CN110751168A - Information pushing method and device, computer equipment and storage medium - Google Patents
Information pushing method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110751168A CN110751168A CN201910827221.9A CN201910827221A CN110751168A CN 110751168 A CN110751168 A CN 110751168A CN 201910827221 A CN201910827221 A CN 201910827221A CN 110751168 A CN110751168 A CN 110751168A
- Authority
- CN
- China
- Prior art keywords
- sample
- user
- screening
- classification
- driving
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000012216 screening Methods 0.000 claims abstract description 149
- 238000013145 classification model Methods 0.000 claims abstract description 54
- 230000009193 crawling Effects 0.000 claims abstract description 9
- 239000002245 particle Substances 0.000 claims description 99
- 238000004590 computer program Methods 0.000 claims description 25
- 230000003044 adaptive effect Effects 0.000 claims description 22
- 238000004422 calculation algorithm Methods 0.000 claims description 16
- 238000013507 mapping Methods 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 abstract description 7
- 238000005065 mining Methods 0.000 abstract description 3
- 238000001914 filtration Methods 0.000 description 20
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000006399 behavior Effects 0.000 description 4
- 239000000284 extract Substances 0.000 description 3
- 230000001360 synchronised effect Effects 0.000 description 2
- 235000019640 taste Nutrition 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to the field of big data, in particular to an information pushing method and device, computer equipment and a storage medium. The method comprises the following steps: receiving an information push instruction which is sent by a terminal and carries a user identifier and a screening word; searching the stored history identification for the history identification consistent with the user identification; when the history identification consistent with the user identification is not searched, acquiring the driving data of the user according to the user identification; analyzing the driving data of the user to obtain user travel parameters; acquiring a driving classification model, and inputting user travel parameters into the driving classification model to obtain classification categories and screening coefficients of users; crawling life information from the Internet according to the screening words; and screening the life information according to the classification category and the screening coefficient, and pushing the screened life information to the terminal. By adopting the method, the deep analysis and mining of the driving data of the user can be realized, and the usability of the driving data of the user is improved.
Description
Technical Field
The present application relates to the field of big data technologies, and in particular, to an information pushing method and apparatus, a computer device, and a storage medium.
Background
At present, a user can inquire driving data of the user from a traffic data management center, but the searched driving data is only a simple record of the driving behavior of the user, the provided data is limited, the timeliness and usability of the data are not strong, reference can not be provided for the user, and therefore a large amount of driving data is wasted after being shelved. Therefore, how to carry out deep data analysis and data mining on the existing driving data is an important problem to be faced by the current technical development.
Disclosure of Invention
In view of the foregoing, it is desirable to provide an information push method, an apparatus, a computer device, and a storage medium capable of accurately providing push information for a user.
An information pushing method, the method comprising:
receiving an information push instruction which is sent by a terminal and carries a user identifier and a screening word;
searching the stored history identification for the history identification consistent with the user identification;
when the history identification consistent with the user identification is not searched, obtaining the driving data of the user according to the user identification;
analyzing the driving data of the user to obtain user travel parameters;
acquiring a driving classification model, and inputting the user travel parameters into the driving classification model to obtain classification categories and screening coefficients of the user;
crawling life information from the Internet according to the screening words;
and screening the life information according to the classification category and the screening coefficient, and pushing the screened life information to the terminal.
In one embodiment, the method for constructing the driving classification model includes:
obtaining sample driving data and a screening coefficient of a sample person;
extracting a sample driving moment, a corresponding holiday label and a sample driving path from the sample driving data;
generating sample travel parameters of the sample personnel according to the sample travel time, the holiday labels and the sample travel paths;
and classifying the sample personnel by adopting a particle swarm algorithm based on the sample travel parameters, establishing a corresponding relation between classification categories and the screening coefficients, and training by utilizing the corresponding relation to obtain a driving classification model.
In one embodiment, generating the sample travel parameters of the sample person according to the sample travel time, the holiday label and the sample travel route includes:
generating a night label according to the sample driving time;
classifying the sample driving time according to the holiday label and the night label of the sample driving time;
and generating a sample travel parameter according to the sample travel path and the classified sample travel time.
In one embodiment, classifying the sample persons by using a particle swarm algorithm based on the sample travel parameters includes:
mapping the sample personnel into particle swarms in a multidimensional solution space based on the sample travel parameters;
acquiring the classification number;
randomly generating search particles according to the classification quantity;
randomly generating an initial speed and an initial position of the search particle;
calculating an adaptive value of the search particle, and adjusting the initial speed and the initial position of the search particle according to the adaptive value;
and when the global optimal solution of the particle swarm is determined according to the adaptive value, classifying the particle swarm based on the global optimal solution, and outputting a corresponding category.
In one embodiment, the screening the life information according to the classification category and the screening coefficient, and pushing the screened life information to the terminal includes:
obtaining classification characteristic words according to the classification categories;
judging whether the life information has classification characteristic words or not;
and when judging that the classified characteristic words exist in the life information after the preliminary screening, pushing the life information to the terminal according to the screening coefficient.
In one embodiment, after the life information is filtered according to the classification category and the filtering coefficient, and the filtered life information is pushed to the terminal, the method includes:
receiving a feedback result of the life information sent by the terminal;
adjusting the screening coefficient corresponding to the classification category according to the feedback result;
and correspondingly storing the classification categories, the adjusted screening coefficients and the user identifications.
In one embodiment, after searching the stored history identifiers for the history identifier consistent with the user identifier, the method includes:
when a history identification consistent with the user identification is searched, searching the classification category and the screening coefficient corresponding to the history identification;
and screening the life information according to the searched classification category and the screening coefficient, and pushing the screened life information to the terminal.
An information push apparatus, the apparatus comprising:
the instruction receiving module is used for receiving an information push instruction which is sent by the terminal and carries the user identification and the screening words;
the identification searching module is used for searching the history identification which is consistent with the user identification in the stored history identification;
the driving data acquisition module is used for acquiring the driving data of the user according to the user identification when the history identification consistent with the user identification is not searched;
the travel numerical value extraction module is used for analyzing the user driving data to obtain user travel parameters;
the classification acquisition module is used for acquiring a driving classification model and inputting the user travel parameters into the driving classification model to obtain the classification category and the screening coefficient of the user;
the life information acquisition module is used for crawling life information from the Internet according to the screened words;
and the information screening module is used for screening the life information according to the classification category and the screening coefficient and pushing the screened life information to the terminal.
A computer device comprising a memory storing a computer program and a processor implementing the steps of the above method when executing the computer program.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method.
The information pushing method comprises the steps that a server receives an information pushing instruction which is sent by a terminal and carries a user identifier, the user driving data is obtained according to the user identifier, the user driving data is analyzed to obtain user traveling parameters, a driving classification model is obtained, the user traveling parameters are input into the driving classification model to obtain classification categories and screening coefficients of users, life information is crawled from the Internet according to screening words and phrases, the life information is screened according to the classification categories and the screening coefficients, the screened life information is pushed to the terminal, the driving classification model constructed by sample driving data is used for analyzing the user driving data of the users, accurate analysis on the users can be obtained under the condition that the users do not need to provide a large amount of data, and further pushing information aiming at the users is obtained, the method not only realizes deep analysis and mining of the driving data of the user, but also improves the usability of the driving data of the user.
Drawings
Fig. 1 is a diagram illustrating an application scenario of an information push method according to an embodiment;
FIG. 2 is a flowchart illustrating an information pushing method according to an embodiment;
FIG. 3 is a flow chart illustrating the steps of constructing a vehicle model according to an embodiment;
FIG. 4 is a flowchart illustrating a step of classifying driving data according to another embodiment;
FIG. 5 is a block diagram of an information pushing apparatus according to an embodiment;
FIG. 6 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The information pushing method provided by the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The method comprises the steps that a terminal 102 sends an information push instruction carrying a user identification and a screening word to a server 104, the server 104 receives the information push instruction carrying the user identification and the screening word sent by the terminal 102, searches a history identification consistent with the user identification in stored history identifications, acquires driving data of a user according to the user identification when the history identification consistent with the user identification is not searched, the server 104 analyzes the driving data of the user to obtain a user trip parameter and a driving classification model, inputs the user trip parameter into the driving classification model to obtain a classification category and a screening coefficient of the user, the server 104 crawls life information from the internet according to the screening word, screens the life information according to the classification category and the screening coefficient, and pushes the screened life information to the terminal 102. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable smart devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, an information pushing method is provided, which is described by taking the method as an example applied to the server in fig. 1, and includes the following steps:
The server 104 receives an information push instruction which is sent by the terminal and carries the user identification and the screening word. The information push instruction may be a work code including a user identifier and a filtering word, or a code sequence composed of codes indicating the user identifier and the filtering word. The user identifier and the filter word in the information push instruction can be identified by voice information, text information and the like input by the user at the terminal 102. The terminal 102 may obtain voice information or text information input by the user, and recognize an information push instruction of the target enterprise according to the voice information or the text information. For example, a user may click a voice recognition function in the process of using the query APP, and the terminal 102 obtains voice information input by the user, recognizes a user identifier and a filtering word in the information push instruction, and generates an information push instruction carrying the user identifier and the filtering word.
And step 204, searching the stored history identifications for the history identification consistent with the user identification.
The server 104 searches the stored history identifications for a history identification that is consistent with the user identification. The history identifier is the user identifier of the history user who uses the system for search pushing once, and the history identifier can be stored in the history identifier database. The server compares the user identification with the historical identification for judgment, and when the historical identification is completely the same as the user identification, the server judges that the historical identification is consistent with the user identification; when the history identification is different from the user identification, the server judges that the history identification is inconsistent with the user identification. For example, the history identifiers are "AAA", "AAA 3", and "AAA", respectively, the user identifier is "AAA", the server determines that the history identifier "AAA" and the user identifier "AAA" are consistent, and determines that the history identifiers "AAA", "AAA 3" are all inconsistent with the user identifier "AAA".
And step 206, when the history identification consistent with the user identification is not searched, acquiring the driving data of the user according to the user identification.
When the server 104 does not search the history identification consistent with the user identification, the server 104 acquires the driving data of the user according to the user identification. The server 104 may obtain the user driving data from a user driving database stored in the system according to the user identifier, or may obtain the user driving data stored in the traffic management center from the traffic data management center through the user identifier. The traffic data management center can be a high-speed payment management center or an overhead traffic management center. The user driving data in the high-speed payment management center can comprise the times of high speed of the user in a preset period, a driving path of each time, driving time of high speed up and down and the like; the user driving data in the overhead traffic management center may include the number of times the user gets on or off the overhead in a predetermined period, an overhead vehicle speed limit, a driving path for each time, driving time for getting on or off the overhead, and the like.
And 208, analyzing the driving data of the user to obtain a user trip parameter.
The server 104 extracts the user travel parameters from the user driving data. The user travel parameters are various parameters for summarizing user travel behaviors and can be obtained by analyzing the user driving data. The user travel parameters may include user travel time, user travel mileage, user travel frequency, user holiday travel time, user holiday travel mileage, user holiday travel probability, and the like. For example, the user driving data includes the number of times that the user has got high speed in a predetermined period, a driving route of each time, and driving time of getting high speed up and down, the server obtains the travel frequency of the user according to the number of times that the user has got high speed in the predetermined period, obtains the travel mileage of the user according to the driving route, obtains the user driving time according to the driving time that the user has got high speed up and down, and the server can also confirm the user holiday travel probability and the user holiday travel time according to the date included in the driving time, and calculate the user holiday travel mileage according to the user holiday travel time.
The server 104 obtains a driving classification model based on the sample driving data of the sample personnel. The driving classification model is a classification model for analyzing the driving data of the user, which is obtained based on the sample driving data of the sample personnel. The driving classification model can be a relation model which is constructed by analyzing the driving data of the crowd with different classification categories and has corresponding relation with the labels; or a function model constructed by analyzing the driving data of the crowd with different classification categories; or a classification model obtained by analyzing the driving data of different people.
The server 104 inputs the user travel parameters into the driving classification model to obtain the classification category and the screening coefficient of the user. The driving classification model not only classifies the users according to the driving data of the users, but also can determine the screening coefficients of the users for different life information preferences. The server inputs the user trip parameters into the driving classification model, so that the classification category of the user can be obtained first, and then the corresponding screening coefficient is obtained according to the classification category; the server can also input the user trip parameters into the driving classification model, and meanwhile, the classification category and the screening coefficient of the user are obtained. The filtering coefficient is a degree value of possible preference of the user for the life information. The screening coefficients of different classified users for the same kind of life information are different.
And 212, crawling life information from the Internet according to the screening words.
The server 104 crawls life information from the internet according to the screening words. The server can acquire the website which is open with the life information, and acquire the life information containing the screened words according to the website. The life information is various kinds of information related to life. The life information may be various information related to life, such as travel information, shopping information, news information, and the like, which are distributed on the internet. The server can crawl life information from the internet according to the screening words after receiving the information pushing instruction; the server can also obtain the classification category and the screening coefficient of the user and then crawl the life information from the internet according to the screening words.
And 214, screening the life information according to the classification category and the screening coefficient, and pushing the screened life information to the terminal.
The server 104 filters the life information according to the classification category and the filtering coefficient, and pushes the filtered life information to the terminal. The server can perform secondary screening according to the classification category, sort the secondarily screened life information according to the screening coefficient, and sequentially push the secondarily screened life information to the terminal. The server can also screen the life information according to the screening coefficient and the classification category, sort the screened life information and push the sorted life information to the terminal. The server can also judge the similarity of the life information and the screening words and classification categories, multiplies the similarity by the screening coefficient to obtain a recommended value of the life information, and pushes the life information to the terminal in sequence according to the recommended value.
According to the information pushing method, the driving data of the user is analyzed through the driving classification model constructed by the sample driving data, accurate analysis on the user can be obtained under the condition that the user does not need to provide a large amount of data, and then the pushing information aiming at the user is obtained, so that deep analysis and mining on the driving data of the user are achieved, and the usability of the driving data of the user is improved.
In one embodiment, as shown in fig. 3, the method for constructing the driving classification model includes the following steps:
and step 302, obtaining sample driving data and screening coefficients of the sample personnel.
The server 104 obtains sample driving data and screening coefficients of the sample personnel. The sample traffic data is traffic data of sample persons in a predetermined period. The predetermined period may be 1 month, 1 quarter, 1 year, or the like. The server can obtain the sample driving data of the sample personnel from the sample personnel database, and can also obtain the sample driving data of the sample personnel from the traffic data center according to the sample identification of the sample personnel. The screening coefficient can be set by preference of sample personnel for different types of life information; or may be generated by the system for different categories of life information based on the profession, age, life experience, etc. of the sample person.
And step 304, extracting the sample driving time, the corresponding holiday label and the sample driving path from the sample driving data.
The server 104 extracts a sample driving time and a corresponding holiday label from the sample driving data, and extracts a sample driving path corresponding to the sample driving time from the sample driving data. The sample driving data comprises a plurality of sample driving moments, holiday labels and sample driving paths. Each sample driving time, holiday label and sample driving path represents a driving behavior of the user. The sample driving time comprises a trip date and a trip time of the user, and the holiday label corresponds to the trip date. The holiday label is a label capable of judging whether the driving time of the sample is on holidays or not. When the sample driving time is on holidays, the holiday label can be represented by 'holiday'; when the sample driving time is on a working day, the holiday label may be represented by "worker".
The server 104 generates sample travel parameters of the sample personnel according to the sample travel time, the holiday labels and the sample travel paths. The sample travel parameters are various parameters for summarizing the travel behavior of the sample staff, and may include the travel time of the sample staff, the travel mileage of the sample staff, the travel frequency of the sample staff, the travel time of the sample staff on holidays, the travel mileage of the sample staff on holidays, the travel probability of the sample staff on holidays, and the like.
And 308, classifying the sample personnel by adopting a particle swarm algorithm based on the sample travel parameters, establishing a corresponding relation between classification categories and the screening coefficient, and training by utilizing the corresponding relation to obtain a driving classification model.
The server 104 classifies the sample personnel by adopting a particle swarm algorithm based on the sample travel parameters, and establishes a corresponding relation between classification categories and screening coefficients to obtain a driving classification model. And the server determines the classification number of the sample personnel according to the screening coefficient, and then maps each sample personnel into a sample particle of the multi-dimensional solution space according to each parameter in the sample travel parameters of each sample personnel. Since there are multiple sample personnel, these sample particles constitute a population of particles located in a multidimensional solution space. And the server randomly generates search particles according to the classification number, determines a global optimal solution in the particle swarm by using the search particles, classifies the particle swarm according to the global optimal solution, and outputs the classification category corresponding to each sample person. The server 104 analyzes the sample personnel of each classification category to obtain the classification, establishes the corresponding relation between the classification category and the screening coefficient, and then trains by using the corresponding relation to obtain the driving classification model. The server can learn the corresponding relation by adopting a machine learning algorithm or other analysis algorithms to construct a driving classification model.
In the information pushing method, the server is a driving classification model which is constructed by analyzing the sample driving data of the sample personnel by adopting a particle swarm algorithm, and the classification category is not preset by a user or a system, but is generated according to the sample travel parameters of each sample personnel. Therefore, each classification category is more representative, and the person preference of each sample person can be reflected.
In one embodiment, as shown in fig. 4, classifying the sample persons by using a particle swarm algorithm based on the sample travel parameters includes the following steps:
The server 104 maps the sample people into particle swarms in a multidimensional solution space based on the sample travel parameters. The server sets a D-dimensional solving space according to the quantity D of the parameters in the sample trip parameters, and maps the sample personnel into a sample particle in the D-dimensional solving space according to the sample trip parameters of the sample personnel. When the server maps all the sample travel parameters in the multidimensional solving space, the server obtains a particle swarm, and the arrangement of the particle swarm in the D-dimensional solving space is determined according to the numerical values of the sample travel parameters of all the sample personnel.
The server 104 obtains the number of classifications. The classification number m can be determined by the server according to the screening coefficient, and can also be set systematically.
And 406, randomly generating search particles according to the classification quantity.
At step 408, an initial velocity and an initial position of the search particle are randomly generated.
The server 104 randomly generates an initial velocity and an initial position of the search particle. The initial velocity is the initial moving distance of the particle in the D-dimensional solution space, and the distance between the particle and the optimal solution in the D-dimensional solution space can be determined from the initial position.
And the server calculates the adaptive value of each searched particle according to the fitness function and adjusts the initial speed and the initial position of the searched particle according to the adaptive value. Fitness function of
And
wherein,
an adapted value representing the speed is indicated,
the adapted value representing the position is indicated,
which is indicative of the velocity of the particles,and d is the dimension d of each particle, 1,2, …, m, i, 1,2, …, n.
Adjusting the velocity of each particle
And
is of the formula
Wherein k is the number of iterations,
the optimal value is the historical optimal value searched by the particle at the kth time;
the historical optimal values of all the particles searched at the k time are obtained; w is an inertia weight constant used for balancing the global and local searching capability of the particle swarm algorithm; c. C1、c2Is the acceleration constant, c1Is a weight coefficient that tracks the historical optimum of the particle itself, which represents the knowledge of the particle itself. c. C2Is a weight coefficient for the optimal value of the particle tracking population, which represents the knowledge of the particle to the entire population. r is1、r2Is uniformly distributed [0,1 ]]Random numbers within the interval.
The server 104 obtains the set threshold, and when the obtained adaptive value is greater than the set threshold, the server determines that the search particle corresponding to the adaptive value is a global optimal solution of the particle swarm. And the server classifies the particle swarm according to the determined global optimal solution and outputs the sample personnel corresponding to each type of particles. And the server determines the corresponding classification category according to the sample vehicle data of each type of sample personnel and outputs the corresponding classification category.
According to the information pushing method, the sample personnel are mapped to one particle individual in the particle swarm optimization, so that the influence of other information of the sample personnel on classification categories can be reduced, the classification accuracy is improved, each classification category is representative, and the analysis of a user is accurate.
In one embodiment, generating the sample travel parameters of the sample persons according to the sample driving time, the holiday labels and the sample driving paths includes the following steps: generating a night label according to the sample driving time; classifying the sample driving time according to the holiday label and the night label of the sample driving time; and generating a sample travel parameter according to the sample travel path and the classified sample travel time.
The server 104 generates a night label from the sample driving time. The server judges whether the driving time of the sample is within a preset night time period, for example, the night time period can be 19: 00-05: 30, and when the judgment is yes, the server generates a night label indicating night; when the judgment is no, the server generates a night label referring to the day. The server 104 classifies the sample driving times according to the holiday labels and the night labels of the sample driving times, for example, the sample driving times are classified into four categories, namely holiday night, holiday day, workday night, workday day and the like. The server 104 generates sample travel parameters according to the sample travel paths and the classified sample travel moments. The server can count the vehicle using time, trip mileage, trip times, the proportion of the total vehicle using time and the proportion of the total trip mileage of the sample personnel under each classification, and can also count the line ranking, the trip frequency and the like of the most frequent trips of the user in a preset period.
In some embodiments, the method for filtering the life information according to the classification category, the filtering coefficient and the filtering words and pushing the filtered life information to the terminal includes the following steps: obtaining classification characteristic words according to the classification categories; judging whether the life information has classification characteristic words or not; and when judging that the classified characteristic words exist in the life information, pushing the life information to the terminal according to the screening coefficient.
The server 104 obtains the classification feature words according to the classification categories, and the classification feature words can be obtained by training according to the life information preferred by the sample personnel based on the classification categories of the sample personnel. For example, when the classification category is professional classification, the classification feature word may be a term or name related to the occupation; when the classification category is a taste, the classification feature word may be a term or a name corresponding to various tastes. The server 104 determines whether the classification feature words exist in the life information. When the server 104 judges that the classification feature words exist in the life information, the server 104 sorts the life information according to the screening coefficients corresponding to the classification categories, and pushes the life information with a large screening coefficient value to the terminal 102 preferentially.
In another embodiment, after the life information is filtered according to the classification category, the filtering coefficient and the information pushing instruction and is pushed to the terminal, the method includes the following steps: receiving a feedback result of the life information sent by the terminal; adjusting the screening coefficient corresponding to the classification category according to the feedback result; and correspondingly storing the classification categories, the adjusted screening coefficients and the user identifications.
The server 104 receives a feedback result of the pushed life information sent by the terminal 102, wherein the feedback result can be words such as likes, dislikes and commonalities which represent satisfaction degree, and can also be scores which represent satisfaction degree. The server 104 adjusts the screening coefficient corresponding to the classification category according to the feedback result. When the feedback result is words such as likes indicating satisfaction, the server converts the words into corresponding satisfaction numerical values, and then adjusts the screening coefficient according to the satisfaction numerical values, for example, the satisfaction numerical values are input into a preset adjusting function of the screening coefficient to obtain the adjusted screening coefficient. The server 104 stores the classification category, the adjusted screening coefficient and the user identifier correspondingly.
In the information pushing method, the server receives the feedback result of the pushed life information sent by the user through the terminal, and adjusts the screening coefficient according to the feedback result, so that the accuracy of screening the life information is improved for the specific user.
In one embodiment, after searching the stored history identifiers for the history identifier consistent with the user identifier, the method comprises the following steps: when a history identification consistent with the user identification is searched, searching the classification category and the screening coefficient corresponding to the history identification; and screening the life information according to the screening words, the searched classification types and the screening coefficient, and pushing the screened life information to the terminal.
When the server 104 searches the stored history identifiers for the history identifiers consistent with the user identifiers, the server 104 searches the classification categories and the screening coefficients corresponding to the history identifiers. The server 104 filters the life information according to the filtered words, the searched classification categories and the filtering coefficients, and pushes the filtered life information to the terminal 102.
According to the information pushing method, the classification category of the user is rapidly acquired through the user identification, and the living information screening efficiency is improved.
It should be understood that although the various steps in the flow charts of fig. 2-4 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-4 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 5, there is provided an information pushing apparatus including: the system comprises an instruction receiving module 502, an identification searching module 504, a driving data obtaining module 506, a trip value extracting module 508, a classification obtaining module 510, a life information obtaining module 512 and an information screening module 514, wherein:
the instruction receiving module 502 is configured to receive an information push instruction which is sent by a terminal and carries a user identifier and a filtering word.
And an identifier searching module 504, configured to search the stored history identifiers for history identifiers that are consistent with the user identifier.
And the driving data acquisition module 506 is configured to acquire the driving data of the user according to the user identifier when the history identifier consistent with the user identifier is not searched.
And a trip value extraction module 508, configured to analyze the user driving data to obtain a user trip parameter.
And the classification model module 510 is configured to obtain a driving classification model, and input the user travel parameters into the driving classification model to obtain a classification category and a screening coefficient of the user.
And the life information acquisition module 512 is used for crawling life information from the internet according to the screening words.
And an information screening module 514, configured to screen the life information according to the classification category and the screening coefficient, and push the screened life information to the terminal.
In some embodiments, the classification model obtaining module 510 includes a sample information obtaining unit, a sample information extracting unit, a travel parameter generating unit, and a classification model constructing unit, wherein:
and the sample information acquisition unit is used for acquiring sample driving data and screening coefficients of the sample personnel.
And the sample information extraction unit is used for extracting the sample driving time, the corresponding holiday label and the sample driving path from the sample driving data.
And the travel parameter generating unit is used for generating the sample travel parameters of the sample personnel according to the sample travel time, the holiday labels and the sample travel path.
And the classification model construction unit is used for classifying the sample personnel by adopting a particle swarm algorithm based on the sample travel parameters, establishing a corresponding relation between classification categories and the screening coefficients, and training by utilizing the corresponding relation to obtain a driving classification model.
In another embodiment, the classification model obtaining module 510 includes a night label generating unit, a driving time classifying unit, and a travel parameter generating unit, wherein:
and the night label generating unit is used for generating a night label according to the sample driving time.
And the driving time classification unit is used for classifying the sample driving time according to the holiday label and the night label of the sample driving time.
And the travel parameter generating unit is used for generating sample travel parameters according to the sample travel paths and the classified sample travel moments.
In some embodiments, the classification model obtaining module 510 includes a particle mapping unit, a classification number obtaining unit, a search particle generating unit, a velocity and position random generating unit, an adjustment calculating unit, and a particle classifying unit, wherein:
a particle mapping unit for mapping the sample personnel into particle swarms in a multi-dimensional solution space based on the sample travel parameters.
And a classification number acquisition unit for acquiring the classification number.
And the search particle generation unit is used for randomly generating search particles according to the classification number.
And the speed and position random generation unit is used for randomly generating the initial speed and the initial position of the search particle.
And the adjustment calculation unit is used for calculating an adaptive value of the search particle and adjusting the initial speed and the initial position of the search particle according to the adaptive value.
And the particle classification unit is used for classifying the particle swarm based on the global optimal solution and outputting a corresponding classification category when the global optimal solution of the particle swarm is determined according to the adaptive value.
In some embodiments, the information filtering module 516 includes a feature word obtaining unit, an information judging unit, and an information pushing unit, where:
and the characteristic word acquisition unit is used for acquiring classified characteristic words according to the classification categories.
And the information judgment unit is used for judging whether the classification characteristic words exist in the life information.
And the information pushing unit is used for pushing the life information to the terminal according to the screening coefficient when judging that the classification characteristic words exist in the life information.
In another embodiment, the apparatus further comprises a feedback result receiving module, a screening coefficient adjusting module, and a storage module, wherein:
and the feedback result receiving module is used for receiving the feedback result of the life information sent by the terminal.
And the screening coefficient adjusting module is used for adjusting the screening coefficient corresponding to the classification category according to the feedback result.
And the storage module is used for correspondingly storing the classification categories, the adjusted screening coefficients and the user identifications.
In one embodiment, the apparatus further comprises a lookup module and an information screening and pushing module, wherein:
the searching module is used for searching the classification category and the screening coefficient corresponding to the historical identification when the historical identification consistent with the user identification is searched;
and the information screening and pushing module is used for screening the life information according to the searched classification type and the screening coefficient and pushing the screened life information to the terminal.
For specific limitations of the information pushing apparatus, reference may be made to the above limitations of the information pushing method, which is not described herein again. All or part of the modules in the information pushing device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 6. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer equipment is used for storing sample driving data and screening coefficients of sample personnel, classification categories corresponding to user identifications, the screening coefficients, classification feature words corresponding to the classification categories and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement an information push method.
Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, there is provided a computer device comprising a memory storing a computer program and a processor implementing the following steps when the processor executes the computer program:
receiving an information push instruction which is sent by a terminal and carries a user identifier and a screening word;
searching the stored history identification for the history identification consistent with the user identification;
when the history identification consistent with the user identification is not searched, obtaining the driving data of the user according to the user identification;
analyzing the driving data of the user to obtain user travel parameters;
acquiring a driving classification model, and inputting the user travel parameters into the driving classification model to obtain classification categories and screening coefficients of the user;
crawling life information from the Internet according to the screening words;
and screening the life information according to the classification category and the screening coefficient, and pushing the screened life information to the terminal.
In one embodiment, the processor, when executing the computer program, further performs the steps of the method for constructing a vehicle classification model, to: obtaining sample driving data and a screening coefficient of a sample person; extracting a sample driving moment, a corresponding holiday label and a sample driving path from the sample driving data; generating sample travel parameters of the sample personnel according to the sample travel time, the holiday labels and the sample travel paths; and classifying the sample personnel by adopting a particle swarm algorithm based on the sample travel parameters, establishing a corresponding relation between classification categories and the screening coefficients, and training by utilizing the corresponding relation to obtain a driving classification model.
In one embodiment, the processor, when executing the computer program, further performs the step of generating the sample travel parameters of the sample person according to the sample travel time, the holiday label and the sample travel route, and is configured to: generating a night label according to the sample driving time; classifying the sample driving time according to the holiday label and the night label of the sample driving time; and generating a sample travel parameter according to the sample travel path and the classified sample travel time.
In one embodiment, when the processor executes the computer program to perform the step of classifying the sample person by using a particle swarm algorithm based on the sample travel parameter, the processor is further configured to: mapping the sample personnel into particle swarms in a multidimensional solution space based on the sample travel parameters; acquiring the classification number; randomly generating search particles according to the classification quantity; randomly generating an initial speed and an initial position of the search particle; calculating an adaptive value of the search particle, and adjusting the initial speed and the initial position of the search particle according to the adaptive value; and when the global optimal solution of the particle swarm is determined according to the adaptive value, classifying the particle swarm based on the global optimal solution, and outputting a corresponding classification category.
In one embodiment, when the processor executes the computer program to perform the steps of filtering the life information according to the classification category and the filtering coefficient, and pushing the filtered life information to the terminal, the processor is further configured to: obtaining classification characteristic words according to the classification categories; judging whether the life information has classification characteristic words or not; and when judging that the classified characteristic words exist in the life information, pushing the life information to the terminal according to the screening coefficient.
In one embodiment, after the processor executes the computer program to perform screening on the life information according to the classification category and the screening coefficient, and push the screened life information to the terminal, the processor is further configured to: receiving a feedback result of the life information sent by the terminal; adjusting the screening coefficient corresponding to the classification category according to the feedback result; and correspondingly storing the classification categories, the adjusted screening coefficients and the user identifications.
In one embodiment, the processor, when executing the computer program, is further configured to, after the step of searching for a history identifier that is consistent with the user identifier from among the stored history identifiers is performed: when a history identification consistent with the user identification is searched, searching the classification category and the screening coefficient corresponding to the history identification; and screening the life information according to the searched classification category and the screening coefficient, and pushing the screened life information to the terminal.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
receiving an information push instruction which is sent by a terminal and carries a user identifier and a screening word;
searching the stored history identification for the history identification consistent with the user identification;
when the history identification consistent with the user identification is not searched, obtaining the driving data of the user according to the user identification;
analyzing the driving data of the user to obtain user travel parameters;
acquiring a driving classification model, and inputting the user travel parameters into the driving classification model to obtain classification categories and screening coefficients of the user;
crawling life information from the Internet according to the screening words;
and screening the life information according to the classification category and the screening coefficient, and pushing the screened life information to the terminal.
In one embodiment, the computer program when being executed by the processor performs the steps of the method for constructing a vehicle classification model is further configured to: obtaining sample driving data and a screening coefficient of a sample person; extracting a sample driving moment, a corresponding holiday label and a sample driving path from the sample driving data; generating sample travel parameters of the sample personnel according to the sample travel time, the holiday labels and the sample travel paths; and classifying the sample personnel by adopting a particle swarm algorithm based on the sample travel parameters, establishing a corresponding relation between classification categories and the screening coefficients, and training by utilizing the corresponding relation to obtain a driving classification model.
In one embodiment, the computer program when executed by the processor performs the step of generating the sample travel parameters of the sample person from the sample travel time, the holiday label and the sample travel path is further configured to: generating a night label according to the sample driving time; classifying the sample driving time according to the holiday label and the night label of the sample driving time; and generating a sample travel parameter according to the sample travel path and the classified sample travel time.
In one embodiment, the computer program when executed by the processor, further when implementing the step of classifying the sample person using a particle swarm algorithm based on the sample travel parameters, is configured to: mapping the sample personnel into particle swarms in a multidimensional solution space based on the sample travel parameters; acquiring the classification number; randomly generating search particles according to the classification quantity; randomly generating an initial speed and an initial position of the search particle; calculating an adaptive value of the search particle, and adjusting the initial speed and the initial position of the search particle according to the adaptive value; and when the global optimal solution of the particle swarm is determined according to the adaptive value, classifying the particle swarm based on the global optimal solution, and outputting a corresponding classification category.
In one embodiment, the computer program when executed by the processor performs the steps of filtering the life information according to the classification category and the filtering coefficient, and pushing the filtered life information to the terminal, and is further configured to: obtaining classification characteristic words according to the classification categories; judging whether the life information has classification characteristic words or not; and when judging that the classified characteristic words exist in the life information, pushing the life information to the terminal according to the screening coefficient.
In one embodiment, after the step of filtering the life information according to the classification category and the filtering coefficient and pushing the filtered life information to the terminal, the computer program is further configured to: receiving a feedback result of the pushed life information sent by the terminal; adjusting the screening coefficient corresponding to the classification category according to the feedback result; and correspondingly storing the classification categories, the adjusted screening coefficients and the user identifications.
In one embodiment, the computer program, when executed by the processor, further performs the following steps after the step of searching for a history identifier that is consistent with the user identifier from among the stored history identifiers: when a history identification consistent with the user identification is searched, searching the classification category and the screening coefficient corresponding to the history identification; and screening the life information according to the searched classification category and the screening coefficient, and pushing the screened life information to the terminal.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as 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 application, 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 concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. An information pushing method, the method comprising:
receiving an information push instruction which is sent by a terminal and carries a user identifier and a screening word;
searching the stored history identification for the history identification consistent with the user identification;
when the history identification consistent with the user identification is not searched, obtaining the driving data of the user according to the user identification;
analyzing the driving data of the user to obtain user travel parameters;
acquiring a driving classification model, and inputting the user travel parameters into the driving classification model to obtain classification categories and screening coefficients of the user;
crawling life information from the Internet according to the screening words;
and screening the life information according to the classification category and the screening coefficient, and pushing the screened life information to the terminal.
2. The method according to claim 1, wherein the method for constructing the driving classification model comprises the following steps:
obtaining sample driving data and a screening coefficient of a sample person;
extracting a sample driving moment, a corresponding holiday label and a sample driving path from the sample driving data;
generating sample travel parameters of the sample personnel according to the sample travel time, the holiday labels and the sample travel paths;
and classifying the sample personnel by adopting a particle swarm algorithm based on the sample travel parameters, establishing a corresponding relation between classification categories and the screening coefficients, and training by utilizing the corresponding relation to obtain a driving classification model.
3. The method according to claim 2, wherein the generating of the sample travel parameters of the sample person according to the sample travel time, the holiday label and the sample travel path comprises:
generating a night label according to the sample driving time;
classifying the sample driving time according to the holiday label and the night label of the sample driving time;
and generating a sample travel parameter according to the sample travel path and the classified sample travel time.
4. The method of claim 2, wherein the classifying the sample person using a particle swarm algorithm based on the sample travel parameters comprises:
mapping the sample personnel into particle swarms in a multidimensional solution space based on the sample travel parameters;
acquiring the classification number;
randomly generating search particles according to the classification quantity;
randomly generating an initial speed and an initial position of the search particle;
calculating an adaptive value of the search particle, and adjusting the initial speed and the initial position of the search particle according to the adaptive value;
and when the global optimal solution of the particle swarm is determined according to the adaptive value, classifying the particle swarm based on the global optimal solution, and outputting a corresponding classification category.
5. The method of claim 1, wherein the screening the life information according to the classification category and the screening coefficient, and pushing the screened life information to the terminal comprises:
obtaining classification characteristic words according to the classification categories;
judging whether the life information has classification characteristic words or not;
and when judging that the classified characteristic words exist in the life information, pushing the life information to the terminal according to the screening coefficient.
6. The method of claim 1, wherein after the screening the life information according to the classification category and the screening coefficient and pushing the screened life information to the terminal, the method comprises:
receiving a feedback result of the life information sent by the terminal;
adjusting the screening coefficient corresponding to the classification category according to the feedback result;
and correspondingly storing the classification categories, the adjusted screening coefficients and the user identifications.
7. The method of claim 6, wherein after searching the stored history identifiers for the history identifier that matches the user identifier, the method comprises:
when a history identification consistent with the user identification is searched, searching the classification category and the screening coefficient corresponding to the history identification;
and screening the life information according to the searched classification category and the screening coefficient, and pushing the screened life information to the terminal.
8. An information pushing apparatus, characterized in that the apparatus comprises:
the instruction receiving module is used for receiving an information push instruction which is sent by the terminal and carries the user identification and the screening words;
the identification searching module is used for searching the history identification which is consistent with the user identification in the stored history identification;
the driving data acquisition module is used for acquiring the driving data of the user according to the user identification when the history identification consistent with the user identification is not searched;
the travel numerical value extraction module is used for analyzing the user driving data to obtain user travel parameters;
the classification acquisition module is used for acquiring a driving classification model and inputting the user travel parameters into the driving classification model to obtain the classification category and the screening coefficient of the user;
the life information acquisition module is used for crawling life information from the Internet according to the screened words;
and the information screening module is used for screening the life information according to the classification category and the screening coefficient and pushing the screened life information to the terminal.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910827221.9A CN110751168A (en) | 2019-09-03 | 2019-09-03 | Information pushing method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910827221.9A CN110751168A (en) | 2019-09-03 | 2019-09-03 | Information pushing method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110751168A true CN110751168A (en) | 2020-02-04 |
Family
ID=69276009
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910827221.9A Pending CN110751168A (en) | 2019-09-03 | 2019-09-03 | Information pushing method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110751168A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113780333A (en) * | 2021-06-22 | 2021-12-10 | 北京京东拓先科技有限公司 | User group classification method and device |
| CN114757724A (en) * | 2022-06-14 | 2022-07-15 | 湖南三湘银行股份有限公司 | Precise information pushing system and method based on genetic algorithm |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107798066A (en) * | 2017-09-25 | 2018-03-13 | 北京小度信息科技有限公司 | A kind of search term method for pushing, device and terminal |
| WO2019019642A1 (en) * | 2017-07-24 | 2019-01-31 | 深圳壹账通智能科技有限公司 | Application information pushing method and apparatus, and computer device and storage medium |
| CN109767264A (en) * | 2018-12-20 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Product data method for pushing, device, computer equipment and storage medium |
| CN110162719A (en) * | 2019-05-27 | 2019-08-23 | 广州小鹏汽车科技有限公司 | Content delivery method, device, storage medium and computer equipment, vehicle |
-
2019
- 2019-09-03 CN CN201910827221.9A patent/CN110751168A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019019642A1 (en) * | 2017-07-24 | 2019-01-31 | 深圳壹账通智能科技有限公司 | Application information pushing method and apparatus, and computer device and storage medium |
| CN107798066A (en) * | 2017-09-25 | 2018-03-13 | 北京小度信息科技有限公司 | A kind of search term method for pushing, device and terminal |
| CN109767264A (en) * | 2018-12-20 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Product data method for pushing, device, computer equipment and storage medium |
| CN110162719A (en) * | 2019-05-27 | 2019-08-23 | 广州小鹏汽车科技有限公司 | Content delivery method, device, storage medium and computer equipment, vehicle |
Non-Patent Citations (1)
| Title |
|---|
| 张梅军 等著: "《EEMD方法及其在机械故障诊断中的应用》", 北京：国防工业出版社, pages: 123 - 124 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113780333A (en) * | 2021-06-22 | 2021-12-10 | 北京京东拓先科技有限公司 | User group classification method and device |
| CN114757724A (en) * | 2022-06-14 | 2022-07-15 | 湖南三湘银行股份有限公司 | Precise information pushing system and method based on genetic algorithm |
| CN114757724B (en) * | 2022-06-14 | 2022-09-20 | 湖南三湘银行股份有限公司 | Precise information pushing system and method based on genetic algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11170262B2 (en) | Training system, training device, method for training, training data creation device, training data creation method, terminal device, and threshold value changing device | |
| CN107862022B (en) | Culture resource recommendation system | |
| US7930262B2 (en) | System and method for the longitudinal analysis of education outcomes using cohort life cycles, cluster analytics-based cohort analysis, and probabilistic data schemas | |
| CN110163647B (en) | Data processing method and device | |
| CN108230007B (en) | User intention identification method and device, electronic equipment and storage medium | |
| CN101322125B (en) | Improving ranking results using multiple nested ranking | |
| CN110532451A (en) | Search method and device for policy text, storage medium, electronic device | |
| CN111444344B (en) | Entity classification method, entity classification device, computer equipment and storage medium | |
| CN110458324B (en) | Method and device for calculating risk probability and computer equipment | |
| CN108509424B (en) | System information processing method, apparatus, computer device and storage medium | |
| US20160086135A1 (en) | Evaluation apparatus, evaluation method and evaluation system for evaluating evaluation target person | |
| CN105354198B (en) | A kind of data processing method and device | |
| CN112632405A (en) | Recommendation method, device, equipment and storage medium | |
| KR20170131924A (en) | Method, apparatus and computer program for searching image | |
| CN116628339A (en) | Educational resource recommendation method and system based on artificial intelligence | |
| CN113420018A (en) | User behavior data analysis method, device, equipment and storage medium | |
| CN110781204A (en) | Identification information determination method, device, equipment and storage medium of target object | |
| CN110046889A (en) | A kind of detection method, device and the server of abnormal behaviour main body | |
| CN114187036A (en) | Internet advertisement intelligent recommendation management system based on behavior characteristic recognition | |
| CN114881712B (en) | Intelligent advertisement putting method, device, equipment and storage medium | |
| CN110751168A (en) | Information pushing method and device, computer equipment and storage medium | |
| CN110389963B (en) | Channel effect identification method, device, equipment and storage medium based on big data | |
| CN114693409A (en) | Product matching method, device, computer equipment, storage medium and program product | |
| CN114860941A (en) | Industry data management method and system based on data brain | |
| CN117314593B (en) | Insurance item pushing method and system based on user behavior analysis |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200204 |