CN113553407A - Event tracing method and device, electronic equipment and storage medium - Google Patents

Event tracing method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN113553407A
CN113553407A CN202110680960.7A CN202110680960A CN113553407A CN 113553407 A CN113553407 A CN 113553407A CN 202110680960 A CN202110680960 A CN 202110680960A CN 113553407 A CN113553407 A CN 113553407A
Authority
CN
China
Prior art keywords
processed
keyword
event
region
time period
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
Application number
CN202110680960.7A
Other languages
Chinese (zh)
Other versions
CN113553407B (en
Inventor
刘吉
黄际洲
熊昊一
周景博
姜海燕
杨亚鑫
王海峰
窦德景
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN202110680960.7A priority Critical patent/CN113553407B/en
Publication of CN113553407A publication Critical patent/CN113553407A/en
Application granted granted Critical
Publication of CN113553407B publication Critical patent/CN113553407B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06F16/332—Query formulation
    • G06F16/3329—Natural language query formulation or dialogue systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Theoretical Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Human Computer Interaction (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The disclosure provides an event tracing method and device, electronic equipment and a storage medium, and relates to the technical field of data processing, in particular to the technical field of big data and artificial intelligence. The specific implementation scheme is as follows: acquiring event related data of an event to be traced; determining an event correlation degree sequence of the keywords to be processed in the area to be processed according to the search data of the keywords to be processed in each time period and the related object data in the area to be processed in each time period aiming at each keyword to be processed in each area to be processed; and determining origin time points and origin areas of the events to be traced according to the event correlation degree sequences of the keywords to be processed in the areas to be processed. Therefore, the event correlation degree change of the keywords to be processed in the area to be processed can be obtained, and the origin time point and the origin area of the event to be traced can be accurately determined according to the event correlation degree change of the keywords to be processed in the area to be processed.

Description

Event tracing method and device, electronic equipment and storage medium
Technical Field
The present disclosure relates to the field of data processing technologies, and in particular, to the field of big data and artificial intelligence technologies, and in particular, to an event tracing method and apparatus, an electronic device, and a storage medium.
Background
With the advance of urbanization and rapid development of traffic in China, urban areas have high population density and high population mobility, if a pandemic event occurs, a large number of rapid pandemics are caused, and sufficient attention is hardly paid to the pandemic event before the pandemic event reaches a certain degree of severity. After a certain attention is paid, the origin time point and origin area of the epidemic event need to be confirmed in time.
Disclosure of Invention
The disclosure provides an event tracing method, an event tracing device, an electronic device and a storage medium.
According to an aspect of the present disclosure, there is provided an event tracing method, including: acquiring event related data of an event to be traced, wherein the event related data comprises: related object data and keyword search data in each region of each time period; the keyword search data comprises search data of a plurality of keywords related to the event to be traced; for each keyword to be processed in each area to be processed, determining an event correlation degree sequence of the keyword to be processed in the area to be processed according to the search data of the keyword to be processed in each time period and the related object data in the area to be processed in each time period; and determining origin time points and origin areas of the events to be traced according to the event correlation degree sequences of the keywords to be processed in the areas to be processed.
According to another aspect of the present disclosure, there is provided an event tracing apparatus including: the event tracing system comprises an acquisition module, a tracing module and a control module, wherein the acquisition module is used for acquiring event related data of an event to be traced, and the event related data comprises: related object data and keyword search data in each region of each time period; the keyword search data comprises search data of a plurality of keywords related to the event to be traced; a first determining module, configured to determine, for each to-be-processed keyword in each to-be-processed region, an event correlation degree sequence of the to-be-processed keyword in the to-be-processed region according to search data of the to-be-processed keyword in each time period and related object data in the to-be-processed region in each time period; and the second determining module is used for determining origin time points and origin areas of the events to be traced according to the event correlation degree sequences of the keywords to be processed in the areas to be processed.
According to another aspect of the present disclosure, there is provided an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of the first aspect of the present disclosure.
According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of the first aspect of the present disclosure.
According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method of an embodiment of the first aspect of the present disclosure.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a schematic diagram according to a first embodiment of the present disclosure;
FIG. 2 is a schematic diagram according to a second embodiment of the present disclosure;
FIG. 3 is a schematic diagram of search data for keywords to be processed according to an embodiment of the disclosure;
FIG. 4 is a schematic diagram according to a third embodiment of the present disclosure;
FIG. 5 is a schematic diagram according to a fourth embodiment of the present disclosure;
FIG. 6 is a schematic flow diagram of an event tracing method according to an embodiment of the present disclosure;
FIG. 7 is a schematic diagram according to a fifth embodiment of the present disclosure;
fig. 8 is a block diagram of an electronic device for implementing an event tracing method according to an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
With the advance of urbanization and rapid development of traffic in China, urban areas have high population density and high population mobility, if a pandemic event occurs, a large number of rapid pandemics are caused, and sufficient attention is hardly paid to the pandemic event before the pandemic event reaches a certain degree of severity. After a certain attention is paid, the origin time point and origin area of the epidemic event need to be confirmed in time.
In the related art, the possible origin date and origin area of a popular event are inferred using a dynamic system and the number of objects involved over time, but it is difficult to accurately determine the origin time point and origin area of a popular event by making assumptions and inferences of a popular event using a dynamic system and the possible origin date and origin area of a popular event by inferring the number of objects involved over time.
In order to solve the above problems, the present disclosure provides an event tracing method, an event tracing apparatus, an electronic device, and a storage medium.
Fig. 1 is a schematic diagram according to a first embodiment of the present disclosure. It should be noted that the event tracing method according to the embodiment of the present disclosure may be applied to the event tracing apparatus according to the embodiment of the present disclosure, and the apparatus may be configured in an electronic device. The electronic device may be a mobile terminal, for example, a mobile phone, a tablet computer, a personal digital assistant, and other hardware devices with various operating systems.
