CN116629423A - User behavior prediction method, device, equipment and storage medium - Google Patents
User behavior prediction method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN116629423A CN116629423A CN202310589545.XA CN202310589545A CN116629423A CN 116629423 A CN116629423 A CN 116629423A CN 202310589545 A CN202310589545 A CN 202310589545A CN 116629423 A CN116629423 A CN 116629423A
- Authority
- CN
- China
- Prior art keywords
- target
- user
- information
- behavior
- label
- 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 39
- 238000012549 training Methods 0.000 claims abstract description 104
- 238000012360 testing method Methods 0.000 claims abstract description 70
- 230000006399 behavior Effects 0.000 claims description 234
- 238000012216 screening Methods 0.000 claims description 29
- 238000004458 analytical method Methods 0.000 claims description 28
- 239000013598 vector Substances 0.000 claims description 28
- 238000012545 processing Methods 0.000 claims description 19
- 238000000605 extraction Methods 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000004378 air conditioning Methods 0.000 claims description 2
- 238000013473 artificial intelligence Methods 0.000 abstract description 8
- 230000003542 behavioural effect Effects 0.000 abstract description 3
- 230000004044 response Effects 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000001914 filtration Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 235000019800 disodium phosphate Nutrition 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000007246 mechanism Effects 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
- 230000003287 optical effect Effects 0.000 description 1
- 230000003997 social interaction Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 239000002699 waste material Substances 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/211—Selection of the most significant subset of features
- G06F18/2113—Selection of the most significant subset of features by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/285—Selection of pattern recognition techniques, e.g. of classifiers in a multi-classifier system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- 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
- G06Q30/01—Customer relationship services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Strategic Management (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the field of artificial intelligence and finance, and provides a user behavior prediction method, device, equipment and storage medium. According to the method, target labels are screened out from the obtained characteristic labels, training information and user behavior results of a plurality of training users on the target labels are obtained, the training information and the training texts are input into a plurality of behavior prediction models, the predicted behavior results of each behavior prediction model on the plurality of training users are obtained, model indexes are generated according to the user behavior results and the predicted behavior results, the target models are screened out, the user information and the test texts of the test users are predicted based on the target models in response to the user behavior prediction requests, and the target behavior results can be accurately obtained. Furthermore, the present invention also relates to blockchain techniques, where the target behavioral results may be stored in the blockchain.
Description
Technical Field
The present invention relates to the field of artificial intelligence and financial technologies, and in particular, to a method, an apparatus, a device, and a storage medium for predicting user behavior.
Background
At present, in the business scenes of inquiring purchase intention and the like from clients, the users generally send short messages or mails and the like to all clients at random, the uplink response rate of the mode is about 1%, so that great waste of cost is caused, and meanwhile, short message harassment is caused for unintended clients, so that the user experience is influenced.
In order to improve user experience, in the field of artificial intelligence, feedback conditions of users for mass-sending short messages and mass-sending mails are usually predicted first, and whether the users send the short messages is selected according to the predicted conditions. However, in the existing user reply feedback prediction scheme, an arbitrary prediction network model is generally directly used for predicting a user reply feedback request, and the prediction network model is not subjected to service adaptation selection, so that the reply condition of the user to the consultation condition cannot be accurately predicted, and the loss of the client is caused. With the development of financial science and technology, the user reply feedback prediction scheme can support functions of shopping, social interaction, interactive games, resource transfer and the like.
Disclosure of Invention
In view of the foregoing, it is necessary to provide a method, apparatus, device and storage medium for predicting user behavior, which can solve the technical problem of how to accurately predict the response situation of the user to the consultation situation.
In one aspect, the present invention provides a user behavior prediction method, where the user behavior prediction method includes:
screening target labels from the acquired characteristic labels;
acquiring training information and user behavior results of a plurality of training users on the target label, and acquiring training texts;
inputting the training information and the training text into a plurality of pre-trained behavior prediction models to obtain the predicted behavior results of each behavior prediction model on a plurality of training users;
generating model indexes of each behavior prediction model according to the user behavior result and the predicted behavior result;
screening a target model from the behavior prediction models based on a plurality of model indexes;
responding to a user behavior prediction request, and performing prediction processing on user information and test text of a test user in the user behavior prediction request based on the target model to obtain a target behavior result of the test user on the test text.
According to a preferred embodiment of the present invention, the screening the target tag from the obtained plurality of feature tags includes:
acquiring feature information of each feature tag and a feature result corresponding to the feature information;
Calculating the label variance of each characteristic label according to the characteristic information;
counting the information quantity of the feature results with different results corresponding to the feature information with the same value, and counting the feature total quantity of the feature information in each feature tag;
calculating the target proportion of each feature label according to the information quantity and the feature total quantity;
identifying the label type corresponding to each characteristic label;
and screening the target label from the plurality of characteristic labels according to the label variance, the target proportion and the label type.
