CN113590933B - Flight pushing method, system and electronic equipment - Google Patents
Flight pushing method, system and electronic equipment Download PDFInfo
- Publication number
- CN113590933B CN113590933B CN202110632910.1A CN202110632910A CN113590933B CN 113590933 B CN113590933 B CN 113590933B CN 202110632910 A CN202110632910 A CN 202110632910A CN 113590933 B CN113590933 B CN 113590933B
- Authority
- CN
- China
- Prior art keywords
- flight
- data
- user behavior
- pushing
- pushed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000005065 mining Methods 0.000 claims abstract description 67
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 29
- 230000010006 flight Effects 0.000 claims abstract description 29
- 230000006399 behavior Effects 0.000 claims description 76
- 230000004927 fusion Effects 0.000 claims description 34
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000000694 effects Effects 0.000 abstract description 8
- 230000009286 beneficial effect Effects 0.000 description 10
- 230000009193 crawling Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000007499 fusion processing Methods 0.000 description 3
- 238000013139 quantization Methods 0.000 description 3
- 238000009960 carding Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000001364 causal effect Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/26—Visual data mining; Browsing structured data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a flight pushing method, a flight pushing system and electronic equipment, and relates to the field of aviation. The method comprises the following steps: acquiring all user behavior data and all flight data of flights to be pushed; setting a flight decision requirement according to the flight to be pushed; mining association rules of user behavior data and the flight decision requirement according to a preset mining algorithm; and acquiring the flight to be pushed associated with the target user behavior data through the association rule, and pushing the flight to be pushed to the target user. And according to the association rule, targeted pushing is conducted to the target user, and potential demands of the user can be associated through user behavior data and flight decision demands, so that mining precision is improved, and pushing is more accurate. And preferential flight pushing is carried out according to potential requirements in the user behavior data, benign connection with the user is established, the pushing effect is good, and the customer dislike cannot be caused.
Description
Technical Field
The invention relates to the field of aviation, in particular to a flight pushing method, a flight pushing system and electronic equipment.
Background
With the rapid development of passenger aviation, aircraft have become a choice for many people to go out. To increase the boarding rate of flights, airlines typically attract customers to purchase tickets for a particular flight in a discounted or other form of activity. Although airlines have discounted the tickets for a flight, most of the time, the flight still has a stock ticket that is not sold.
At present, when the air ticket of each flight is purchased on a ticket purchasing website according to a travel plan of the user, the user can acquire the discount condition of the air ticket after actively searching when the discount inventory air ticket exists on the flight. Therefore, the user cannot timely learn which flight has the discounted air ticket, and the airline company pushes the air ticket to the client according to the discount information of each flight, but the push matching rate is often poor and is shielded by the client as the advertisement marketing information, so that the airline company does not improve the boarding rate of the flight, and other popularization of the airline company is influenced.
Disclosure of Invention
The invention aims to solve the technical problem of providing a flight pushing method, a flight pushing system and electronic equipment aiming at the defects of the prior art.
The technical scheme for solving the technical problems is as follows:
a flight pushing method, comprising:
s1, acquiring all user behavior data and all flight data of flights to be pushed;
s2, setting flight decision requirements according to flights to be pushed;
s3, mining association rules of user behavior data and the flight decision requirement according to a preset mining algorithm;
s4, acquiring the flight to be pushed associated with the target user behavior data through the association rule, and pushing the flight to be pushed to the target user.
The beneficial effects of the invention are as follows: the association rule of the user behavior data and the flight decision requirement is obtained through an mining algorithm, the target user is pushed in a targeted manner according to the association rule, and the potential requirement of the user can be associated through the user behavior data and the flight decision requirement, so that mining precision is improved, and pushing is more accurate. And preferential flight pushing is carried out according to potential requirements in the user behavior data, benign connection with the user is established, the pushing effect is good, and the customer dislike cannot be caused.
Further, the method further comprises the following steps:
s30, calculating an influence factor related to the flight decision requirement from the user behavior data through a preset mining method;
the step S3 specifically comprises the following steps: and mining association rules of the user behavior data and the flight decision requirement according to a preset mining algorithm and combining the influence factors.
The beneficial effects of adopting the further scheme are as follows: by obtaining important association factors, namely influence factors, when a client makes a flight decision, mining calculation of irrelevant data is reduced, mining matching degree is high, and mining precision and efficiency are improved.
Further, the user behavior data includes: multisource data;
the step S30 specifically includes:
carrying out fusion classification on the multi-source data;
establishing an association relation between the multi-source data subjected to fusion classification and the flight decision requirement, and quantifying the association relation through a distance entropy;
performing fusion calculation according to the quantized association relation to obtain the distance entropy of the flight decision requirement and the multi-source data;
and when the distance entropy meets a preset condition, the multi-source data corresponding to the current distance entropy is the influence factor.
The beneficial effects of adopting the further scheme are as follows: according to the scheme, the multi-source data and the decision requirement are subjected to deep association and fusion according to the association degree and the trust degree; based on the process of continuously approaching the distance between the multisource data and the decision requirement in the feature fusion process, the association quantization of the distance entropy is carried out, the stability of fusion promotion by the optimal distance is realized, and the minimum total entropy and the maximum information quantity of the fusion system are achieved.
The traditional data carding method adopts modes such as manual classification, and the relevance and non-logic processing capacity among various data sources exceed manual processing capacity, so that optimal data fusion can be realized through the scheme of fusion classification and deep relevance, and the information quantity is guaranteed to be most reasonable.
Further, the method further comprises the following steps: the distance entropy is calculated by:
wherein, the formula for calculating the distance between the optimal set and other sets is as follows:
wherein the multisource data and the flight decision requirement are in m sets, n knowledge elements exist in each set, O j * The optimal value of the respective set is set, i.e. the optimal value in the j-th set, j=1, 2., m; o (O) ij Information unit values representing the j-th set and the i-th set, i=1, 2., n;
the formula for calculating the distance entropy of the ith set is as follows:
the beneficial effects of adopting the further scheme are as follows: according to the scheme, the multi-source data and the decision requirement are subjected to deep association and fusion according to the association degree and the trust degree through the distance entropy.
Further, the method further comprises the following steps:
carrying out fine granularity division on the influence factors according to the corresponding weight coefficients to obtain the influence factors after weight distribution;
dividing the influence factors into multiple layers according to types to obtain the influence factors of multiple layers.
The beneficial effects of adopting the further scheme are as follows: in the existing scheme, multi-level influence factors are constructed from a large amount of non-granularity and non-level data, and compared with the method for directly mining a large amount of data, the method can improve the support of item sets in association rule mining through multi-level relations.
Further, the method further comprises the following steps: and calculating and obtaining the weight coefficient according to the importance of the influence factor relative to the flight decision requirement.
The beneficial effects of adopting the further scheme are as follows: according to the scheme, the influence factors are divided through the weight coefficients, so that the level and category division is more accurate.
Further, the step S3 specifically includes:
and respectively carrying out association mining on the influence factors of the multiple levels and the flight decision requirement through an Apriori algorithm to obtain multiple levels of association rules.
The beneficial effects of adopting the further scheme are as follows: the existing user behavior data comprises a large amount of ungranular and non-hierarchical data, frequent item sets are obtained through iteration of influence factors processed through multiple layers and fine granularity by using an Apriori algorithm, and item sets which do not meet the minimum support degree are filtered, so that potential association rules can be mined.
Further, the method further comprises the following steps: user behavior data and flight data of flights to be pushed are obtained through a crawler tool,
the crawler tool includes: a concurrent crawler tool of master node and slave node in master-slave mode; the master node is used for maintaining a queue to be crawled of the whole crawler and task allocation work, and the slave node is used for receiving the task delegated by the master node;
each slave node maintains a task queue and a new link queue in real time, and after the slave node completes the task queue, the new link queue of the slave node is merged into a queue to be climbed of the master node;
the master node continues to delegate the links of the queues to be crawled to each slave node, and the slave nodes continue to crawl all new user behavior data and all flight data of flights to be pushed.
The beneficial effects of adopting the further scheme are as follows: because the user behavior data and the flight data are very large in volume, a single-process crawler can hardly meet the requirement of quickly crawling a large amount of data. Through the concurrent data crawling function, user behavior data and flight data can be directly obtained from a large amount of data; the data crawling efficiency is improved.
The other technical scheme for solving the technical problems is as follows:
a flight push system, comprising: the system comprises a multi-source data acquisition module, a configuration module, an excavating module and a pushing module;
the multi-source data acquisition module is used for acquiring all user behavior data and all flight data of flights to be pushed;
the configuration module is used for setting flight decision requirements according to flights to be pushed;
the mining module is used for mining association rules of user behavior data and the flight decision requirement according to a preset mining algorithm;
the pushing module is used for acquiring flights to be pushed associated with the target user behavior data through the association rule and pushing the flights to be pushed to the target user.
The beneficial effects of the invention are as follows: the association rule of the user behavior data and the flight decision requirement is obtained through an mining algorithm, the target user is pushed in a targeted manner according to the association rule, and the potential requirement of the user can be associated through the user behavior data and the flight decision requirement, so that mining precision is improved, and pushing is more accurate. And preferential flight pushing is carried out according to potential requirements in the user behavior data, benign connection with the user is established, the pushing effect is good, and the customer dislike cannot be caused.
The other technical scheme for solving the technical problems is as follows:
an electronic device comprising a memory, a processor and a program stored on the memory and running on the processor, the processor implementing a flight pushing method according to any one of the above aspects when executing the program.
The beneficial effects of the invention are as follows: the association rule of the user behavior data and the flight decision requirement is obtained through an mining algorithm, the target user is pushed in a targeted manner according to the association rule, and the potential requirement of the user can be associated through the user behavior data and the flight decision requirement, so that mining precision is improved, and pushing is more accurate. And preferential flight pushing is carried out according to potential requirements in the user behavior data, benign connection with the user is established, the pushing effect is good, and the customer dislike cannot be caused.
Drawings
Fig. 1 is a schematic flow chart of a flight pushing method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram showing the association of flight decision requirements with the user behavior data according to other embodiments of the present invention;
FIG. 3 is a schematic diagram of a multi-layer relationship of influence factors provided by other embodiments of the present invention;
fig. 4 is a flow chart of a flight pushing method for increasing an impact factor according to another embodiment of the present invention;
FIG. 5 is a flow chart of calculating an influence factor according to other embodiments of the present invention;
fig. 6 is a schematic structural diagram of a flight pushing system according to an embodiment of the present invention.
Detailed Description
The principles and features of the present invention are described below with reference to the drawings, the illustrated embodiments are provided for illustration only and are not intended to limit the scope of the present invention.
As shown in fig. 1, a flight pushing method provided in an embodiment of the present invention includes:
s1, acquiring all user behavior data and all flight data of flights to be pushed; all the user behavior data can be understood as mining the existing user behavior data as much as possible, and the more fully mined association rules are more accurate.
S2, setting flight decision requirements according to flights to be pushed;
s3, mining association rules of user behavior data and the flight decision requirement according to a preset mining algorithm;
it should be noted that, in an embodiment, an impact factor related to the flight decision requirement may be calculated from the user behavior data by a preset mining method; wherein the influencing factors are equivalent to important relevant factors when the client makes a flight decision. The user behavior data includes: multisource data; the association of flight decision requirements with the user behavior data is shown in fig. 2, wherein the multi-source data may include consumption data, web browsing data, query data, travel data, and the like.
Wherein, the process of calculating the influence factor may include: carrying out fusion classification on the multi-source data; in one embodiment, the multi-source data types may be classified using a k-means spatial cluster analysis method.
Establishing an association relation between the multi-source data subjected to fusion classification and the flight decision requirement, and quantifying the association relation through a distance entropy;
performing fusion calculation according to the quantized association relation to obtain the distance entropy of the flight decision requirement and the multi-source data;
and when the distance entropy meets a preset condition, the multi-source data corresponding to the current distance entropy is the influence factor. The preset conditions may include: the total entropy of the fusion system is minimum, and the information content is maximized.
And mining association rules of the user behavior data and the flight decision requirement according to a preset mining algorithm and combining the influence factors. The preset mining algorithm may include: the Apriori classical association rule mining algorithm generates candidate sets based on Apriori properties, and greatly compresses the size of frequent item sets.
In an embodiment, before mining the association rule, the method may further include:
carrying out fine granularity division on the influence factors according to the corresponding weight coefficients to obtain the influence factors after weight distribution;
dividing the influence factors into multiple layers according to types to obtain the influence factors of multiple layers.
In an embodiment, the mining of travel plan behaviors can be established in the angles of time sequences, behavior space patterns and the like through construction in multi-source data type classification, the user behaviors are divided into fine granularity by introducing the travel plan behavior event sequences and the weight values of behavior space pattern parameters, and the first-layer, second-layer and even third-layer types are adopted in the dividing process, so that the granularity of different types is more accurate, and mapping among multi-parameter dimensions can be performed when clustering is performed. The multi-layer relation diagram of the influence factors is shown in fig. 3, and the influence factors can comprise two-layer type division, as shown in fig. 3, or can be more than three layers; the first layer of influence factor related user behavior data may include: consumption data, web browsing data, query data, travel data, and the like; a second layer: the consumption data may include: travel mass consumption, ticket consumption, and the like; the web browsing data may include: air ticket browsing information, scenic spot browsing information, travel attack browsing information and the like; the query data may include: location query information, sight spot query information, geographic query information, and the like; trip data may include ride vehicle travel, and the like.
May further include: third layer: for example, the location query information may include: short-range location queries and long-range location queries, the near and far may be defined by whether there is a route in transit.
May further include: and respectively carrying out association mining on the influence factors of the multiple levels and the flight decision requirement through an Apriori algorithm to obtain multiple levels of association rules.
S4, acquiring the flight to be pushed associated with the target user behavior data through the association rule, and pushing the flight to be pushed to the target user.
The association rule of the user behavior data and the flight decision requirement is obtained through an mining algorithm, the target user is pushed in a targeted manner according to the association rule, and the potential requirement of the user can be associated through the user behavior data and the flight decision requirement, so that mining precision is improved, and pushing is more accurate. And preferential flight pushing is carried out according to potential requirements in the user behavior data, benign connection with the user is established, the pushing effect is good, and the customer dislike cannot be caused.
Preferably, in any of the above embodiments, as shown in fig. 4, the method further includes:
s30, calculating an influence factor related to the flight decision requirement from the user behavior data through a preset mining method;
the step S3 specifically comprises the following steps: and mining association rules of the user behavior data and the flight decision requirement according to a preset mining algorithm and combining the influence factors.
By obtaining important association factors, namely influence factors, when a client makes a flight decision, mining calculation of irrelevant data is reduced, mining matching degree is high, and mining precision and efficiency are improved.
Preferably, in any of the above embodiments, as shown in fig. 5, the user behavior data includes: multisource data;
the step S30 specifically includes:
carrying out fusion classification on the multi-source data;
establishing an association relation between the multi-source data subjected to fusion classification and the flight decision requirement, and quantifying the association relation through a distance entropy;
performing fusion calculation according to the quantized association relation to obtain the distance entropy of the flight decision requirement and the multi-source data;
and when the distance entropy meets a preset condition, the multi-source data corresponding to the current distance entropy is the influence factor.
According to the scheme, the multi-source data and the decision requirement are subjected to deep association and fusion according to the association degree and the trust degree; based on the process of continuously approaching the distance between the multisource data and the decision requirement in the feature fusion process, the association quantization of the distance entropy is carried out, the stability of fusion promotion by the optimal distance is realized, and the minimum total entropy and the maximum information quantity of the fusion system are achieved.
The traditional data carding method adopts modes such as manual classification, and the relevance and non-logic processing capacity among various data sources exceed manual processing capacity, so that optimal data fusion can be realized through the scheme of fusion classification and deep relevance, and the information quantity is guaranteed to be most reasonable.
Preferably, in any of the above embodiments, the method further includes: the distance entropy is calculated by:
wherein, the formula for calculating the distance between the optimal set and other sets is as follows:
wherein the multisource data and the flight decision requirement are in m sets, n knowledge elements exist in each set, O j * The optimal value of each set, i.e., the optimal value in the j-th set, j =1，2...,m；O ij Information unit values representing the j-th set and the i-th set, i=1, 2., n;
the formula for calculating the distance entropy of the ith set is as follows:
in a certain embodiment, the thread data obtained according to the clustering algorithm are represented by knowledge elements, the granularity principle is utilized, the fused multi-source knowledge data is represented by the threads, and the granularity principle is utilized to describe the multi-source knowledge data through the concept, the attribute and the association of the multi-source data and the decision requirement object. Performing knowledge element representation om= (Cm, am, rm, BFm) on a multi-source data object, wherein Cm is a concept and attribute set of the object; am is the extracted keyword set; rm represents associations and mappings with other data sources and decision requirements; BFm the trust level of the data, and the optional multi-source data and the decision requirement are deeply associated and fused according to the association level and the trust level, and the relation between the keywords can be causal, sequential, following, concurrent, mutually exclusive and spatial relation.
And (5) associated quantization based on distance entropy. The feature fusion process is based on the fact that multisource data are continuously pulled close, the distance between the requirements is decided, fusion stability is promoted through the optimal distance, and the purposes of minimizing the total entropy of a fusion system and maximizing the information quantity are achieved.
And carrying out association between the multi-source data and the decision requirement according to the distance entropy, wherein the larger the distance entropy is, the lower the similarity between the representation sets is, and optionally, carrying out semantic association and fusion by combining the multi-source data trust attribute and the distance entropy so as to form a multi-source data and decision requirement semantic association graph.
Optionally, before fusion detection is performed, a decision requirement set is constructed, and the decision requirement set is subjected to grading according to the decision requirement.
According to the scheme, the multi-source data and the decision requirement are subjected to deep association and fusion according to the association degree and the trust degree through the distance entropy.
Preferably, in any of the above embodiments, the method further includes:
carrying out fine granularity division on the influence factors according to the corresponding weight coefficients to obtain the influence factors after weight distribution;
dividing the influence factors into multiple layers according to types to obtain the influence factors of multiple layers.
In an embodiment, dividing the influence factor according to the weight coefficient may include: the first layer of influence factor related user behavior data may include: consumption data, web browsing data, query data, travel data, and the like; a second layer: the consumption data may include: travel mass consumption, ticket consumption, and the like; the web browsing data may include: air ticket browsing information, scenic spot browsing information, travel attack browsing information and the like; the query data may include: location query information, sight spot query information, geographic query information, and the like; trip data may include ride vehicle travel, and the like. Respectively performing weight distribution on the first layer data and the second layer data, for example, performing weight distribution on the first layer consumption data, the web browsing data, the query data, the travel data and the like, wherein the distribution result can be: consumption data: 0.1; web browsing data: 0.1; querying data: 0.1; travel data: 0.1; the second layer of query data: location query information: 0.2; scenic spot query information: 0.2; and geographic query information: 0.2; third layer of place query information: short-range location query: 0.01; and remote location query: 0.4. the weight coefficient can be set according to the importance of the influence factor relative to the flight decision requirement;
in an embodiment, when the weight coefficient score meets a certain condition through combination of multiple layers and different types of influence factors, the matching degree of the travel demands of the clients making the same kind of behaviors and the flight decision demands corresponding to the association rules is considered to be very high, and corresponding flights can be pushed to the clients. The certain condition can be that which action operations are performed by the user before the user selects the flight according to the historical consumption information of the user, the set of the action operations can be used as a necessary condition for the user to perform when selecting the flight, weight information is set for each action operation according to the necessary degree, and a weight score is calculated. For example, each time the user makes a type a operation before selecting flight H, then a1, a2 operation under type a, B type operation, B1 operation under type B, C2 operation under type C, so the user selects flight H, the necessary action operations include: A. b, C, a1, a2, b1 and c2, the respective operations calculate the final score from the respective weight information.
In the existing scheme, multi-level influence factors are constructed from a large amount of non-granularity and non-level data, and compared with the method for directly mining a large amount of data, the method can improve the support of item sets in association rule mining through multi-level relations.
Preferably, in any of the above embodiments, the method further includes: and calculating and obtaining the weight coefficient according to the importance of the influence factor relative to the flight decision requirement.
According to the scheme, the influence factors are divided through the weight coefficients, so that the level and category division is more accurate.
Preferably, in any of the foregoing embodiments, the S3 specifically includes:
and respectively carrying out association mining on the influence factors of the multiple levels and the flight decision requirement through an Apriori algorithm to obtain multiple levels of association rules.
The existing user behavior data comprises a large amount of ungranular and non-hierarchical data, frequent item sets are obtained through iteration of influence factors processed through multiple layers and fine granularity by using an Apriori algorithm, and item sets which do not meet the minimum support degree are filtered, so that potential association rules can be mined.
Preferably, in any of the above embodiments, the method further includes: user behavior data and flight data of flights to be pushed are obtained through a crawler tool,
the crawler tool includes: a concurrent crawler tool of master node and slave node in master-slave mode; the master node is used for maintaining a queue to be crawled of the whole crawler and task allocation work, and the slave node is used for receiving the task delegated by the master node;
each slave node maintains a task queue and a new link queue in real time, and after the slave node completes the task queue, the new link queue of the slave node is merged into a queue to be climbed of the master node;
the master node continues to delegate the links of the queues to be crawled to each slave node, and the slave nodes continue to crawl all new user behavior data and all flight data of flights to be pushed.
Because the user behavior data and the flight data are very large in volume, a single-process crawler can hardly meet the requirement of quickly crawling a large amount of data. Through the concurrent data crawling function, user behavior data and flight data can be directly obtained from a large amount of data; the data crawling efficiency is improved.
In one embodiment, as shown in fig. 6, a flight pushing system includes: a multi-source data acquisition module 11, a configuration module 12, an excavating module 13 and a pushing module 14;
the multi-source data acquisition module 11 is used for acquiring all user behavior data and all flight data of flights to be pushed;
the configuration module 12 is configured to set flight decision requirements according to flights to be pushed;
the mining module 13 is configured to mine association rules of the user behavior data and the flight decision requirement according to a preset mining algorithm;
the pushing module 14 is configured to obtain, according to the association rule, a flight to be pushed associated with the target user behavior data, and push the flight to the target user.
The association rule of the user behavior data and the flight decision requirement is obtained through an mining algorithm, the target user is pushed in a targeted manner according to the association rule, and the potential requirement of the user can be associated through the user behavior data and the flight decision requirement, so that mining precision is improved, and pushing is more accurate. And preferential flight pushing is carried out according to potential requirements in the user behavior data, benign connection with the user is established, the pushing effect is good, and the customer dislike cannot be caused.
Preferably, in any of the above embodiments, the method further includes: the influence factor acquisition module is used for calculating influence factors related to the flight decision requirement from the user behavior data through a preset mining method;
the mining module 13 is specifically configured to mine association rules of the user behavior data and the flight decision requirement according to a preset mining algorithm in combination with the influence factors.
Preferably, in any of the above embodiments, the user behavior data includes: multisource data;
the influence factor acquisition module is specifically used for carrying out fusion classification on the multi-source data;
establishing an association relation between the multi-source data subjected to fusion classification and the flight decision requirement, and quantifying the association relation through a distance entropy;
performing fusion calculation according to the quantized association relation to obtain the distance entropy of the flight decision requirement and the multi-source data;
and when the distance entropy meets a preset condition, the multi-source data corresponding to the current distance entropy is the influence factor.
Preferably, in any of the above embodiments, the influence factor obtaining module is further specifically configured to calculate the distance entropy by:
wherein, the formula for calculating the distance between the optimal set and other sets is as follows:
wherein the multisource data and the flight decision requirement are in m sets, n knowledge elements exist in each set, O j * The optimal value of the respective set is set, i.e. the optimal value in the j-th set, j=1, 2., m; o (O) ij Information unit values representing the j-th set and the i-th set, i=1, 2., n;
the formula for calculating the distance entropy of the ith set is as follows:
preferably, in any of the above embodiments, the method further includes: the multi-level division module is used for carrying out fine granularity division on the influence factors according to the corresponding weight coefficients to obtain the influence factors after weight distribution;
dividing the influence factors into multiple layers according to types to obtain the influence factors of multiple layers.
Preferably, in any of the above embodiments, the method further includes: and the weight coefficient calculation module is used for calculating and obtaining the weight coefficient according to the importance of the influence factor relative to the flight decision requirement.
Preferably, in any embodiment of the foregoing, the mining module 13 is specifically configured to perform association mining on the impact factors of multiple levels and the flight decision requirement respectively through Apriori algorithm, so as to obtain multiple levels of association rules.
Preferably, in any of the above embodiments, the method further includes: a data acquisition module for acquiring user behavior data and flight data of flights to be pushed through a crawler tool,
the crawler tool includes: a concurrent crawler tool of master node and slave node in master-slave mode; the master node is used for maintaining a queue to be crawled of the whole crawler and task allocation work, and the slave node is used for receiving the task delegated by the master node;
each slave node maintains a task queue and a new link queue in real time, and after the slave node completes the task queue, the new link queue of the slave node is merged into a queue to be climbed of the master node;
the master node continues to delegate the links of the queues to be crawled to each slave node, and the slave nodes continue to crawl all new user behavior data and all flight data of flights to be pushed.
In one embodiment, an electronic device includes a memory, a processor, and a program stored on the memory and running on the processor, where the processor implements a flight pushing method as in any of the embodiments above when executing the program.
The association rule of the user behavior data and the flight decision requirement is obtained through an mining algorithm, the target user is pushed in a targeted manner according to the association rule, and the potential requirement of the user can be associated through the user behavior data and the flight decision requirement, so that mining precision is improved, and pushing is more accurate. And preferential flight pushing is carried out according to potential requirements in the user behavior data, benign connection with the user is established, the pushing effect is good, and the customer dislike cannot be caused.
It is to be understood that in some embodiments, some or all of the alternatives described in the various embodiments above may be included.
It should be noted that, the foregoing embodiments are product embodiments corresponding to the previous method embodiments, and the description of each optional implementation manner in the product embodiments may refer to the corresponding description in the foregoing method embodiments, which is not repeated herein.
The reader will appreciate that in the description of this specification, a description of terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of elements is merely a logical functional division, and there may be additional divisions of actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment of the present invention.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention is essentially or a part contributing to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-only memory (ROM), a random access memory (RAM, randomAccessMemory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The present invention is not limited to the above embodiments, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the present invention, and these modifications and substitutions are intended to be included in the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (8)
1. A flight pushing method, comprising:
s1, acquiring all user behavior data and all flight data of flights to be pushed;
s2, setting flight decision requirements according to flights to be pushed;
s3, mining association rules of user behavior data and the flight decision requirement according to a preset mining algorithm;
s4, acquiring flights to be pushed associated with the target user behavior data through the association rule, and pushing the flights to be pushed to the target user;
further comprises:
s30, carrying out fusion classification on the multi-source data;
establishing an association relation between the multi-source data subjected to fusion classification and the flight decision requirement, and quantifying the association relation through a distance entropy;
performing fusion calculation according to the quantized association relation to obtain the distance entropy of the flight decision requirement and the multi-source data;
when the distance entropy meets a preset condition, multi-source data corresponding to the current distance entropy is an influence factor;
the step S3 specifically comprises the following steps: and mining association rules of the user behavior data and the flight decision requirement according to a preset mining algorithm and combining the influence factors.
2. A flight pushing method as claimed in claim 1, further comprising: the distance entropy is calculated by:
wherein, the formula for calculating the distance between the optimal set and other sets is as follows:
wherein the multisource data and the flight decision requirement are in m sets, n knowledge elements exist in each set, O j * The optimal value of the respective set is set, i.e. the optimal value in the j-th set, j=1, 2., m; o (O) ij Information element values representing the jth and ith sets, i=1，2...,n；
The formula for calculating the distance entropy of the ith set is as follows:
3. a flight pushing method as claimed in claim 1, further comprising:
carrying out fine granularity division on the influence factors according to the corresponding weight coefficients to obtain the influence factors after weight distribution;
dividing the influence factors into multiple layers according to types to obtain the influence factors of multiple layers.
4. A flight pushing method as claimed in claim 3, further comprising: and calculating and obtaining the weight coefficient according to the importance of the influence factor relative to the flight decision requirement.
5. A flight pushing method according to claim 3 or 4, wherein S3 specifically comprises:
and respectively carrying out association mining on the influence factors of the multiple levels and the flight decision requirement through an Apriori algorithm to obtain multiple levels of association rules.
6. A flight pushing method as claimed in claim 1, further comprising:
user behavior data and flight data of flights to be pushed are obtained through a crawler tool,
the crawler tool includes: a concurrent crawler tool of master node and slave node in master-slave mode; the master node is used for maintaining a queue to be crawled of the whole crawler and task allocation work, and the slave node is used for receiving the task delegated by the master node;
each slave node maintains a task queue and a new link queue in real time, and after the slave node completes the task queue, the new link queue of the slave node is merged into a queue to be climbed of the master node;
the master node continues to delegate the links of the queues to be crawled to each slave node, and the slave nodes continue to crawl all new user behavior data and all flight data of flights to be pushed.
7. A flight pushing system, comprising: the system comprises a multi-source data acquisition module, a configuration module, an excavating module and a pushing module;
the multi-source data acquisition module is used for acquiring all user behavior data and all flight data of flights to be pushed;
the configuration module is used for setting flight decision requirements according to flights to be pushed;
the mining module is used for mining association rules of user behavior data and the flight decision requirement according to a preset mining algorithm;
the pushing module is used for acquiring flights to be pushed associated with the target user behavior data through the association rule and pushing the flights to be pushed to the target user;
the mining module is specifically used for mining association rules of user behavior data and the flight decision requirement according to a preset mining algorithm and combining influence factors;
further comprises: the influence factor acquisition module is used for establishing an association relation between the multi-source data subjected to fusion classification and the flight decision requirement, and quantifying the association relation through distance entropy;
performing fusion calculation according to the quantized association relation to obtain the distance entropy of the flight decision requirement and the multi-source data;
and when the distance entropy meets a preset condition, the multi-source data corresponding to the current distance entropy is the influence factor.
8. An electronic device comprising a memory, a processor and a program stored on the memory and running on the processor, wherein the processor implements a flight pushing method according to any one of claims 1 to 6 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110632910.1A CN113590933B (en) | 2021-06-07 | 2021-06-07 | Flight pushing method, system and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110632910.1A CN113590933B (en) | 2021-06-07 | 2021-06-07 | Flight pushing method, system and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113590933A CN113590933A (en) | 2021-11-02 |
| CN113590933B true CN113590933B (en) | 2023-05-09 |
Family
ID=78243541
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110632910.1A Active CN113590933B (en) | 2021-06-07 | 2021-06-07 | Flight pushing method, system and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113590933B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115759386B (en) * | 2022-11-11 | 2023-07-07 | 中国民航科学技术研究院 | Method and device for predicting flight execution result of civil aviation flight and electronic equipment |
| CN115920420A (en) * | 2023-02-20 | 2023-04-07 | 自贡创赢智能科技有限公司 | Electronic dinosaur of trailing type |
| CN116132528B (en) * | 2023-04-19 | 2023-07-04 | 民航成都信息技术有限公司 | Flight management message pushing method and device and electronic equipment |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040260598A1 (en) * | 2003-06-19 | 2004-12-23 | International Business Machines Corporation | Method and apparatus for notifying vendors of flight plan changes in order to target advertising |
| CN112307341A (en) * | 2020-11-02 | 2021-02-02 | 沈阳民航东北凯亚有限公司 | Flight pushing method and device |
| CN112365062A (en) * | 2020-11-13 | 2021-02-12 | 中国民航大学 | Method and system for mining implicit interactive features and recommending flights of civil aviation passengers |
-
2021
- 2021-06-07 CN CN202110632910.1A patent/CN113590933B/en active Active
Non-Patent Citations (3)
| Title |
|---|
| Di Bin 等."Distributed coordinated task allocation for heterogeneous UAVs based on capacities".《IEEE》.2013,全文. * |
| 丁建立 等."基于关联规则挖掘的航班协同保障数据知识发现研究".《计算机应用与软件》.2016,第33卷(第11期),全文. * |
| 曹卫东."基于改进贝叶斯网络结构学习的航班延误波及分析".《中国博士学位论文全文数据库 基础科学辑》.2010,全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113590933A (en) | 2021-11-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113590933B (en) | Flight pushing method, system and electronic equipment | |
| Chiu et al. | An intelligent market segmentation system using k-means and particle swarm optimization | |
| Huang et al. | Link prediction approach to collaborative filtering | |
| Jing et al. | An entropy weighting k-means algorithm for subspace clustering of high-dimensional sparse data | |
| Liu et al. | A robust model for paper reviewer assignment | |
| Sabau | Survey of clustering based financial fraud detection research | |
| Boyack et al. | Clustering more than two million biomedical publications: Comparing the accuracies of nine text-based similarity approaches | |
| CN102792262B (en) | Use the method and system of claim analysis sequence intellectual property document | |
| US8818996B2 (en) | Method and system for probabilistically quantifying and visualizing relevance between two or more citationally or contextually related data objects | |
| CN109255586B (en) | Online personalized recommendation method for e-government affairs handling | |
| Combe et al. | Combining relations and text in scientific network clustering | |
| US20090299975A1 (en) | System and method for document analysis, processing and information extraction | |
| Lin et al. | Website reorganization using an ant colony system | |
| US20120259855A1 (en) | Document clustering system, document clustering method, and recording medium | |
| CN104268292A (en) | Label word library update method of portrait system | |
| Zhang et al. | Identifying Global Exceptional Patterns in Multi-database Mining. | |
| Jung et al. | Analyzing future communities in growing citation networks | |
| US20160364477A1 (en) | Computerized systems and methods for generating interactive cluster charts of human resources-related documents | |
| CN106547864A (en) | A kind of Personalized search based on query expansion | |
| Kondadadi et al. | A modified fuzzy art for soft document clustering | |
| CN105786810B (en) | The method for building up and device of classification mapping relations | |
| KR101625124B1 (en) | The Technology Valuation Model Using Quantitative Patent Analysis | |
| Wang et al. | Link prediction in heterogeneous collaboration networks | |
| Bueno et al. | Profiling clients in the tourism sector using fuzzy linguistic models based on 2-tuples | |
| Chen et al. | An evolutionary PageRank approach for journal ranking with expert judgements |
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 |