As shown in fig. 1, the event tracing method may include the following steps:
step 101, obtaining event related data of an event to be traced, wherein the event related data comprises: related object data and keyword search data in each region of each time period; the keyword search data includes search data for a plurality of keywords related to the event to be traced.
In the embodiment of the present disclosure, a popular event that needs to be traced back to the origin time point and the origin area may be taken as an event to be traced back. The related object data may be population data related to the event to be traced, the keyword search data may be a data volume obtained by a user inputting a keyword related to the event to be traced in a search engine for search, and optionally, the population data related to the event to be traced in each time period and the data volume obtained by the user inputting the keyword related to the event to be traced in the search engine for search may be counted to obtain the related object data and the keyword search data in each time period and each region. It should be noted that the keyword search data may include search data of a plurality of keywords related to the event to be traced.
Step 102, aiming at each keyword to be processed in each area to be processed, determining an event correlation degree sequence of the keyword to be processed in the area to be processed according to the search data of the keyword to be processed in each time period and the related object data in the area to be processed in each time period.
Further, for each keyword to be processed in each area to be processed, search data of the keyword to be processed in each time period in the area to be processed may be acquired, related object data in the area to be processed in each time period may be acquired, then, according to the search data of the keyword to be processed in each time period and the related object data in the area to be processed in each time period, event correlation of the keyword to be processed in the area to be processed may be determined, and according to the event correlation of the keyword to be processed in the area to be processed, an event correlation sequence of the keyword to be processed in the area to be processed may be determined.
And 103, determining origin time points and origin areas of the events to be traced according to the event correlation degree sequences of the keywords to be processed in the areas to be processed.
That is to say, the event correlation sequence for determining the keywords to be processed in the area to be processed may include the event correlation of the keywords to be processed in the area to be processed, the event correlation of the keywords to be processed in the area to be processed may be obtained according to the event correlation sequence of the keywords to be processed in the area to be processed, and the origin time point and the origin area of the event to be traced may be determined according to the event correlation change of the keywords to be processed in the area to be processed.
In order to improve the usability of the embodiment of the present disclosure, in the embodiment of the present disclosure, according to the event correlation sequence of the to-be-processed keyword in the to-be-processed region, the event correlation of the to-be-processed keyword in the to-be-processed region may be obtained, and for the to-be-processed region with higher event correlation of the to-be-processed keyword, an early warning may be performed, so as to avoid a large-scale prevalence of a popular event in the to-be-processed region.
In summary, event-related data of an event to be traced back is acquired, where the event-related data includes: related object data and keyword search data in each region of each time period; the keyword search data comprises search data of a plurality of keywords related to the event to be traced; determining an event correlation degree sequence of the keywords to be processed in the area to be processed according to the search data of the keywords to be processed in each time period and the related object data in the area to be processed in each time period aiming at each keyword to be processed in each area to be processed; and determining origin time points and origin areas of the events to be traced according to the event correlation degree sequences of the keywords to be processed in the areas to be processed. Therefore, the event correlation degree change of the keywords to be processed in the area to be processed can be obtained according to the event correlation degree sequence of the keywords to be processed in each area to be processed, and the origin time point and the origin area of the event to be traced can be accurately determined according to the event correlation degree change of the keywords to be processed in the area to be processed.
In order to accurately determine an event correlation sequence of keywords to be processed in a region to be processed, as shown in fig. 2, fig. 2 is a schematic diagram according to a second embodiment of the present disclosure, in the embodiment of the present disclosure, an event correlation between a keyword to be processed in a time period and an event to be traced back is determined according to search data of the keyword to be processed at each time point in each time period and related object data in the region to be processed at each time point, and the embodiment shown in fig. 2 may include the following steps:
step 201, obtaining event related data of an event to be traced, wherein the event related data includes: related object data and keyword search data in each region of each time period; the keyword search data includes search data for a plurality of keywords related to the event to be traced.
Step 202, determining event correlation between the keywords to be processed and the events to be traced in each time period according to the search data of the keywords to be processed at each time point in each time period and the related object data in the areas to be processed at each time point, for each time period, for each keyword to be processed in each area to be processed.
Optionally, performing dynamic time warping or detrending cross-correlation analysis on the search data of the keyword to be processed at each time point in each time period and the related object data in the region to be processed at each time point, and determining the corresponding relationship between the search data of the keyword to be processed at each time point and the related object data in the region to be processed at each time point; and determining the event correlation degree of the keywords to be processed and the events to be traced according to the search data of the keywords to be processed at each time point and the corresponding related object data.
That is, as shown in fig. 3, for the search data of the keyword to be processed at each time point (e.g., divided into 3 time points on average in 1 month to 3 months) in each time period (e.g., 1 month to 3 months) in each region to be processed, and the object-related data in the region to be processed at each time point, processing may be performed through dynamic time warping or detrending cross-correlation analysis, obtaining a correspondence between the search data of the keyword to be processed at each time point and the object-related data in the region to be processed at each time point, and then determining the event correlation between the keyword to be processed and the event to be traced according to the search data of the keyword to be processed at each time point and the corresponding object-related data. For example, when the data amount of the search data of the keyword to be processed at each time point and the corresponding related object data are more, the event correlation degree between the keyword to be processed and the event to be traced back is also greater, and when the data amount of the search data of the keyword to be processed at each time point and the corresponding related object data are less, the event correlation degree between the keyword to be processed and the event to be traced back is also less.
Step 203, generating an event correlation degree sequence of the keywords to be processed in the candidate region according to the event correlation degree of the keywords to be processed in each time period and the events to be traced.
Further, the event relevancy of the keywords to be processed in each time period and the events to be traced back are arranged according to the time period sequence, an event relevancy sequence of the keywords to be processed in the area to be processed can be generated, and the event relevancy sequence of the keywords to be processed in the area to be processed is used as the event relevancy sequence of the keywords to be processed in the candidate area.
And 204, determining origin time points and origin areas of the events to be traced according to the event correlation degree sequences of the keywords to be processed in the areas to be processed.
In the embodiment of the present disclosure, steps 201 and 204 may be implemented by any one of the embodiments of the present disclosure, which is not limited in the embodiment of the present disclosure and is not described again.
In summary, event-related data of an event to be traced back is acquired, where the event-related data includes: related object data and keyword search data in each region of each time period; the keyword search data comprises search data of a plurality of keywords related to the event to be traced; determining event correlation degrees of the keywords to be processed and events to be traced in each time period according to search data of the keywords to be processed at each time point in each time period and related object data in the areas to be processed at each time point, aiming at each time period and each keyword to be processed in each area to be processed; generating an event correlation degree sequence of the keywords to be processed in the candidate region according to the event correlation degree of the keywords to be processed in each time period and the events to be traced; and determining origin time points and origin areas of the events to be traced according to the event correlation degree sequences of the keywords to be processed in the areas to be processed. Therefore, the event correlation degree change of the keywords to be processed in the area to be processed can be obtained according to the event correlation degree sequence of the keywords to be processed in each area to be processed, and the origin time point and the origin area of the event to be traced can be accurately determined according to the event correlation degree change of the keywords to be processed in the area to be processed.
In order to more accurately determine the event correlation sequence of the keywords to be processed in the region to be processed, as shown in fig. 4, fig. 4 is a schematic diagram according to a third embodiment of the present disclosure, and in the embodiment of the present disclosure, since there may be a large difference between the search data of the keywords to be processed in each time period in each region to be processed and the related object data in the region to be processed in each time period, the search data of the keywords to be processed in each time period and the related object data in the region to be processed in each time period may be respectively normalized. The embodiment shown in fig. 4 may include the following steps:
step 401, obtaining event related data of an event to be traced, where the event related data includes: related object data and keyword search data in each region of each time period; the keyword search data includes search data for a plurality of keywords related to the event to be traced.
Step 402, aiming at each keyword to be processed in each area to be processed, normalizing the search data of the keyword to be processed in each time period.
Optionally, determining a normalization parameter of the keyword to be processed according to the search data of the keyword to be processed in each time period, where the normalization parameter includes: average value and standard value; and for each piece of search data, carrying out processing of subtracting the average value and dividing the average value by the standard value on the search data to realize the normalization processing of the search data.
That is, the search data of the keywords to be processed in each time period may be added, the addition result may be compared with the number of time periods, the average value of the search data of the keywords to be processed may be obtained, and the standard value of the search data of the keywords to be processed may be calculated according to the average value of the search data of the keywords to be processed in each time period and the search data of the keywords to be processed. For each piece of search data, the process of subtracting the average value and the process of dividing by the standard value can be performed on the search data, so as to realize the normalization process on the search data, which can be expressed as the following formula:
Normalize(Date Index Value)＝(Date Index Value-μ)/σ；
wherein, norm (Date Index Value) represents the normalization processing result of the search data, Date Index Value represents the search data of the keyword to be processed, μ is the average Value of the search data of the keyword to be processed, and σ represents the standard Value of the search data of the keyword to be processed.
And 403, performing normalization processing on the related object data in the region to be processed in each time period.
Optionally, a normalization parameter related to the object data in the region to be processed is determined according to the object data related to the region to be processed in each time period, where the normalization parameter includes: average value and standard value; for the object-related data, the object-related data may be subjected to a process of subtracting the average value and a process of dividing by a standard value, and a normalization process of the object-related data may be performed.
That is, the object-related data in the area to be processed in each period may be added, the addition result may be compared with the number of periods, an average value of the object-related data in the area to be processed may be obtained, and the standard value of the object-related data in the area to be processed may be calculated from the average values of the object-related data in the area to be processed in each period and the object-related data in the area to be processed. For each object data, the object data can be subjected to a process of subtracting the average value and a process of dividing by the standard value, so as to realize the normalization process of the object data, which can be expressed as the following formula:
Normalize(Date Index Value′)＝(Date Index Value′-μ′)/σ′；
where norm (Date Index Value ') denotes a result of normalization processing with respect to object data, Date Index Value' denotes object data with respect to the area to be processed, μ 'denotes an average Value of object data with respect to the area to be processed, and σ' denotes a standard Value of object data with respect to the area to be processed.
Step 404, for each keyword to be processed in each area to be processed, for each time period, determining the event correlation degree between the keyword to be processed in the time period and the event to be traced according to the search data of the keyword to be processed at each time point in the time period and the related object data in the area to be processed at each time point.
Step 405, generating an event correlation degree sequence of the keywords to be processed in the candidate region according to the event correlation degree of the keywords to be processed in each time period and the events to be traced.
And step 406, determining origin time points and origin areas of the events to be traced according to the event correlation degree sequences of the keywords to be processed in the areas to be processed.
In the embodiment of the present disclosure, the steps 401 and 404-406 may be implemented by any method in each embodiment of the present disclosure, and the embodiment of the present disclosure does not limit this and is not described again.
In summary, event-related data of an event to be traced back is acquired, where the event-related data includes: related object data and keyword search data in each region of each time period; the keyword search data comprises search data of a plurality of keywords related to the event to be traced; for each keyword to be processed in each area to be processed, carrying out normalization processing on the search data of the keyword to be processed in each time period; carrying out normalization processing on related object data in the region to be processed in each time period; determining event correlation degrees of the keywords to be processed and events to be traced in each time period according to search data of the keywords to be processed at each time point in each time period and related object data in the areas to be processed at each time point, aiming at each time period and each keyword to be processed in each area to be processed; generating an event correlation degree sequence of the keywords to be processed in the candidate region according to the event correlation degree of the keywords to be processed in each time period and the events to be traced; and determining origin time points and origin areas of the events to be traced according to the event correlation degree sequences of the keywords to be processed in the areas to be processed. Therefore, according to the search data of each keyword to be processed in each area to be processed after normalization processing and the related object data in each area to be processed at each time point, the event correlation degree of the keyword to be processed in a time period and the event to be traced event can be accurately determined, further, according to the event correlation degree sequence of each keyword to be processed in each area to be processed, the event correlation degree change of the keyword to be processed in the area to be processed is obtained, and according to the event correlation degree change of the keyword to be processed in the area to be processed, the origin time point and the origin area of the event to be traced can be accurately determined.
In order to accurately determine the origin time point and the origin region of the event to be traced, as shown in fig. 5, fig. 5 is a schematic diagram according to a fourth embodiment of the present disclosure, and in the embodiment of the present disclosure, for each region to be processed, the event correlation mutation point of the target keyword in the region to be processed may be determined according to the event correlation sequence of the target keyword in the region to be processed, so as to determine the origin time point and the origin region of the event to be traced. The embodiment shown in fig. 5 may include the following steps:
step 501, obtaining event related data of an event to be traced, wherein the event related data includes: related object data and keyword search data in each region of each time period; the keyword search data includes search data for a plurality of keywords related to the event to be traced.
Step 502, for each keyword to be processed in each region to be processed, determining an event correlation sequence of the keyword to be processed in the region to be processed according to the search data of the keyword to be processed in each time period and the related object data in the region to be processed in each time period.
Step 503, selecting a target keyword from each to-be-processed keyword according to the event correlation sequence of each to-be-processed keyword in each to-be-processed region.
Optionally, for each to-be-processed region, sorting each to-be-processed keyword according to the event correlation sequence of each to-be-processed keyword in the to-be-processed region to obtain a keyword sorting result of the to-be-processed region; and selecting the top N keywords from the keyword sequencing results of the regions to be processed as target keywords, wherein N is a non-zero natural number.
As a possible implementation manner of the embodiment of the present disclosure, in order to obtain the to-be-processed keywords corresponding to the event relevancy sequence with higher relevancy, in the embodiment of the present disclosure, for each to-be-processed region, the event relevancy sequences of the to-be-processed keywords in the to-be-processed region may be compared with each other, the to-be-processed keywords may be sorted according to the relevancy comparison result, the top N to-be-processed keywords in the sorting result may be used as the target keywords, that is, the top N to-be-processed keywords corresponding to the event relevancy sequence with higher relevancy may be used as the target keywords. Wherein N is a non-zero natural number. For example, the target keyword is a mask, disinfection, or the like.
Step 504, aiming at each region to be processed, determining an event correlation mutation point of the target keywords in the region to be processed according to the event correlation sequence of the target keywords in the region to be processed.
That is to say, for each to-be-processed region, according to the event correlation sequence of the target keyword in the to-be-processed region, a point with a large fluctuation in the event correlation of the target keyword in the to-be-processed region in the event correlation sequence of the target keyword in the to-be-processed region can be determined, and the point with the large fluctuation in the event correlation of the target keyword in the to-be-processed region is used as the event correlation mutation point of the target keyword in the to-be-processed region. For example, the target keyword is "mask", a point of the event correlation degree of the "mask" in the region to be processed in the event correlation degree sequence of the "mask" in the region to be processed is determined to have a large fluctuation according to the event correlation degree sequence of the "mask" in the region to be processed, and the point of the event correlation degree of the "mask" in the region to be processed, which has a large fluctuation, is used as an event correlation degree mutation point of the "mask" in the region to be processed.
Optionally, for each to-be-processed region, performing normal distribution fitting processing according to the event correlation sequence of the target keyword in the to-be-processed region, and determining fitted normal distribution; determining a target time period corresponding to the correlation degree with the maximum corresponding difference function value according to the fitted normal distribution and an event correlation degree sequence of the target key words in the region to be processed, wherein the difference function is that the target time period is taken as a variable, and a first fitting error in each time period before the target time period plus a second fitting error in each time period after the target time period minus a third fitting error in all time periods; and determining the target time period as an event correlation catastrophe point of the target keywords in the region to be processed.
In the embodiment of the present disclosure, a normal distribution fitting process may be performed on the event correlation sequence of the target keyword in the region to be processed, and a fitted normal distribution is determined, which may be specifically expressed as the following formula:
zt|θt～N(θt,1)；
wherein, thetatIs a constant segmented over time, e.g. thetatIs one day, thetatIs one month or thetatOne week, etc., ztIs the correlation over a time segment.
Then, according to the fitted normal distribution and an event correlation sequence of a target keyword in a region to be processed, determining a target time period corresponding to the correlation with the maximum corresponding difference function value, wherein the difference function is that the target time period is taken as a variable, a first fitting error in each time period before the target time period, a second fitting error in each time period after the target time period and a third fitting error in all time periods; determining the target time period as an event correlation mutation point of the target keyword in the region to be processed, which can be expressed as the following formula:
LR＝maxτ{l(z1:r)+l(zr+1:n)-l(z1:n)}；
where LR represents the correlation with the largest difference function value, l (z)1:r) Representing a first fitting error, l (z), over respective time periods prior to the target time periodr+1:n) Representing a second fitting error, l (z), over each time segment after the target time segment1:n) Third fitting error over all time periods, z corresponding to LRrAnd determining the event correlation mutation points of the target keywords in the region to be processed.
And 505, determining origin time points and origin areas of the events to be traced according to the event correlation catastrophe points of the target keywords in the areas to be processed.
As a possible implementation manner of the embodiment of the present disclosure, in order to accurately determine the origin time point and the origin region of the event to be traced, the earliest event relevance mutation point among the event relevance mutation points of the target keyword in each region to be processed may be determined as the origin time point; and determining the region to which the earliest event-related mutation point belongs as an origin region. For example, when there are a plurality of event correlation mutation points of the target keywords in each to-be-processed region, the earliest event correlation mutation point among the event correlation mutation points of the target keywords in each to-be-processed region may be determined as an origin time point, and a region to which the earliest event correlation mutation point belongs is correspondingly determined as an origin region.
In the embodiment of the present disclosure, the steps 501-502 may be implemented by any one of the embodiments of the present disclosure, which is not limited by the embodiment of the present disclosure and is not described again.
In summary, event-related data of an event to be traced back is acquired, where the event-related data includes: related object data and keyword search data in each region of each time period; the keyword search data comprises search data of a plurality of keywords related to the event to be traced; determining an event correlation degree sequence of the keywords to be processed in the area to be processed according to the search data of the keywords to be processed in each time period and the related object data in the area to be processed in each time period aiming at each keyword to be processed in each area to be processed; selecting a target keyword from each keyword to be processed according to the event correlation sequence of each keyword to be processed in each region to be processed; aiming at each region to be processed, determining an event correlation catastrophe point of a target keyword in the region to be processed according to an event correlation sequence of the target keyword in the region to be processed; and determining origin time points and origin areas of the events to be traced according to the event correlation catastrophe points of the target keywords in each area to be processed. Therefore, according to the event correlation catastrophe points of the target keywords in each to-be-processed area, the origin time point and the origin area of the to-be-traced event can be accurately determined.
In order that those skilled in the art will more clearly understand the disclosure, the description will now be given by way of example.
For example, as shown in fig. 6, for the related object data and the keyword search data in each region of each time period, the corresponding relationship between the search data of the keyword to be processed at each time point and the related object data in the region to be processed at each time point can be determined through dynamic time warping or detrending cross-correlation analysis, so as to determine the event correlation degree between the keyword to be processed and the event to be traced, the event correlation degree analysis of the keyword to be processed and the event to be traced is performed to determine the keyword list (keyword sorting result) of the region to be processed, the first N keywords in the keyword list are used as the target keywords, the target keyword mutation points in the region to be processed are determined according to the event correlation degree sequence of the target keywords in the region to be processed, the target keyword mutation points in the region to be processed are determined according to the target keyword mutation points in the region to be processed, the starting point (origin time point) of the group reaction time of the popular event (event to be traced) is determined, and the area corresponding to the starting point of the group reaction time is used as the origin area of the popular event. In order to further verify the accuracy of the result, similar search data analysis can be performed through popular events in different time regions, object migration related data analysis is performed, and the correctness verification is performed on the starting point of the group reaction time of the popular event and the area corresponding to the starting point of the group reaction time.
The event tracing method of the embodiment of the disclosure obtains event-related data of an event to be traced, wherein the event-related data includes: related object data and keyword search data in each region of each time period; the keyword search data comprises search data of a plurality of keywords related to the event to be traced; determining an event correlation degree sequence of the keywords to be processed in the area to be processed according to the search data of the keywords to be processed in each time period and the related object data in the area to be processed in each time period aiming at each keyword to be processed in each area to be processed; and determining origin time points and origin areas of the events to be traced according to the event correlation degree sequences of the keywords to be processed in the areas to be processed. Therefore, the event correlation degree change of the keywords to be processed in the area to be processed can be obtained according to the event correlation degree sequence of the keywords to be processed in each area to be processed, and the origin time point and the origin area of the event to be traced can be accurately determined according to the event correlation degree change of the keywords to be processed in the area to be processed.
In order to implement the above embodiment, the present disclosure further provides an event tracing apparatus.
Fig. 7 is a schematic diagram of a fifth embodiment according to the present disclosure, and as shown in fig. 7, an event tracing apparatus 700 includes: an obtaining module 710, a first determining module 720, and a second determining module 730.
The obtaining module 710 is configured to obtain event-related data of an event to be traced, where the event-related data includes: related object data and keyword search data in each region of each time period; the keyword search data comprises search data of a plurality of keywords related to the event to be traced; a first determining module 720, configured to determine, for each to-be-processed keyword in each to-be-processed region, an event correlation sequence of the to-be-processed keyword in the to-be-processed region according to search data of the to-be-processed keyword in each time period and related object data in the to-be-processed region in each time period; the second determining module 730 is configured to determine an origin time point and an origin region of the event to be traced according to the event correlation sequence of each keyword to be processed in each area to be processed.
As a possible implementation manner of the embodiment of the present disclosure, the first determining module 720 is specifically configured to: determining event correlation degrees of the keywords to be processed and events to be traced in each time period according to search data of the keywords to be processed at each time point in each time period and related object data in the areas to be processed at each time point, aiming at each time period and each keyword to be processed in each area to be processed; and generating an event correlation sequence of the keywords to be processed in the candidate region according to the event correlation of the keywords to be processed in each time period and the events to be traced.
As a possible implementation manner of the embodiment of the present disclosure, the first determining module 720 is further configured to: performing dynamic time warping or detrending cross-correlation analysis on the search data of the keywords to be processed at each time point and the related object data in the area to be processed at each time point, and determining the corresponding relation between the search data of the keywords to be processed at each time point and the related object data in the area to be processed at each time point; and determining the event correlation degree of the keywords to be processed and the events to be traced according to the search data of the keywords to be processed at each time point and the corresponding related object data.
As a possible implementation manner of the embodiment of the present disclosure, the event tracing apparatus 700 further includes: and a processing module.
The processing module is used for carrying out normalization processing on the search data of the keywords to be processed in each time period aiming at each keyword to be processed in each area to be processed; and carrying out normalization processing on the related object data in the region to be processed in each time period.
As a possible implementation manner of the embodiment of the present disclosure, the second determining module 730 is specifically configured to: selecting a target keyword from each keyword to be processed according to the event correlation sequence of each keyword to be processed in each region to be processed; aiming at each region to be processed, determining an event correlation catastrophe point of a target keyword in the region to be processed according to an event correlation sequence of the target keyword in the region to be processed; and determining origin time points and origin areas of the events to be traced according to the event correlation catastrophe points of the target keywords in each area to be processed.
As a possible implementation manner of the embodiment of the present disclosure, the second determining module 730 is further configured to: for each to-be-processed area, sorting each to-be-processed keyword according to the event correlation sequence of each to-be-processed keyword in the to-be-processed area to obtain a keyword sorting result of the to-be-processed area; and selecting the top N keywords from the keyword sequencing results of the regions to be processed as target keywords, wherein N is a non-zero natural number.
As a possible implementation manner of the embodiment of the present disclosure, the second determining module 730 is further configured to: for each region to be processed, performing normal distribution fitting processing according to the event correlation degree sequence of the target keyword in the region to be processed, and determining fitted normal distribution; determining a target time period corresponding to the correlation degree with the maximum corresponding difference function value according to the fitted normal distribution and an event correlation degree sequence of the target key words in the region to be processed, wherein the difference function is that the target time period is taken as a variable, and a first fitting error in each time period before the target time period plus a second fitting error in each time period after the target time period minus a third fitting error in all time periods; and determining the target time period as an event correlation catastrophe point of the target keywords in the region to be processed.
As a possible implementation manner of the embodiment of the present disclosure, the second determining module 730 is further configured to: determining the earliest event correlation mutation point in the event correlation mutation points of the target keywords in each to-be-processed area as an origin time point; and determining the region to which the earliest event-related mutation point belongs as an origin region.
The event tracing device of the embodiment of the present disclosure obtains event-related data of an event to be traced, where the event-related data includes: related object data and keyword search data in each region of each time period; the keyword search data comprises search data of a plurality of keywords related to the event to be traced; determining an event correlation degree sequence of the keywords to be processed in the area to be processed according to the search data of the keywords to be processed in each time period and the related object data in the area to be processed in each time period aiming at each keyword to be processed in each area to be processed; and determining origin time points and origin areas of the events to be traced according to the event correlation degree sequences of the keywords to be processed in the areas to be processed. Therefore, the event correlation degree change of the keywords to be processed in the area to be processed can be obtained according to the event correlation degree sequence of the keywords to be processed in each area to be processed, and the origin time point and the origin area of the event to be traced can be accurately determined according to the event correlation degree change of the keywords to be processed in the area to be processed.
The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.
FIG. 8 illustrates a schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 8, the apparatus 800 includes a computing unit 801 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM)802 or a computer program loaded from a storage unit 808 into a Random Access Memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The calculation unit 801, the ROM 802, and the RAM 803 are connected to each other by a bus 804. An input/output (I/O) interface 805 is also connected to bus 804.
A number of components in the device 800 are connected to the I/O interface 805, including: an input unit 806, such as a keyboard, a mouse, or the like; an output unit 807 such as various types of displays, speakers, and the like; a storage unit 808, such as a magnetic disk, optical disk, or the like; and a communication unit 809 such as a network card, modem, wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
Computing unit 801 may be a variety of general and/or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and the like. The computing unit 801 performs the various methods and processes described above, such as an event tracing method. For example, in some embodiments, the event tracing method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program can be loaded and/or installed onto device 800 via ROM 802 and/or communications unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the event tracing method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the event tracing method in any other suitable manner (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), the internet, and blockchain networks.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may also be a server of a distributed system, or a server incorporating a blockchain.
It should be noted that artificial intelligence is a subject for studying a computer to simulate some human thinking processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), and includes both hardware and software technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing, and the like; the artificial intelligence software technology mainly comprises a computer vision technology, a voice recognition technology, a natural language processing technology, machine learning/deep learning, a big data processing technology, a knowledge map technology and the like.
In the technical scheme of the disclosure, the acquisition, storage, application and the like of the personal information of the related user all accord with the regulations of related laws and regulations, and do not violate the good customs of the public order.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims (19)

1. An event tracing method comprising:
acquiring event related data of an event to be traced, wherein the event related data comprises: related object data and keyword search data in each region of each time period; the keyword search data comprises search data of a plurality of keywords related to the event to be traced;
for each keyword to be processed in each area to be processed, determining an event correlation degree sequence of the keyword to be processed in the area to be processed according to the search data of the keyword to be processed in each time period and the related object data in the area to be processed in each time period;
and determining origin time points and origin areas of the events to be traced according to the event correlation degree sequences of the keywords to be processed in the areas to be processed.
2. The method according to claim 1, wherein the determining, for each keyword to be processed in each region to be processed, an event correlation sequence of the keyword to be processed in the region to be processed according to search data of the keyword to be processed in each time period and related object data in the region to be processed in each time period comprises:
for each keyword to be processed in each area to be processed, determining event correlation of the keyword to be processed and the event to be traced in each time period according to search data of the keyword to be processed at each time point in the time period and related object data in the area to be processed at each time point;
and generating an event correlation sequence of the keywords to be processed in the candidate area according to the event correlation of the keywords to be processed and the events to be traced in each time period.
3. The method according to claim 2, wherein the determining the event correlation degree between the keyword to be processed and the event to be traced in the time period according to the search data of the keyword to be processed at each time point in the time period and the related object data in the area to be processed at each time point in the time period comprises:
performing dynamic time warping or detrending cross-correlation analysis on the search data of the keyword to be processed at each time point and the related object data in the region to be processed at each time point, and determining the corresponding relationship between the search data of the keyword to be processed at each time point and the related object data in the region to be processed at each time point;
and determining the event correlation degree of the keywords to be processed and the events to be traced according to the search data of the keywords to be processed at each time point and the corresponding related object data.
4. The method according to claim 2 or 3, wherein before determining, for each time period, an event correlation degree of the keyword to be processed and the event to be traced in the time period according to the search data of the keyword to be processed at each time point in the time period and the related object data in the area to be processed at each time point, the method further comprises:
for each keyword to be processed in each area to be processed, carrying out normalization processing on the search data of the keyword to be processed in each time period;
and carrying out normalization processing on the related object data in the region to be processed in each time period.
5. The method according to claim 1, wherein the determining an origin time point and an origin region of the event to be traced according to the event correlation sequence of each keyword to be processed in each region to be processed comprises:
selecting a target keyword from each keyword to be processed according to the event correlation sequence of each keyword to be processed in each region to be processed;
aiming at each region to be processed, determining an event correlation mutation point of the target keyword in the region to be processed according to the event correlation sequence of the target keyword in the region to be processed;
and determining origin time points and origin areas of the events to be traced according to the event correlation catastrophe points of the target keywords in each area to be processed.
6. The method according to claim 5, wherein the selecting a target keyword from each of the keywords to be processed according to the event correlation sequence of each of the keywords to be processed in each of the regions to be processed comprises:
for each to-be-processed area, sorting each to-be-processed keyword according to the event correlation sequence of each to-be-processed keyword in the to-be-processed area to obtain a keyword sorting result of the to-be-processed area;
and selecting the first N keywords from the keyword sequencing results of the regions to be processed as the target keywords, wherein N is a non-zero natural number.
7. The method of claim 5, wherein the determining, for each to-be-processed region, event correlation mutation points of the target keywords in the to-be-processed region according to the event correlation sequence of the target keywords in the to-be-processed region comprises:
for each region to be processed, performing normal distribution fitting processing according to the event correlation degree sequence of the target keyword in the region to be processed, and determining fitted normal distribution;
determining a target time period corresponding to the correlation degree with the maximum corresponding difference function value according to the fitted normal distribution and the event correlation degree sequence of the target keyword in the region to be processed, wherein the difference function is that a target time period is taken as a variable, and a first fitting error in each time period before the target time period + a second fitting error in each time period after the target time period-a third fitting error in all time periods;
and determining the target time period as an event correlation catastrophe point of the target keyword in the region to be processed.
8. The method of claim 5, wherein the determining the origin time point and the origin region of the event to be traced according to the event correlation mutation point of the target keyword in each region to be processed comprises:
determining the earliest event correlation mutation point in the event correlation mutation points of the target keywords in each to-be-processed area as the origin time point;
and determining the region to which the earliest event-related mutation point belongs as the origin region.
9. An event tracing apparatus comprising:
the event tracing system comprises an acquisition module, a tracing module and a control module, wherein the acquisition module is used for acquiring event related data of an event to be traced, and the event related data comprises: related object data and keyword search data in each region of each time period; the keyword search data comprises search data of a plurality of keywords related to the event to be traced;
a first determining module, configured to determine, for each to-be-processed keyword in each to-be-processed region, an event correlation degree sequence of the to-be-processed keyword in the to-be-processed region according to search data of the to-be-processed keyword in each time period and related object data in the to-be-processed region in each time period;
and the second determining module is used for determining origin time points and origin areas of the events to be traced according to the event correlation degree sequences of the keywords to be processed in the areas to be processed.
10. The apparatus of claim 9, wherein the first determining module is specifically configured to:
for each keyword to be processed in each area to be processed, determining event correlation of the keyword to be processed and the event to be traced in each time period according to search data of the keyword to be processed at each time point in the time period and related object data in the area to be processed at each time point;
and generating an event correlation sequence of the keywords to be processed in the candidate area according to the event correlation of the keywords to be processed and the events to be traced in each time period.
11. The apparatus of claim 10, wherein the first determining module is further configured to:
performing dynamic time warping or detrending cross-correlation analysis on the search data of the keyword to be processed at each time point and the related object data in the region to be processed at each time point, and determining the corresponding relationship between the search data of the keyword to be processed at each time point and the related object data in the region to be processed at each time point;
and determining the event correlation degree of the keywords to be processed and the events to be traced according to the search data of the keywords to be processed at each time point and the corresponding related object data.
12. The apparatus of claim 10 or 11, wherein the apparatus further comprises:
the processing module is used for carrying out normalization processing on the search data of the keywords to be processed in each time period aiming at each keyword to be processed in each area to be processed; and
and carrying out normalization processing on the related object data in the region to be processed in each time period.
13. The apparatus of claim 9, wherein the second determining module is specifically configured to:
selecting a target keyword from each keyword to be processed according to the event correlation sequence of each keyword to be processed in each region to be processed;
aiming at each region to be processed, determining an event correlation mutation point of the target keyword in the region to be processed according to the event correlation sequence of the target keyword in the region to be processed;
and determining origin time points and origin areas of the events to be traced according to the event correlation catastrophe points of the target keywords in each area to be processed.
14. The apparatus of claim 13, wherein the second determining means is further configured to:
for each to-be-processed area, sorting each to-be-processed keyword according to the event correlation sequence of each to-be-processed keyword in the to-be-processed area to obtain a keyword sorting result of the to-be-processed area;
and selecting the first N keywords from the keyword sequencing results of the regions to be processed as the target keywords, wherein N is a non-zero natural number.
15. The apparatus of claim 13, wherein the second determining means is further configured to:
for each region to be processed, performing normal distribution fitting processing according to the event correlation degree sequence of the target keyword in the region to be processed, and determining fitted normal distribution;
determining a target time period corresponding to the correlation degree with the maximum corresponding difference function value according to the fitted normal distribution and the event correlation degree sequence of the target keyword in the region to be processed, wherein the difference function is that a target time period is taken as a variable, and a first fitting error in each time period before the target time period + a second fitting error in each time period after the target time period-a third fitting error in all time periods;
and determining the target time period as an event correlation catastrophe point of the target keyword in the region to be processed.
16. The apparatus of claim 13, wherein the second determining means is further configured to:
determining the earliest event correlation mutation point in the event correlation mutation points of the target keywords in each to-be-processed area as the origin time point;
and determining the region to which the earliest event-related mutation point belongs as the origin region.
17. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.
18. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-8.
19. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-8.
CN202110680960.7A 2021-06-18 2021-06-18 Event tracing method and device, electronic equipment and storage medium Active CN113553407B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110680960.7A CN113553407B (en) 2021-06-18 2021-06-18 Event tracing method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110680960.7A CN113553407B (en) 2021-06-18 2021-06-18 Event tracing method and device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN113553407A true CN113553407A (en) 2021-10-26
CN113553407B CN113553407B (en) 2022-09-27

Family

ID=78102211

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110680960.7A Active CN113553407B (en) 2021-06-18 2021-06-18 Event tracing method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113553407B (en)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104778202A (en) * 2015-02-05 2015-07-15 北京航空航天大学 Analysis method and system based on event evolution process of key words
CN108255933A (en) * 2017-12-07 2018-07-06 北京大学 A kind of social media dynamic event develops visual analysis method and system
CN110175293A (en) * 2019-05-30 2019-08-27 北京小米智能科技有限公司 A kind of method, apparatus and electronic equipment of determining news train of thought
KR20190100533A (en) * 2018-02-09 2019-08-29 (주)다음소프트 Database module using artificial intelligence, economic data providing system and method using the same
CN110222249A (en) * 2019-05-06 2019-09-10 平安科技（深圳）有限公司 Date storage method, device, computer equipment and storage medium
CN110543457A (en) * 2019-09-11 2019-12-06 北京明略软件***有限公司 Track type document processing method and device, storage medium and electronic device
CN110555108A (en) * 2018-05-31 2019-12-10 北京百度网讯科技有限公司 Event context generation method, device, equipment and storage medium
CN112307360A (en) * 2019-07-30 2021-02-02 百度在线网络技术（北京）有限公司 Search engine based regional event detection method and device and search engine
CN112328747A (en) * 2020-11-06 2021-02-05 平安科技（深圳）有限公司 Event context generation method and device, terminal equipment and storage medium

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104778202A (en) * 2015-02-05 2015-07-15 北京航空航天大学 Analysis method and system based on event evolution process of key words
CN108255933A (en) * 2017-12-07 2018-07-06 北京大学 A kind of social media dynamic event develops visual analysis method and system
KR20190100533A (en) * 2018-02-09 2019-08-29 (주)다음소프트 Database module using artificial intelligence, economic data providing system and method using the same
CN110555108A (en) * 2018-05-31 2019-12-10 北京百度网讯科技有限公司 Event context generation method, device, equipment and storage medium
CN110222249A (en) * 2019-05-06 2019-09-10 平安科技（深圳）有限公司 Date storage method, device, computer equipment and storage medium
CN110175293A (en) * 2019-05-30 2019-08-27 北京小米智能科技有限公司 A kind of method, apparatus and electronic equipment of determining news train of thought
CN112307360A (en) * 2019-07-30 2021-02-02 百度在线网络技术（北京）有限公司 Search engine based regional event detection method and device and search engine
CN110543457A (en) * 2019-09-11 2019-12-06 北京明略软件***有限公司 Track type document processing method and device, storage medium and electronic device
CN112328747A (en) * 2020-11-06 2021-02-05 平安科技（深圳）有限公司 Event context generation method and device, terminal equipment and storage medium

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
刘荣叁等: "面向新浪微博的信息溯源技术研究", 《智能计算机与应用》 *
陈黎明等: "面向新闻事件的故事树构建方法", 《计算机工程与设计》 *

Also Published As

Publication number Publication date
CN113553407B (en) 2022-09-27

Similar Documents

Publication Publication Date Title
JP7438303B2 (en) Deep learning model training methods, natural language processing methods and devices, electronic devices, storage media and computer programs
CN112527281B (en) Operator upgrading method and device based on artificial intelligence, electronic equipment and medium
CN113407850B (en) Method and device for determining and acquiring virtual image and electronic equipment
CN113360580A (en) Abnormal event detection method, device, equipment and medium based on knowledge graph
CN114492831A (en) Method and device for generating federal learning model
US20240070454A1 (en) Lightweight model training method, image processing method, electronic device, and storage medium
EP4191478A1 (en) Method and apparatus for compressing neural network model
EP3992814A2 (en) Method and apparatus for generating user interest profile, electronic device and storage medium
CN114861059A (en) Resource recommendation method and device, electronic equipment and storage medium
CN114743586B (en) Mirror image storage implementation method and device of storage model and storage medium
CN114490965B (en) Question processing method and device, electronic equipment and storage medium
EP4134838A1 (en) Word mining method and apparatus, electronic device and readable storage medium
CN113553407B (en) Event tracing method and device, electronic equipment and storage medium
CN115292467A (en) Information processing and model training method, apparatus, device, medium, and program product
CN114445682A (en) Method, device, electronic equipment, storage medium and product for training model
CN113408632A (en) Method and device for improving image classification accuracy, electronic equipment and storage medium
CN115641481A (en) Method and device for training image processing model and image processing
CN115840867A (en) Generation method and device of mathematical problem solving model, electronic equipment and storage medium
CN114330221A (en) Score board implementation method, score board, electronic device and storage medium
CN114490969A (en) Question and answer method and device based on table and electronic equipment
CN113361575A (en) Model training method and device and electronic equipment
CN114119972A (en) Model acquisition and object processing method and device, electronic equipment and storage medium
CN112632999A (en) Named entity recognition model obtaining method, named entity recognition device and named entity recognition medium
CN112905743A (en) Text object detection method and device, electronic equipment and storage medium
CN115168727B (en) User habit mining method and device and electronic equipment

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