According to a preferred embodiment of the present invention, the selecting the target tag from the plurality of feature tags according to the tag variance, the target proportion and the tag type includes:
comparing the tag variance with a first preset threshold and comparing the target proportion with a second preset threshold;
if the label variances corresponding to the characteristic labels under the same label type are smaller than the first preset threshold value, and the target proportions corresponding to the characteristic labels under the same label type are larger than the second preset threshold value, selecting the characteristic label with the largest label variance and/or the smallest target proportion from the characteristic labels of the label type as the target label; or alternatively
If the label variances corresponding to the characteristic labels in the same label type are not smaller than the first preset threshold, selecting the characteristic label with the label variance larger than or equal to the first preset threshold from the characteristic labels of the characteristic labels as the target label; or alternatively
And if the target proportion corresponding to the characteristic labels in the same label type is not greater than the second preset threshold, selecting the characteristic label with the target proportion smaller than or equal to the second preset threshold from the characteristic labels of the characteristic labels as the target label.
According to a preferred embodiment of the present invention, the inputting the training information and the training text into a plurality of pre-trained behavior prediction models, and obtaining the predicted behavior results of each behavior prediction model for the plurality of training users includes:
identifying the information type of the training information;
coding the training information with the character type based on a preset coding table to obtain a first code, and coding the training text to obtain a second code;
performing numerical conversion on the training information with the numerical information type to obtain numerical distribution information;
Carrying out standardization processing on the numerical distribution information to obtain a third code;
splicing the first code, the second code and the third code to obtain a target code;
and processing the target codes according to the behavior prediction models to obtain the predicted behavior result.
According to a preferred embodiment of the present invention, the plurality of model indexes includes a first index, a second index, a third index and a fourth index, and the generating the model index of each behavior prediction model according to the user behavior result and the predicted behavior result includes:
for each behavior prediction model, counting the number of the training users with the predicted behavior result and the user behavior result being the first configuration result as a first number, and counting the number of the training users with the predicted behavior result and the user behavior result being the second configuration result as a second number;
counting the number of the training users with the predicted behavior result being the first configuration result and the user behavior result being the second configuration result as a third number, and counting the number of the training users with the predicted behavior result being the second configuration result and the user behavior result being the first configuration result as a fourth number;
Generating the first index according to the first quantity and the fourth quantity, and generating the second index according to the first quantity and the third quantity;
generating a third index according to the first quantity, the second quantity, the third quantity and the fourth quantity, and generating the fourth index according to the first index and the second index.
According to a preferred embodiment of the present invention, the predicting, based on the target model, the user information and the test text of the test user in the user behavior prediction request, and obtaining the target behavior result of the test user on the test text includes:
analyzing a request message of the user behavior prediction request to obtain data information carried by the request message;
extracting a user identification of the test user from the data information;
generating a query statement based on the user identification and the target tag;
operating the query statement based on a configuration information base to obtain the user information;
positioning the test text from the path address in the data information;
information coding is carried out on the user information and the test text, and an input vector is obtained;
And carrying out predictive analysis on the input vector according to the target model to obtain the target behavior result.
According to a preferred embodiment of the present invention, the target model includes a forward network layer, a reverse network layer, and a plurality of prediction analysis trees, and the performing prediction analysis on the input vector according to the target model, to obtain the target behavior result includes:
performing feature extraction on the input vector based on the forward network layer to obtain a first feature, and performing feature extraction on the input vector based on the reverse network layer to obtain a second feature;
generating target features of the input vector according to the first features and the second features;
obtaining a matching result matched with the target feature from each prediction analysis tree;
and counting the number of results of each matching result, and determining the matching result with the largest number of results as the target behavior result.
On the other hand, the invention also provides a user behavior prediction device, which comprises:
the screening unit is used for screening target labels from the acquired plurality of characteristic labels;
the acquisition unit is used for acquiring training information and user behavior results of a plurality of training users on the target label and acquiring training texts;
The input unit is used for inputting the training information and the training text into a plurality of pre-trained behavior prediction models to obtain the predicted behavior results of each behavior prediction model on a plurality of training users;
the generating unit is used for generating model indexes of each behavior prediction model according to the user behavior result and the predicted behavior result;
the screening unit is further used for screening a target model from the behavior prediction models based on a plurality of model indexes;
the prediction unit is used for responding to a user behavior prediction request, and predicting the user information and the test text of the test user in the user behavior prediction request based on the target model to obtain a target behavior result of the test user on the test text.
In another aspect, the present invention also proposes an electronic device, including:
a memory storing computer readable instructions; a kind of electronic device with high-pressure air-conditioning system
And a processor executing computer readable instructions stored in the memory to implement the user behavior prediction method.
In another aspect, the present invention also proposes a computer readable storage medium having stored therein computer readable instructions that are executed by a processor in an electronic device to implement the user behavior prediction method.
According to the technical scheme, the target labels can be reasonably screened by carrying out feature analysis on the plurality of feature labels, and the behavior prediction analysis efficiency can be improved due to the reduction of the analysis on the plurality of feature labels.
Drawings
FIG. 1 is a flow chart of a preferred embodiment of the user behavior prediction method of the present application.
FIG. 2 is a model structure diagram of a target model in the user behavior prediction method of the present application.
FIG. 3 is a functional block diagram of a preferred embodiment of the user behavior prediction apparatus of the present application.
Fig. 4 is a schematic structural diagram of an electronic device according to a preferred embodiment of the present application for implementing a user behavior prediction method.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.
FIG. 1 is a flow chart of a method for predicting user behavior according to a preferred embodiment of the present invention. The order of the steps in the flowchart may be changed and some steps may be omitted according to various needs.
The user behavior prediction method can acquire and process related data based on 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, big data processing 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.
The user behavior prediction method is applied to one or more electronic devices, wherein the electronic devices are devices capable of automatically performing numerical calculation and/or information processing according to preset or stored computer readable instructions, and the hardware comprises, but is not limited to, microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASICs), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital signal processors (Digital Signal Processor, DSPs), embedded devices and the like.
The electronic device may be any electronic product that can interact with a user in a human-computer manner, such as a personal computer, tablet computer, smart phone, personal digital assistant (Personal Digital Assistant, PDA), game console, interactive internet protocol television (Internet Protocol Television, IPTV), smart wearable device, etc.
The electronic device may comprise a network device and/or a user device. Wherein the network device includes, but is not limited to, a single network electronic device, a group of electronic devices made up of multiple network electronic devices, or a Cloud based Cloud Computing (Cloud Computing) made up of a large number of hosts or network electronic devices.
The network in which the electronic device is located includes, but is not limited to: the internet, wide area networks, metropolitan area networks, local area networks, virtual private networks (Virtual Private Network, VPN), etc.
And 101, screening target labels from the acquired plurality of characteristic labels.
In at least one embodiment of the present invention, the plurality of feature tags may include, but are not limited to: user interest tags, user transaction tags, etc.
The target label is a characteristic label with larger variance of characteristic information and smaller conflict between the characteristic information and a characteristic result.
In at least one embodiment of the present invention, the electronic device screening the target tag from the acquired plurality of feature tags includes:
acquiring feature information of each feature tag and a feature result corresponding to the feature information;
calculating the label variance of each characteristic label according to the characteristic information;
counting the information quantity of the feature results with different results corresponding to the feature information with the same value, and counting the feature total quantity of the feature information in each feature tag;
calculating the target proportion of each feature label according to the information quantity and the feature total quantity;
identifying the label type corresponding to each characteristic label;
And screening the target label from the plurality of characteristic labels according to the label variance, the target proportion and the label type.
The feature information refers to information corresponding to the feature tag, for example, the feature tag is a tag of interest to a user, and the feature information may be internet surfing or the like.
The feature result refers to a result corresponding to the feature information of the feature labels at the same time, for example, the feature result may be that user feedback is received.
The target ratio refers to the ratio of the amount of information to the total amount of features.
The tag types include, but are not limited to: prediction type, statistics type, facts type, etc.
The feature results can be prevented from being distinguished accurately due to the fact that the difference of the feature information is small by calculating the tag variance, the feature results corresponding to a large number of feature information with the same value can be prevented from being present in the target tag by calculating the target proportion, and then the tag type is combined, the determination rationality of the target tag is improved, the number of the feature tags can be reduced by screening the feature tags, and accordingly the behavior analysis efficiency is improved.
Specifically, the electronic device selecting the target tag from the plurality of feature tags according to the tag variance, the target proportion and the tag type includes:
comparing the tag variance with a first preset threshold and comparing the target proportion with a second preset threshold;
if the label variances corresponding to the characteristic labels under the same label type are smaller than the first preset threshold value, and the target proportions corresponding to the characteristic labels under the same label type are larger than the second preset threshold value, selecting the characteristic label with the largest label variance and/or the smallest target proportion from the characteristic labels of the label type as the target label; or alternatively
If the label variances corresponding to the characteristic labels in the same label type are not smaller than the first preset threshold, selecting the characteristic label with the label variance larger than or equal to the first preset threshold from the characteristic labels of the characteristic labels as the target label; or alternatively
And if the target proportion corresponding to the characteristic labels in the same label type is not greater than the second preset threshold, selecting the characteristic label with the target proportion smaller than or equal to the second preset threshold from the characteristic labels of the characteristic labels as the target label.
The first preset threshold and the second preset threshold may be set according to actual requirements, which is not limited in the present application.
By the implementation manner, the characteristic labels corresponding to any label type can be prevented from being removed due to unreasonable setting of the first preset threshold value and the second preset threshold value, and therefore the determination rationality of the target labels is improved.
102, obtaining training information and user behavior results of a plurality of training users on the target label, and obtaining training texts.
In at least one embodiment of the present application, the plurality of training users may be users of any known feedback scenario.
The training information refers to specific information corresponding to the plurality of training users on the target label.
The user behavior results include, but are not limited to: and receiving the user feedback and not receiving the user feedback.
The training text may be short message content about the redemption business.
And 103, inputting the training information and the training text into a plurality of pre-trained behavior prediction models to obtain the predicted behavior results of each behavior prediction model on the plurality of training users.
In at least one embodiment of the invention, the plurality of behavior prediction models comprises a combination of at least one of the following models:
behavior prediction model based on random forest algorithm, behavior prediction model based on gradient lifting decision tree, behavior prediction model based on logistic regression algorithm, behavior prediction model based on extreme gradient lifting.
In at least one embodiment of the present invention, the predicted behavioral results include, but are not limited to: and receiving the user feedback and not receiving the user feedback.
In at least one embodiment of the present invention, the electronic device inputting the training information and the training text into a plurality of behavior prediction models that are trained in advance, and obtaining the predicted behavior results of each behavior prediction model for the plurality of training users includes:
identifying the information type of the training information;
coding the training information with the character type based on a preset coding table to obtain a first code, and coding the training text to obtain a second code;
performing numerical conversion on the training information with the numerical information type to obtain numerical distribution information;
Carrying out standardization processing on the numerical distribution information to obtain a third code;
splicing the first code, the second code and the third code to obtain a target code;
and processing the target codes according to the behavior prediction models to obtain the predicted behavior result.
Wherein the information types include: the character type and the numerical type.
The preset encoding table stores the mapping relation between a plurality of characters and element vectors.
The numerical distribution information is information generated after numerical conversion of the training information with the numerical information type.
The information type is identified, the training information with the character type is encoded through the preset encoding table, the problem of sparse matrix in the first encoding can be avoided, the numerical distribution information can be enabled to present a certain distribution rule through numerical conversion of the training information with the numerical type, the encoding accuracy of the third encoding is improved, and therefore the training information and the training text can be accurately represented by combining the first encoding, the second encoding and the third encoding, the target encoding is processed through the behavior prediction models, and the problem of prediction errors caused by characterization errors can be avoided.
Specifically, the numerical distribution information is generated according to the following formula:
y=log (n+1), where y represents the numerical distribution information and n represents training information whose information type is numerical.
The numerical distribution information can be enabled to present a certain distribution rule through a logarithmic function, and the numerical distribution information can be prevented from having no meaning through introducing the numerical value 1.
104, generating model indexes of each behavior prediction model according to the user behavior result and the predicted behavior result.
In at least one embodiment of the present invention, the plurality of model metrics includes a first metric, a second metric, a third metric, and a fourth metric.
In at least one embodiment of the present invention, the generating, by the electronic device, a model index of each behavior prediction model according to the user behavior result and the predicted behavior result includes:
for each behavior prediction model, counting the number of the training users with the predicted behavior result and the user behavior result being the first configuration result as a first number, and counting the number of the training users with the predicted behavior result and the user behavior result being the second configuration result as a second number;
Counting the number of the training users with the predicted behavior result being the first configuration result and the user behavior result being the second configuration result as a third number, and counting the number of the training users with the predicted behavior result being the second configuration result and the user behavior result being the first configuration result as a fourth number;
generating the first index according to the first quantity and the fourth quantity, and generating the second index according to the first quantity and the third quantity;
generating a third index according to the first quantity, the second quantity, the third quantity and the fourth quantity, and generating the fourth index according to the first index and the second index.
Wherein the first configuration result is generally set to receive user feedback, and the second configuration result is generally set to not receive user feedback.
By comparing the predicted behavior result and the user behavior result with the first configuration result and the second configuration result respectively, the first quantity, the second quantity, the third quantity and the fourth quantity can be accurately quantified, and therefore the generation accuracy of model indexes of each behavior prediction model is improved.
Specifically, the generation formula of the first index is:
the generation formula of the second index is as follows:
the generation formula of the third index is as follows:
the fourth index is generated according to the following formula:
wherein k is 1 Represents the first index, k 2 Representing the second index, k 3 Represents the third index, k 4 And (c) representing the fourth index, a representing the first quantity, b representing the second quantity, c representing the third quantity, d representing the fourth quantity, and z representing a preset constant.
And 105, screening a target model from the behavior prediction models based on the model indexes.
In at least one embodiment of the present invention, the target model refers to a behavior prediction model with the largest of the plurality of model indexes.
FIG. 2 is a diagram showing the structure of the target model in the user behavior prediction method of the present invention. In fig. 2, the target model may include a forward network layer, a reverse network layer, and a plurality of predictive analysis trees. The object model may also have other manifestations.
In at least one embodiment of the present invention, the electronic device, based on a plurality of the model metrics, selecting a target model from the plurality of behavior prediction models includes:
Performing weighted sum operation on the model indexes to obtain target indexes;
and determining a behavior prediction model corresponding to the target index with the maximum value as the target model.
By the implementation mode, the target model can be rapidly determined.
106, responding to a user behavior prediction request, and performing prediction processing on user information and test text of a test user in the user behavior prediction request based on the target model to obtain a target behavior result of the test user on the test text.
It should be emphasized that, to further ensure the privacy and security of the target behavior results, the target behavior results may also be stored in a blockchain node.
In at least one embodiment of the present invention, the user behavior prediction request may be a request that is triggered to be generated when it is required to detect whether the user replies with content to the content of a sms or a mail. The information carried by the user behavior prediction request includes, but is not limited to: user identification of the test user, path address of the test text, etc. The test user refers to a user needing to conduct behavior prediction on the test text, the test text refers to a text needing to conduct user behavior prediction, and the test text can be short message content.
The user information refers to data information corresponding to the test user on the target label.
The target behavioral results may include, but are not limited to: and receiving the user feedback and not receiving the user feedback.
In at least one embodiment of the invention, the electronic device
Predicting the user information and the test text of the test user in the user behavior prediction request based on the target model, wherein the obtaining the target behavior result of the test user on the test text comprises the following steps:
analyzing a request message of the user behavior prediction request to obtain data information carried by the request message;
extracting a user identification of the test user from the data information;
generating a query statement based on the user identification and the target tag;
operating the query statement based on a configuration information base to obtain the user information;
positioning the test text from the path address in the data information;
information coding is carried out on the user information and the test text, and an input vector is obtained;
and carrying out predictive analysis on the input vector according to the target model to obtain the target behavior result.
Wherein the user identification is used to uniquely identify the test user.
The query statement may be a structured query statement.
The configuration information base stores a plurality of personal basic information authorized by the user.
The data information can be rapidly obtained by analyzing the request message, and further the user information can be directly obtained from the configuration information base through the user identification and the target label, so that the obtaining efficiency of the user information is improved, and the generating efficiency of the target behavior result is improved.
Specifically, the generating manner of the input vector is similar to that of the target code, which is not described in detail in the present application.
Specifically, when the target model includes a forward network layer, a reverse network layer, and a plurality of predictive analysis trees, the electronic device performs predictive analysis on the input vector according to the target model, and obtaining the target behavior result includes:
performing feature extraction on the input vector based on the forward network layer to obtain a first feature, and performing feature extraction on the input vector based on the reverse network layer to obtain a second feature;
Generating target features of the input vector according to the first features and the second features;
obtaining a matching result matched with the target feature from each prediction analysis tree;
and counting the number of results of each matching result, and determining the matching result with the largest number of results as the target behavior result.
The forward network layer and the reverse network layer may be network layers in a two-way memory neural network.
The target feature refers to an element average sum of feature elements in the first feature and feature elements of the second feature.
The forward network layer and the reverse network layer are used for extracting the characteristics of the input vector, the forward characteristics and the reverse characteristics of the input vector can be combined for characterizing the target characteristics, the characteristic capability of the target characteristics is improved, the matching results can be reasonably screened out through the plurality of predictive analysis trees, and the target behavior results can be accurately identified through the plurality of matching results.
According to the technical scheme, the target labels can be reasonably screened by carrying out feature analysis on the plurality of feature labels, and the behavior prediction analysis efficiency can be improved due to the reduction of the analysis on the plurality of feature labels.
FIG. 3 is a functional block diagram of a preferred embodiment of the user behavior prediction apparatus of the present invention. The user behavior prediction apparatus 11 includes a filtering unit 110, an acquisition unit 111, an input unit 112, a generation unit 113, and a prediction unit 114. The module/unit referred to herein is a series of computer readable instructions capable of being retrieved by the processor 13 and performing a fixed function and stored in the memory 12. In the present embodiment, the functions of the respective modules/units will be described in detail in the following embodiments.
A screening unit 110, configured to screen out a target tag from the acquired plurality of feature tags;
an obtaining unit 111, configured to obtain training information and user behavior results of a plurality of training users on the target label, and obtain training texts;
an input unit 112, configured to input the training information and the training text into a plurality of pre-trained behavior prediction models, to obtain a predicted behavior result of each behavior prediction model for the plurality of training users;
a generating unit 113, configured to generate a model index of each behavior prediction model according to the user behavior result and the predicted behavior result;
The screening unit 110 is further configured to screen a target model from the plurality of behavior prediction models based on a plurality of model indexes;
and the prediction unit 114 is configured to respond to a user behavior prediction request, and perform prediction processing on user information and test text of a test user in the user behavior prediction request based on the target model, so as to obtain a target behavior result of the test user on the test text.
In at least one embodiment of the present invention, the filtering unit 110 is further configured to obtain feature information of each feature tag and a feature result corresponding to the feature information;
calculating the label variance of each characteristic label according to the characteristic information;
counting the information quantity of the feature results with different results corresponding to the feature information with the same value, and counting the feature total quantity of the feature information in each feature tag;
calculating the target proportion of each feature label according to the information quantity and the feature total quantity;
identifying the label type corresponding to each characteristic label;
and screening the target label from the plurality of characteristic labels according to the label variance, the target proportion and the label type.
In at least one embodiment of the present invention, the filtering unit 110 is further configured to compare the tag variance with a first preset threshold value, and compare the target proportion with a second preset threshold value;
if the label variances corresponding to the characteristic labels under the same label type are smaller than the first preset threshold value, and the target proportions corresponding to the characteristic labels under the same label type are larger than the second preset threshold value, selecting the characteristic label with the largest label variance and/or the smallest target proportion from the characteristic labels of the label type as the target label; or alternatively
If the label variances corresponding to the characteristic labels in the same label type are not smaller than the first preset threshold, selecting the characteristic label with the label variance larger than or equal to the first preset threshold from the characteristic labels of the characteristic labels as the target label; or alternatively
And if the target proportion corresponding to the characteristic labels in the same label type is not greater than the second preset threshold, selecting the characteristic label with the target proportion smaller than or equal to the second preset threshold from the characteristic labels of the characteristic labels as the target label.
In at least one embodiment of the present invention, the input unit 112 is further configured to identify an information type of the training information;
coding the training information with the character type based on a preset coding table to obtain a first code, and coding the training text to obtain a second code;
performing numerical conversion on the training information with the numerical information type to obtain numerical distribution information;
carrying out standardization processing on the numerical distribution information to obtain a third code;
splicing the first code, the second code and the third code to obtain a target code;
and processing the target codes according to the behavior prediction models to obtain the predicted behavior result.
In at least one embodiment of the invention, the plurality of behavior prediction models comprises a combination of at least one of the following models:
behavior prediction model based on random forest algorithm, behavior prediction model based on gradient lifting decision tree, behavior prediction model based on logistic regression algorithm, behavior prediction model based on extreme gradient lifting.
In at least one embodiment of the present invention, the plurality of model indexes include a first index, a second index, a third index, and a fourth index, and the generating unit 113 is further configured to, for each behavior prediction model, count, as a first number, the number of users of the training users whose predicted behavior result and user behavior result are both first configuration results, and count, as a second number, the number of users of the training users whose predicted behavior result and user behavior result are both second configuration results;
Counting the number of the training users with the predicted behavior result being the first configuration result and the user behavior result being the second configuration result as a third number, and counting the number of the training users with the predicted behavior result being the second configuration result and the user behavior result being the first configuration result as a fourth number;
generating the first index according to the first quantity and the fourth quantity, and generating the second index according to the first quantity and the third quantity;
generating a third index according to the first quantity, the second quantity, the third quantity and the fourth quantity, and generating the fourth index according to the first index and the second index.
In at least one embodiment of the present invention, the generation formula of the first index is:
the generation formula of the second index is as follows:
the generation formula of the third index is as follows:
the fourth index is generated according to the following formula:
wherein k is 1 Represents the first index, k 2 Representing the second index, k 3 Represents the third index, k 4 And (c) representing the fourth index, a representing the first quantity, b representing the second quantity, c representing the third quantity, d representing the fourth quantity, and z representing a preset constant.
In at least one embodiment of the present invention, the predicting, based on the target model, the user information of the test user and the test text in the user behavior prediction request, to obtain the target behavior result of the test user on the test text includes:
analyzing a request message of the user behavior prediction request to obtain data information carried by the request message;
extracting a user identification of the test user from the data information;
generating a query statement based on the user identification and the target tag;
operating the query statement based on a configuration information base to obtain the user information;
positioning the test text from the path address in the data information;
information coding is carried out on the user information and the test text, and an input vector is obtained;
and carrying out predictive analysis on the input vector according to the target model to obtain the target behavior result.
In at least one embodiment of the present invention, the target model includes a forward network layer, a reverse network layer, and a plurality of prediction analysis trees, and performing prediction analysis on the input vector according to the target model, to obtain the target behavior result includes:
Performing feature extraction on the input vector based on the forward network layer to obtain a first feature, and performing feature extraction on the input vector based on the reverse network layer to obtain a second feature;
generating target features of the input vector according to the first features and the second features;
obtaining a matching result matched with the target feature from each prediction analysis tree;
and counting the number of results of each matching result, and determining the matching result with the largest number of results as the target behavior result.
According to the technical scheme, the target labels can be reasonably screened by carrying out feature analysis on the plurality of feature labels, and the behavior prediction analysis efficiency can be improved due to the reduction of the analysis on the plurality of feature labels.
Fig. 4 is a schematic structural diagram of an electronic device according to a preferred embodiment of the present invention for implementing the user behavior prediction method.
In one embodiment of the invention, the electronic device 1 includes, but is not limited to, a memory 12, a processor 13, and computer readable instructions, such as a user behavior prediction program, stored in the memory 12 and executable on the processor 13.
It will be appreciated by those skilled in the art that the schematic diagram is merely an example of the electronic device 1 and does not constitute a limitation of the electronic device 1, and may include more or less components than illustrated, or may combine certain components, or different components, e.g. the electronic device 1 may further include input-output devices, network access devices, buses, etc.
The processor 13 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor, etc., and the processor 13 is an operation core and a control center of the electronic device 1, connects various parts of the entire electronic device 1 using various interfaces and lines, and executes an operating system of the electronic device 1 and various installed applications, program codes, etc.
Illustratively, the computer readable instructions may be partitioned into one or more modules/units that are stored in the memory 12 and executed by the processor 13 to complete the present invention. The one or more modules/units may be a series of computer readable instructions capable of performing a specific function, the computer readable instructions describing a process of executing the computer readable instructions in the electronic device 1. For example, the computer-readable instructions may be divided into a screening unit 110, an acquisition unit 111, an input unit 112, a generation unit 113, and a prediction unit 114.
The memory 12 may be used to store the computer readable instructions and/or modules, and the processor 13 may implement various functions of the electronic device 1 by executing or executing the computer readable instructions and/or modules stored in the memory 12 and invoking data stored in the memory 12. The memory 12 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data created according to the use of the electronic device, etc. Memory 12 may include non-volatile and volatile memory, such as: a hard disk, memory, plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card), at least one disk storage device, flash memory device, or other storage device.
The memory 12 may be an external memory and/or an internal memory of the electronic device 1. Further, the memory 12 may be a physical memory, such as a memory bank, a TF Card (Trans-flash Card), or the like.
The integrated modules/units of the electronic device 1 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as separate products. Based on such understanding, the present invention may also be implemented by implementing all or part of the processes in the methods of the embodiments described above, by instructing the associated hardware by means of computer readable instructions, which may be stored in a computer readable storage medium, the computer readable instructions, when executed by a processor, implementing the steps of the respective method embodiments described above.
Wherein the computer readable instructions comprise computer readable instruction code which may be in the form of source code, object code, executable files, or in some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer readable instruction code, a recording medium, a USB flash disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory).
The blockchain is a novel application mode of computer technologies such as distributed user behavior prediction, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
In connection with fig. 1, the memory 12 in the electronic device 1 stores computer readable instructions implementing a user behavior prediction method, the processor 13 being executable to implement:
screening target labels from the acquired characteristic labels;
acquiring training information and user behavior results of a plurality of training users on the target label, and acquiring training texts;
inputting the training information and the training text into a plurality of pre-trained behavior prediction models to obtain the predicted behavior results of each behavior prediction model on a plurality of training users;
Generating model indexes of each behavior prediction model according to the user behavior result and the predicted behavior result;
screening a target model from the behavior prediction models based on a plurality of model indexes;
responding to a user behavior prediction request, and performing prediction processing on user information and test text of a test user in the user behavior prediction request based on the target model to obtain a target behavior result of the test user on the test text.
In particular, the specific implementation method of the processor 13 on the computer readable instructions may refer to the description of the relevant steps in the corresponding embodiment of fig. 1, which is not repeated herein.
In the several embodiments provided in the present invention, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.
The computer readable storage medium has stored thereon computer readable instructions, wherein the computer readable instructions when executed by the processor 13 are configured to implement the steps of:
Screening target labels from the acquired characteristic labels;
acquiring training information and user behavior results of a plurality of training users on the target label, and acquiring training texts;
inputting the training information and the training text into a plurality of pre-trained behavior prediction models to obtain the predicted behavior results of each behavior prediction model on a plurality of training users;
generating model indexes of each behavior prediction model according to the user behavior result and the predicted behavior result;
screening a target model from the behavior prediction models based on a plurality of model indexes;
responding to a user behavior prediction request, and performing prediction processing on user information and test text of a test user in the user behavior prediction request based on the target model to obtain a target behavior result of the test user on the test text.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. The units or means may also be implemented by one unit or means in software or hardware. The terms first, second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (10)
1. A user behavior prediction method, characterized in that the user behavior prediction method comprises:
screening target labels from the acquired characteristic labels;
acquiring training information and user behavior results of a plurality of training users on the target label, and acquiring training texts;
inputting the training information and the training text into a plurality of pre-trained behavior prediction models to obtain the predicted behavior results of each behavior prediction model on a plurality of training users;
generating model indexes of each behavior prediction model according to the user behavior result and the predicted behavior result;
screening a target model from the behavior prediction models based on a plurality of model indexes;
responding to a user behavior prediction request, and performing prediction processing on user information and test text of a test user in the user behavior prediction request based on the target model to obtain a target behavior result of the test user on the test text.
2. The method of claim 1, wherein the screening the target tag from the plurality of obtained feature tags comprises:
acquiring feature information of each feature tag and a feature result corresponding to the feature information;
Calculating the label variance of each characteristic label according to the characteristic information;
counting the information quantity of the feature results with different results corresponding to the feature information with the same value, and counting the feature total quantity of the feature information in each feature tag;
calculating the target proportion of each feature label according to the information quantity and the feature total quantity;
identifying the label type corresponding to each characteristic label;
and screening the target label from the plurality of characteristic labels according to the label variance, the target proportion and the label type.
3. The method of claim 2, wherein said selecting said target label from said plurality of feature labels based on said label variance, said target proportion, and said label type comprises:
comparing the tag variance with a first preset threshold and comparing the target proportion with a second preset threshold;
if the label variances corresponding to the characteristic labels under the same label type are smaller than the first preset threshold value, and the target proportions corresponding to the characteristic labels under the same label type are larger than the second preset threshold value, selecting the characteristic label with the largest label variance and/or the smallest target proportion from the characteristic labels of the label type as the target label; or alternatively
If the label variances corresponding to the characteristic labels in the same label type are not smaller than the first preset threshold, selecting the characteristic label with the label variance larger than or equal to the first preset threshold from the characteristic labels of the characteristic labels as the target label; or alternatively
And if the target proportion corresponding to the characteristic labels in the same label type is not greater than the second preset threshold, selecting the characteristic label with the target proportion smaller than or equal to the second preset threshold from the characteristic labels of the characteristic labels as the target label.
4. The method for predicting user behavior according to claim 1, wherein the inputting the training information and the training text into a plurality of pre-trained behavior prediction models to obtain predicted behavior results of each behavior prediction model for the plurality of training users comprises:
identifying the information type of the training information;
coding the training information with the character type based on a preset coding table to obtain a first code, and coding the training text to obtain a second code;
performing numerical conversion on the training information with the numerical information type to obtain numerical distribution information;
Carrying out standardization processing on the numerical distribution information to obtain a third code;
splicing the first code, the second code and the third code to obtain a target code;
and processing the target codes according to the behavior prediction models to obtain the predicted behavior result.
5. The method of claim 1, wherein the plurality of model metrics includes a first metric, a second metric, a third metric, and a fourth metric, and wherein generating model metrics for each behavior prediction model based on the user behavior results and the predicted behavior results comprises:
for each behavior prediction model, counting the number of the training users with the predicted behavior result and the user behavior result being the first configuration result as a first number, and counting the number of the training users with the predicted behavior result and the user behavior result being the second configuration result as a second number;
counting the number of the training users with the predicted behavior result being the first configuration result and the user behavior result being the second configuration result as a third number, and counting the number of the training users with the predicted behavior result being the second configuration result and the user behavior result being the first configuration result as a fourth number;
Generating the first index according to the first quantity and the fourth quantity, and generating the second index according to the first quantity and the third quantity;
generating a third index according to the first quantity, the second quantity, the third quantity and the fourth quantity, and generating the fourth index according to the first index and the second index.
6. The method for predicting user behavior according to claim 1, wherein the predicting the user information and the test text of the test user in the user behavior prediction request based on the target model, to obtain the target behavior result of the test user on the test text, comprises:
analyzing a request message of the user behavior prediction request to obtain data information carried by the request message;
extracting a user identification of the test user from the data information;
generating a query statement based on the user identification and the target tag;
operating the query statement based on a configuration information base to obtain the user information;
positioning the test text from the path address in the data information;
information coding is carried out on the user information and the test text, and an input vector is obtained;
And carrying out predictive analysis on the input vector according to the target model to obtain the target behavior result.
7. The method of claim 6, wherein the target model includes a forward network layer, a reverse network layer, and a plurality of predictive analysis trees, wherein performing predictive analysis on the input vector according to the target model to obtain the target behavior result includes:
performing feature extraction on the input vector based on the forward network layer to obtain a first feature, and performing feature extraction on the input vector based on the reverse network layer to obtain a second feature;
generating target features of the input vector according to the first features and the second features;
obtaining a matching result matched with the target feature from each prediction analysis tree;
and counting the number of results of each matching result, and determining the matching result with the largest number of results as the target behavior result.
8. A user behavior prediction apparatus, characterized in that the user behavior prediction apparatus comprises:
the screening unit is used for screening target labels from the acquired plurality of characteristic labels;
the acquisition unit is used for acquiring training information and user behavior results of a plurality of training users on the target label and acquiring training texts;
The input unit is used for inputting the training information and the training text into a plurality of pre-trained behavior prediction models to obtain the predicted behavior results of each behavior prediction model on a plurality of training users;
the generating unit is used for generating model indexes of each behavior prediction model according to the user behavior result and the predicted behavior result;
the screening unit is further used for screening a target model from the behavior prediction models based on a plurality of model indexes;
the prediction unit is used for responding to a user behavior prediction request, and predicting the user information and the test text of the test user in the user behavior prediction request based on the target model to obtain a target behavior result of the test user on the test text.
9. An electronic device, the electronic device comprising:
a memory storing computer readable instructions; a kind of electronic device with high-pressure air-conditioning system
A processor executing computer readable instructions stored in the memory to implement the user behavior prediction method of any one of claims 1 to 7.
10. A computer-readable storage medium, characterized by: the computer readable storage medium has stored therein computer readable instructions that are executed by a processor in an electronic device to implement the user behavior prediction method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310589545.XA CN116629423A (en) | 2023-05-24 | 2023-05-24 | User behavior prediction method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310589545.XA CN116629423A (en) | 2023-05-24 | 2023-05-24 | User behavior prediction method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116629423A true CN116629423A (en) | 2023-08-22 |
Family
ID=87616587
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310589545.XA Pending CN116629423A (en) | 2023-05-24 | 2023-05-24 | User behavior prediction method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116629423A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117555428A (en) * | 2024-01-12 | 2024-02-13 | 太一云境技术有限公司 | Artificial intelligent interaction method, system, computer equipment and storage medium thereof |
-
2023
- 2023-05-24 CN CN202310589545.XA patent/CN116629423A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117555428A (en) * | 2024-01-12 | 2024-02-13 | 太一云境技术有限公司 | Artificial intelligent interaction method, system, computer equipment and storage medium thereof |
| CN117555428B (en) * | 2024-01-12 | 2024-04-19 | 太一云境技术有限公司 | Artificial intelligent interaction method, system, computer equipment and storage medium thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111695033B (en) | Enterprise public opinion analysis method, enterprise public opinion analysis device, electronic equipment and medium | |
| CN110402570B (en) | Information processing method and system, server, terminal, computer storage medium | |
| CN112669138B (en) | Data processing method and related equipment | |
| CN111401700A (en) | Data analysis method, device, computer system and readable storage medium | |
| CN113656547B (en) | Text matching method, device, equipment and storage medium | |
| CN111597309A (en) | Similar enterprise recommendation method and device, electronic equipment and medium | |
| CN113688923A (en) | Intelligent order abnormity detection method and device, electronic equipment and storage medium | |
| CN115222443A (en) | Client group division method, device, equipment and storage medium | |
| CN116629423A (en) | User behavior prediction method, device, equipment and storage medium | |
| CN114860742A (en) | Artificial intelligence-based AI customer service interaction method, device, equipment and medium | |
| CN113656699A (en) | User feature vector determination method, related device and medium | |
| CN112634017A (en) | Remote card opening activation method and device, electronic equipment and computer storage medium | |
| CN112950347A (en) | Resource data processing optimization method and device, storage medium and terminal | |
| CN116402625A (en) | Customer evaluation method, apparatus, computer device and storage medium | |
| CN111552865A (en) | User interest portrait method and related equipment | |
| CN115037790B (en) | Abnormal registration identification method, device, equipment and storage medium | |
| CN113269179B (en) | Data processing method, device, equipment and storage medium | |
| CN113516205B (en) | Employee stability classification method based on artificial intelligence and related equipment | |
| CN113326365B (en) | Reply sentence generation method, device, equipment and storage medium | |
| CN114580354A (en) | Synonym-based information encoding method, device, equipment and storage medium | |
| CN113591881A (en) | Intention recognition method and device based on model fusion, electronic equipment and medium | |
| CN114048330A (en) | Risk conduction probability knowledge graph generation method, device, equipment and storage medium | |
| CN111859985A (en) | AI customer service model testing method, device, electronic equipment and storage medium | |
| CN112417096B (en) | Question-answer pair matching method, device, electronic equipment and storage medium | |
| CN112667659B (en) | Feature processing method and related equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |