses the target text and assigns a second candidate expiration time to the target text when traversing to a time word in the target text.
The electronic equipment can traverse the full target text, when the time words in the time word set exist in the full target text, the electronic equipment judges that the target text has strong timeliness, and distributes candidate failure time to the target text according to a preset failure time distribution rule corresponding to the time words, and the candidate failure time is recorded as second candidate failure time.
The time word is a word representing time, and the form of the time word is also various, and can be defined by a person skilled in the art according to experience, and a time word set comprising a plurality of time words is formed. For example, temporal words include, but are not limited to, 'morning', 'noon', 'afternoon', 'just', 'tomorrow', 'yesterday', 'today', 'tonight', 'morning', etc. In addition, the expiration time allocation rule corresponding to the time word may be set by a person of ordinary skill in the art according to actual needs, for example, in the embodiment of the present application, the expiration time allocation rule corresponding to the time character string is configured as:
and on the basis of the publishing time of the target text, adding 24 hours to the publishing time of the target text to serve as candidate failure time of the target text.
At 205, the electronic device identifies a text category of the target text and assigns a third candidate expiration time for the target text based on the text category.
Some abstract categories corresponding to the text are time-efficient, such as "political affairs" and "sports", and can be calibrated by those skilled in the art according to experience. Correspondingly, the electronic equipment can identify the text type of the target text, if the target text is the text type which is calibrated in advance and has timeliness, the target text is judged to have stronger timeliness, and further candidate failure time is distributed to the target text according to a preset failure time distribution rule corresponding to the text type and is recorded as third candidate failure time.
For example, the sports category can be subdivided into subcategories of "football", "basketball", "badminton", and the like, and the subcategories have different timeliness. Accordingly, the aforementioned large category is designated as the primary text category, and its further subdivided sub-categories are designated as the secondary text categories.
In order to realize the identification of the target text category, in the embodiment of the application, a primary text classification model for primary category classification and a secondary text classification model for secondary category classification are trained in advance in a machine learning manner.
The machine learning is a multi-field cross subject, relates to multiple subjects such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and the like, and generally comprises technologies such as neural network, belief network, reinforcement learning, transfer learning, inductive learning and the like.
Illustratively, when the text category of the target text is identified, the electronic device first calls a pre-trained primary text classification model to perform primary classification on the target text to obtain a primary text category of the target text, when the primary text category of the target text is a pre-calibrated primary text category with timeliness, the electronic device further calls a secondary text classification model corresponding to the primary text category to perform secondary classification on the target text to obtain a secondary text category of the target text, and candidate failure time is allocated to the target text according to a preset failure time allocation rule corresponding to the secondary text category. In addition, the expiration time allocation rule corresponding to the secondary text category may be set by a person of ordinary skill in the art according to actual needs, for example, taking the primary text category "sports" as an example, in the embodiment of the present application, the expiration time allocation rule corresponding to the secondary text category is configured as:
if the secondary text category of the target text is football, taking 24 days of the day as candidate failure time;
if the secondary text category of the target text is basketball, taking 24 hours of the next day as candidate failure time;
if the second-level text type of the target text is "badminton", 24 hours on the last day of the week is used as the candidate expiration time.
At 206, the electronic device identifies keywords in the target text, and if the identified keywords include preset time-sensitive keywords, assigns a fourth candidate expiration time to the target text.
The electronic equipment can firstly identify keywords in the target text (the keywords can be keywords in the full text of the target text or keywords in the text part of the target text), then further identify whether preset timeliness keywords exist in the keywords, if yes, the target text is judged to have strong timeliness, and candidate failure time is distributed to the target text according to a preset failure time distribution rule corresponding to the timeliness keywords and is recorded as fourth candidate failure time.
The timeliness keywords may be all contents capable of reflecting timeliness, such as current hot words, for example, "bad weather," "typhoon," and the like. In addition, the expiration time allocation rule corresponding to the time-efficient keyword may be set by a person of ordinary skill in the art according to actual needs, for example, in the embodiment of the present application, the expiration time allocation rule corresponding to the time-efficient keyword is configured as:
the next day 24 is taken as the candidate expiration time of the target text.
It should be noted that the execution sequence of 203-206 is not affected by the sequence number, and may be executed in parallel at the same time, or executed serially in order of the sequence number.
In 207, the electronic device determines a candidate failure time farther from the current time from among the first candidate failure time and the second candidate failure time, and corrects the candidate failure time according to a preset correction duration to obtain a corrected candidate failure time.
In the embodiment of the application, in consideration of the pushing Time and the exposure Time of the text to be guaranteed, for the strong timeliness result obtained by matching, that is, the first candidate failure Time and the second candidate failure Time, the candidate failure Time farther from the current Time in the two candidate failure times is taken, and the preset correction Time length is added to the candidate failure Time (an empirical value can be taken by a person skilled in the art according to actual needs, for example, set to be 18 hours), so that the corrected candidate failure Time is obtained and is recorded as Limit _ Time 1.
At 208, the electronic device determines a candidate failing time closest to the current time among the third candidate failing time, the fourth candidate failing time, and the corrected candidate failing time as a target failing time of the target text.
In addition, considering that the probability that the text is pushed by mistake after failure is reduced, for the results with stronger timeliness obtained by matching, namely the third candidate failure Time and the fourth candidate failure Time, the candidate failure Time which is closer to the current Time in the two candidate times is taken as Limit _ Time 2; finally, the candidate failure Time closer to the current Time (i.e., the third candidate failure Time, the fourth candidate failure Time, and the candidate failure Time closest to the current Time in the corrected candidate failure times) in the Limit _ Time1 and the Limit _ Time2 is taken as the target failure Time of the target text, and may be represented as:
Limit_Time＝min(Limit_Time1，Limit_Time2)。
the embodiment of the application also provides a text processing device. Referring to fig. 5, fig. 5 is a schematic structural diagram of a text processing apparatus according to an embodiment of the present disclosure. The text processing apparatus is applied to an electronic device, the electronic device includes a memory and a file system for managing the memory, the text processing apparatus includes a text obtaining module 301, a policy obtaining module 302, an aging analysis module 303, and a time determination module 304, as follows:
the text acquisition module 301 is configured to acquire a target text that needs to be subjected to timeliness analysis;
a policy obtaining module 302, configured to obtain multiple timeliness analysis policies with preset different dimensions;
the timeliness analysis module 303 is configured to perform timeliness analysis on the target text according to the multiple timeliness analysis strategies, so as to obtain multiple candidate failure times corresponding to the target text;
and the time determining module 304 is configured to fuse the multiple candidate expiration times into a target expiration time of the target text according to a preset time fusion policy.
In an embodiment, when the target text is subjected to timeliness analysis according to a plurality of timeliness analysis policies, respectively, to obtain a plurality of candidate expiration times corresponding to the target text, the timeliness analysis module 303 is configured to:
generating a regular expression of the time character string, matching the target text according to the regular expression, and if the matching is successful, allocating first candidate failure time to the target text;
traversing the target text, and when time words in the target text are traversed, allocating second candidate failure time to the target text;
identifying the text type of the target text, and distributing third candidate failure time to the target text according to the text type;
and identifying keywords in the target text, and if the identified keywords comprise preset time-efficiency keywords, allocating fourth candidate failure time to the target text.
In an embodiment, when fusing the candidate expiration times into the target expiration time of the target text according to a preset time fusion policy, the time determination module 304 is configured to:
determining candidate failure time far away from the current time in the first candidate failure time and the second candidate failure time, and correcting the candidate failure time according to preset correction time to obtain corrected candidate failure time;
and determining the third candidate failure time, the fourth candidate failure time and the candidate failure time which is closest to the current time in the corrected candidate failure times as the target failure time of the target text.
In an embodiment, when fusing the candidate expiration times into the target expiration time of the target text according to a preset time fusion policy, the time determination module 304 is configured to:
obtaining the effective duration corresponding to each candidate failure time;
carrying out weighted summation according to the preset weight corresponding to each effective time length to obtain weighted time length;
and determining the target failure time of the target text according to the weighted duration.
In one embodiment, in identifying keywords in the target text, the aging analysis module 303 is configured to:
performing word segmentation operation on the target text to obtain a word segmentation set;
deleting preset stop words in the segmentation set, and identifying keywords from the segmentation set after the preset stop words are deleted according to a preset keyword identification strategy.
In an embodiment, before performing the timeliness analysis on the target text according to the plurality of timeliness analysis policies, the timeliness analysis module 303 is further configured to:
deleting invalid characters in the target text to obtain the target text after deleting the invalid characters;
when the target text is subjected to timeliness analysis according to a plurality of timeliness analysis policies, the timeliness analysis module 303 is configured to:
and respectively carrying out timeliness analysis on the target text after the invalid characters are deleted according to a plurality of timeliness analysis strategies.
In an embodiment, the text processing apparatus further includes a text pushing module, configured to push the target text according to the target dead time after the time determining module 304 fuses the multiple candidate dead times into the target dead time of the target text according to a preset time fusion policy.
It should be noted that the text processing apparatus provided in this embodiment of the present application and the text processing method in the foregoing embodiment belong to the same concept, and any method provided in the text processing method embodiment may be run on the text processing apparatus, and a specific implementation process thereof is described in detail in the text processing method embodiment, and is not described herein again.
The embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the stored computer program is executed on a computer, the computer is caused to execute the steps in the text processing method provided by the embodiment of the present application. The storage medium may be a magnetic disk, an optical disk, a Read Only Memory (ROM), a Random Access Memory (RAM), or the like.
Referring to fig. 6, the electronic device includes a processor 401 and a memory 402, wherein the processor 401 is electrically connected to the memory 402.
The processor 401 is a control center of the electronic device, connects various parts of the entire electronic device using various interfaces and lines, performs various functions of the electronic device and processes data by running or loading a computer program stored in the memory 402 and calling data stored in the memory 402.
The memory 402 may be used to store software programs and modules, and the processor 401 executes various functional applications and data processing by operating the computer programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, a computer program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data created according to use of the electronic device, and the like. Further, the memory 402 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 402 may also include a memory controller to provide the processor 401 access to the memory 402.
In this embodiment, the processor 401 in the electronic device loads instructions corresponding to one or more processes of the computer program into the memory 402 according to the following steps, and the processor 401 runs the computer program stored in the memory 402, so as to implement various functions, as follows:
acquiring a target text needing to be subjected to timeliness analysis;
acquiring a plurality of timeliness analysis strategies with preset different dimensions;
respectively carrying out timeliness analysis on the target text according to the timeliness analysis strategies to obtain a plurality of candidate failure times corresponding to the target text;
and fusing the candidate dead time into the target dead time of the target text according to a preset time fusion strategy.
Referring to fig. 7, fig. 7 is another schematic structural diagram of the electronic device according to the embodiment of the present disclosure, and the difference from the electronic device shown in fig. 6 is that the electronic device further includes components such as an input unit 403 and an output unit 404.
The input unit 403 may be used for receiving input numbers, character information, or user characteristic information (such as fingerprints), and generating a keyboard, a mouse, a joystick, an optical or trackball signal input, etc., related to user setting and function control, among others.
The output unit 404 may be used to display information input by the user or information provided to the user, such as a screen.
In the embodiment of the present application, the processor 401, by calling the computer program in the memory 402, is configured to execute:
acquiring a target text needing to be subjected to timeliness analysis;
acquiring a plurality of timeliness analysis strategies with preset different dimensions;
respectively carrying out timeliness analysis on the target text according to the timeliness analysis strategies to obtain a plurality of candidate failure times corresponding to the target text;
and fusing the candidate dead time into the target dead time of the target text according to a preset time fusion strategy.
In an embodiment, when the target text is subjected to timeliness analysis according to a plurality of timeliness analysis policies, respectively, to obtain a plurality of candidate expiration times corresponding to the target text, the processor 401 executes:
generating a regular expression of the time character string, matching the target text according to the regular expression, and if the matching is successful, allocating first candidate failure time to the target text;
traversing the target text, and when time words in the target text are traversed, allocating second candidate failure time to the target text;
identifying the text type of the target text, and distributing third candidate failure time to the target text according to the text type;
and identifying keywords in the target text, and if the identified keywords comprise preset time-efficiency keywords, allocating fourth candidate failure time to the target text.
In an embodiment, when fusing a plurality of candidate expiration times into a target expiration time of a target text according to a preset time fusion policy, the processor 401 performs:
determining candidate failure time far away from the current time in the first candidate failure time and the second candidate failure time, and correcting the candidate failure time according to preset correction time to obtain corrected candidate failure time;
and determining the third candidate failure time, the fourth candidate failure time and the candidate failure time which is closest to the current time in the corrected candidate failure times as the target failure time of the target text.
In an embodiment, when fusing a plurality of candidate expiration times into a target expiration time of a target text according to a preset time fusion policy, the processor 401 performs:
obtaining the effective duration corresponding to each candidate failure time;
carrying out weighted summation according to the preset weight corresponding to each effective time length to obtain weighted time length;
and determining the target failure time of the target text according to the weighted duration.
In one embodiment, in identifying keywords in the target text, processor 401 performs:
performing word segmentation operation on the target text to obtain a word segmentation set;
deleting preset stop words in the segmentation set, and identifying keywords from the segmentation set after the preset stop words are deleted according to a preset keyword identification strategy.
In an embodiment, before performing timeliness analysis on the target text according to a plurality of timeliness analysis policies, respectively, the processor 401 further performs:
deleting invalid characters in the target text to obtain the target text after deleting the invalid characters;
when the target text is subjected to timeliness analysis according to a plurality of timeliness analysis policies, the processor 401 performs:
and respectively carrying out timeliness analysis on the target text after the invalid characters are deleted according to a plurality of timeliness analysis strategies.
In an embodiment, after fusing the candidate expiration times into the target expiration time of the target text according to a preset time fusion policy, the processor 401 further performs:
and pushing the target text according to the target failure time.
It should be noted that the electronic device provided in the embodiment of the present application and the text processing method in the foregoing embodiment belong to the same concept, and any method provided in the text processing method embodiment may be run on the electronic device, and a specific implementation process thereof is described in detail in the feature extraction method embodiment, and is not described herein again.
It should be noted that, for the text processing method of the embodiment of the present application, it can be understood by a person skilled in the art that all or part of the process of implementing the text processing method of the embodiment of the present application can be completed by controlling the relevant hardware through a computer program, where the computer program can be stored in a computer-readable storage medium, such as a memory of an electronic device, and executed by at least one processor in the electronic device, and during the execution process, the process of the embodiment of the text processing method can be included. The storage medium may be a magnetic disk, an optical disk, a read-only memory, a random access memory, etc.
In the text processing apparatus according to the embodiment of the present application, each functional module may be integrated into one processing chip, or each module may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium, such as a read-only memory, a magnetic or optical disk, or the like.
The text processing method, the text processing apparatus, the storage medium, and the electronic device provided in the embodiments of the present application are described in detail above, and a specific example is applied in the text to explain the principle and the implementation of the present application, and the description of the above embodiments is only used to help understand the method and the core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (10)
1. A method of text processing, comprising:
acquiring a target text needing to be subjected to timeliness analysis;
acquiring a plurality of timeliness analysis strategies with preset different dimensions;
respectively carrying out timeliness analysis on the target text according to the timeliness analysis strategies to obtain a plurality of candidate failure times corresponding to the target text;
and according to a preset time fusion strategy, fusing the candidate dead times into a target dead time of the target text.
2. The text processing method according to claim 1, wherein the time-based analysis of the target text according to the time-based analysis strategies to obtain candidate failure times corresponding to the target text comprises:
generating a regular expression of a time character string, matching the target text according to the regular expression, and if the matching is successful, allocating first candidate failure time to the target text;
traversing the target text, and when time words in the target text are traversed, allocating second candidate failure time to the target text;
identifying the text type of the target text, and allocating third candidate failure time to the target text according to the text type;
and identifying keywords in the target text, and if the identified keywords comprise preset time-efficiency keywords, allocating fourth candidate failure time to the target text.
3. The method according to claim 2, wherein the fusing the candidate dead times into the target dead time of the target text according to a preset time fusion policy comprises:
determining candidate failure time far away from the current time in the first candidate failure time and the second candidate failure time, and correcting the candidate failure time according to preset correction time to obtain corrected candidate failure time;
and determining the candidate failure time which is closest to the current time in the third candidate failure time, the fourth candidate failure time and the corrected candidate failure time as the target failure time of the target text.
4. The method according to claim 2, wherein the fusing the candidate dead times into the target dead time of the target text according to a preset time fusion policy comprises:
obtaining the effective duration corresponding to each candidate failure time;
carrying out weighted summation according to the preset weight corresponding to each effective time length to obtain weighted time length;
and determining the target failure time of the target text according to the weighted duration.
5. The method of claim 2, wherein the identifying keywords in the target text comprises:
performing word segmentation operation on the target text to obtain a word segmentation set;
deleting preset stop words in the word segmentation set, and identifying keywords from the word segmentation set after the preset stop words are deleted according to a preset keyword identification strategy.
6. The text processing method according to any one of claims 1-5, wherein before the time effectiveness analysis of the target text according to the plurality of time effectiveness analysis strategies, the method further comprises:
deleting the invalid characters in the target text to obtain the target text with the invalid characters deleted;
the time effectiveness analysis is respectively carried out on the target text according to the plurality of time effectiveness analysis strategies, and the time effectiveness analysis comprises the following steps:
and respectively carrying out timeliness analysis on the target text after the invalid characters are deleted according to the plurality of timeliness analysis strategies.
7. The method according to any one of claims 1 to 5, wherein the fusing the candidate expiration times to the target expiration time of the target text according to a preset time fusion policy further comprises:
and pushing the target text according to the target failure time.
8. A text processing apparatus, comprising:
the text acquisition module is used for acquiring a target text which needs to be subjected to timeliness analysis;
the strategy acquisition module is used for acquiring a plurality of timeliness analysis strategies with different preset dimensions;
the time effectiveness analysis module is used for respectively carrying out time effectiveness analysis on the target text according to the time effectiveness analysis strategies to obtain a plurality of candidate failure times corresponding to the target text;
and the time determining module is used for fusing the candidate dead times into the target dead time of the target text according to a preset time fusion strategy.
9. A storage medium having stored thereon a computer program, characterized in that, when the computer program is called by a processor, it causes the processor to execute a text processing method according to any one of claims 1 to 7.
10. An electronic device, comprising a processor and a memory, wherein the memory stores a computer program, and the processor is configured to execute the text processing method according to any one of claims 1 to 7 by calling the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911229978.4A CN110929018B (en) | 2019-12-04 | 2019-12-04 | Text processing method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911229978.4A CN110929018B (en) | 2019-12-04 | 2019-12-04 | Text processing method and device, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110929018A true CN110929018A (en) | 2020-03-27 |
| CN110929018B CN110929018B (en) | 2023-03-21 |
Family
ID=69856825
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911229978.4A Active CN110929018B (en) | 2019-12-04 | 2019-12-04 | Text processing method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110929018B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113407714A (en) * | 2020-11-04 | 2021-09-17 | 腾讯科技（深圳）有限公司 | Data processing method and device based on aging, electronic equipment and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105068869A (en) * | 2015-09-29 | 2015-11-18 | 北京网诺星云科技有限公司 | Method and device for pushing information in mobile terminal |
| CN105095368A (en) * | 2015-06-29 | 2015-11-25 | 北京金山安全软件有限公司 | Method and device for sequencing news information |
| CN106951435A (en) * | 2017-02-08 | 2017-07-14 | 广州神马移动信息科技有限公司 | News recommends method, equipment and programmable device |
| CN108446296A (en) * | 2018-01-24 | 2018-08-24 | 北京奇艺世纪科技有限公司 | A kind of information processing method and device |
| CN109660591A (en) * | 2018-11-02 | 2019-04-19 | 北京奇虎科技有限公司 | The automatic push method, apparatus and calculating equipment of Personalize News |
| US20190147050A1 (en) * | 2017-11-16 | 2019-05-16 | Baidu Online Network Technology (Beijing) Co., Ltd | Method and apparatus for recommending news |
| US20190197129A1 (en) * | 2017-12-26 | 2019-06-27 | Baidu Online Network Technology (Beijing) Co., Ltd . | Text analyzing method and device, server and computer-readable storage medium |
| CN110020104A (en) * | 2017-09-05 | 2019-07-16 | 腾讯科技（北京）有限公司 | News handles method, apparatus, storage medium and computer equipment |
| CN110472154A (en) * | 2019-08-26 | 2019-11-19 | 秒针信息技术有限公司 | A kind of resource supplying method, apparatus, electronic equipment and readable storage medium storing program for executing |
-
2019
- 2019-12-04 CN CN201911229978.4A patent/CN110929018B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105095368A (en) * | 2015-06-29 | 2015-11-25 | 北京金山安全软件有限公司 | Method and device for sequencing news information |
| CN105068869A (en) * | 2015-09-29 | 2015-11-18 | 北京网诺星云科技有限公司 | Method and device for pushing information in mobile terminal |
| CN106951435A (en) * | 2017-02-08 | 2017-07-14 | 广州神马移动信息科技有限公司 | News recommends method, equipment and programmable device |
| CN110020104A (en) * | 2017-09-05 | 2019-07-16 | 腾讯科技（北京）有限公司 | News handles method, apparatus, storage medium and computer equipment |
| US20190147050A1 (en) * | 2017-11-16 | 2019-05-16 | Baidu Online Network Technology (Beijing) Co., Ltd | Method and apparatus for recommending news |
| US20190197129A1 (en) * | 2017-12-26 | 2019-06-27 | Baidu Online Network Technology (Beijing) Co., Ltd . | Text analyzing method and device, server and computer-readable storage medium |
| CN108446296A (en) * | 2018-01-24 | 2018-08-24 | 北京奇艺世纪科技有限公司 | A kind of information processing method and device |
| CN109660591A (en) * | 2018-11-02 | 2019-04-19 | 北京奇虎科技有限公司 | The automatic push method, apparatus and calculating equipment of Personalize News |
| CN110472154A (en) * | 2019-08-26 | 2019-11-19 | 秒针信息技术有限公司 | A kind of resource supplying method, apparatus, electronic equipment and readable storage medium storing program for executing |
Non-Patent Citations (1)
| Title |
|---|
| 孟令中等: "软件失效模式的自动生成方法研究", 《计算机科学与探索》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113407714A (en) * | 2020-11-04 | 2021-09-17 | 腾讯科技（深圳）有限公司 | Data processing method and device based on aging, electronic equipment and storage medium |
| CN113407714B (en) * | 2020-11-04 | 2024-03-12 | 腾讯科技（深圳）有限公司 | Aging-based data processing method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110929018B (en) | 2023-03-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109033229B (en) | Question and answer processing method and device | |
| CN108073568B (en) | Keyword extraction method and device | |
| CN108376151B (en) | Question classification method and device, computer equipment and storage medium | |
| KR100682897B1 (en) | Method and apparatus for updating dictionary | |
| US11222310B2 (en) | Automatic tagging for online job listings | |
| CN110717034A (en) | Ontology construction method and device | |
| CN110888990B (en) | Text recommendation method, device, equipment and medium | |
| CN108376129B (en) | Error correction method and device | |
| CN108287821B (en) | High-quality text screening method and device and electronic equipment | |
| WO2015120798A1 (en) | Method for processing network media information and related system | |
| CN110674408B (en) | Service platform, and real-time generation method and device of training sample | |
| CN109299245B (en) | Method and device for recalling knowledge points | |
| CN110889463A (en) | Sample labeling method and device, server and machine-readable storage medium | |
| CN106528532A (en) | Text error correction method and device and terminal | |
| JP2007528520A (en) | Method and system for managing websites registered with search engines | |
| CN109165691B (en) | Training method and device for model for identifying cheating users and electronic equipment | |
| KR102104316B1 (en) | Apparatus for predicting stock price of company by analyzing news and operating method thereof | |
| CN108108353B (en) | Video semantic annotation method and device based on bullet screen and electronic equipment | |
| CN112966865B (en) | Number-carrying network-switching prediction method, device and equipment | |
| CN110929018B (en) | Text processing method and device, storage medium and electronic equipment | |
| US20140114982A1 (en) | Automatic taxonomy merge | |
| CN112163415A (en) | User intention identification method and device for feedback content and electronic equipment | |
| CN115794898B (en) | Financial information recommendation method and device, electronic equipment and storage medium | |
| CN107577667B (en) | Entity word processing method and device | |
| CN113656575B (en) | Training data generation method and device, electronic equipment and readable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |