CN117391782A - Advertisement putting method, device, equipment and storage medium thereof - Google Patents
Advertisement putting method, device, equipment and storage medium thereof Download PDFInfo
- Publication number
- CN117391782A CN117391782A CN202311387638.0A CN202311387638A CN117391782A CN 117391782 A CN117391782 A CN 117391782A CN 202311387638 A CN202311387638 A CN 202311387638A CN 117391782 A CN117391782 A CN 117391782A
- Authority
- CN
- China
- Prior art keywords
- user
- target
- behavior data
- real
- data
- 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 38
- 238000012549 training Methods 0.000 claims abstract description 36
- 230000006399 behavior Effects 0.000 claims description 140
- 238000004140 cleaning Methods 0.000 claims description 77
- 239000013598 vector Substances 0.000 claims description 64
- 238000012545 processing Methods 0.000 claims description 57
- 238000004364 calculation method Methods 0.000 claims description 48
- 238000012544 monitoring process Methods 0.000 claims description 27
- 238000013135 deep learning Methods 0.000 claims description 25
- 238000005070 sampling Methods 0.000 claims description 20
- 238000002716 delivery method Methods 0.000 claims description 13
- 238000010606 normalization Methods 0.000 claims description 8
- 238000005457 optimization Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 13
- 238000010586 diagram Methods 0.000 description 8
- 238000013473 artificial intelligence Methods 0.000 description 5
- 238000012896 Statistical algorithm Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 230000003542 behavioural effect Effects 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000010365 information processing Effects 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
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- 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
- G06N20/00—Machine learning
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0277—Online advertisement
-
- 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)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Marketing (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Entrepreneurship & Innovation (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application belongs to the technical field of financial science and technology, is applied to an advertisement putting scene, relates to an advertisement putting method, an advertisement putting device, advertisement putting equipment and advertisement putting storage media, and performs label model training through user historical behavior data, so that label words which more accord with the user behavior data can be trained, the label words can be combined conveniently, and advertisements which are interested in the label words can be put into a target user terminal more accurately. Model prediction and model real-time updating are carried out through the user real-time behavior data, tag words corresponding to the user real-time behavior data can be obtained through prediction, advertisements to be put in can be adjusted in time according to the tag words corresponding to the user real-time behavior data, and the user real-time behavior change condition is accurately combined. When the interest point of the user changes, the advertisement to be put is adjusted in time, the interest change of the user is fully considered, and meanwhile, the model is updated in real time, so that the result after each model prediction can be used for supporting data for the next model prediction.
Description
Technical Field
The application relates to the technical field of financial science and technology, and is applied to advertisement putting scenes, in particular to an advertisement putting method, an advertisement putting device, advertisement putting equipment and a storage medium of the advertisement putting device.
Background
With the rapid development of the internet, various industries seek industry breakthrough points by relying on the internet, and in recent years, the financial industry is expanding online business around the internet. Because the financial industry involves a large amount of traffic and data, the financial products are continuously updated in category as the demand of users for products is continuously increased.
How to realize product advertisement recommendation according to user behavior data is always a core problem of a recommendation system. The user tag is used as an important component of product advertisement recommendation, and the accuracy and the real-time performance of the user tag play a vital role in the performance and the effect of a recommendation system. In the existing user tag calculation model, the traditional user tag calculation method is often used only with some simple statistical algorithms, and the algorithms have some defects: the traditional statistical algorithm can only calculate the approximate range of the label, and has lower precision for the label; under the big data environment, the traditional statistical algorithm needs a large amount of calculation time and calculation resources, and has poor calculation efficiency; the traditional statistical algorithm can only calculate a new label through brand new data, and it is difficult to calculate the label on the real-time behavior data of the user.
Therefore, in advertisement delivery to users, there is also a problem that advertisements to be delivered cannot be adjusted in time by quickly combining with real-time interest changes of users.
Disclosure of Invention
The embodiment of the application aims to provide an advertisement putting method, device and equipment and a storage medium thereof, so as to solve the problem that in the prior art, advertisements to be put on can not be quickly combined with real-time interest changes of users to timely adjust the advertisements to be put on.
In order to solve the above technical problems, the embodiment of the present application provides an advertisement delivery method, which adopts the following technical scheme:
an advertisement delivery method, comprising the steps of:
acquiring user history behavior data in a target user terminal;
inputting the user historical behavior data into a label model to be trained, and performing model training to obtain a label model after training, wherein the label model after training comprises characteristic classification results of the user historical behavior data and label words corresponding to all the characteristic classification results;
monitoring a target user terminal according to a preset real-time monitoring component to obtain user real-time behavior data;
inputting the real-time behavior data of the user into the trained tag model, updating the model in real time, and outputting a feature classification result of predicting the real-time behavior data of the user and a tag word corresponding to the feature classification result through the model;
And putting a target advertisement to the target user terminal according to the tag words, wherein the target advertisement is marked in advance according to the different tag words.
Further, the step of inputting the user history behavior data into a label model to be trained, performing model training, and obtaining a trained label model specifically includes:
taking the historical behavior data of the user as target data;
performing cleaning treatment on the target data through a preset cleaning assembly to obtain the target data after the cleaning treatment, wherein the cleaning treatment comprises pretreatment and deduplication treatment;
inputting the cleaned target data into a preset deep learning component for feature vector calculation to obtain a feature vector calculation result, wherein a dictionary and word vectors corresponding to words in the dictionary are preset in the deep learning component;
performing feature classification on the target data after the cleaning treatment according to the feature vector calculation result and a preset feature classification strategy to obtain a feature classification result;
performing iterative sampling on the feature classification results by adopting a block sampling method to obtain sampling results respectively corresponding to all feature classification results;
And calculating the highest frequency word corresponding to the target feature classification result according to the sampling result and the dictionary, and taking the highest frequency word as the tag word corresponding to the target feature classification result to obtain the trained tag model.
Further, the step of monitoring the target user terminal according to the preset real-time monitoring component to obtain the real-time behavior data of the user specifically includes:
monitoring a target user terminal through the real-time monitoring component to obtain a monitoring result;
analyzing the monitoring result to obtain user operation information;
and acquiring user real-time behavior data from a target log or a target event according to the user operation information.
Further, the step of inputting the user real-time behavior data into the trained tag model to update the model in real time, and predicting a feature classification result to which the user real-time behavior data belongs and a tag word corresponding to the feature classification result through model output specifically includes:
taking the user real-time behavior data as target data;
performing cleaning treatment on the target data through a preset cleaning assembly to obtain the target data after the cleaning treatment, wherein the cleaning treatment comprises pretreatment and deduplication treatment;
Inputting the cleaned target data into a preset deep learning component for feature vector calculation to obtain a feature vector calculation result, wherein a dictionary and word vectors corresponding to words in the dictionary are preset in the deep learning component;
determining a feature classification result to which the target data belongs according to the feature vector calculation result;
adding the target data into the feature classification result according to the feature classification result to which the target data belongs, and updating the model in real time;
and identifying the tag word corresponding to the user real-time behavior data according to the feature classification result of the target data.
Further, the step of performing cleaning processing on the target data through a preset cleaning assembly to obtain the cleaned target data specifically includes:
performing missing value processing on the target data based on a missing value processing sub-component preset in the cleaning component to obtain first-order behavior data;
performing outlier optimization processing on the first-order behavior data according to an outlier processing sub-component preset in the cleaning component to obtain second-order behavior data;
Performing de-duplication processing on the second-order behavior data through a pre-set de-duplication processing sub-assembly in the cleaning assembly to obtain third-order behavior data;
and carrying out unified processing on the numerical format and the data type format of the third-order behavior data through a preset data format unified sub-component in the cleaning component to obtain the target data after the cleaning processing.
Further, the step of inputting the target data after the cleaning process into a preset deep learning component to perform feature vector calculation to obtain a feature vector calculation result specifically includes:
acquiring target data input into the deep learning component;
identifying target words included in the target data according to the dictionary, wherein the target words are words included in the dictionary;
and calculating word vectors and values corresponding to the target data as the feature vector calculation results according to the target words and word vectors corresponding to the words in the dictionary respectively.
Further, the step of classifying the features of the cleaned target data according to the feature vector calculation result and a preset feature classification policy specifically includes:
Normalizing the feature vector calculation result according to a preset normalization processing component to obtain a normalization processing result;
identifying a classification interval preset according to the characteristic classification strategy;
performing interval classification on the normalization processing result according to the classification interval to obtain an interval classification result;
according to a preset statistical component, counting the number of normalized values in the classification result of each interval to obtain a statistical result;
according to the statistical result and a preset rejection strategy, rejecting the interval classification results with the number of normalized values smaller than the preset target number, and counting the classification category number of the interval classification results which are not rejected;
the classified category number is used as the category number of characteristic classification of the target data after the cleaning treatment;
and identifying the target data after the cleaning treatment corresponding to the non-removed interval classification result according to the non-removed interval classification result and the feature vector calculation result, and finishing the feature classification of the target data after the cleaning treatment.
In order to solve the technical problems, the embodiment of the application also provides an advertisement putting device, which adopts the following technical scheme:
An advertising device, comprising:
the user historical behavior data acquisition module is used for acquiring user historical behavior data in the target user terminal;
the label model training module is used for inputting the user historical behavior data into a label model to be trained, and carrying out model training to obtain a label model after training, wherein the label model after training comprises characteristic classification results of the user historical behavior data and label words corresponding to all the characteristic classification results;
the user real-time behavior data acquisition module is used for monitoring the target user terminal according to the preset real-time monitoring component so as to acquire user real-time behavior data;
the label model prediction module is used for inputting the real-time behavior data of the user into the trained label model, updating the model in real time, and predicting a feature classification result to which the real-time behavior data of the user belongs and a label word corresponding to the feature classification result through model output;
and the advertisement putting module is used for putting target advertisements to the target user terminal according to the tag words, wherein the target advertisements are marked in advance according to the tag words.
In order to solve the above technical problems, the embodiments of the present application further provide a computer device, which adopts the following technical schemes:
a computer device comprising a memory having stored therein computer readable instructions which when executed by a processor implement the steps of the advertising method described above.
In order to solve the above technical problems, embodiments of the present application further provide a computer readable storage medium, which adopts the following technical solutions:
a computer readable storage medium having stored thereon computer readable instructions which when executed by a processor implement the steps of the advertisement delivery method as described above.
Compared with the prior art, the embodiment of the application has the following main beneficial effects:
according to the advertisement putting method, through the historical behavior data of the user, the tag model training is carried out, tag words which more accord with the behavior data of the user can be trained, the tag words can be combined conveniently, and the advertisement interesting to the target user terminal can be put more accurately. Model prediction and model real-time updating are carried out through the user real-time behavior data, tag words corresponding to the user real-time behavior data can be obtained through prediction, advertisements to be put in can be adjusted in time according to the tag words corresponding to the user real-time behavior data, and the user real-time behavior change condition is accurately combined. When the interest point of the user changes, the advertisement to be put can be adjusted in time, the interest change of the user is fully considered, and meanwhile, the model is updated in real time, so that the result after each model prediction can be used for data support for the next model prediction.
Drawings
For a clearer description of the solution in the present application, a brief description will be given below of the drawings that are needed in the description of the embodiments of the present application, it being obvious that the drawings in the following description are some embodiments of the present application, and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art.
FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;
FIG. 2 is a flow chart of one embodiment of an advertisement delivery method according to the present application;
FIG. 3 is a flow chart of one embodiment of step 202 of FIG. 2;
FIG. 4 is a flow chart of one embodiment of step 304 shown in FIG. 3;
FIG. 5 is a flow chart of one embodiment of step 203 shown in FIG. 2;
FIG. 6 is a flow chart of one embodiment of step 204 shown in FIG. 2;
FIG. 7 is a schematic diagram illustrating the construction of one embodiment of an advertisement delivery device according to the present application;
FIG. 8 is a schematic diagram of one embodiment of a tag model training module 702 shown in FIG. 7;
FIG. 9 is a schematic diagram of one embodiment of the tag model prediction module 704 of FIG. 7;
FIG. 10 is a schematic structural diagram of one embodiment of a computer device according to the present application.
Detailed Description
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the applications herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having" and any variations thereof in the description and claims of the present application and in the description of the figures above are intended to cover non-exclusive inclusions. The terms first, second and the like in the description and in the claims or in the above-described figures, are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
In order to better understand the technical solutions of the present application, the following description will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings.
As shown in fig. 1, a system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. Various communication client applications, such as a web browser application, a shopping class application, a search class application, an instant messaging tool, a mailbox client, social platform software, etc., may be installed on the terminal devices 101, 102, 103.
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablet computers, electronic book readers, MP3 players (Moving Picture ExpertsGroup Audio Layer III, dynamic video expert compression standard audio plane 3), MP4 (Moving PictureExperts Group Audio Layer IV, dynamic video expert compression standard audio plane 4) players, laptop and desktop computers, and the like.
The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the terminal devices 101, 102, 103.
It should be noted that, the advertisement delivery method provided in the embodiments of the present application is generally executed by a server/terminal device, and accordingly, the advertisement delivery device is generally disposed in the server/terminal device.
It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, a flow chart of one embodiment of an advertising method according to the present application is shown. The advertisement putting method comprises the following steps:
step 201, obtaining user historical behavior data in a target user terminal.
In this embodiment, the user history behavior data may be according to user history operation information, where the user history operation information includes page history browsing amount, history click times, history payment, history subscription information, and the like, and then the user history behavior data and dynamic change conditions of the user history behavior data are obtained from a target history log or a target history event according to the user history operation information.
Step 202, inputting the user historical behavior data into a label model to be trained, and performing model training to obtain a trained label model, wherein the trained label model comprises characteristic classification results of the user historical behavior data and label words corresponding to all characteristic classification results respectively.
With continued reference to FIG. 3, FIG. 3 is a flow chart of one embodiment of step 202 shown in FIG. 2, comprising:
step 301, taking the historical behavior data of the user as target data;
step 302, cleaning the target data through a preset cleaning assembly to obtain cleaned target data, wherein the cleaning process comprises pretreatment and de-duplication treatment;
in this embodiment, the step of performing cleaning processing on the target data by using a preset cleaning component to obtain the cleaned target data specifically includes: performing missing value processing on the target data based on a missing value processing sub-component preset in the cleaning component to obtain first-order behavior data; performing outlier optimization processing on the first-order behavior data according to an outlier processing sub-component preset in the cleaning component to obtain second-order behavior data; performing de-duplication processing on the second-order behavior data through a pre-set de-duplication processing sub-assembly in the cleaning assembly to obtain third-order behavior data; and carrying out unified processing on the numerical format and the data type format of the third-order behavior data through a preset data format unified sub-component in the cleaning component to obtain the target data after the cleaning processing.
Step 303, inputting the cleaned target data into a preset deep learning component for feature vector calculation to obtain a feature vector calculation result, wherein a dictionary and word vectors corresponding to words in the dictionary are preset in the deep learning component;
in this embodiment, the step of inputting the cleaned target data into a preset deep learning component to perform feature vector calculation, and obtaining a feature vector calculation result specifically includes: acquiring target data input into the deep learning component; identifying target words included in the target data according to the dictionary, wherein the target words are words included in the dictionary; and calculating word vectors and values corresponding to the target data as the feature vector calculation results according to the target words and word vectors corresponding to the words in the dictionary respectively.
Step 304, performing feature classification on the target data after the cleaning treatment according to the feature vector calculation result and a preset feature classification strategy to obtain a feature classification result;
with continued reference to FIG. 4, FIG. 4 is a flow chart of one embodiment of step 304 shown in FIG. 3, including:
Step 401, normalizing the feature vector calculation result according to a preset normalization processing component to obtain a normalization processing result;
step 402, identifying a classification interval preset according to the feature classification strategy;
step 403, performing interval classification on the normalized processing result according to the classification interval to obtain an interval classification result;
step 404, counting the number of normalized values in the classification result of each interval according to a preset counting assembly to obtain a counting result;
step 405, according to the statistical result and a preset rejection strategy, rejecting the interval classification results with the number of normalized values smaller than the preset target number, and counting the classification category number of the interval classification results which are not rejected;
step 406, using the classified category number as the category number of the feature classification of the target data after the cleaning process;
step 407, identifying the target data after the cleaning process corresponding to the non-removed interval classification result according to the non-removed interval classification result and the feature vector calculation result, and completing the feature classification of the target data after the cleaning process.
Step 305, performing iterative sampling on the feature classification result by adopting a block sampling method to obtain sampling results respectively corresponding to all feature classification results;
in this embodiment, the sampling iterative mode and the block sampling mode, where the block sampling mode refers to splitting a large-scale data set into a plurality of small subsets, training on each subset, and updating model parameters according to the result of the subset training. For example, a data set is divided into small batches of data, and then training is performed on each small batch of data. The method ensures that the consumption of calculation and storage resources is effectively reduced when the label model is trained, thereby improving the training speed and efficiency.
And 306, calculating the highest frequency word corresponding to the target feature classification result according to the sampling result and the dictionary, and taking the highest frequency word as the tag word corresponding to the target feature classification result to obtain the tag model after training.
Through the historical behavior data of the user, the tag model training is carried out, tag words which more accord with the behavior data of the user can be trained, the tag words can be conveniently combined later, and the advertisements which are interested in the target user terminal can be accurately put in.
And 203, monitoring the target user terminal according to a preset real-time monitoring component to obtain user real-time behavior data.
With continued reference to fig. 5, fig. 5 is a flow chart of one embodiment of step 203 shown in fig. 2, comprising:
step 501, monitoring a target user terminal through the real-time monitoring component to obtain a monitoring result;
step 502, analyzing the monitoring result to obtain user operation information;
and step 503, according to the user operation information, acquiring user real-time behavior data from a target log or a target event.
Specifically, the user operation information includes page browsing amount, clicking times, payment and subscription information, etc., and then user behavior data and dynamic change conditions of the user behavior data are obtained from a target log or a target event according to the user operation information. The target log or the target event refers to a log for recording the real-time behavior data of the user or an event text for recording the real-time behavior data of the user.
And 204, inputting the real-time behavior data of the user into the trained tag model, updating the model in real time, and outputting a feature classification result of predicting the real-time behavior data of the user and a tag word corresponding to the feature classification result through the model.
With continued reference to FIG. 6, FIG. 6 is a flow chart of one embodiment of step 204 shown in FIG. 2, comprising:
step 601, taking the user real-time behavior data as target data;
step 602, performing cleaning treatment on the target data through a preset cleaning assembly to obtain the cleaned target data, wherein the cleaning treatment comprises pretreatment and de-duplication treatment;
in this embodiment, the step of performing cleaning processing on the target data by using a preset cleaning component to obtain the cleaned target data specifically includes: performing missing value processing on the target data based on a missing value processing sub-component preset in the cleaning component to obtain first-order behavior data; performing outlier optimization processing on the first-order behavior data according to an outlier processing sub-component preset in the cleaning component to obtain second-order behavior data; performing de-duplication processing on the second-order behavior data through a pre-set de-duplication processing sub-assembly in the cleaning assembly to obtain third-order behavior data; and carrying out unified processing on the numerical format and the data type format of the third-order behavior data through a preset data format unified sub-component in the cleaning component to obtain the target data after the cleaning processing.
Step 603, inputting the target data after the cleaning processing into a preset deep learning component for feature vector calculation, and obtaining a feature vector calculation result, wherein a dictionary and word vectors corresponding to each word in the dictionary are preset in the deep learning component;
in this embodiment, the step of inputting the cleaned target data into a preset deep learning component to perform feature vector calculation, and obtaining a feature vector calculation result specifically includes: acquiring target data input into the deep learning component; identifying target words included in the target data according to the dictionary, wherein the target words are words included in the dictionary; and calculating word vectors and values corresponding to the target data as the feature vector calculation results according to the target words and word vectors corresponding to the words in the dictionary respectively.
Step 604, determining a feature classification result to which the target data belongs according to the feature vector calculation result;
step 605, adding the target data into the feature classification result according to the feature classification result to which the target data belongs, and updating the model in real time;
Step 606, identifying the tag word corresponding to the user real-time behavior data according to the feature classification result of the target data.
Model prediction and model real-time updating are carried out through the user real-time behavior data, tag words corresponding to the user real-time behavior data can be obtained through prediction, advertisements to be put in can be adjusted in time according to the tag words corresponding to the user real-time behavior data, and the user real-time behavior change condition is accurately combined. When the interest point of the user changes, the advertisement to be put can be adjusted in time, the interest change of the user is fully considered, and meanwhile, the model is updated in real time, so that the result after each model prediction can be used for data support for the next model prediction.
And 205, putting a target advertisement to the target user terminal according to the tag words, wherein the target advertisement is marked in advance according to the difference of the tag words.
According to the method and the device, through the historical behavior data of the user, the tag model training is carried out, tag words which more accord with the behavior data of the user can be trained, the tag words can be combined conveniently, and the advertisements which are interested in the target user terminal can be accurately put in. Model prediction and model real-time updating are carried out through the user real-time behavior data, tag words corresponding to the user real-time behavior data can be obtained through prediction, advertisements to be put in can be adjusted in time according to the tag words corresponding to the user real-time behavior data, and the user real-time behavior change condition is accurately combined. When the interest point of the user changes, the advertisement to be put can be adjusted in time, the interest change of the user is fully considered, and meanwhile, the model is updated in real time, so that the result after each model prediction can be used for data support for the next model prediction.
The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.
Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, large advertising technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.
According to the embodiment of the application, through the historical behavior data of the user, the tag model training is carried out, the tag words which more accord with the behavior data of the user can be trained, the tag words can be combined conveniently, and the advertisements which are interested in the target user terminal can be accurately put in. Model prediction and model real-time updating are carried out through the user real-time behavior data, tag words corresponding to the user real-time behavior data can be obtained through prediction, advertisements to be put in can be adjusted in time according to the tag words corresponding to the user real-time behavior data, and the user real-time behavior change condition is accurately combined. When the interest point of the user changes, the advertisement to be put can be adjusted in time, the interest change of the user is fully considered, and meanwhile, the model is updated in real time, so that the result after each model prediction can be used for data support for the next model prediction.
With further reference to fig. 7, as an implementation of the method shown in fig. 2, the present application provides an embodiment of an advertisement delivery device, where an embodiment of the device corresponds to the embodiment of the method shown in fig. 2, and the device may be specifically applied to various electronic devices.
As shown in fig. 7, an advertisement delivery device 700 according to the present embodiment includes: a user historical behavioral data acquisition module 701, a tag model training module 702, a user real-time behavioral data acquisition module 703, a tag model prediction module 704, and an advertisement delivery module 705. Wherein:
a user historical behavior data acquisition module 701, configured to acquire user historical behavior data in a target user terminal;
the tag model training module 702 is configured to input the user historical behavior data into a tag model to be trained, and perform model training to obtain a trained tag model, where the trained tag model includes feature classification results of the user historical behavior data and tag words corresponding to all feature classification results;
the user real-time behavior data acquisition module 703 is configured to monitor the target user terminal according to a preset real-time monitoring component to obtain user real-time behavior data;
The tag model prediction module 704 is configured to input the real-time behavior data of the user into the trained tag model, update the model in real time, and output a feature classification result to which the predicted real-time behavior data of the user belongs and a tag word corresponding to the feature classification result through the model;
and the advertisement putting module 705 is configured to put a target advertisement to the target user terminal according to the tag word, where the target advertisement has been labeled in advance according to the tag word.
With continued reference to fig. 8, fig. 8 is a schematic diagram of an embodiment of the tag model training module 702 shown in fig. 7, where the tag model training module 702 includes a target data first determining sub-module 801, a data first cleaning sub-module 802, a feature vector first computing sub-module 803, a feature classifying sub-module 804, a data sampling sub-module 805, and a tag word determining sub-module 806. Wherein:
a target data first determining sub-module 801, configured to take the user historical behavior data as target data;
a data first cleaning sub-module 802, configured to perform cleaning processing on the target data through a preset cleaning component, to obtain target data after the cleaning processing, where the cleaning processing includes preprocessing and deduplication processing;
A first feature vector computing sub-module 803, configured to input the cleaned target data into a preset deep learning component for feature vector computation, and obtain a feature vector computation result, where a dictionary and word vectors corresponding to each word in the dictionary are preset in the deep learning component;
the feature classification sub-module 804 is configured to perform feature classification on the cleaned target data according to the feature vector calculation result and a preset feature classification policy, so as to obtain a feature classification result;
the data sampling sub-module 805 is configured to iteratively sample the feature classification result by using a block sampling method, so as to obtain sampling results corresponding to all feature classification results respectively;
and a tag word determining sub-module 806, configured to calculate, according to the sampling result and the dictionary, a highest frequency word corresponding to the target feature classification result, and use the highest frequency word as a tag word corresponding to the target feature classification result, to obtain the trained tag model.
With continued reference to fig. 9, fig. 9 is a schematic structural diagram of an embodiment of the tag model prediction module 704 shown in fig. 7, where the tag model prediction module 704 includes a target data second determination sub-module 901, a data second cleaning sub-module 902, a feature vector second calculation sub-module 903, a feature classification determination sub-module 904, a model real-time update sub-module 905, and a tag word recognition sub-module 906.
Wherein:
a target data second determining sub-module 901, configured to take the user real-time behavior data as target data;
a data second cleaning sub-module 902, configured to perform cleaning processing on the target data through a preset cleaning component, to obtain target data after the cleaning processing, where the cleaning processing includes preprocessing and deduplication processing;
a second feature vector computing sub-module 903, configured to input the cleaned target data into a preset deep learning component for feature vector computation, to obtain a feature vector computation result, where a dictionary and word vectors corresponding to each word in the dictionary are preset in the deep learning component;
a feature classification determining sub-module 904, configured to determine a feature classification result to which the target data belongs according to the feature vector calculation result;
the model real-time updating sub-module 905 is configured to add the target data to the feature classification result according to the feature classification result to which the target data belongs, and update the model in real time;
and the tag word recognition sub-module 906 is configured to recognize a tag word corresponding to the user real-time behavior data according to the feature classification result to which the target data belongs.
According to the method and the device, through the historical behavior data of the user, the tag model training is carried out, tag words which more accord with the behavior data of the user can be trained, the tag words can be combined conveniently, and the advertisements which are interested in the target user terminal can be accurately put in. Model prediction and model real-time updating are carried out through the user real-time behavior data, tag words corresponding to the user real-time behavior data can be obtained through prediction, advertisements to be put in can be adjusted in time according to the tag words corresponding to the user real-time behavior data, and the user real-time behavior change condition is accurately combined. When the interest point of the user changes, the advertisement to be put can be adjusted in time, the interest change of the user is fully considered, and meanwhile, the model is updated in real time, so that the result after each model prediction can be used for data support for the next model prediction.
Those skilled in the art will appreciate that implementing all or part of the above described embodiment methods may be accomplished by computer readable instructions, stored on a computer readable storage medium, that the program when executed may comprise the steps of embodiments of the methods described above. The storage medium may be a nonvolatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a random access Memory (Random Access Memory, RAM).
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.
In order to solve the technical problems, the embodiment of the application also provides computer equipment. Referring specifically to fig. 10, fig. 10 is a basic structural block diagram of a computer device according to the present embodiment.
The computer device 10 includes a memory 10a, a processor 10b, and a network interface 10c communicatively coupled to each other via a system bus. It should be noted that only computer device 10 having components 10a-10c is shown in the figures, but it should be understood that not all of the illustrated components need be implemented and that more or fewer components may alternatively be implemented. It will be appreciated by those skilled in the art that the computer device herein is a device capable of automatically performing numerical calculations and/or information processing in accordance with predetermined or stored instructions, the hardware of which includes, but is not limited to, microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASICs), programmable gate arrays (fields-Programmable Gate Array, FPGAs), digital processors (Digital Signal Processor, DSPs), embedded devices, etc.
The computer equipment can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing equipment. The computer equipment can perform man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch pad or voice control equipment and the like.
The memory 10a includes at least one type of readable storage medium including flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), programmable Read Only Memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the storage 10a may be an internal storage unit of the computer device 10, such as a hard disk or a memory of the computer device 10. In other embodiments, the memory 10a may also be an external storage device of the computer device 10, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like, which are provided on the computer device 10. Of course, the memory 10a may also include both internal storage units of the computer device 10 and external storage devices thereof. In this embodiment, the memory 10a is generally used to store an operating system and various application software installed on the computer device 10, such as computer readable instructions of an advertisement delivery method. Further, the memory 10a may be used to temporarily store various types of data that have been output or are to be output.
The processor 10b may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other advertising chip in some embodiments. The processor 10b is generally used to control the overall operation of the computer device 10. In this embodiment, the processor 10b is configured to execute computer readable instructions stored in the memory 10a or process data, such as computer readable instructions for executing the advertisement delivery method.
The network interface 10c may comprise a wireless network interface or a wired network interface, the network interface 10c typically being used to establish a communication connection between the computer device 10 and other electronic devices.
The computer equipment provided by the embodiment belongs to the technical field of financial science and technology and is applied to an advertisement putting scene. According to the method and the device, through the historical behavior data of the user, the tag model training is carried out, tag words which more accord with the behavior data of the user can be trained, the tag words can be combined conveniently, and the advertisements which are interested in the target user terminal can be accurately put in. Model prediction and model real-time updating are carried out through the user real-time behavior data, tag words corresponding to the user real-time behavior data can be obtained through prediction, advertisements to be put in can be adjusted in time according to the tag words corresponding to the user real-time behavior data, and the user real-time behavior change condition is accurately combined. When the interest point of the user changes, the advertisement to be put can be adjusted in time, the interest change of the user is fully considered, and meanwhile, the model is updated in real time, so that the result after each model prediction can be used for data support for the next model prediction.
The present application also provides another embodiment, namely, a computer-readable storage medium storing computer-readable instructions executable by a processor to cause the processor to perform the steps of the advertisement delivery method as described above.
The computer readable storage medium provided by the embodiment belongs to the technical field of financial science and technology, and is applied to advertisement putting scenes. According to the method and the device, through the historical behavior data of the user, the tag model training is carried out, tag words which more accord with the behavior data of the user can be trained, the tag words can be combined conveniently, and the advertisements which are interested in the target user terminal can be accurately put in. Model prediction and model real-time updating are carried out through the user real-time behavior data, tag words corresponding to the user real-time behavior data can be obtained through prediction, advertisements to be put in can be adjusted in time according to the tag words corresponding to the user real-time behavior data, and the user real-time behavior change condition is accurately combined. When the interest point of the user changes, the advertisement to be put can be adjusted in time, the interest change of the user is fully considered, and meanwhile, the model is updated in real time, so that the result after each model prediction can be used for data support for the next model prediction.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk), comprising several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method described in the embodiments of the present application.
It is apparent that the embodiments described above are only some embodiments of the present application, but not all embodiments, the preferred embodiments of the present application are given in the drawings, but not limiting the patent scope of the present application. This application may be embodied in many different forms, but rather, embodiments are provided in order to provide a more thorough understanding of the present disclosure. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described in the foregoing, or equivalents may be substituted for elements thereof. All equivalent structures made by the specification and the drawings of the application are directly or indirectly applied to other related technical fields, and are also within the protection scope of the application.
Claims (10)
1. An advertising method, comprising the steps of:
acquiring user history behavior data in a target user terminal;
inputting the user historical behavior data into a label model to be trained, and performing model training to obtain a label model after training, wherein the label model after training comprises characteristic classification results of the user historical behavior data and label words corresponding to all the characteristic classification results;
monitoring a target user terminal according to a preset real-time monitoring component to obtain user real-time behavior data;
inputting the real-time behavior data of the user into the trained tag model, updating the model in real time, and outputting a feature classification result of predicting the real-time behavior data of the user and a tag word corresponding to the feature classification result through the model;
and putting a target advertisement to the target user terminal according to the tag words, wherein the target advertisement is marked in advance according to the different tag words.
2. The advertisement delivery method according to claim 1, wherein the step of inputting the user history behavior data into a label model to be trained, performing model training, and obtaining a trained label model specifically comprises:
Taking the historical behavior data of the user as target data;
performing cleaning treatment on the target data through a preset cleaning assembly to obtain the target data after the cleaning treatment, wherein the cleaning treatment comprises pretreatment and deduplication treatment;
inputting the cleaned target data into a preset deep learning component for feature vector calculation to obtain a feature vector calculation result, wherein a dictionary and word vectors corresponding to words in the dictionary are preset in the deep learning component;
performing feature classification on the target data after the cleaning treatment according to the feature vector calculation result and a preset feature classification strategy to obtain a feature classification result;
performing iterative sampling on the feature classification results by adopting a block sampling method to obtain sampling results respectively corresponding to all feature classification results;
and calculating the highest frequency word corresponding to the target feature classification result according to the sampling result and the dictionary, and taking the highest frequency word as the tag word corresponding to the target feature classification result to obtain the trained tag model.
3. The advertisement putting method according to claim 1, wherein the step of monitoring the target user terminal according to the preset real-time monitoring component to obtain the real-time behavior data of the user specifically comprises:
Monitoring a target user terminal through the real-time monitoring component to obtain a monitoring result;
analyzing the monitoring result to obtain user operation information;
and acquiring user real-time behavior data from a target log or a target event according to the user operation information.
4. The advertisement delivery method according to claim 1, wherein the step of inputting the user real-time behavior data into the trained tag model to update the model in real time, and outputting a feature classification result to which the predicted user real-time behavior data belongs and a tag word corresponding to the feature classification result through the model specifically comprises:
taking the user real-time behavior data as target data;
performing cleaning treatment on the target data through a preset cleaning assembly to obtain the target data after the cleaning treatment, wherein the cleaning treatment comprises pretreatment and deduplication treatment;
inputting the cleaned target data into a preset deep learning component for feature vector calculation to obtain a feature vector calculation result, wherein a dictionary and word vectors corresponding to words in the dictionary are preset in the deep learning component;
Determining a feature classification result to which the target data belongs according to the feature vector calculation result;
adding the target data into the feature classification result according to the feature classification result to which the target data belongs, and updating the model in real time;
and identifying the tag word corresponding to the user real-time behavior data according to the feature classification result of the target data.
5. The advertisement delivery method according to claim 2 or 4, wherein the step of performing cleaning processing on the target data by a preset cleaning component to obtain cleaned target data specifically comprises:
performing missing value processing on the target data based on a missing value processing sub-component preset in the cleaning component to obtain first-order behavior data;
performing outlier optimization processing on the first-order behavior data according to an outlier processing sub-component preset in the cleaning component to obtain second-order behavior data;
performing de-duplication processing on the second-order behavior data through a pre-set de-duplication processing sub-assembly in the cleaning assembly to obtain third-order behavior data;
and carrying out unified processing on the numerical format and the data type format of the third-order behavior data through a preset data format unified sub-component in the cleaning component to obtain the target data after the cleaning processing.
6. The advertisement delivery method according to claim 2 or 4, wherein the step of inputting the cleaned target data into a preset deep learning component to perform feature vector calculation, and obtaining a feature vector calculation result specifically includes:
acquiring target data input into the deep learning component;
identifying target words included in the target data according to the dictionary, wherein the target words are words included in the dictionary;
and calculating word vectors and values corresponding to the target data as the feature vector calculation results according to the target words and word vectors corresponding to the words in the dictionary respectively.
7. The advertisement delivery method according to claim 2, wherein the step of classifying the characteristics of the target data after the cleaning process according to the characteristic vector calculation result and a preset characteristic classification policy specifically includes:
normalizing the feature vector calculation result according to a preset normalization processing component to obtain a normalization processing result;
identifying a classification interval preset according to the characteristic classification strategy;
Performing interval classification on the normalization processing result according to the classification interval to obtain an interval classification result;
according to a preset statistical component, counting the number of normalized values in the classification result of each interval to obtain a statistical result;
according to the statistical result and a preset rejection strategy, rejecting the interval classification results with the number of normalized values smaller than the preset target number, and counting the classification category number of the interval classification results which are not rejected;
the classified category number is used as the category number of characteristic classification of the target data after the cleaning treatment;
and identifying the target data after the cleaning treatment corresponding to the non-removed interval classification result according to the non-removed interval classification result and the feature vector calculation result, and finishing the feature classification of the target data after the cleaning treatment.
8. An advertising device, comprising:
the user historical behavior data acquisition module is used for acquiring user historical behavior data in the target user terminal;
the label model training module is used for inputting the user historical behavior data into a label model to be trained, and carrying out model training to obtain a label model after training, wherein the label model after training comprises characteristic classification results of the user historical behavior data and label words corresponding to all the characteristic classification results;
The user real-time behavior data acquisition module is used for monitoring the target user terminal according to the preset real-time monitoring component so as to acquire user real-time behavior data;
the label model prediction module is used for inputting the real-time behavior data of the user into the trained label model, updating the model in real time, and predicting a feature classification result to which the real-time behavior data of the user belongs and a label word corresponding to the feature classification result through model output;
and the advertisement putting module is used for putting target advertisements to the target user terminal according to the tag words, wherein the target advertisements are marked in advance according to the tag words.
9. A computer device comprising a memory having stored therein computer readable instructions which when executed by a processor implement the steps of the advertising method of any one of claims 1 to 7.
10. A computer readable storage medium having stored thereon computer readable instructions which when executed by a processor implement the steps of the advertising method as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311387638.0A CN117391782A (en) | 2023-10-24 | 2023-10-24 | Advertisement putting method, device, equipment and storage medium thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311387638.0A CN117391782A (en) | 2023-10-24 | 2023-10-24 | Advertisement putting method, device, equipment and storage medium thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117391782A true CN117391782A (en) | 2024-01-12 |
Family
ID=89438719
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311387638.0A Pending CN117391782A (en) | 2023-10-24 | 2023-10-24 | Advertisement putting method, device, equipment and storage medium thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117391782A (en) |
-
2023
- 2023-10-24 CN CN202311387638.0A patent/CN117391782A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110825956A (en) | Information flow recommendation method and device, computer equipment and storage medium | |
| CN114780727A (en) | Text classification method and device based on reinforcement learning, computer equipment and medium | |
| CN112995414B (en) | Behavior quality inspection method, device, equipment and storage medium based on voice call | |
| CN113743721A (en) | Marketing strategy generation method and device, computer equipment and storage medium | |
| CN116431878A (en) | Vector retrieval service method, device, equipment and storage medium thereof | |
| CN114398466A (en) | Complaint analysis method and device based on semantic recognition, computer equipment and medium | |
| CN117234505A (en) | Interactive page generation method, device, equipment and storage medium thereof | |
| CN116703466A (en) | System access quantity prediction method based on improved wolf algorithm and related equipment thereof | |
| CN117275466A (en) | Business intention recognition method, device, equipment and storage medium thereof | |
| CN116796729A (en) | Text recommendation method, device, equipment and storage medium based on feature enhancement | |
| CN111127057B (en) | Multi-dimensional user portrait recovery method | |
| CN116821493A (en) | Message pushing method, device, computer equipment and storage medium | |
| CN116841846A (en) | Real-time log abnormality detection method, device, equipment and storage medium thereof | |
| CN116703520A (en) | Product recommendation method based on improved K-means algorithm and related equipment thereof | |
| CN116701593A (en) | Chinese question-answering model training method based on GraphQL and related equipment thereof | |
| CN116703515A (en) | Recommendation method and device based on artificial intelligence, computer equipment and storage medium | |
| CN115185625A (en) | Self-recommendation type interface updating method based on configurable card and related equipment thereof | |
| CN117391782A (en) | Advertisement putting method, device, equipment and storage medium thereof | |
| CN112069807A (en) | Text data theme extraction method and device, computer equipment and storage medium | |
| CN114866818B (en) | Video recommendation method, device, computer equipment and storage medium | |
| CN117493563A (en) | Session intention analysis method, device, equipment and storage medium thereof | |
| CN117421207A (en) | Intelligent evaluation influence point test method, intelligent evaluation influence point test device, computer equipment and storage medium | |
| CN115203502A (en) | Business data processing method and device, electronic equipment and storage medium | |
| CN117609013A (en) | Software defect prediction method and device based on fuzzy weighted width learning | |
| CN116662418A (en) | Report realization method, device and equipment based on configuration and storage medium thereof |
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 |