CN109766367B - Hot event determination method and device, computer equipment and storage medium - Google Patents
Hot event determination method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109766367B CN109766367B CN201710629638.5A CN201710629638A CN109766367B CN 109766367 B CN109766367 B CN 109766367B CN 201710629638 A CN201710629638 A CN 201710629638A CN 109766367 B CN109766367 B CN 109766367B
- Authority
- CN
- China
- Prior art keywords
- event
- sequence
- value
- determining
- recent
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Debugging And Monitoring (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
A hotspot event determination method, device, equipment and storage medium are provided, and the method of one embodiment comprises the following steps: acquiring each event sequence in a historical event database, wherein any one event sequence comprises each event and the occurrence frequency of each event; for any event sequence, determining an event value parameter value of each event in the event sequence according to the occurrence frequency of each event in the event sequence; determining a recent event validity parameter value of each event in the event sequence; for any event, determining the total value of the event value parameter of the event according to the event value parameter value of the event in each event sequence, and determining the total value of the recent event validity of the event according to the recent event validity parameter value of the event in each event sequence; and determining the hot events according to the total value of the event value parameter and the total value of the recent effectiveness of the events of each event. The embodiment improves the accuracy and performance of hot event prediction.
Description
Technical Field
The present invention relates to the field of digital mining technologies, and in particular, to a method for determining a hot event, a device for determining a hot event, a computer device, and a computer storage medium.
Background
Network hotspot Events generally have an abrupt and staged nature, the discovery of Network Hotspot Events (NHEM) can also be called Topic detection and tracking (TDT for short), and various clustering algorithms are generally used for data Mining in the discovery and Mining of Network hotspot Events at present. In the current data mining mechanism, the implementation is simple, but the calculation amount is huge based on different types of clustering technologies, the quality of a clustering result is related to the adding sequence of a new document, the sensitivity is high, and the inaccuracy of a hotspot event mining result can be caused when the hotspot event mining mechanism is applied to the determination of the hotspot event.
Disclosure of Invention
Based on this, it is necessary to provide a method for determining a hotspot event, a device for determining a hotspot event, a computer device and a computer storage medium, so as to improve the accuracy of mining and determining the hotspot event.
Accordingly, the following technical scheme is adopted in one embodiment:
a hot spot event determination method includes the following steps:
acquiring each event sequence in a historical event database, wherein any one event sequence comprises each event with time context and the occurrence frequency of each event;
for any event sequence, determining an event value parameter value of each event in the event sequence according to the occurrence frequency of each event in the event sequence; determining a sequence recent effectiveness parameter value of the event sequence according to the sequence order of the event sequence in the historical event database, and determining an event recent effectiveness parameter value of each event in the event sequence according to the sequence recent effectiveness parameter value of the event sequence;
for any event, determining the total value of the event value parameter of the event according to the event value parameter value of the event in each event sequence, and determining the total value of the recent event validity of the event according to the recent event validity parameter value of the event in each event sequence;
and determining the hot events from the events according to the total value of the event value parameter and the total value of the recent effectiveness of the events.
A hotspot event determination device, comprising:
the acquisition module is used for acquiring each event sequence in the historical event database, and any one event sequence comprises each event with time context and the occurrence frequency of each event;
the value determining module is used for determining an event value parameter value of each event in the event sequence for any event sequence; the event value parameter value calculation module is also used for determining the total value of the event value parameter of any event according to the event value parameter value of the event in each event sequence;
the recent effectiveness determining module is used for determining a sequence recent effectiveness parameter value of any event sequence and determining an event recent effectiveness parameter value of each event in the event sequence; the system is also used for determining the total value of the event recent validity of any event according to the parameter value of the event recent validity of the event in each event sequence;
and the hot event determining module is used for determining the hot events from the events according to the total value of the event value parameters of the events and the total value of the recent effectiveness of the events.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method as described above when executing the computer program.
A computer storage medium having a computer program stored thereon, wherein the program, when executed by a processor, performs the steps of the method as described above.
Based on the scheme of the embodiment, based on the events with time context in the historical event database and the event sequences of the occurrence times of the events, the event value parameter values of the events in the event sequences are determined, the event value parameter total values of the events are determined according to the event value parameter values, the event near-term effectiveness parameter values of the event sequences are determined, the event near-term effectiveness total values of the events are determined according to the event value parameter total values and the event near-term effectiveness total values of the events, the hot events are mined and determined through the event sequences based on the time sequence characteristics, the limitation that the hot event prediction with the time sequence characteristics cannot be carried out is broken through, and the accuracy and the performance of the hot event prediction are improved.
Drawings
FIG. 1 is a schematic illustration of an operating environment for an embodiment of the present invention;
FIG. 2 is a diagram illustrating the architecture of the terminal/server according to one embodiment;
FIG. 3 is a schematic flow diagram of a method for hot event determination in one embodiment;
FIG. 4 is a diagram of a sequence tree, an inverted index table, and a lookup table for inserting a first event sequence in an example application;
FIG. 5 is a diagram of a sequence tree, an inverted index table, and a lookup table for inserting a second sequence of events in an example application;
FIG. 6 is a diagram of a sequence tree, an inverted index table, and a lookup table for inserting a third event sequence in an example application;
FIG. 7 is a diagram of a sequence tree, an inverted index table, and a lookup table for inserting a fourth event sequence in an example application;
FIG. 8 is a diagram of a sequence tree, an inverted index table, and a lookup table for inserting a fifth event sequence in an example application;
FIG. 9 is a diagram of a sequence tree after compressing frequent sub-sequences in an example application;
FIG. 10 is a diagram of a sequence tree after merging of a sub-sequence branch in an application example;
FIG. 11 is a diagram of a sequence tree after merging branches of a second subsequence in an example application;
FIG. 12 is a diagram of a sequence tree after merging a third subsequence branch in an example application;
FIG. 13 is a diagram of a sequence tree after compressing frequent sub-sequences and merging sub-sequence branches in an application example;
fig. 14 is a schematic structural diagram of a hot spot event determination device in one embodiment.
Detailed Description
To facilitate an understanding of the invention, the invention will now be described more fully with reference to the accompanying drawings. Preferred embodiments of the present invention are shown in the drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "or/and" includes any and all combinations of one or more of the associated listed items.
Fig. 1 shows a schematic diagram of an operating environment in an embodiment of the present invention, as shown in fig. 1, the operating environment relates to a terminal/server 101 and a server 102, and the terminal/server 101 and the server 102 can communicate with each other through a network. The terminal/server 101 may obtain information of various events that have occurred in history from each server 102 and store the information in a historical event database, which may be located on the terminal/server 101 or on a database server external to the terminal/server 101. The terminal/server 101 may acquire each event having a temporal relationship and the number of occurrences of each event from the server 102, or may acquire each event already occurred from the server 102 and then form each event having a temporal relationship and the number of occurrences of each event. The embodiment of the invention relates to a scheme for mining and determining a hot event by a terminal/server 101.
A schematic diagram of a structure of the terminal/server 101 in one embodiment is shown in fig. 2, which includes a processor, a power supply module, a storage medium, a memory and a communication interface connected by a system bus. Wherein the processor is used for providing calculation and control capability and supporting the operation of the whole terminal/server. The storage medium stores an operating system, a database, and a computer application of a hot event determination device that, when executed by a processor, implements a hot event determination method. The memory provides an environment for running a computer application program in the storage medium, and the communication interface is used for network communication. Those skilled in the art will appreciate that the structure shown in fig. 2 is a block diagram of only a portion of the structure associated with the embodiment, and does not constitute a limitation on the terminal/server to which the embodiment is applied, and a specific terminal/server may include more or less components than those shown in the figure, or combine some components, or have a different arrangement of components.
Fig. 3 shows a flowchart of a hot event determining method in an embodiment, and as shown in fig. 3, the hot event determining method in the embodiment includes steps S301 to S304.
Step S301: and acquiring each event sequence in the historical event database, wherein any one event sequence comprises each event with a time context and the occurrence frequency of each event.
An event sequence constitutes a complete information flow, and in an event sequence, more than two events are included, each event may also be referred to as an item in a specific application, and an event includes a specific event name and may also carry a timestamp identifier or an identifier (e.g., an event number) for indicating a time sequence so as to identify a context relationship between events in an event sequence. Taking the event number as an example, it can be set that an event with a larger event number occurs after an event with a smaller event number.
The historical event database may include a plurality of event sequences, and each event sequence may also be sorted based on the sequence of events. In one specific example, the sequence of events may be determined based on the time of occurrence of the first event in the sequences of events.
Step S302: for any event sequence, determining an event value parameter value of each event in the event sequence according to the occurrence frequency of each event in the event sequence; and determining a sequence recent effectiveness parameter value of the event sequence according to the sequence order of the event sequence in the historical event database, and determining an event recent effectiveness parameter value of each event in the event sequence according to the sequence recent effectiveness parameter value of the event sequence.
The event value parameter value represents the value or risk of the event to a certain extent. In one example, the manner of determining the value of the event value parameter of the event in any one event sequence in the event sequence may be: and determining the event value parameter value of each event in the event sequence according to the event value unit value of each event in the event sequence and the occurrence frequency of each event in the event sequence. Wherein, the unit value of the event value can be set by self-definition in combination with actual needs. In one example of application, the value of the event value parameter of an event in the event sequence may be the product of the value of the event value unit of the event and the number of times the event occurs in the event sequence.
The sequence recent effectiveness parameter value of the event sequence represents the recent effectiveness degree of the event sequence to a certain extent. In one example, when determining the value of the sequence near-term validity parameter of the event sequence, the value may be determined according to a time decay factor, the number of event sequences in the historical event database, and the sequence order of the event sequences in the historical event database, so as to obtain a near-term validity value related to time. The time decay factor may be a custom value.
After determining the sequence near future validity parameter value for the sequence of events, the sequence near future validity parameter value may be used as the event near future validity parameter value for each event in the sequence of events.
Step S303: for any event, determining the total value of the event value parameter of the event according to the event value parameter value of the event in each event sequence, and determining the total value of the recent event validity of the event according to the parameter value of the recent event validity of the event in each event sequence.
In one example, when determining the total value of the event value parameter of an event, for any event, the sum of the values of the event value parameter of the event in each event sequence may be used as the total value of the event value parameter of the event. In determining the total event near future validity value of the event, for any event, the sum of the values of the event near future validity parameters of the event in each event sequence may be used as the total event near future validity value of the event.
Step S304: and determining the hot events from the events according to the total value of the event value parameter and the total value of the recent effectiveness of the events.
In one particular example, an event may be determined to be a hotspot event when the event value parameter total value of the event is greater than or equal to the event value threshold and the event recent validity total value of the event is greater than or equal to the recent validity value threshold.
Based on the scheme of the embodiment, based on the events with time context in the historical event database and the event sequences of the occurrence times of the events, the event value parameter values of the events in the event sequences are determined, the event value parameter total values of the events are determined according to the event value parameter values, the event near-term effectiveness parameter values of the event sequences are determined, the event near-term effectiveness total values of the events are determined according to the event value parameter total values and the event near-term effectiveness total values of the events, the hot events are mined and determined through the event sequences based on the time sequence characteristics, the limitation that the hot event prediction with the time sequence characteristics cannot be carried out is broken through, and the accuracy and the performance of the hot event prediction are improved.
In some technical scenarios, two or more event sequences may include two or more events that are the same, and the sequence of the two or more events in the event sequences is the same, in which case, for the purpose of reducing the amount of computation, the two or more events may be considered as a whole. In one embodiment, the sub-sequence of the two or more events, i.e. the sub-sequence containing the at least two events, may be referred to as an event. In this case, the original event in the event (i.e. the sub-sequence) is referred to as a sub-event, i.e. in this case, the event is a sub-sequence including at least two sub-events. Wherein the event value parameter value of such an event (i.e. the sub-sequence) is the sum of the event value parameter values of the sub-events in the sub-sequence.
In one embodiment, the sub-sequence may be a sub-sequence in the historical event database that includes a number of event sequences for the sub-sequence greater than or equal to a minimum support threshold. That is, when the number of event sequences including an entirety including two or more events is greater than or equal to the minimum support threshold, the entirety including two or more events is regarded as a subsequence (or an entirety of events).
In this case, in one example, when the determined hotspot event is a subsequence, a later-in-time sub-event in the subsequence may be determined as the predicted hotspot event to occur, that is, the later-in-time sub-event in the subsequence is predicted as the predicted hotspot event to occur, so that prediction of future hotspot events is simultaneously achieved.
In an application example, after the event sequences in the historical event database are obtained, an event sequence tree, an inverted index table and a lookup table may be further generated. Then, according to the sequence order of each event sequence in the historical event database, the following process can be executed for any one event sequence:
storing information of each event in each event sequence in the sequence tree by taking the event as a node, wherein the information of the event comprises: the node name of the node where the event is located, the father node of the node where the event is located, the child node of the node where the event is located, the event value parameter value of the event and the recent event validity parameter value;
adding the identification of the event sequence and the index information of each event in the event sequence in a reverse index table;
and adding the identifier of the event sequence in a lookup table, and pointing the identifier of the event sequence to the last node of each event in the event sequence in the sequence tree.
Thus, a storage structure based on the sequence tree, the inverted index table, and the lookup table may be used to store key useful information for the sequence of events. Wherein the reverse index table can be used to quickly find the related sequence of a given event, and the lookup table is used to link the sequence tree and the reverse index table, which points to the last tree node of each event sequence in the sequence tree, and the function of which is to quickly retrieve the collection of related event sequences from the sequence tree by the event sequence identification
In one example, for the sub-sequence containing more than two sub-events described above, the sub-sequence may be added to the sequence tree as a tree node. At this time, before adding each event sequence to the sequence tree, each event sequence may be analyzed, and when the number of event sequences in which a certain sub sequence occurs (i.e., the number of event sequences including the sub sequence) is greater than or equal to the minimum support degree threshold, the sub sequence may be added to the sequence tree as a new item (or a new event, a sub sequence event, etc.) as a node. Thereby reducing the number of nodes of the sequence tree to compress the storage space of the sequence tree.
Wherein, in one example, when a first event prior in time in the sequence of events is not a root node of an existing sequence tree, the root node of the first event is created in the sequence tree.
In one example, the following steps may also be included:
and identifying branches with only one leaf node in the sequence tree, and respectively merging and representing the branches with only one leaf node as one tree node.
Therefore, the branches with only one leaf node can be combined into one tree node to be represented in the sequence tree, so that the number of the nodes of the sequence tree can be reduced, and the storage space of the sequence tree can be compressed.
Based on the embodiments described above, the following description is given with reference to a specific application example.
The time sequence characteristics related to timeliness become an important characteristic which needs to be applied in the development of network events, for example, hot events of internet outbreaks in daily life, and the sequence of occurrence of the hot events hides extremely important useful value information. Most data belong to sequence models and have certain continuity, so that a model capable of characterizing time sequence is an important basis for realizing data content understanding. Moreover, for different hot events, the intrinsic values (value, risk value, weight, interestingness, and the like) of the hot events are different, the specific example of the invention combines the time sequence characteristics, evolution trend and frequency characteristics of historical events to detect and determine the hot events, and can predict network hot events which may occur in the future on the basis, thereby achieving the purposes of information recommendation and user tracking.
In this specific application example, first, each event sequence needs to be obtained from a historical event database, where the historical event database is a time-sequence database, and data stored in the database has time sequence. The contents of the historical event database store in one specific application example may be as shown in table 1 below. In table 1 below, an example of what is originally stored in the database is shown. For purposes of brief explanation, only 5 event sequences in the database are shown in table 1.
TABLE 1 time-sequenced historical event database (original)
If the event (item) in table 1, named "shenzhen mountain landslide", is represented by the letter code a, "first survivor is saved" is represented by the letter code B, "victim mortor activity" is represented by the letter code C, "deep case suspect" is represented by the letter code D, and "second world internet meeting" is represented by the letter code a, table 1 can be converted to the following table 2.
TABLE 2
| Sequence of | Event (item): number of occurrences |
| s1 | {A}:3,{B}:6,{C}:2 |
| s2 | {A}:1,{B}:3 |
| s3 | {A}:9,{B}:3,{D}:8,{C}:5 |
| s4 | {B}:4,{C}:2 |
| s5 | {E}:3,{A}:2,{B}:3,{A}:1 |
In table 1 and table 2 above, the sequence represents an event sequence, and an event sequence is a complete information stream. Where s1, s2, s3, s4, s5 are identifiers of the respective event sequences, and s1, s2, s3, s4, s5 may be ordered according to a certain rule, for example, by time (e.g., based on the ordering of the occurrence events of the first event in s1, s2, s3, s4, s 5).
The event (item) is the smallest component unit in the event sequence, and for an event sequence, it is composed of a plurality of events, and the plurality of events are ordered, as shown in the event sequence s1 in table 2, which includes { a, B, C }. Events may be identified by or in conjunction with a timestamp, or may be an identifier (e.g., event number eventid) that indicates chronological order to identify context between events in a sequence of events. Taking the event number eventid as an example, it can be considered that an event with a larger event number eventid occurs after an event with a smaller event number eventid. The above table 2 also includes information on the number of occurrences of each event, and for example, in the event sequence s1 in table 2, the event a occurs 3 times, the event B occurs 6 times, and the event C occurs 2 times.
Based on the above, it can be determined that the historical event database in this example contains a plurality of sequences (i.e., event sequences), each event sequence is composed of a plurality of event events, and the plurality of events in each event sequence are time-ordered, and thus, the historical event database in this example is a sequence database.
After obtaining each event sequence in the historical event database, the value parameter value of each event in each event sequence, that is, the value of each event in each event sequence, can be determined. In order to determine the value of the event value parameter in each event in the event sequence, the unit value of each event (event value unit value) needs to be obtained first. In conjunction with table 2, the unit value (unit value of event value) of each event in one application example is shown in table 3 below:
TABLE 3 event Unit value Table
| Event(s) | A | B | C | D | |
| Unit value | |||||
| 6 | 12 | 1 | 9 | 3 |
As shown in table 3 above, the unit value (event value unit value) corresponding to each event in the time-series historical event database is recorded in the table, and is not related to the event sequence, and once the unit value of one event is determined, the unit value does not change even though the unit value appears in different event sequences, so the unit value can also be called as unit external value, and is an expression form of external value or risk, which represents the unit value (or risk) corresponding to the occurrence of a certain event, and as shown in fig. 3, the unit value of event a occurring once is 6; the unit value of event B occurring once is 12; the unit value of event C, D, E occurring once is 1, 9, and 3, respectively.
Based on the unit value of each event (event value unit value) and the number of times of occurrence of the event in the current event sequence in the event sequence, an event value parameter value of the event in the event sequence can be determined, and the event value parameter value can be specifically the product of the event value parameter value of the event and the number of times of occurrence of the event in the event sequence. As shown in table 2 and table 3, the event value parameter value of event a in the event sequence s1 (the value of event a in the event sequence s1) is: 6 (unit value of event a) × 3 (number of occurrences of event a in the sequence s1 ═ 18). The value of the event value parameter for each of the other events in the sequence of events may be handled in the same manner.
In one example, after obtaining the event value parameter value (value) of each event in each event sequence, the sequence value parameter value of each event sequence may be further determined according to the event value parameter value of each event in each event sequence, and then the total value of the value parameter of the historical event database may be determined according to the sequence value parameter value of each event sequence.
When the sequence value parameter value of the event sequence is determined according to the event value parameter value of each event in the event sequence, the sum of the event value parameter values of each event in the event sequence can be used as the sequence value parameter value of the event sequence. The sequence value parameter value represents the value or risk of the event sequence. Combining table 2 and table 3, if the event sequence s2 includes events a and B, and the event sequence s5 includes events E, A and B, the sequence value parameter values (the value of the sequence s2) of the event sequence s2 are: the value of event a in sequence s2 (event value parameter value) 6 × 1+ the value of event B in sequence s2 (event value parameter value) 12 × 3 ═ 42. Similarly, the sequence value parameter value for the sequence of events s5 (the value of the sequence s 5) is 3 × 3+2 × 6+3 × 12+1 × 6 ═ 63.
When the total value of the value parameter of the historical event database is determined according to the event value parameter values of the event sequences, the sum of the event value parameter values of the event sequences in the historical event database can be used as the total value of the value parameter of the historical event database. As shown in tables 2 and 3, the total value (total value) of the value parameter of the database including sequences s1 to s5 is: 92+42+167+50+63 is 414.
On the other hand, in one example, after obtaining the event value parameter value (value) of each event in each event sequence, it may be determined to obtain an event value parameter total value for each event. For any event, the sum of the event value parameter values of the event in each event sequence can be used as the total value of the event value parameter of the event. With reference to table 2, since the event C occurs in the event sequences s1, s3, and s4, the total value of the event value parameter of the event C is: event value parameter value for event C in sequence s 1+ event value parameter value for event C in sequence s 3+ event value parameter value for event C in sequence s 4.
Subsequently, a sequence near-term validity parameter value for each event sequence is determined, which represents to some extent the near-term validity of the event sequence. In one example, when determining the recent validity parameter value of the event sequence, the recent validity parameter value may be determined according to a time decay factor, the number of event sequences in the historical event database, and the sequence order of the event sequences in the historical event database, so as to obtain a time-dependent valid value for representing the recent validity of the event sequence. The time decay factor may be a custom value.
The determination of the value of the sequence near-term validity parameter for a sequence of events in one specific application example may be performed using the following formula:
wherein S iscurrentRepresenting the number of event sequences in the historical event database, SqThe sequence of the event sequence in the historical event database is represented, delta represents a self-defined time attenuation factor, and the value interval is delta E (0, 1)]。
Assuming that δ is set to 0.1 and the historical event database shown in table 2 includes 10 event sequences in total, the sequence recent validity parameter value of the event sequence s1 is R (s1) ═ 1-0.1(10-1)0.3874, the recent sequence validity parameter value of the event sequence s2 is R (s2) ═ 1-0.1)(10-2)＝0.4305。
After determining the sequence near future validity parameter value for the sequence of events, the sequence near future validity parameter value for the sequence of events may be used as the event near future validity parameter value for each event in the sequence of events.
After determining the event recent validity parameter value of each event in each event sequence, an event recent validity total value of each event may be determined, which may specifically be a sum of the event recent validity parameter values of the event in each event sequence.
After the total value of the event value parameter and the total value of the recent effectiveness of the event of each event are determined, whether the event is a hot event or not can be determined. In one example, when determining a hotspot event from events, the event may be determined to be a hotspot event when the total value of the event value parameter of the event is greater than or equal to an event value threshold (also referred to as a lowest value threshold), and the total value of the event's recent validity is greater than or equal to a recent validity threshold (also referred to as a lowest recent validity threshold). That is, when the total value of the event value parameter of the event is greater than or equal to the event value threshold and the total value of the event recent validity of the event is greater than or equal to the recent validity value threshold, the event may be referred to as a high-value event that is valid in the near future and may be determined to be a hot event. The event value threshold and the recent effective value threshold can be set in a self-defined mode.
In the execution process of the scheme, the method can be further optimized, and for the frequent sub-sequences in the historical event database, the frequent sub-sequences can be integrally used as one event to complete the process.
In the scheme of this embodiment, for sequence x and sequence y, if there is an order mapping, so that each event in x is included in some event in y, it is referred to as x is included in y, and x is a subsequence of y, for example, sequence D- > a is a subsequence of sequence D- > AB- > a.
Recording the number of sequences including the sequence s in the whole sequence set as the support degree of the sequence s, and if there is a sequence s which is a subsequence of a certain sequence of the data set D, the support degree is: support(s) is the number of times sequence s appears in the n sequences of data set D.
In this case, by setting the minimum support threshold min _ support, when the support(s) of a certain sequence s is greater than or equal to the minimum support threshold min _ support, the sequence s may be referred to as a frequent sequence or as a sequence pattern. The effect of the sequence pattern is that, assuming a sequence pattern of < { Shenzhen mountain landslide }, { first survivor rescue } > is obtained (tip brackets indicate that the elements inside it are ordered, and the previous one occurs before the next), it can be considered that if the event { Shenzhen mountain landslide } occurs, then the event { first survivor rescue } is most likely to occur later.
Accordingly, in this specific example scenario, after obtaining the event sequences in the historical event database, the historical event data may be analyzed to determine whether there is a subsequence with a support degree reaching the lowest support degree threshold in the database, and the subsequence may be analyzed as an entire event.
For a subsequence, the value (event value parameter value) of the subsequence in a certain event sequence to which the subsequence belongs is: the sum of the values of the events in the subsequence in the sequence of events may be a sum. As shown in table 2 and table 3, the value of the subsequence BC containing only the event B, C in the event sequence s3 is: the value of event B in sequence s3 was 12 × 3+ the value of event C in sequence s3 was 1 × 5 ═ 41.
After obtaining the value of the sub-sequence in each event sequence to which the sub-sequence belongs (or comprises the sub-sequence), summing the values of the sub-sequence in all event sequences comprising the sub-sequence, thereby obtaining the total value of the sub-sequence in the database, namely the total value of the event value parameter of the sub-sequence.
On the other hand, for a sub-sequence, a recent valid value of the sub-sequence in the event sequence containing the sub-sequence (i.e. the value of the event recent validity parameter of the sub-sequence in the event sequence) may also be calculated, and in a specific example, the recent valid value of the sub-sequence in the event sequence may be equal to the recent valid value of the event sequence (i.e. the value of the sequence recent validity parameter of the event sequence). And summing the recent effective values of the sub-sequence in the event sequences of the sub-sequence, so as to obtain the recent effective value of the sub-sequence in the database (namely the total value of the recent effective values of the events of the sub-sequence).
After determining the total value of each sub-sequence in the database (i.e. the total value of the event value parameter of the sub-sequence) and the recent valid value in the database (i.e. the total value of the event recent validity of the sub-sequence), the sub-sequence can be combined with other time analysis hot events. In one example, when the total value of the sub-sequence in the database is greater than or equal to an event value threshold (also referred to as a lowest value threshold) and the recent significance value of the sub-sequence in the database is greater than or equal to a recent significance value threshold (also referred to as a lowest recent significance threshold), the event is determined to be a hot event, and the sub-sequence is determined to be a recently significant high-value sub-sequence. Meanwhile, the sub-event with the later time in the sub-sequence can be determined as the predicted hotspot event to be generated, namely, the sub-event with the later event in the sub-sequence is predicted as the predicted hotspot event to be generated, so that the prediction of the future hotspot event is realized at the same time. The event value threshold and the recent effective value threshold can be set in a self-defined mode.
In one specific example, an event sequence tree, an inverted index table, and a lookup table may be further generated. Then, according to the sequence order of each event sequence in the historical event database, the following process can be executed for any one event sequence:
storing information of each event in each event sequence in the sequence tree by taking the event as a node, wherein the information of the event comprises: the node name of the node where the event is located, the father node of the node where the event is located, the child node of the node where the event is located, the event value parameter value of the event and the recent event validity parameter value;
adding the identification of the event sequence and the index information of each event in the event sequence in a reverse index table;
and adding the identifier of the event sequence in a lookup table, and pointing the identifier of the event sequence to the last node of each event in the event sequence in the sequence tree.
By taking the schematic diagrams shown in table 2 and table 3 as examples, assuming that the database corresponding to table 2 actually includes 10 event sequences, the schematic diagrams of the sequence tree, the inverted index table, and the lookup table after the first event sequence s1< a, B, C > is inserted are shown in fig. 4, where in fig. 4, a: 18, 0.3874 represents the value of event a in the sequence s1 (event value parameter value), 0.3874 represents the recent valid value of the sequence s1, that is, the recent valid value of event a after insertion into the sequence s 1.
Next, a schematic diagram of the sequence tree, the inverted index table and the lookup table after the second event sequence s2< a, B > is inserted is shown in fig. 5, and in fig. 5, the value and the recent significant value of the node A, B are changed due to the data in the time sequence s2 being superimposed. Similarly, the sequence tree, the inverted index table and the lookup table after the third event sequence s3< a, B, D, C > is inserted are shown in fig. 6, and the sequence tree, the inverted index table and the lookup table after the fourth event sequence s4< B, C > are shown in fig. 7. As shown in fig. 7, when s4< B, C > is inserted, since the existing node of event B is not the root node of the sequence tree, it is necessary to create a root node of event B in the sequence tree. Similarly, the sequence tree, the inverted index table and the lookup table after the fifth event sequence s5< E, A, B, A > are inserted are shown in FIG. 8.
Referring to the initially established sequence tree shown in fig. 8, it can be found that event sequences s1, s2, s3, s5 in the sequence tree have common sub-sequences < a, B >, which are frequent sub-sequences assuming a minimum support threshold of 3 and high-value sub-sequences assuming a minimum value threshold of 150. In this case, the sub-sequence < a, B > may be compressed to save storage space of the sequence tree.
In one example, when a sub-sequence < A, B > is identified as a frequent sub-sequence based on event sequence analysis in the database, a corresponding new entry may be generated in the set and, when each event sequence is inserted, replaced with the corresponding new entry when the sub-sequence < A, B > is involved. Assuming that the sub-sequence < A, B > is replaced by a new item X, a schematic diagram of the sequence tree after compressing the frequent sub-sequences < A, B > is shown in FIG. 9. Comparing fig. 8 and fig. 9, it can be seen that the originally initially constructed sequence tree needs 11 nodes, but after the above-mentioned generation of new items for frequent sub-sequences is performed, only 9 nodes are needed, thereby saving the storage space of the sequence tree.
On the other hand, referring to the initially established sequence tree shown in fig. 8, it can be found that the initially generated sequence tree includes a branch with only one leaf node, and such a branch with only one leaf node occupies more space for storing nodes, and therefore, in an example, such branches may be further merged, that is, the branch with only one leaf node is merged and represented as one tree node, thereby reducing the number of nodes of the sequence tree.
For the initially established sequence tree shown in fig. 8, after identifying the sub-sequence branches of only one leaf node in the sequence tree, assuming that sub-sequence branches < D, C > are merged and denoted as DC, the schematic diagram of the sequence tree after merging sub-sequence branches < D, C > is shown in fig. 10. Similarly, assuming that sub-sequence branch < B, C > is merged and denoted BC, a schematic diagram of the sequence tree after merging sub-sequence branch < B, C > is shown in FIG. 11. Assuming that the sub-sequence branches < E, A, B, A > are merged and then denoted EABA, a schematic diagram of the sequence tree after merging the sub-sequence branches < E, A, B, A > is shown in FIG. 12.
Comparing fig. 8 and fig. 12, it can be seen that the originally initially constructed sequence tree needs 11 nodes, but after the 3 sub-sequence branches are merged, only 6 nodes are needed, thereby saving the storage space of the sequence tree.
In another example, the compressing of the frequent sub-sequences, the compressing of the new entries generated for the frequent sub-sequences, and the compressing of the sub-sequence branches merged for only one leaf node may be performed simultaneously. As for the initially established sequence tree shown in fig. 8, a schematic diagram of a sequence tree after compressing frequent subsequences and merging subsequences branches in an application example is shown in fig. 13, and comparing fig. 8 and fig. 13, it can be seen that the initially established sequence tree originally needs 11 nodes, but after the compression is performed by simultaneously adopting the two compression methods, only 5 nodes are needed, and the storage space of the sequence tree is saved to the maximum extent.
Based on the same idea as the method, an example also provides a hot event determination device. Fig. 14 shows a schematic structural diagram of a hot spot event determining apparatus in one example. As shown in fig. 14, the hot event determination device in this example includes: an acquisition module 1401, a value determination module 1402, a recent effectiveness determination module 1403, and a hotspot event determination module 1404.
The acquiring module 1401 is configured to acquire each event sequence in the historical event database, where any event sequence includes each event having a time context and occurrence frequency of each event;
an event sequence constitutes a complete information flow, and in an event sequence, more than two events are included, each event may also be referred to as an item in a specific application, and an event includes a specific event name and may also carry a timestamp identifier or an identifier (e.g., an event number) for indicating a time sequence so as to identify a context relationship between events in an event sequence. Taking the event number as an example, it can be set that an event with a larger event number occurs after an event with a smaller event number.
The historical event database may include a plurality of event sequences, and each event sequence may also be sorted based on the sequence of events. In one specific example, the sequence of events may be determined based on the time of occurrence of the first event in the sequences of events.
A value determining module 1402, configured to determine, for any event sequence, an event value parameter value of each event in the event sequence according to the occurrence frequency of each event in the event sequence; and the method is also used for determining the total value of the event value parameter of any event according to the event value parameter value of the event in each event sequence.
The event value parameter value represents the value or risk of the event to a certain extent. In one example, the manner of determining the event value parameter value of the event in any one event sequence may be: and determining the event value parameter value of each event in the event sequence according to the event value unit value of each event in the event sequence and the occurrence frequency of each event in the event sequence. Wherein, the unit value of the event value can be set by self-definition in combination with actual needs. In one example of application, the value of the event value parameter of an event in the event sequence may be the product of the value of the event value unit of the event and the number of times the event occurs in the event sequence.
The recent effectiveness parameter value of the event sequence represents the recent effectiveness degree of the event sequence to a certain extent. In one example, when determining the recent validity parameter value of the event sequence, the recent validity parameter value may be determined according to a time decay factor, the number of event sequences in the historical event database, and the sequence order of the event sequences in the historical event database, so as to obtain a time-dependent valid value. The time decay factor may be a custom value.
After determining the recent validity parameter value for the sequence of events, the recent validity parameter value may be used as the event recent validity parameter value for each event in the sequence of events.
A recent effectiveness determining module 1403, configured to determine, for any event sequence, a recent effectiveness parameter value of the event sequence according to the sequence order of the event sequence in the historical event database, and determine, according to the sequence recent effectiveness parameter value of the event sequence, an event recent effectiveness parameter value of each event in the event sequence; and the system is also used for determining the total event recent validity value of any event according to the event recent validity parameter value of the event in each event sequence.
In one example, when determining the total value of the event value parameter of an event, for any event, the sum of the values of the event value parameter of the event in each event sequence may be used as the total value of the event value parameter of the event. In determining the total event near future validity value of the event, for any event, the sum of the values of the event near future validity parameters of the event in each event sequence may be used as the total event near future validity value of the event.
And a hot event determining module 1404, configured to determine a hot event from each event according to the total value of the event value parameter of each event and the total value of the recent validity of the event.
In one particular example, an event may be determined to be a hotspot event when the event value parameter total value of the event is greater than or equal to the event value threshold and the event recent validity total value of the event is greater than or equal to the recent validity value threshold.
In some technical scenarios, two or more event sequences may include two or more events that are the same, and the sequence of the two or more events in the event sequences is the same, in which case, for the purpose of reducing the amount of computation, the two or more events may be considered as a whole. In one embodiment, the sub-sequence of the two or more events, i.e. the sub-sequence containing the at least two events, may be referred to as an event. In this case, the original event in the event (i.e. the sub-sequence) is referred to as a sub-event, i.e. in this case, the event is a sub-sequence including at least two sub-events. Wherein the event value parameter value of such an event (i.e. the sub-sequence) is the sum of the event value parameter values of the sub-events in the sub-sequence.
In one embodiment, the sub-sequence may be a sub-sequence in the historical event database that includes a number of event sequences for the sub-sequence greater than or equal to a minimum support threshold. That is, when the number of event sequences including an entirety including two or more events is greater than or equal to the minimum support threshold, the entirety including two or more events is regarded as a subsequence (or an entirety of events).
In this case, in one example, when the determined hotspot event is a subsequence, hotspot event determining module 1404 may determine a later-in-time sub-event in the subsequence as the predicted hotspot event to occur, that is, the later-in-time sub-event in the subsequence is predicted as the future hotspot event, thereby simultaneously achieving prediction of future hotspot events.
In one example, as shown in fig. 14, the apparatus may further include:
a sequence tree processing module 1405, configured to generate an event sequence tree, and store, for any event sequence, information of each event in each event sequence in the sequence tree with the event as a node according to a sequence order of each event sequence in the historical event database, where the information of the event includes: the node name of the node where the event is located, the father node of the node where the event is located, the child node of the node where the event is located, the event value parameter value of the event and the recent event validity parameter value;
the reverse index table processing module 1406 is configured to generate a reverse index table, and add, to any event sequence, an identifier of the event sequence and index information of each event in the event sequence in the reverse index table according to a sequence order of each event sequence in the historical event database;
the lookup table processing module 1407 is configured to generate a lookup table, add an identifier of an event sequence to the lookup table according to the sequence order of each event sequence in the historical event database, and point the identifier of the event sequence to the last node of each event in the event sequence in the sequence tree.
Thus, a storage structure based on the sequence tree, the inverted index table, and the lookup table may be used to store key useful information for the sequence of events. The reverse index table can be used to quickly find the relevant sequence of a given event, and the lookup table is used to link the sequence tree and the reverse index table, which points to the last tree node of each event sequence in the sequence tree, and the function of the reverse index table is that the collection of relevant event sequences can be quickly retrieved from the sequence tree through the event sequence identification.
In one example, the sequence tree processing module 1405 also creates a root node of a first event in the sequence tree that is prior in time in the sequence of events when the first event is not a root node of an existing sequence tree.
As shown in fig. 14, the hot event determining apparatus in one example may further include:
and a branch merging module 1408, configured to identify branches with only one leaf node in the sequence tree, and merge and represent each branch with only one leaf node as one tree node.
Based on the examples described above, there is also provided in one embodiment a computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor, when executing the program, implements any one of the hot event determination methods in the embodiments described above.
It will be understood by those skilled in the art that all or part of the processes in the methods of the embodiments described above may be implemented by a computer program, which is stored in a non-volatile computer readable storage medium, and in the embodiments of the present invention, the program may be stored in the storage medium of a computer system and executed by at least one processor in the computer system to implement the processes of the embodiments including the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
Accordingly, in an embodiment, a storage medium is further provided, on which a computer program is stored, wherein the program is executed by a processor to implement any one of the hot spot event determination methods in the above embodiments.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A hot spot event determination method is characterized by comprising the following steps:
acquiring each event sequence in a historical event database, wherein any one event sequence comprises each event with time context and the occurrence frequency of each event;
for any event sequence, determining an event value parameter value of each event in the event sequence according to the occurrence frequency of each event in the event sequence; determining a sequence recent effectiveness parameter value of the event sequence according to the sequence order of the event sequence in the historical event database, and determining an event recent effectiveness parameter value of each event in the event sequence according to the sequence recent effectiveness parameter value of the event sequence;
for any event, determining the total value of the event value parameter of the event according to the event value parameter value of the event in each event sequence, and determining the total value of the recent event validity of the event according to the recent event validity parameter value of the event in each event sequence;
and determining the hot events from the events according to the total value of the event value parameter and the total value of the recent effectiveness of the events.
2. The hotspot event determination method of claim 1, comprising at least one of:
for any event sequence, determining an event value parameter value of each event in the event sequence according to the event value unit value of each event in the event sequence and the occurrence frequency of each event in the event sequence;
and for any event sequence, determining a sequence recent validity parameter value of the event sequence according to the time attenuation factor, the number of the event sequences in the historical event database and the sequence order of the event sequence in the historical event database.
3. The method according to claim 1, wherein an event is a subsequence including at least one sub-event, and when the hot event is a subsequence, a sub-event in the subsequence that is later in time is determined as a predicted hot event that is about to occur.
4. The method for determining hot spot events according to any one of claims 1 to 3, further comprising the following steps after obtaining each event sequence in the historical event database:
generating an event sequence tree, a reverse index table and a lookup table; according to the sequence order of each event sequence in the historical event database, the following processes are executed for any event sequence:
storing information of each event in each event sequence in the sequence tree by taking the event as a node, wherein the information of the event comprises: the node name of the node where the event is located, the father node of the node where the event is located, the child node of the node where the event is located, the event value parameter value of the event and the recent event validity parameter value;
adding the identification of the event sequence and the index information of each event in the event sequence in a reverse index table;
and adding the identifier of the event sequence in a lookup table, and pointing the identifier of the event sequence to the last node of each event in the event sequence in the sequence tree.
5. The method for determining hot spot events according to claim 4, further comprising the steps of: and identifying branches with only one leaf node in the sequence tree, and respectively merging and representing the branches with only one leaf node as one tree node.
6. A hotspot event determination device, comprising:
the acquisition module is used for acquiring each event sequence in the historical event database, and any one event sequence comprises each event with time context and the occurrence frequency of each event;
the value determining module is used for determining the event value parameter value of each event in the event sequence according to the occurrence frequency of each event in the event sequence for any event sequence; the event value parameter value calculation module is also used for determining the total value of the event value parameter of any event according to the event value parameter value of the event in each event sequence;
the recent effectiveness determining module is used for determining a recent effectiveness parameter value of any event sequence according to the sequence order of the event sequence in the historical event database, and determining an event recent effectiveness parameter value of each event in the event sequence according to the sequence recent effectiveness parameter value of the event sequence; the system is also used for determining the total value of the event recent validity of any event according to the parameter value of the event recent validity of the event in each event sequence;
and the hot event determining module is used for determining the hot events from the events according to the total value of the event value parameters of the events and the total value of the recent effectiveness of the events.
7. The apparatus according to claim 6, wherein the event is a sub-sequence comprising at least one sub-event;
and when the hot event is a subsequence, the hot event determining module determines a sub-event in the subsequence after the time as a predicted hot event to be generated.
8. The hotspot event determination device of claim 6 or 7, further comprising:
a sequence tree processing module, configured to generate an event sequence tree, and store, for any event sequence, information of each event in each event sequence in the sequence tree by using the event as a node according to a sequence order of each event sequence in the historical event database, where the information of the event includes: the node name of the node where the event is located, the father node of the node where the event is located, the child node of the node where the event is located, the event value parameter value of the event and the recent event validity parameter value;
the reverse index table processing module is used for generating a reverse index table and adding the identifier of the event sequence and the index information of each event in the event sequence to any event sequence according to the sequence order of each event sequence in the historical event database;
and the lookup table processing module is used for generating a lookup table, adding an identifier of the event sequence to any event sequence according to the sequence order of each event sequence in the historical event database, and pointing the identifier of the event sequence to the last node of each event in the event sequence in the sequence tree.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 5 when executing the computer program.
10. A computer storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710629638.5A CN109766367B (en) | 2017-07-28 | 2017-07-28 | Hot event determination method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710629638.5A CN109766367B (en) | 2017-07-28 | 2017-07-28 | Hot event determination method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109766367A CN109766367A (en) | 2019-05-17 |
| CN109766367B true CN109766367B (en) | 2021-06-08 |
Family
ID=66448657
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710629638.5A Active CN109766367B (en) | 2017-07-28 | 2017-07-28 | Hot event determination method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109766367B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1991002316A1 (en) * | 1989-07-28 | 1991-02-21 | Udo Quilitz | Process for allocating data sets to time values of a consecutive sequence |
| CN101819573A (en) * | 2009-09-15 | 2010-09-01 | 电子科技大学 | Self-adaptive network public opinion identification method |
| CN104598539A (en) * | 2014-12-30 | 2015-05-06 | 中国联合网络通信有限公司广东省分公司 | Internet event hot degree calculation method and terminal |
| CN104598450A (en) * | 2013-10-30 | 2015-05-06 | 北大方正集团有限公司 | Popularity analysis method and system of network public opinion event |
| CN106446179A (en) * | 2016-09-28 | 2017-02-22 | 东软集团股份有限公司 | Hot topic generation method and device |
| CN106528755A (en) * | 2016-10-28 | 2017-03-22 | 东软集团股份有限公司 | Hot topic generation method and device |
| CN107066537A (en) * | 2017-03-06 | 2017-08-18 | 广州神马移动信息科技有限公司 | Hot news generation method, equipment, electronic equipment |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101296128A (en) * | 2007-04-24 | 2008-10-29 | 北京大学 | Method for monitoring abnormal state of internet information |
| CN104008106B (en) * | 2013-02-25 | 2018-07-20 | 腾讯科技（深圳）有限公司 | A kind of method and device obtaining much-talked-about topic |
-
2017
- 2017-07-28 CN CN201710629638.5A patent/CN109766367B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1991002316A1 (en) * | 1989-07-28 | 1991-02-21 | Udo Quilitz | Process for allocating data sets to time values of a consecutive sequence |
| CN101819573A (en) * | 2009-09-15 | 2010-09-01 | 电子科技大学 | Self-adaptive network public opinion identification method |
| CN104598450A (en) * | 2013-10-30 | 2015-05-06 | 北大方正集团有限公司 | Popularity analysis method and system of network public opinion event |
| CN104598539A (en) * | 2014-12-30 | 2015-05-06 | 中国联合网络通信有限公司广东省分公司 | Internet event hot degree calculation method and terminal |
| CN106446179A (en) * | 2016-09-28 | 2017-02-22 | 东软集团股份有限公司 | Hot topic generation method and device |
| CN106528755A (en) * | 2016-10-28 | 2017-03-22 | 东软集团股份有限公司 | Hot topic generation method and device |
| CN107066537A (en) * | 2017-03-06 | 2017-08-18 | 广州神马移动信息科技有限公司 | Hot news generation method, equipment, electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 我国网络舆情热点话题发现研究综述;游丹丹;《现代情报》;20170331;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109766367A (en) | 2019-05-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106874281B (en) | Method and device for realizing database read-write separation | |
| US20170091190A1 (en) | Computer system programmed to identify common subsequences in logs | |
| CN111600746A (en) | Network fault positioning method, device and equipment | |
| CN110134663B (en) | Organization structure data processing method and device and electronic equipment | |
| US10250550B2 (en) | Social message monitoring method and apparatus | |
| CN110674397B (en) | Method, device, equipment and readable medium for training age point prediction model | |
| CN111158999B (en) | Formatting time calculation method and device | |
| CN113407623A (en) | Data processing method and device and server | |
| JP6481387B2 (en) | Related information providing method, related information providing apparatus, and related information providing program | |
| CN109766367B (en) | Hot event determination method and device, computer equipment and storage medium | |
| CN112463795A (en) | Dynamic hash method, device, equipment and storage medium | |
| CN111414527A (en) | Similar item query method and device and storage medium | |
| Helal et al. | Runtime deduction of case ID for unlabeled business process execution events | |
| EP4024296A1 (en) | Information processing program, information processing method, and information processing device | |
| US20230306343A1 (en) | Business process management system and method thereof | |
| CN113901456A (en) | User behavior security prediction method, device, equipment and medium | |
| CN106777981B (en) | Behavior data verification method and device | |
| KR20120101925A (en) | Apparatus for discovering sequential patterns over data stream using dual tree and method thereof | |
| CN114185937B (en) | Big data tracing method and system based on digital finance | |
| CN116304117B (en) | Data processing method, system and storage medium for acquiring text information | |
| CN113220842B (en) | Processing method, device and equipment for maritime affair administration punishment cutting template | |
| CN106649069A (en) | User behavior statistical method and system | |
| CN113220707A (en) | Method and device for combining multiple service index data in real time and computer equipment | |
| CN109101187B (en) | Method and device for reconstructing data | |
| CN117171251A (en) | Data integration method, medium, device and computing 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 |