CN114936326A - Information recommendation method, device, equipment and storage medium based on artificial intelligence - Google Patents
Information recommendation method, device, equipment and storage medium based on artificial intelligence Download PDFInfo
- Publication number
- CN114936326A CN114936326A CN202210852981.7A CN202210852981A CN114936326A CN 114936326 A CN114936326 A CN 114936326A CN 202210852981 A CN202210852981 A CN 202210852981A CN 114936326 A CN114936326 A CN 114936326A
- Authority
- CN
- China
- Prior art keywords
- user
- data
- information
- behavior
- preset
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
-
- 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
- G06N3/045—Combinations of networks
-
- 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
- G06N3/047—Probabilistic or stochastic networks
-
- 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
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention relates to the field of artificial intelligence, and discloses an information recommendation method, device, equipment and storage medium based on artificial intelligence, which are used for improving the accuracy of information recommendation. The information recommendation method based on artificial intelligence comprises the following steps: generating user preference data corresponding to the user according to the basic information and the browsing information; standardizing the user preference data to obtain standard user preference data, and extracting a plurality of user tags and behavior data in the standard user preference data; generating a characteristic value according to the behavior data, and generating coded data according to the characteristic value; inputting the coded data into an information recommendation model set for data processing to obtain a prediction probability, wherein the information recommendation model set comprises an LSTM model and a DNN model; inquiring a service information recommendation list according to the prediction probability to obtain service information to be recommended; and pushing the service information to be recommended to a visual terminal, and visually displaying the service information to be recommended through the visual terminal.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to an information recommendation method, device, equipment and storage medium based on artificial intelligence.
Background
An application program, which refers to a computer program for performing one or more specific tasks, operates in a user mode, can interact with a user, and has a visual user interface. With the rapid development of computer technology, more and more applications are applied to various industries, and applications in some financial business industries are generated accordingly. Information recommendation of business applications is very important, but information recommendation of existing business applications is messy and is not meaningful information recommendation.
At present, users can have no purpose in many cases when browsing product detail pages, and information recommendation of the existing scheme does not carry out personalized recommendation aiming at the users, so that the users cannot find the product information wanted by the users quickly.
Disclosure of Invention
The invention provides an information recommendation method, device, equipment and storage medium based on artificial intelligence, which are used for improving the accuracy of information recommendation.
The invention provides an artificial intelligence based information recommendation method in a first aspect, which comprises the following steps: acquiring basic information and browsing information of a user from a preset service application program, and generating user preference data corresponding to the user according to the basic information and the browsing information; standardizing the user preference data to obtain standard user preference data, and extracting a plurality of user tags and behavior data corresponding to the user from the standard user preference data; generating a characteristic value corresponding to each user tag according to the behavior data, and generating coded data according to the characteristic value corresponding to each user tag; inputting the coded data into a preset information recommendation model set for data processing to obtain a prediction probability, wherein the information recommendation model set comprises an LSTM model and a DNN model; inquiring a preset service information recommendation list according to the prediction probability to obtain service information to be recommended corresponding to the user; and pushing the service information to be recommended to a preset visual terminal, and visually displaying the service information to be recommended through the visual terminal.
Optionally, in a first implementation manner of the first aspect of the present invention, the obtaining basic information and browsing information of a user from a preset service application, and generating user preference data corresponding to the user according to the basic information and the browsing information includes: inquiring basic information and browsing information of a user from a preset service application program; extracting the registration information and the credit information of the user in the basic information, and carrying out authority verification on the registration information and the credit information to obtain a verification result; if the verification result is passed, performing tagging processing on the basic information to obtain user tag data corresponding to the user, and generating behavior data corresponding to the user according to the browsing information; and determining the user tag data and the behavior data as user preference data corresponding to the user.
Optionally, in a second implementation manner of the first aspect of the present invention, the normalizing the user preference data to obtain standard user preference data, and extracting a plurality of user tags and behavior data corresponding to the user in the standard user preference data includes: extracting the user preference data from a preset database; performing data cleaning on the user preference data through a preset data warehouse tool to obtain the user preference data after the data cleaning; calling a preset function to carry out normalization processing on the user preference data after the data cleaning to obtain standard user preference data; extracting a plurality of user tags and behavior data in the standard user preference data.
Optionally, in a third implementation manner of the first aspect of the present invention, the generating a feature value corresponding to each user tag according to the behavior data, and generating encoded data according to the feature value corresponding to each user tag includes: analyzing the behavior data to obtain a plurality of behavior characteristics in the behavior data, and determining the behavior frequency of each behavior characteristic according to the behavior characteristics; sequencing the behavior characteristics based on the behavior frequency to obtain behavior characteristic sequencing; matching the plurality of user labels according to the behavior feature ordering, wherein each behavior feature corresponds to each user label one to one; taking the behavior frequency of each behavior characteristic as a characteristic value corresponding to the user label corresponding to each behavior characteristic; and sorting according to the behavior characteristics and generating coded data according to the characteristic values.
Optionally, in a fourth implementation manner of the first aspect of the present invention, the inputting the encoded data into a preset information recommendation model set for data processing to obtain a prediction probability, where the information recommendation model set includes an LSTM model and a DNN model, and includes: carrying out vector conversion on the coded data to obtain an input hidden vector; inputting the input hidden vector into an LSTM model in a preset information recommendation model set for data processing to obtain a first prediction probability corresponding to the LSTM model; inputting the input hidden vector into a DNN model in a preset information recommendation model set for data processing to obtain a second prediction probability corresponding to the DNN model; acquiring preset weights corresponding to the LSTM model and the DNN model; and carrying out probability generation on the first prediction probability and the second prediction probability according to the preset weight to obtain the prediction probability.
Optionally, in a fifth implementation manner of the first aspect of the present invention, the inputting the input hidden vector into an LSTM model in a preset information recommendation model set to perform data processing, so as to obtain a first prediction probability corresponding to the LSTM model, includes: inputting the input hidden vector into an LSTM model in a preset information recommendation model set, wherein the LSTM model comprises: the system comprises an input layer, a bidirectional long-time memory network, an embedded layer and an output layer; carrying out one-hot vector coding on the input hidden vector through the input layer to obtain an initial vector; performing feature calculation on the initial vector through the bidirectional long-time and short-time memory network to obtain a feature vector; carrying out standardization processing on the characteristic vector through the embedding layer to obtain a standard vector; and performing probability calculation on the standard vector through the output layer to obtain a first prediction probability.
Optionally, in a sixth implementation manner of the first aspect of the present invention, the querying a preset service information recommendation list according to the prediction probability to obtain service information to be recommended corresponding to the user includes: acquiring a service information recommendation list, wherein the service information recommendation list comprises a plurality of pieces of service information to be recommended, and each piece of service information to be recommended corresponds to a preset target value; inquiring a preset target value equal to the prediction probability to obtain a matching target value; and taking the service information to be recommended corresponding to the matching target value as the service information to be recommended corresponding to the user.
The second aspect of the present invention provides an artificial intelligence-based information recommendation apparatus, including: the acquisition module is used for acquiring basic information and browsing information of a user from a preset service application program and generating user preference data corresponding to the user according to the basic information and the browsing information; the standardization module is used for standardizing the user preference data to obtain standard user preference data and extracting a plurality of user tags and behavior data corresponding to the user from the standard user preference data; the generating module is used for generating a characteristic value corresponding to each user tag according to the behavior data and generating coded data according to the characteristic value corresponding to each user tag; the processing module is used for inputting the coded data into a preset information recommendation model set for data processing to obtain a prediction probability, wherein the information recommendation model set comprises an LSTM model and a DNN model; the query module is used for querying a preset service information recommendation list according to the prediction probability to obtain service information to be recommended corresponding to the user; and the display module is used for pushing the service information to be recommended to a preset visual terminal and visually displaying the service information to be recommended through the visual terminal.
Optionally, in a first implementation manner of the second aspect of the present invention, the obtaining module is specifically configured to: inquiring basic information and browsing information of a user from a preset service application program; extracting the registration information and the credit information of the user in the basic information, and carrying out authority verification on the registration information and the credit information to obtain a verification result; if the verification result is passed, performing tagging processing on the basic information to obtain user tag data corresponding to the user, and generating behavior data corresponding to the user according to the browsing information; and determining the user tag data and the behavior data as user preference data corresponding to the user.
Optionally, in a second implementation manner of the second aspect of the present invention, the normalization module is specifically configured to: extracting the user preference data from a preset database; performing data cleaning on the user preference data through a preset data warehouse tool to obtain the user preference data after the data cleaning; calling a preset function to carry out normalization processing on the user preference data after the data cleaning to obtain standard user preference data; extracting a plurality of user tags and behavior data in the standard user preference data.
Optionally, in a third implementation manner of the second aspect of the present invention, the generating module is specifically configured to: analyzing the behavior data to obtain a plurality of behavior characteristics in the behavior data, and determining the behavior frequency of each behavior characteristic according to the behavior characteristics; sequencing the behavior characteristics based on the behavior frequency to obtain behavior characteristic sequencing; matching the plurality of user labels according to the behavior feature ordering, wherein each behavior feature corresponds to each user label one to one; taking the behavior frequency of each behavior characteristic as a characteristic value corresponding to the user label corresponding to each behavior characteristic; and sorting according to the behavior characteristics and generating coded data according to the characteristic values.
Optionally, in a fourth implementation manner of the second aspect of the present invention, the processing module further includes: the conversion unit is used for carrying out vector conversion on the coded data to obtain an input hidden vector; the first data processing unit is used for inputting the input hidden vector into an LSTM model in a preset information recommendation model set for data processing to obtain a first prediction probability corresponding to the LSTM model; the second data processing unit is used for inputting the input hidden vector into a DNN model in a preset information recommendation model set for data processing to obtain a second prediction probability corresponding to the DNN model; the obtaining unit is used for obtaining preset weights corresponding to the LSTM model and the DNN model; and the generating unit is used for carrying out probability generation on the first prediction probability and the second prediction probability according to the preset weight to obtain the prediction probability.
Optionally, in a fifth implementation manner of the second aspect of the present invention, the first data processing unit is specifically configured to: inputting the input hidden vector into an LSTM model in a preset information recommendation model set, wherein the LSTM model comprises: the system comprises an input layer, a bidirectional long-time memory network, an embedded layer and an output layer; carrying out one-hot vector coding on the input hidden vector through the input layer to obtain an initial vector; performing feature calculation on the initial vector through the bidirectional long-time and short-time memory network to obtain a feature vector; carrying out standardization processing on the characteristic vector through the embedding layer to obtain a standard vector; and performing probability calculation on the standard vector through the output layer to obtain a first prediction probability.
Optionally, in a sixth implementation manner of the second aspect of the present invention, the query module is specifically configured to: acquiring a service information recommendation list, wherein the service information recommendation list comprises a plurality of pieces of service information to be recommended, and each piece of service information to be recommended corresponds to a preset target value; inquiring a preset target value equal to the prediction probability to obtain a matching target value; and taking the service information to be recommended corresponding to the matching target value as the service information to be recommended corresponding to the user.
The third aspect of the present invention provides an artificial intelligence-based information recommendation apparatus, including: a memory and at least one processor, the memory having instructions stored therein; the at least one processor invokes the instructions in the memory to cause the artificial intelligence based information recommendation device to perform the artificial intelligence based information recommendation method described above.
A fourth aspect of the present invention provides a computer-readable storage medium having stored therein instructions, which, when run on a computer, cause the computer to execute the artificial intelligence based information recommendation method described above.
In the technical scheme provided by the invention, basic information and browsing information of a user are acquired from a preset service application program, and user preference data corresponding to the user is generated according to the basic information and the browsing information; standardizing the user preference data to obtain standard user preference data, and extracting a plurality of user tags and behavior data corresponding to the user from the standard user preference data; generating a characteristic value corresponding to each user tag according to the behavior data, and generating coded data according to the characteristic value corresponding to each user tag; inputting the coded data into a preset information recommendation model set for data processing to obtain a prediction probability, wherein the information recommendation model set comprises an LSTM model and a DNN model; inquiring a preset service information recommendation list according to the prediction probability to obtain service information to be recommended corresponding to the user; and pushing the service information to be recommended to a preset visual terminal, and visually displaying the service information to be recommended through the visual terminal. According to the method, the accuracy of the portrait of the user is improved by analyzing the preference data of the user, and the user preference data is analyzed through the pre-trained model set, so that the prediction probability of the model set is more accurate compared with that of a traditional single model, and the accuracy of information recommendation is improved.
Drawings
FIG. 1 is a schematic diagram of an embodiment of an artificial intelligence-based information recommendation method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of another embodiment of an artificial intelligence based information recommendation method according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an embodiment of an artificial intelligence-based information recommendation apparatus according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of another embodiment of an artificial intelligence-based information recommendation apparatus according to an embodiment of the present invention;
FIG. 5 is a diagram of an embodiment of an artificial intelligence based information recommendation apparatus according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides an information recommendation method, device, equipment and storage medium based on artificial intelligence, which are used for improving the accuracy of information recommendation. The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be implemented in other sequences than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
For convenience of understanding, a detailed flow of an embodiment of the present invention is described below, and referring to fig. 1, an embodiment of an artificial intelligence based information recommendation method in an embodiment of the present invention includes:
101. acquiring basic information and browsing information of a user from a preset service application program, and generating user preference data corresponding to the user according to the basic information and the browsing information;
it is to be understood that the executing subject of the present invention may be an artificial intelligence based information recommendation apparatus, and may also be a terminal or a server, which is not limited herein. The embodiment of the present invention is described by taking a server as an execution subject.
It should be noted that, the user is a user to be recommended, the user opens a preset service application program, the service application program may be a service application program of a related financial industry such as stock, fund and the like, and when opening user page content, the user page content includes: the key, the news, the community, etc. The basic information of the user includes: the method comprises the following steps of registering information and credit information of a user, wherein the credit information is specifically transaction credit records of the user, and the browsing information comprises: browsing, collecting, applying for and clicking rate of the service application program by the user. Specifically, the server performs data analysis according to the basic information and the browsing information, the data analysis can calculate the relevance of the preference of the user, store the preference information of the user in a tagged manner, generate behavior data according to the operation behaviors of the user, such as click rate, and the like, store the behavior data, and finally obtain the user preference data of the user.
102. Standardizing the user preference data to obtain standard user preference data, and extracting a plurality of user tags and behavior data corresponding to users in the standard user preference data;
specifically, the server performs data standardization processing through a distributed data warehouse HIVE and a user-defined function UDF to obtain standard user preference data of the user; the server carries out data standardization processing on the user preference data to find and correct recognizable errors in the data files, checks data consistency, processes invalid values, missing values and the like, and extracts a plurality of user tags and behavior data corresponding to users in the standard user preference data.
103. Generating a characteristic value corresponding to each user tag according to the behavior data, and generating coded data according to the characteristic value corresponding to each user tag;
specifically, the server performs feature analysis to obtain a plurality of behavior features, and determines a behavior frequency of each behavior feature, where the behavior frequency is used to indicate a frequency of an operation behavior corresponding to the behavior feature of the user; the server carries out behavior feature sequencing and matches a plurality of user tags, wherein each behavior feature of the user corresponds to one user tag; the server takes the frequency of the behavior feature as a feature value and generates encoded data.
104. Inputting the coded data into a preset information recommendation model set for data processing to obtain a prediction probability, wherein the information recommendation model set comprises an LSTM model and a DNN model;
it should be noted that the information recommendation model set includes an LSTM model and a DNN model, where the LSTM model is a long-short term memory network, which is a time-cycle neural network, and specifically includes an input layer, a bidirectional long-short term memory network, an embedded layer, and an output layer; the DNN model is a deep learning network that includes an input layer, a hidden layer, and an output layer. Furthermore, the LSTM model performs probability calculation on the coded data to obtain a first prediction probability value corresponding to the LSTM model, the DNN model performs probability calculation on the coded data to obtain a second prediction probability corresponding to the DNN model, and the server performs normalization operation on the prediction probability values output by the LSTM model and the DNN model according to preset model weight to generate the prediction probability of the information recommendation model set. In the embodiment, probability prediction is performed through the information recommendation model set which is constructed in advance, and compared with the probability prediction performed by a traditional single model, the probability prediction method has a better prediction effect, so that the pushed information is more in line with personal preference of a user.
105. Inquiring a preset service information recommendation list according to the prediction probability to obtain service information to be recommended corresponding to the user;
it should be noted that the preset service information recommendation list includes a plurality of pieces of service information to be recommended, where the service information to be recommended may be: daily financial news, market analysis tweets, and the like. And the server inquires according to the prediction probability to obtain the service information to be recommended of the user.
106. And pushing the service information to be recommended to a preset visual terminal, and visually displaying the service information to be recommended through the visual terminal.
Specifically, the server pushes the service information to be recommended to a visual terminal used by the user currently browsing the service application program, and the visual terminal receives the service information to be recommended pushed by the server and visually displays the service information to be recommended so that the user can browse the service information.
In the embodiment of the invention, basic information and browsing information of a user are obtained from a preset service application program, and user preference data corresponding to the user is generated according to the basic information and the browsing information; standardizing the user preference data to obtain standard user preference data, and extracting a plurality of user tags and behavior data corresponding to users in the standard user preference data; generating a characteristic value corresponding to each user tag according to the behavior data, and generating coded data according to the characteristic value corresponding to each user tag; inputting the coded data into a preset information recommendation model set for data processing to obtain a prediction probability, wherein the information recommendation model set comprises an LSTM model and a DNN model; inquiring a preset service information recommendation list according to the prediction probability to obtain service information to be recommended corresponding to the user; and pushing the service information to be recommended to a preset visual terminal, and visually displaying the service information to be recommended through the visual terminal. According to the method, the preference data of the user are analyzed, so that the accuracy of the portrait of the user is improved, and the preference data of the user are analyzed through the pre-trained model set, so that the prediction probability of the model set is more accurate compared with that of a traditional single model, and the accuracy of information recommendation is improved.
Referring to fig. 2, another embodiment of the artificial intelligence based information recommendation method according to the embodiment of the present invention includes:
201. acquiring basic information and browsing information of a user from a preset service application program, and generating user preference data corresponding to the user according to the basic information and the browsing information;
optionally, the server queries basic information and browsing information of the user from a preset service application program; extracting registration information and credit information of a user in basic information, wherein the registration information specifically comprises a mobile phone number, a name, a gender and the like of the user, the credit information specifically is information of a transaction credit record of the user, a server performs authority verification on the registration information and the credit information, the server verifies login authority of the user to obtain a verification result, and the verification result comprises a pass or a fail; if the verification result is that the user passes the verification, performing tagging processing on the basic information to obtain user tag data corresponding to the user, and generating behavior data corresponding to the user according to the browsing information; and determining the user tag data and the behavior data as user preference data corresponding to the user. Further, if the verification result is that the service data program does not pass, personalized information recommendation is not performed on the user, and visual recommendation is performed on the user through preset standard recommendation information, wherein the standard recommendation information is push information which can be received by the user of each service data program.
202. Standardizing the user preference data to obtain standard user preference data, and extracting a plurality of user tags and behavior data corresponding to users in the standard user preference data;
optionally, the server stores the user preference data in a preset database, and the server extracts the user preference data of the user from the database; the server performs data cleaning on the user preference data through a preset data warehouse tool to obtain the user preference data after the data cleaning, the data cleaning operation can find and correct recognizable error data in the user preference data, the consistency of the user preference data can be checked, invalid values, missing values and the like can be processed, and the data warehouse tool can be a distributed data warehouse HIVE; the server calls a preset function to carry out normalization processing on the user preference data after data cleaning to obtain standard user preference data, wherein the function can be a user-defined function UDF; the server extracts a plurality of user tags and behavior data in the standard user preference data.
203. Generating a characteristic value corresponding to each user tag according to the behavior data, and generating coded data according to the characteristic value corresponding to each user tag;
optionally, the server analyzes the behavior data to obtain a plurality of behavior features in the behavior data, where the behavior features are, for example: the click rate of the user, the page pause duration and the like; determining the behavior frequency of each behavior feature according to the plurality of behavior features, wherein the behavior frequency is, for example, the click rate of the user is generated into the behavior frequency corresponding to the click rate of the user, and when the click rate is 3 times, the behavior frequency is determined to be 3; the server sorts the behavior characteristics based on the behavior frequency, and sorts the behavior characteristics from large to small according to the magnitude sequence of the behavior frequency to obtain behavior characteristic sorting; the server matches a plurality of user labels according to the behavior feature sequence, wherein each behavior feature corresponds to each user label one to one; the server takes the behavior frequency of each behavior feature as a feature value corresponding to the user tag corresponding to each behavior feature, for example: when the behavior frequency is 3, determining that the characteristic value is 3; and sorting according to the behavior characteristics and generating coded data according to the characteristic values, sorting the characteristic values of the user in a one-to-one correspondence manner according to the sorting sequence of the behavior characteristics, and coding the characteristic values of the sorting sequence into vectors to obtain the coded data.
204. Carrying out vector conversion on the coded data to obtain an input hidden vector;
specifically, the server performs implicit vector coding processing on the coded data according to the behavior characteristic sequence to obtain an input sequence, and the server converts the input sequence into a coded vector to obtain an input hidden vector. Because different skill trees and behavior frequency differences are large in actual user behaviors, the method and the device adopt an up-sampling and down-sampling mode to carry out sample balance, and therefore the server generates an input sequence according to the coded data and carries out vector conversion on the input sequence to obtain an input hidden vector.
205. Inputting the input hidden vector into an LSTM model in a preset information recommendation model set for data processing to obtain a first prediction probability corresponding to the LSTM model;
optionally, the server inputs the input hidden vector into an LSTM model in a preset information recommendation model set, where the LSTM model includes: the system comprises an input layer, a bidirectional long-time memory network, an embedded layer and an output layer; the method comprises the steps that one-hot vector coding is carried out on an input hidden vector through an input layer to obtain an initial vector, the input hidden vector is converted into the initial vector by a server according to a preset embbbling vector conversion rule, the input hidden vector cannot be directly identified by a bidirectional long-time memory network, and therefore the input hidden vector needs to be converted into a vector which can be identified by a neural network to obtain the initial vector; performing feature calculation on the initial vector through a bidirectional long-and-short-term memory network to obtain a feature vector, specifically, performing multilayer superposition calculation on the initial vector through the bidirectional long-and-short-term memory network to obtain the feature vector; carrying out standardization processing on the characteristic vector through an embedding layer to obtain a standard vector; and performing probability calculation on the standard vector through an output layer to obtain a first prediction probability, wherein the output layer is a sigmiod function, and performing probability prediction on the standard vector through the function to generate the first prediction probability of the LSTM model.
206. Inputting the input hidden vector into a DNN model in a preset information recommendation model set for data processing to obtain a second prediction probability corresponding to the DNN model;
it should be noted that the neural network layers inside the DNN model may be divided into three types, i.e., an input layer, a hidden layer and an output layer, where the first layer is an input layer, the last layer is an output layer, and the middle layers are hidden layers, and the layers of the DNN model are fully connected, that is, any neuron on the ith layer is necessarily connected to any neuron on the (i + 1) th layer. The DNN model enables the model to be output from original input to final output by reducing manual preprocessing and subsequent processing, more space can be automatically adjusted according to data is provided for the model, and the overall fitting degree of the model is increased. And the server inputs the input hidden vector into a DNN model in a preset information recommendation model set, and finally outputs a second prediction probability corresponding to the DNN model through an output layer in the DNN model in a construction mode that a computation kernel of a hidden layer neuron in the DNN model is X X W + b and a softmax function (a Sigmoid function is used in binary classification) is used as a nonlinear kernel.
207. Acquiring preset weights corresponding to the LSTM model and the DNN model;
specifically, the server searches preset LSTM models and preset weights corresponding to DNN models from the database, wherein the LSTM models are set to be 0.6 in weight and the DNN models are set to be 0.4 in weight.
208. Carrying out probability generation on the first prediction probability and the second prediction probability according to a preset weight to obtain a prediction probability;
specifically, the server performs probability generation on the first prediction probability and the second prediction probability according to a preset weight to obtain prediction probabilities, for example: and when the first prediction probability is 1 and the second prediction probability is 6, calculating to obtain the prediction probability of 3 according to the weight 0.6 of the LSTM model and the weight 0.4 of the DNN model.
209. Inquiring a preset service information recommendation list according to the prediction probability to obtain service information to be recommended corresponding to the user;
optionally, the server obtains a service information recommendation list, where the service information recommendation list includes a plurality of pieces of service information to be recommended, and each piece of service information to be recommended corresponds to a preset target value; inquiring a preset target value equal to the prediction probability to obtain a matching target value; and taking the service information to be recommended corresponding to the matching target value as the service information to be recommended corresponding to the user. The preset service information recommendation list comprises a plurality of pieces of service information to be recommended, and the service information to be recommended may be: daily financial news, market analysis tweets, and the like. And the server inquires according to the prediction probability to obtain the service information to be recommended of the user.
210. And pushing the service information to be recommended to a preset visual terminal, and visually displaying the service information to be recommended through the visual terminal.
Specifically, the server pushes the service information to be recommended to a visual terminal used by the user currently browsing the service application program, and the visual terminal receives the service information to be recommended pushed by the server and visually displays the service information to be recommended so that the user can browse the service information.
In the embodiment of the invention, basic information and browsing information of a user are obtained from a preset service application program, and user preference data corresponding to the user is generated according to the basic information and the browsing information; standardizing the user preference data to obtain standard user preference data, and extracting a plurality of user tags and behavior data corresponding to users in the standard user preference data; generating a characteristic value corresponding to each user tag according to the behavior data, and generating coded data according to the characteristic value corresponding to each user tag; inputting the coded data into a preset information recommendation model set for data processing to obtain a prediction probability, wherein the information recommendation model set comprises an LSTM model and a DNN model; inquiring a preset service information recommendation list according to the prediction probability to obtain service information to be recommended corresponding to the user; and pushing the service information to be recommended to a preset visual terminal, and visually displaying the service information to be recommended through the visual terminal. According to the method, the accuracy of the portrait of the user is improved by analyzing the preference data of the user, and the user preference data is analyzed through the pre-trained model set, so that the prediction probability of the model set is more accurate compared with that of a traditional single model, and the accuracy of information recommendation is improved.
In the above description of the information recommendation method based on artificial intelligence in the embodiment of the present invention, referring to fig. 3, an information recommendation apparatus based on artificial intelligence in the embodiment of the present invention is described below, where an embodiment of the information recommendation apparatus based on artificial intelligence in the embodiment of the present invention includes:
an obtaining module 301, configured to obtain basic information and browsing information of a user from a preset service application program, and generate user preference data corresponding to the user according to the basic information and the browsing information;
a standardization module 302, configured to standardize the user preference data to obtain standard user preference data, and extract a plurality of user tags and behavior data corresponding to the user from the standard user preference data;
a generating module 303, configured to generate a feature value corresponding to each user tag according to the behavior data, and generate encoded data according to the feature value corresponding to each user tag;
the processing module 304 is configured to input the encoded data into a preset information recommendation model set for data processing to obtain a prediction probability, where the information recommendation model set includes an LSTM model and a DNN model;
the query module 305 is configured to query a preset service information recommendation list according to the prediction probability to obtain service information to be recommended corresponding to the user;
the display module 306 is configured to push the service information to be recommended to a preset visual terminal, and visually display the service information to be recommended through the visual terminal.
In the embodiment of the invention, basic information and browsing information of a user are obtained from a preset service application program, and user preference data corresponding to the user is generated according to the basic information and the browsing information; standardizing the user preference data to obtain standard user preference data, and extracting a plurality of user tags and behavior data corresponding to the user from the standard user preference data; generating a characteristic value corresponding to each user tag according to the behavior data, and generating coded data according to the characteristic value corresponding to each user tag; inputting the coded data into a preset information recommendation model set for data processing to obtain a prediction probability, wherein the information recommendation model set comprises an LSTM model and a DNN model; inquiring a preset service information recommendation list according to the prediction probability to obtain service information to be recommended corresponding to the user; and pushing the service information to be recommended to a preset visual terminal, and visually displaying the service information to be recommended through the visual terminal. According to the method, the preference data of the user are analyzed, so that the accuracy of the portrait of the user is improved, and the preference data of the user are analyzed through the pre-trained model set, so that the prediction probability of the model set is more accurate compared with that of a traditional single model, and the accuracy of information recommendation is improved.
Referring to fig. 4, another embodiment of the artificial intelligence based information recommendation apparatus according to the embodiment of the present invention includes:
an obtaining module 301, configured to obtain basic information and browsing information of a user from a preset service application program, and generate user preference data corresponding to the user according to the basic information and the browsing information;
a standardization module 302, configured to standardize the user preference data to obtain standard user preference data, and extract a plurality of user tags and behavior data corresponding to the user from the standard user preference data;
a generating module 303, configured to generate a feature value corresponding to each user tag according to the behavior data, and generate encoded data according to the feature value corresponding to each user tag;
the processing module 304 is configured to input the encoded data into a preset information recommendation model set for data processing to obtain a prediction probability, where the information recommendation model set includes an LSTM model and a DNN model;
the query module 305 is configured to query a preset service information recommendation list according to the prediction probability to obtain service information to be recommended corresponding to the user;
the display module 306 is configured to push the service information to be recommended to a preset visual terminal, and visually display the service information to be recommended through the visual terminal.
Optionally, the obtaining module 301 is specifically configured to: inquiring basic information and browsing information of a user from a preset service application program; extracting the registration information and the credit information of the user in the basic information, and carrying out authority verification on the registration information and the credit information to obtain a verification result; if the verification result is that the basic information passes, performing tagging processing on the basic information to obtain user tag data corresponding to the user, and generating behavior data corresponding to the user according to the browsing information; and determining the user tag data and the behavior data as user preference data corresponding to the user.
Optionally, the normalization module 302 is specifically configured to: extracting the user preference data from a preset database; performing data cleaning on the user preference data through a preset data warehouse tool to obtain the user preference data after the data cleaning; calling a preset function to carry out normalization processing on the user preference data after the data cleaning to obtain standard user preference data; extracting a plurality of user tags and behavior data in the standard user preference data.
Optionally, the generating module 303 is specifically configured to: analyzing the behavior data to obtain a plurality of behavior characteristics in the behavior data, and determining the behavior frequency of each behavior characteristic according to the behavior characteristics; sequencing the behavior characteristics based on the behavior frequency to obtain behavior characteristic sequencing; matching the plurality of user labels according to the behavior feature ordering, wherein each behavior feature corresponds to each user label one to one; taking the behavior frequency of each behavior characteristic as a characteristic value corresponding to the user label corresponding to each behavior characteristic; and sequencing according to the behavior characteristics and generating coded data according to the characteristic values.
Optionally, the processing module 304 further includes: a converting unit 3041, configured to perform vector conversion on the encoded data to obtain an input hidden vector; a first data processing unit 3042, configured to input the input hidden vector into an LSTM model in a preset information recommendation model set to perform data processing, so as to obtain a first prediction probability corresponding to the LSTM model; a second data processing unit 3043, configured to input the input hidden vector into a preset information recommendation model set, and perform data processing on the DNN model to obtain a second prediction probability corresponding to the DNN model; an obtaining unit 3044, configured to obtain preset weights corresponding to the LSTM model and the DNN model; a generating unit 3045, configured to perform probability generation on the first prediction probability and the second prediction probability according to the preset weight, so as to obtain a prediction probability.
Optionally, the first data processing unit 3042 is specifically configured to: inputting the input hidden vector into an LSTM model in a preset information recommendation model set, wherein the LSTM model comprises: the system comprises an input layer, a bidirectional long-time memory network, an embedded layer and an output layer; carrying out one-hot vector coding on the input hidden vector through the input layer to obtain an initial vector; performing feature calculation on the initial vector through the bidirectional long-time and short-time memory network to obtain a feature vector; carrying out standardization processing on the characteristic vector through the embedding layer to obtain a standard vector; and performing probability calculation on the standard vector through the output layer to obtain a first prediction probability.
Optionally, the query module 305 is specifically configured to: acquiring a service information recommendation list, wherein the service information recommendation list comprises a plurality of pieces of service information to be recommended, and each piece of service information to be recommended corresponds to a preset target value; inquiring a preset target value equal to the prediction probability to obtain a matching target value; and taking the service information to be recommended corresponding to the matching target value as the service information to be recommended corresponding to the user.
In the embodiment of the invention, basic information and browsing information of a user are obtained from a preset service application program, and user preference data corresponding to the user is generated according to the basic information and the browsing information; standardizing the user preference data to obtain standard user preference data, and extracting a plurality of user tags and behavior data corresponding to the user from the standard user preference data; generating a characteristic value corresponding to each user tag according to the behavior data, and generating coded data according to the characteristic value corresponding to each user tag; inputting the coded data into a preset information recommendation model set for data processing to obtain a prediction probability, wherein the information recommendation model set comprises an LSTM model and a DNN model; inquiring a preset service information recommendation list according to the prediction probability to obtain service information to be recommended corresponding to the user; and pushing the service information to be recommended to a preset visual terminal, and visually displaying the service information to be recommended through the visual terminal. According to the method, the preference data of the user are analyzed, so that the accuracy of the portrait of the user is improved, and the preference data of the user are analyzed through the pre-trained model set, so that the prediction probability of the model set is more accurate compared with that of a traditional single model, and the accuracy of information recommendation is improved.
Fig. 3 and 4 above describe the artificial intelligence based information recommendation apparatus in the embodiment of the present invention in detail from the perspective of the modular functional entity, and the following describes the artificial intelligence based information recommendation apparatus in the embodiment of the present invention in detail from the perspective of the hardware processing.
Fig. 5 is a schematic structural diagram of an artificial intelligence based information recommendation device 500 according to an embodiment of the present invention, which may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 510 (e.g., one or more processors) and a memory 520, one or more storage media 530 (e.g., one or more mass storage devices) for storing applications 533 or data 532. Memory 520 and storage media 530 may be, among other things, transient or persistent storage. The program stored on the storage medium 530 may include one or more modules (not shown), each of which may include a series of instruction operations for the artificial intelligence based information recommendation device 500. Still further, the processor 510 may be configured to communicate with the storage medium 530 to execute a series of instruction operations in the storage medium 530 on the artificial intelligence based information recommendation device 500.
The artificial intelligence based information recommendation device 500 may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input-output interfaces 560, and/or one or more operating systems 531, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, and the like. Those skilled in the art will appreciate that the configuration of the artificial intelligence based information recommendation device illustrated in FIG. 5 does not constitute a limitation of the artificial intelligence based information recommendation device and may include more or less components than those illustrated, or some components may be combined, or a different arrangement of components.
The invention also provides an artificial intelligence based information recommendation device, which comprises a memory and a processor, wherein the memory stores computer readable instructions, and the computer readable instructions, when executed by the processor, cause the processor to execute the steps of the artificial intelligence based information recommendation method in the above embodiments.
The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, having stored therein instructions, which, when executed on a computer, cause the computer to perform the steps of the artificial intelligence based information recommendation method.
Further, the computer-readable storage medium 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 required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. An artificial intelligence based information recommendation method is characterized in that the artificial intelligence based information recommendation method comprises the following steps:
acquiring basic information and browsing information of a user from a preset service application program, and generating user preference data corresponding to the user according to the basic information and the browsing information;
standardizing the user preference data to obtain standard user preference data, and extracting a plurality of user tags and behavior data corresponding to the user from the standard user preference data;
generating a characteristic value corresponding to each user tag according to the behavior data, and generating coded data according to the characteristic value corresponding to each user tag;
inputting the coded data into a preset information recommendation model set for data processing to obtain a prediction probability, wherein the information recommendation model set comprises an LSTM model and a DNN model;
inquiring a preset service information recommendation list according to the prediction probability to obtain service information to be recommended corresponding to the user;
and pushing the service information to be recommended to a preset visual terminal, and visually displaying the service information to be recommended through the visual terminal.
2. The artificial intelligence based information recommendation method according to claim 1, wherein the obtaining of the basic information and the browsing information of the user from a preset service application and the generating of the user preference data corresponding to the user according to the basic information and the browsing information comprises:
inquiring basic information and browsing information of a user from a preset service application program;
extracting the registration information and the credit information of the user in the basic information, and carrying out authority verification on the registration information and the credit information to obtain a verification result;
if the verification result is that the basic information passes, performing tagging processing on the basic information to obtain user tag data corresponding to the user, and generating behavior data corresponding to the user according to the browsing information;
and determining the user tag data and the behavior data as user preference data corresponding to the user.
3. The artificial intelligence based information recommendation method according to claim 1, wherein the standardizing the user preference data to obtain standard user preference data, and extracting a plurality of user tags and behavior data corresponding to the user from the standard user preference data comprises:
extracting the user preference data from a preset database;
performing data cleaning on the user preference data through a preset data warehouse tool to obtain the user preference data after the data cleaning;
calling a preset function to carry out normalization processing on the user preference data after the data cleaning to obtain standard user preference data;
extracting a plurality of user tags and behavior data in the standard user preference data.
4. The artificial intelligence based information recommendation method according to claim 1, wherein the generating a feature value corresponding to each user tag according to the behavior data and generating encoded data according to the feature value corresponding to each user tag comprises:
analyzing the behavior data to obtain a plurality of behavior characteristics in the behavior data, and determining the behavior frequency of each behavior characteristic according to the behavior characteristics;
sequencing the behavior characteristics based on the behavior frequency to obtain behavior characteristic sequencing;
matching the plurality of user labels according to the behavior feature ordering, wherein each behavior feature corresponds to each user label one to one;
taking the behavior frequency of each behavior characteristic as a characteristic value corresponding to the user label corresponding to each behavior characteristic;
and sorting according to the behavior characteristics and generating coded data according to the characteristic values.
5. The artificial intelligence based information recommendation method according to claim 1, wherein the inputting the encoded data into a preset information recommendation model set for data processing to obtain a prediction probability, wherein the information recommendation model set comprises an LSTM model and a DNN model, and comprises:
performing vector conversion on the coded data to obtain an input hidden vector;
inputting the input hidden vector into an LSTM model in a preset information recommendation model set for data processing to obtain a first prediction probability corresponding to the LSTM model;
inputting the input hidden vector into a DNN model in a preset information recommendation model set for data processing to obtain a second prediction probability corresponding to the DNN model;
acquiring preset weights corresponding to the LSTM model and the DNN model;
and carrying out probability generation on the first prediction probability and the second prediction probability according to the preset weight to obtain the prediction probability.
6. The artificial intelligence-based information recommendation method according to claim 5, wherein the inputting the input hidden vector into an LSTM model in a preset information recommendation model set for data processing to obtain a first prediction probability corresponding to the LSTM model comprises:
inputting the input hidden vector into an LSTM model in a preset information recommendation model set, wherein the LSTM model comprises: the system comprises an input layer, a bidirectional long-time memory network, an embedded layer and an output layer;
carrying out one-hot vector coding on the input hidden vector through the input layer to obtain an initial vector;
performing feature calculation on the initial vector through the bidirectional long-time and short-time memory network to obtain a feature vector;
carrying out standardization processing on the characteristic vector through the embedding layer to obtain a standard vector;
and performing probability calculation on the standard vector through the output layer to obtain a first prediction probability.
7. The artificial intelligence-based information recommendation method according to claim 1, wherein the querying a preset service information recommendation list according to the prediction probability to obtain service information to be recommended corresponding to the user comprises:
acquiring a service information recommendation list, wherein the service information recommendation list comprises a plurality of pieces of service information to be recommended, and each piece of service information to be recommended corresponds to a preset target value;
inquiring a preset target value equal to the prediction probability to obtain a matching target value;
and taking the service information to be recommended corresponding to the matching target value as the service information to be recommended corresponding to the user.
8. An artificial intelligence based information recommendation apparatus, characterized in that the artificial intelligence based information recommendation apparatus comprises:
the acquisition module is used for acquiring basic information and browsing information of a user from a preset service application program and generating user preference data corresponding to the user according to the basic information and the browsing information;
the standardization module is used for standardizing the user preference data to obtain standard user preference data and extracting a plurality of user tags and behavior data corresponding to the user from the standard user preference data;
the generating module is used for generating a characteristic value corresponding to each user tag according to the behavior data and generating coded data according to the characteristic value corresponding to each user tag;
the processing module is used for inputting the coded data into a preset information recommendation model set for data processing to obtain a prediction probability, wherein the information recommendation model set comprises an LSTM model and a DNN model;
the query module is used for querying a preset service information recommendation list according to the prediction probability to obtain the service information to be recommended corresponding to the user;
and the display module is used for pushing the service information to be recommended to a preset visual terminal and visually displaying the service information to be recommended through the visual terminal.
9. An artificial intelligence based information recommendation apparatus, characterized in that the artificial intelligence based information recommendation apparatus comprises: a memory and at least one processor, the memory having instructions stored therein;
the at least one processor invokes the instructions in the memory to cause the artificial intelligence based information recommendation device to perform the artificial intelligence based information recommendation method of any of claims 1-7.
10. A computer-readable storage medium having instructions stored thereon, wherein the instructions, when executed by a processor, implement the artificial intelligence based information recommendation method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210852981.7A CN114936326B (en) | 2022-07-20 | 2022-07-20 | Information recommendation method, device, equipment and storage medium based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210852981.7A CN114936326B (en) | 2022-07-20 | 2022-07-20 | Information recommendation method, device, equipment and storage medium based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114936326A true CN114936326A (en) | 2022-08-23 |
| CN114936326B CN114936326B (en) | 2022-11-29 |
Family
ID=82867714
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210852981.7A Active CN114936326B (en) | 2022-07-20 | 2022-07-20 | Information recommendation method, device, equipment and storage medium based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114936326B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115294682A (en) * | 2022-10-09 | 2022-11-04 | 深圳壹家智能锁有限公司 | Data management method, device and equipment for intelligent door lock and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109359244A (en) * | 2018-10-30 | 2019-02-19 | 中国科学院计算技术研究所 | A kind of recommendation method for personalized information and device |
| CN110413837A (en) * | 2019-05-30 | 2019-11-05 | 腾讯科技（深圳）有限公司 | Video recommendation method and device |
| KR20200101068A (en) * | 2019-02-19 | 2020-08-27 | 오드컨셉 주식회사 | A method of providing a fashion item recommendation service using a body shape and purchase history |
| CN111651584A (en) * | 2020-04-17 | 2020-09-11 | 世纪保众(北京)网络科技有限公司 | Insurance article recommendation method based on user behavior characteristics and article attributes |
| CN112529665A (en) * | 2020-12-18 | 2021-03-19 | 平安银行股份有限公司 | Product recommendation method and device based on combined model and computer equipment |
| KR20210042867A (en) * | 2020-09-01 | 2021-04-20 | 베이징 바이두 넷컴 사이언스 앤 테크놀로지 코., 엘티디. | Content recommendation method, apparatus, equipment and medium |
| CN112837106A (en) * | 2019-11-22 | 2021-05-25 | 上海哔哩哔哩科技有限公司 | Commodity recommendation method and device and computer equipment |
| CN113626704A (en) * | 2021-08-10 | 2021-11-09 | 平安国际智慧城市科技股份有限公司 | Method, device and equipment for recommending information based on word2vec model |
| CN114596126A (en) * | 2022-04-26 | 2022-06-07 | 土巴兔集团股份有限公司 | Advertisement recommendation method and device |
-
2022
- 2022-07-20 CN CN202210852981.7A patent/CN114936326B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109359244A (en) * | 2018-10-30 | 2019-02-19 | 中国科学院计算技术研究所 | A kind of recommendation method for personalized information and device |
| KR20200101068A (en) * | 2019-02-19 | 2020-08-27 | 오드컨셉 주식회사 | A method of providing a fashion item recommendation service using a body shape and purchase history |
| CN110413837A (en) * | 2019-05-30 | 2019-11-05 | 腾讯科技（深圳）有限公司 | Video recommendation method and device |
| CN112837106A (en) * | 2019-11-22 | 2021-05-25 | 上海哔哩哔哩科技有限公司 | Commodity recommendation method and device and computer equipment |
| CN111651584A (en) * | 2020-04-17 | 2020-09-11 | 世纪保众(北京)网络科技有限公司 | Insurance article recommendation method based on user behavior characteristics and article attributes |
| KR20210042867A (en) * | 2020-09-01 | 2021-04-20 | 베이징 바이두 넷컴 사이언스 앤 테크놀로지 코., 엘티디. | Content recommendation method, apparatus, equipment and medium |
| CN112529665A (en) * | 2020-12-18 | 2021-03-19 | 平安银行股份有限公司 | Product recommendation method and device based on combined model and computer equipment |
| CN113626704A (en) * | 2021-08-10 | 2021-11-09 | 平安国际智慧城市科技股份有限公司 | Method, device and equipment for recommending information based on word2vec model |
| CN114596126A (en) * | 2022-04-26 | 2022-06-07 | 土巴兔集团股份有限公司 | Advertisement recommendation method and device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115294682A (en) * | 2022-10-09 | 2022-11-04 | 深圳壹家智能锁有限公司 | Data management method, device and equipment for intelligent door lock and storage medium |
| CN115294682B (en) * | 2022-10-09 | 2022-12-06 | 深圳壹家智能锁有限公司 | Data management method, device and equipment for intelligent door lock and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114936326B (en) | 2022-11-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109522557B (en) | Training method and device of text relation extraction model and readable storage medium | |
| CN109886294B (en) | Knowledge fusion method, apparatus, computer device and storage medium | |
| EP3717984B1 (en) | Method and apparatus for providing personalized self-help experience | |
| CN114372573B (en) | User portrait information recognition method and device, computer equipment and storage medium | |
| CN112085565A (en) | Deep learning-based information recommendation method, device, equipment and storage medium | |
| CN111324738B (en) | Method and system for determining text label | |
| CN114693215A (en) | Purchase request processing method and device, computer equipment and storage medium | |
| CN111767375A (en) | Semantic recall method and device, computer equipment and storage medium | |
| CN114528845A (en) | Abnormal log analysis method and device and electronic equipment | |
| CN113762392A (en) | Financial product recommendation method, device, equipment and medium based on artificial intelligence | |
| CN114936326B (en) | Information recommendation method, device, equipment and storage medium based on artificial intelligence | |
| CN115374354A (en) | Scientific and technological service recommendation method, device, equipment and medium based on machine learning | |
| CN113836929B (en) | Named entity recognition method, device, equipment and storage medium | |
| CN117149996B (en) | Man-machine interface digital conversation mining method and AI system for artificial intelligence application | |
| CN118245745A (en) | Task processing, object recommendation, model training method and computing device | |
| CN113297346A (en) | Text intention recognition method, device, equipment and storage medium | |
| CN117217812A (en) | User behavior prediction method and device, computer equipment and storage medium | |
| CN116680401A (en) | Document processing method, document processing device, apparatus and storage medium | |
| CN115718889A (en) | Industry classification method and device for company profile | |
| Hamad et al. | Sentiment analysis of restaurant reviews in social media using naïve bayes | |
| CN114880590A (en) | Multi-language website currency automatic conversion system and method thereof | |
| CN115099832A (en) | Abnormal user detection method and device, equipment, medium and product thereof | |
| CN113611427A (en) | User portrait generation method, device, equipment and storage medium | |
| CN116562952A (en) | False transaction order detection method and device | |
| Vazquez et al. | Retrieving and Ranking Relevant JavaScript Technologies from Web Repositories |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20221031 Address after: No. 1901, Building F, Natural Residence, Futian District, Shenzhen, Guangdong 518000 Applicant after: Chen Shouhong Address before: 33b, building 4, Dachong Business Center (phase III), Dachong community, Yuehai street, Nanshan District, Shenzhen, Guangdong 518000 Applicant before: Shenzhen gelonghui Information Technology Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |