CN115002200B - Message pushing method, device, equipment and storage medium based on user portrait - Google Patents
Message pushing method, device, equipment and storage medium based on user portrait Download PDFInfo
- Publication number
- CN115002200B CN115002200B CN202210610313.3A CN202210610313A CN115002200B CN 115002200 B CN115002200 B CN 115002200B CN 202210610313 A CN202210610313 A CN 202210610313A CN 115002200 B CN115002200 B CN 115002200B
- Authority
- CN
- China
- Prior art keywords
- label
- message
- model
- labels
- fact
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
Abstract
The invention relates to the field of big data, and discloses a message pushing method, a device, equipment and a medium based on user portraits, wherein the method comprises the following steps: obtaining a message to be pushed, analyzing the category to which the message to be pushed belongs by utilizing a pre-constructed multi-classification model, and setting one or more message labels for the message to be pushed according to the category; acquiring basic information and historical behavior data of a client, and carrying out statistical analysis on the basic information and the historical behavior data to obtain a fact label of the client; modeling analysis is carried out according to the fact label to obtain a model label of the client, and prediction analysis is carried out on the model label to obtain a prediction label of the client; generating a user portrait of each client according to the fact label, the model label and the prediction label; determining one or more user labels for each customer based on the user representation of the customer; and matching the message label with the user label, and pushing the message to be pushed to the client according to the matching result. The invention can improve the accuracy of message pushing.
Description
Technical Field
The present invention relates to the field of big data, and in particular, to a message pushing method and apparatus based on user portraits, an electronic device, and a readable storage medium.
Background
Along with popularization and application of enterprise WeChat, the enterprise can push messages for clients through the enterprise WeChat, so that interaction between the enterprise and the clients is improved, actual convenience is brought to the clients through the messages, and user experience can be improved. However, at present, when the enterprise pushes the message for the user, the enterprise does not treat the message differently according to the situation of the user, and inaccurate mass message pushing also causes harassment to the client and makes the client dislike, so that the user experience is reduced.
Disclosure of Invention
The invention provides a message pushing method, a message pushing device, electronic equipment and a computer readable storage medium based on user portraits, and aims to improve the accuracy of message pushing.
In order to achieve the above object, the present invention provides a message pushing method based on user portrait, which includes:
obtaining a message to be pushed, analyzing the category to which the message to be pushed belongs by utilizing a pre-constructed multi-classification model, and setting one or more message labels for the message to be pushed according to the category;
Acquiring basic information of a client and historical behavior data of the client, and carrying out statistical analysis on the basic information and the historical behavior data to obtain a fact label of the client;
modeling analysis is carried out according to the fact label to obtain a model label of the client, and prediction analysis is carried out on the model label to obtain a prediction label of the client;
generating a user portrait of each client according to the fact label, the model label and the prediction label;
determining one or more user labels for each of said clients based on said client's user profile;
and matching the message label with the user label, and pushing the message to be pushed to the corresponding client according to the matching result.
Optionally, the generating a user portrait of each client according to the prediction label, the model label and the fact label includes:
according to the number of the prediction labels, the model labels and the fact labels in the current clients and all clients, calculating the actual weights of the prediction labels, the model labels and the fact labels to obtain the actual weights of the prediction labels, the actual weights of the model labels and the actual weights of the fact labels respectively;
And generating a user portrait of each client according to the actual weight of the predictive label, the actual weight of the model label and the actual weight of the fact label.
Optionally, calculating the actual weights of the prediction tags, the model tags and the fact tags according to the number of the prediction tags, the model tags and the fact tags in the current clients and all clients to obtain the actual weights of the prediction tags, the actual weights of the model tags and the actual weights of the fact tags respectively, including:
counting the number of the predictive labels, the model labels and the fact labels of the clients to obtain the number of the predictive labels, the number of the model labels and the number of the fact labels respectively;
calculating the duty ratios of the prediction tags, the model tags and the fact tags in all tags of the clients according to the number of the prediction tags, the number of the model tags and the number of the fact tags, and respectively obtaining a first weight of the prediction tags, a first weight of the model tags and a first weight of the fact tags;
counting the label numbers of the prediction labels, the model labels and the fact labels of all clients to respectively obtain the total prediction label number, the total model label number and the total fact label number;
Calculating the duty ratios of the predictive label, the model label and the fact label in all labels of all clients according to the total predictive label number, the total model label number and the total fact label number to respectively obtain a second weight of the predictive label, a second weight of the model label and a second weight of the fact label;
according to the first weight and the second weight of the prediction tag, the first weight and the second weight of the model tag, the first weight and the second weight of the fact tag, the actual weights of the prediction tag, the model tag and the fact tag are calculated by using a TF-IDF algorithm.
Optionally, the determining one or more user labels of the clients according to the user portrait of each client includes:
matching the user portrait with a pre-constructed candidate word template to obtain a candidate word set in the user portrait;
carrying out key information classification judgment on the candidate word set by utilizing a pre-trained key information classification model to obtain key information in the user portrait;
and generating one or more user labels of the clients according to the key information.
Optionally, the analyzing, by using the pre-constructed multi-classification model, the category to which the message to be pushed belongs includes:
acquiring a training data set consisting of a historical push message data set and a category to which the historical push message data set belongs, and constructing a first training set and a second training set based on the training data set;
acquiring a pre-constructed original multi-classification model, and carrying out model training on the original multi-classification model pair by utilizing the first training set to obtain an original multi-classification model;
performing model test on the initial multi-classification model by using the second training set, and adjusting super parameters in the initial multi-classification model according to test results to obtain a trained multi-classification model;
and classifying the message to be pushed by using the trained multi-classification model to obtain the category of the message to be pushed.
Optionally, the analyzing, by using the pre-constructed multi-classification model, the category to which the message to be pushed belongs may further include:
performing word segmentation processing on the message to be pushed to obtain a word segmentation message set;
calculating the weight of each word in the word segmentation message set by using a TF-LDF algorithm to obtain the weight of the word;
Extracting words in the word segmentation message set corresponding to the word weight being greater than a preset threshold value to obtain keywords in the word segmentation message set;
performing part-of-speech tagging on the keywords by searching a preset dictionary, and determining word senses of the keywords;
and determining the category of the message to be pushed according to the word meaning of the keyword.
Optionally, after the message to be pushed is pushed to the corresponding client according to the matching result, the method further includes:
collecting feedback information of the client to the message to be pushed;
identifying and classifying the feedback information to obtain negative feedback information;
and adjusting the corresponding user portrait of the client according to the negative feedback information.
In order to solve the above problems, the present invention further provides a message pushing device based on user portraits, the device comprising:
the message label module to be pushed is used for acquiring a message to be pushed, analyzing the category to which the message to be pushed belongs by utilizing a pre-constructed multi-classification model, and setting one or more message labels for the message to be pushed according to the category;
the user portrait generation module is used for acquiring basic information of a client, carrying out statistical analysis on the basic information and the historical behavior data of the client according to the basic information, obtaining a fact label of the client, carrying out modeling analysis according to the fact label, obtaining a model label of the client, carrying out predictive analysis on the model label, obtaining a predictive label of the client, and generating a user portrait of each client according to the fact label, the model label and the predictive label;
And the message pushing module is used for determining one or more user labels of the clients according to the user portrait of each client, matching the message labels with the user labels, and pushing the message to be pushed to the corresponding client according to a matching result.
In order to solve the above-mentioned problems, the present invention also provides an electronic apparatus including:
a memory storing at least one computer program; a kind of electronic device with high-pressure air-conditioning system
And the processor executes the computer program stored in the memory to realize the message pushing method based on the user portrait.
In order to solve the above-mentioned problems, the present invention further provides a computer readable storage medium, in which at least one computer program is stored, the at least one computer program being executed by a processor in an electronic device to implement the above-mentioned message pushing method based on user portraits.
According to the message pushing method, device, electronic equipment and readable storage medium based on the user portrait, the user portrait of the user is generated by acquiring the basic information and the historical behavior data of the user, then the user portrait is matched with the message label of the message to be pushed according to the user portrait, and the message is pushed according to the matching result, so that the preference and the demand of the user are well mastered, unnecessary message pushing is reduced, and the message pushing accuracy is improved.
Drawings
FIG. 1 is a flow chart of a message pushing method based on user portraits according to an embodiment of the present application;
FIG. 2 is a schematic block diagram of a message pushing device based on user portraits according to an embodiment of the present application;
FIG. 3 is a schematic diagram of an internal structure of an electronic device for implementing a message pushing method based on user portraits according to an embodiment of the present application;
the achievement of the objects, functional features and advantages of the present application will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The embodiment of the application provides a message pushing method based on user portraits. The execution subject of the message pushing method based on the user portrait comprises at least one of a server, a terminal and the like which can be configured to execute the method provided by the embodiment of the application. In other words, the message pushing method based on the user portraits can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (ContentDelivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.
Referring to fig. 1, a flowchart of a message pushing method based on a user portrait according to an embodiment of the present invention is provided, where in the embodiment of the present invention, the message pushing method based on a user portrait includes:
s1, obtaining a message to be pushed, analyzing the category to which the message to be pushed belongs by utilizing a pre-constructed multi-classification model, and setting one or more message labels for the message to be pushed according to the category.
In the embodiment of the present invention, the message to be pushed may be any type of information, such as product information to be promoted, activity information to be held, etc. of an enterprise.
In one embodiment of the present invention, the category to which the message to be pushed belongs may be an application scenario to which the message to be pushed belongs. For example, the categories may be beverage coupons, such as coffee coupons, salon campaigns, and cash benefits, etc., where the salon campaigns may include, for example, a academy of Yinian invitation, and the cash benefits may be, for example, new collar 60-membered benefits, etc.
In the embodiment of the invention, different message labels can be set for the message to be pushed according to different dimensions of the category to which the message to be pushed belongs. The message label can comprise a consumption label, a content label, a date label, an age label, a high-potential label and the like. In one embodiment of the present invention, the multi-classification model may be a k nearest neighbor (k-Nearest Neighbors) model, a Decision tree (Decision Trees) model, a Naive Bayes model, a Random Forest (Random Forest) model, or a gradient Boosting (Gradient Boosting) model. The multi-classification model, after being trained, can be used to classify messages to be pushed.
In the embodiment of the invention, the training of the multi-classification model can be performed by a supervised learning method, namely, the history push message is used as a training set, and the multi-classification model is iteratively trained according to the category to which the history push message belongs.
In detail, the analyzing, by using the pre-constructed multi-classification model, the category to which the message to be pushed belongs includes:
acquiring a training data set consisting of a historical push message data set and a category to which the historical push message data set belongs, and constructing a first training set and a second training set based on the training data set;
acquiring a pre-constructed original multi-classification model, and carrying out model training on the original multi-classification model pair by utilizing the first training set to obtain an original multi-classification model;
performing model test on the initial multi-classification model by using the second training set, and adjusting super parameters in the initial multi-classification model according to test results to obtain a trained multi-classification model;
and classifying the message to be pushed by using the trained multi-classification model to obtain the category of the message to be pushed.
In other embodiments of the present invention, the multi-classification model may also be a semantic analysis model based on a natural language processing technology, where the category of the message to be pushed is obtained by performing semantic analysis on the message to be pushed.
In detail, the analyzing, by using the pre-constructed multi-classification model, the category to which the message to be pushed belongs may further include:
performing word segmentation processing on the message to be pushed to obtain a word segmentation message set;
calculating the weight of each word in the word segmentation message set by using a TF-LDF algorithm to obtain the weight of the word;
extracting words with the weight greater than a preset threshold value from the word segmentation message set to obtain keywords;
performing word meaning marking on the keywords by searching a preset dictionary, and determining the word meaning of the keywords;
and determining the category of the message to be pushed according to the word meaning of the keyword.
Further, according to the embodiment of the invention, one or more message labels can be set for the message to be pushed according to a preset category-label table.
And recording one or more message labels corresponding to each message category in the category-label table. For example, if the message to be pushed is a beverage coupon, the corresponding message label includes a consumption label of beverage, a content label of preferential activity, a date label of full suitability, an age label of young men and women, a high potential label of full suitability, etc.
S2, acquiring basic information of the client and historical behavior data of the client, and performing statistical analysis on the basic information and the historical behavior data to obtain a fact label of the client.
In the embodiment of the invention, the basic information can be static attributes of the client, such as age, gender, working condition, consumption level and the like of the client. The historical behavior data can be dynamic data of a user, including browsing records, searching records, purchasing records and the like. The fact label includes population attribute, income condition, purchase frequency, product purchase frequency and the like.
In an alternative embodiment of the present invention, the historical behavior data of the client may be crawled by using a crawler technology according to the basic information.
According to the embodiment of the invention, the fact label of the client is obtained by carrying out statistical analysis on the basic information and the historical behavior data, the interest and hobbies of the client are preliminarily determined, and a foundation is laid for generating the user portrait subsequently.
And S3, carrying out modeling analysis according to the fact label to obtain a model label of the client, and carrying out prediction analysis on the model label to obtain a prediction label of the client.
In the embodiment of the invention, the model tag comprises user interest, user influence, product preference, channel preference and the like. The predictive labels include recent demand, consumption capacity, loss probability, and the like.
In an alternative embodiment of the present invention, since the fact label is not enough to represent all the characteristics of the client, modeling analysis is further required according to the fact label, and further prediction analysis is performed on the result of the modeling analysis, so that the hobbies and interests of the client are predicted more accurately, and the accuracy of message pushing is improved.
And S4, generating the user portrait of each client according to the fact label, the model label and the prediction label.
In an alternative embodiment of the invention, the user portrait of the client is generated according to the weight ratio by calculating the weight ratio of the fact label, the model label and the prediction label of the client, so that the image of the client such as the interest and the like is more specific.
In detail, the generating a user portrait of each client according to the fact label, the model label and the prediction label includes:
according to the number of the prediction labels, the model labels and the fact labels in the current clients and all clients, calculating the actual weights of the prediction labels, the model labels and the fact labels to obtain the actual weights of the prediction labels, the actual weights of the model labels and the actual weights of the fact labels respectively;
And generating a user portrait of each client according to the actual weight of the predictive label, the actual weight of the model label and the actual weight of the fact label.
In the embodiment of the invention, all clients can be all clients including the current client.
According to the invention, the actual weight of the predictive label, the actual weight of the model label and the actual weight of the fact label are used for determining the duty ratio of the predictive label, the model label and the fact label in the user image, and the user image is generated according to the duty ratio, so that the user image can truly show the interests, the hobbies, the basic information and the like of the client, and the accuracy of the user image is improved.
Further, calculating the actual weights of the prediction tag, the model tag and the fact tag according to the number of the prediction tag, the model tag and the fact tag in the current clients and all clients to obtain the actual weights of the prediction tag, the actual weights of the model tag and the actual weights of the fact tag respectively, including:
counting the number of the predictive labels, the model labels and the fact labels of the clients to obtain the number of the predictive labels, the number of the model labels and the number of the fact labels respectively;
Calculating the duty ratios of the prediction tags, the model tags and the fact tags in all tags of the clients according to the number of the prediction tags, the number of the model tags and the number of the fact tags, and respectively obtaining a first weight of the prediction tags, a first weight of the model tags and a first weight of the fact tags;
counting the label numbers of the prediction labels, the model labels and the fact labels of all clients to respectively obtain the total prediction label number, the total model label number and the total fact label number;
calculating the duty ratios of the predictive label, the model label and the fact label in all labels of all clients according to the total predictive label number, the total model label number and the total fact label number to respectively obtain a second weight of the predictive label, a second weight of the model label and a second weight of the fact label;
according to the first weight and the second weight of the prediction tag, the first weight and the second weight of the model tag, the first weight and the second weight of the fact tag, the actual weights of the prediction tag, the model tag and the fact tag are calculated by using a TF-IDF algorithm. S5, determining one or more user labels of the clients according to the user portrait of each client.
In the embodiment of the invention, the user tag can be tag data corresponding to the enterprise message tag, and comprises a consumption tag, a content tag, a date tag, an age tag, a high-potential tag and the like.
In an alternative embodiment of the present invention, the user portrait includes attribute data of the client, a tag keyword may be determined by matching the attribute data with a preset candidate word template, and then a user tag of the client is generated according to the tag keyword.
In detail, the determining one or more user labels of the clients according to the user portrait of each client includes:
matching the user portrait with a pre-constructed candidate word template to obtain a candidate word set in the user portrait;
carrying out key information classification judgment on the candidate word set by utilizing a pre-trained key information classification model to obtain key information in the user portrait;
and generating one or more user labels of the clients according to the key information.
And S6, matching the message label with the user label, and pushing the message to be pushed to a corresponding client according to a matching result.
In the embodiment of the invention, the message label is matched with the user label, so that the messages pushed to the clients are all messages required by the users, the occurrence of poor user experience caused by message pushing is reduced, and the accuracy of enterprise micro message pushing is improved.
In an alternative embodiment of the invention, the points of interest of some customers vary over time, for example, a customer needs to drink a lot of coffee during a period of time due to the working pressure, for which purpose a lot of information about the coffee is searched, and when the customer does not have the working pressure, it is obviously less accurate to push a coffee coupon to the customer. Therefore, when the message pushing is carried out to the client according to the original user portrait, the feedback information of the client can be obtained in real time, and the user portrait is regulated according to the feedback information, so that the enterprise micro message pushing is more accurate.
In detail, after the message to be pushed is pushed to the corresponding client according to the matching result, the method further includes:
collecting feedback information of the client to the message to be pushed;
identifying and classifying the feedback information to obtain negative feedback information;
And adjusting the corresponding user portrait of the client according to the negative feedback information.
According to the embodiment of the invention, the user portrait of the user is generated by acquiring the basic information and the historical behavior data of the user, then the user portrait is matched with the message label of the message to be pushed, and the message is pushed according to the matching result, so that the preference and the demand of the user are well mastered, unnecessary message pushing is reduced, and the accuracy of message pushing is improved.
As shown in FIG. 2, a functional block diagram of a user portrayal-based message pushing device of the present invention is shown.
The message pushing device 100 based on user portraits can be installed in an electronic device. Depending on the implementation, the message pushing device based on the user portrait may include a message tag module 101 to be pushed, a user portrait generating module 102, and a message pushing module 103, where the modules may also be referred to as units, and refer to a series of computer program segments that can be executed by a processor of an electronic device and can perform a fixed function, and are stored in a memory of the electronic device.
In the present embodiment, the functions concerning the respective modules/units are as follows:
The message label module 101 is configured to obtain a message to be pushed, analyze a category to which the message to be pushed belongs by using a pre-constructed multi-classification model, and set one or more message labels for the message to be pushed according to the category.
In the embodiment of the present invention, the message to be pushed may be any type of information, such as product information to be promoted, activity information to be held, etc. of an enterprise.
In one embodiment of the present invention, the category to which the message to be pushed belongs may be an application scenario to which the message to be pushed belongs. For example, the categories may be beverage coupons, such as coffee coupons, salon campaigns, and cash benefits, etc., where the salon campaigns may include, for example, a academy of Yinian invitation, and the cash benefits may be, for example, new collar 60-membered benefits, etc.
In the embodiment of the invention, different message labels can be set for the message to be pushed according to different dimensions of the category to which the message to be pushed belongs. The message label can comprise a consumption label, a content label, a date label, an age label, a high-potential label and the like. In one embodiment of the present invention, the multi-classification model may be a k nearest neighbor (k-Nearest Neighbors) model, a Decision tree (Decision Trees) model, a Naive Bayes model, a Random Forest (Random Forest) model, or a gradient Boosting (Gradient Boosting) model. The multi-classification model, after being trained, can be used to classify messages to be pushed.
In the embodiment of the invention, the training of the multi-classification model can be performed by a supervised learning method, namely, the history push message is used as a training set, and the multi-classification model is iteratively trained according to the category to which the history push message belongs.
In detail, the analyzing, by using the pre-constructed multi-classification model, the category to which the message to be pushed belongs includes:
acquiring a training data set consisting of a historical push message data set and a category to which the historical push message data set belongs, and constructing a first training set and a second training set based on the training data set;
acquiring a pre-constructed original multi-classification model, and carrying out model training on the original multi-classification model pair by utilizing the first training set to obtain an original multi-classification model;
performing model test on the initial multi-classification model by using the second training set, and adjusting super parameters in the initial multi-classification model according to test results to obtain a trained multi-classification model;
and classifying the message to be pushed by using the trained multi-classification model to obtain the category of the message to be pushed.
In other embodiments of the present invention, the multi-classification model may also be a semantic analysis model based on a natural language processing technology, where the category of the message to be pushed is obtained by performing semantic analysis on the message to be pushed.
In detail, the analyzing, by using the pre-constructed multi-classification model, the category to which the message to be pushed belongs may further include:
performing word segmentation processing on the message to be pushed to obtain a word segmentation message set;
calculating the weight of each word in the word segmentation message set by using a TF-LDF algorithm to obtain the weight of the word;
extracting words with the weight greater than a preset threshold value from the word segmentation message set to obtain keywords;
performing word meaning marking on the keywords by searching a preset dictionary, and determining the word meaning of the keywords;
and determining the category of the message to be pushed according to the word meaning of the keyword.
Further, according to the embodiment of the invention, one or more message labels can be set for the message to be pushed according to a preset category-label table.
And recording one or more message labels corresponding to each message category in the category-label table. For example, if the message to be pushed is a beverage coupon, the corresponding message label includes a consumption label of beverage, a content label of preferential activity, a date label of full suitability, an age label of young men and women, a high potential label of full suitability, etc.
The user portrait generating module 102 is configured to obtain basic information of a client, perform statistical analysis on the basic information and the historical behavior data of the client according to the basic information, obtain a fact label of the client, perform modeling analysis according to the fact label, obtain a model label of the client, and perform predictive analysis on the model label to obtain a predictive label of the client, and generate a user portrait of each client according to the fact label, the model label and the predictive label.
In the embodiment of the invention, the basic information can be static attributes of the client, such as age, gender, working condition, consumption level and the like of the client. The historical behavior data can be dynamic data of a user, including browsing records, searching records, purchasing records and the like. The fact label includes population attribute, income condition, purchase frequency, product purchase frequency and the like.
In an alternative embodiment of the present invention, the historical behavior data of the client may be crawled by using a crawler technology according to the basic information.
According to the embodiment of the invention, the fact label of the client is obtained by carrying out statistical analysis on the basic information and the historical behavior data, the interest and hobbies of the client are preliminarily determined, and a foundation is laid for generating the user portrait subsequently.
In the embodiment of the invention, the model tag comprises user interest, user influence, product preference, channel preference and the like. The predictive labels include recent demand, consumption capacity, loss probability, and the like.
In an alternative embodiment of the present invention, since the fact label is not enough to represent all the characteristics of the client, modeling analysis is further required according to the fact label, and further prediction analysis is performed on the result of the modeling analysis, so that the hobbies and interests of the client are predicted more accurately, and the accuracy of message pushing is improved.
In an alternative embodiment of the invention, the user portrait of the client is generated according to the weight ratio by calculating the weight ratio of the fact label, the model label and the prediction label of the client, so that the image of the client such as the interest and the like is more specific.
In detail, the generating a user portrait of each client according to the fact label, the model label and the prediction label includes:
according to the number of the prediction labels, the model labels and the fact labels in the current clients and all clients, calculating the actual weights of the prediction labels, the model labels and the fact labels to obtain the actual weights of the prediction labels, the actual weights of the model labels and the actual weights of the fact labels respectively;
and generating a user portrait of each client according to the actual weight of the predictive label, the actual weight of the model label and the actual weight of the fact label.
In the embodiment of the invention, all clients can be all clients including the current client.
According to the invention, the actual weight of the predictive label, the actual weight of the model label and the actual weight of the fact label are used for determining the duty ratio of the predictive label, the model label and the fact label in the user image, and the user image is generated according to the duty ratio, so that the user image can truly show the interests, the hobbies, the basic information and the like of the client, and the accuracy of the user image is improved.
Further, calculating the actual weights of the prediction tag, the model tag and the fact tag according to the number of the prediction tag, the model tag and the fact tag in the current clients and all clients to obtain the actual weights of the prediction tag, the actual weights of the model tag and the actual weights of the fact tag respectively, including:
counting the number of the predictive labels, the model labels and the fact labels of the clients to obtain the number of the predictive labels, the number of the model labels and the number of the fact labels respectively;
calculating the duty ratios of the prediction tags, the model tags and the fact tags in all tags of the clients according to the number of the prediction tags, the number of the model tags and the number of the fact tags, and respectively obtaining a first weight of the prediction tags, a first weight of the model tags and a first weight of the fact tags;
counting the label numbers of the prediction labels, the model labels and the fact labels of all clients to respectively obtain the total prediction label number, the total model label number and the total fact label number;
calculating the duty ratios of the predictive label, the model label and the fact label in all labels of all clients according to the total predictive label number, the total model label number and the total fact label number to respectively obtain a second weight of the predictive label, a second weight of the model label and a second weight of the fact label;
According to the first weight and the second weight of the prediction tag, the first weight and the second weight of the model tag, the first weight and the second weight of the fact tag, the actual weights of the prediction tag, the model tag and the fact tag are calculated by using a TF-IDF algorithm. The message pushing module 103 is configured to determine one or more user labels of the clients according to the user portrait of each client, match the message label with the user label, and push the message to be pushed to the corresponding client according to the matching result.
In the embodiment of the invention, the user tag can be tag data corresponding to the enterprise message tag, and comprises a consumption tag, a content tag, a date tag, an age tag, a high-potential tag and the like.
In an alternative embodiment of the present invention, the user portrait includes attribute data of the client, a tag keyword may be determined by matching the attribute data with a preset candidate word template, and then a user tag of the client is generated according to the tag keyword.
In detail, the determining one or more user labels of the clients according to the user portrait of each client includes:
Matching the user portrait with a pre-constructed candidate word template to obtain a candidate word set in the user portrait;
carrying out key information classification judgment on the candidate word set by utilizing a pre-trained key information classification model to obtain key information in the user portrait;
and generating one or more user labels of the clients according to the key information.
In the embodiment of the invention, the message label is matched with the user label, so that the messages pushed to the clients are all messages required by the users, the occurrence of poor user experience caused by message pushing is reduced, and the accuracy of enterprise micro message pushing is improved.
In an alternative embodiment of the invention, the points of interest of some customers vary over time, for example, a customer needs to drink a lot of coffee during a period of time due to the working pressure, for which purpose a lot of information about the coffee is searched, and when the customer does not have the working pressure, it is obviously less accurate to push a coffee coupon to the customer. Therefore, when the message pushing is carried out to the client according to the original user portrait, the feedback information of the client can be obtained in real time, and the user portrait is regulated according to the feedback information, so that the enterprise micro message pushing is more accurate.
In detail, after the message to be pushed is pushed to the corresponding client according to the matching result, the method further includes:
collecting feedback information of the client to the message to be pushed;
identifying and classifying the feedback information to obtain negative feedback information;
and adjusting the corresponding user portrait of the client according to the negative feedback information.
Fig. 3 is a schematic structural diagram of an electronic device for implementing a message pushing method based on user portraits.
The electronic device may comprise a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may further comprise a computer program stored in the memory 11 and executable on the processor 10, such as a message pushing program based on user portraits.
The memory 11 includes at least one type of readable storage medium, including flash memory, a mobile hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device, such as a mobile hard disk of the electronic device. The memory 11 may in other embodiments also be an external storage device of the electronic device, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device. The memory 11 may be used not only for storing application software installed in an electronic device and various data, such as a code of a message pushing program based on a user portrait, but also for temporarily storing data that has been output or is to be output.
The processor 10 may be comprised of integrated circuits in some embodiments, for example, a single packaged integrated circuit, or may be comprised of multiple integrated circuits packaged with the same or different functions, including one or more central processing units (Central Processing unit, CPU), microprocessors, digital processing chips, graphics processors, combinations of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various parts of the entire electronic device using various interfaces and lines, and executes various functions of the electronic device and processes data by running or executing programs or modules (e.g., a message pushing program based on a user portrait, etc.) stored in the memory 11, and calling data stored in the memory 11.
The communication bus 12 may be a peripheral component interconnect standard (perIPheral component interconnect, PCI) bus, or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The communication bus 12 is arranged to enable a connection communication between the memory 11 and at least one processor 10 etc. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.
Fig. 3 shows only an electronic device with components, and it will be understood by those skilled in the art that the structure shown in fig. 3 is not limiting of the electronic device and may include fewer or more components than shown, or may combine certain components, or a different arrangement of components.
For example, although not shown, the electronic device may further include a power source (such as a battery) for supplying power to the respective components, and preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management, and the like are implemented through the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The electronic device may further include various sensors, bluetooth modules, wi-Fi modules, etc., which are not described herein.
Optionally, the communication interface 13 may comprise a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), typically used to establish a communication connection between the electronic device and other electronic devices.
Optionally, the communication interface 13 may further comprise a user interface, which may be a Display, an input unit, such as a Keyboard (Keyboard), or a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device and for displaying a visual user interface.
It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.
The message pushing program based on the user image stored in the memory 11 in the electronic device is a combination of a plurality of computer programs, which when run in the processor 10 can realize:
obtaining a message to be pushed, analyzing the category to which the message to be pushed belongs by utilizing a pre-constructed multi-classification model, and setting one or more message labels for the message to be pushed according to the category;
Acquiring basic information of a client and historical behavior data of the client, and carrying out statistical analysis on the basic information and the historical behavior data to obtain a fact label of the client;
modeling analysis is carried out according to the fact label to obtain a model label of the client, and prediction analysis is carried out on the model label to obtain a prediction label of the client;
generating a user portrait of each client according to the fact label, the model label and the prediction label;
determining one or more user labels for each of said clients based on said client's user profile;
and matching the message label with the user label, and pushing the message to be pushed to the corresponding client according to the matching result.
In particular, the specific implementation method of the processor 10 on the computer program may refer to the description of the relevant steps in the corresponding embodiment of fig. 1, which is not repeated herein.
Further, the electronic device integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. The computer readable medium may be non-volatile or volatile. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).
Embodiments of the present invention may also provide a computer readable storage medium storing a computer program which, when executed by a processor of an electronic device, may implement:
obtaining a message to be pushed, analyzing the category to which the message to be pushed belongs by utilizing a pre-constructed multi-classification model, and setting one or more message labels for the message to be pushed according to the category;
acquiring basic information of a client and historical behavior data of the client, and carrying out statistical analysis on the basic information and the historical behavior data to obtain a fact label of the client;
modeling analysis is carried out according to the fact label to obtain a model label of the client, and prediction analysis is carried out on the model label to obtain a prediction label of the client;
generating a user portrait of each client according to the fact label, the model label and the prediction label;
determining one or more user labels for each of said clients based on said client's user profile;
and matching the message label with the user label, and pushing the message to be pushed to the corresponding client according to the matching result.
Further, the computer-usable 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 from the use of blockchain nodes, and the like.
In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method 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 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.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.
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.
The blockchain is a novel application mode of computer technologies such as distributed data storage, 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.
The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. A plurality of units or means recited in the system claims can also be implemented by means of software or hardware by means of one unit or means. The terms 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 application and not for limiting the same, and although the present application 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 application without departing from the spirit and scope of the technical solution of the present application.
Claims (8)
1. A message pushing method based on user portraits, the method comprising:
Obtaining a message to be pushed, analyzing the category to which the message to be pushed belongs by utilizing a pre-constructed multi-classification model, and setting one or more message labels for the message to be pushed according to the category;
acquiring basic information of a client and historical behavior data of the client, and carrying out statistical analysis on the basic information and the historical behavior data to obtain a fact label of the client;
modeling analysis is carried out according to the fact label to obtain a model label of the client, and prediction analysis is carried out on the model label to obtain a prediction label of the client;
generating a user portrait of each client according to the fact label, the model label and the prediction label;
determining one or more user labels for each of said clients based on said client's user profile;
matching the message label with the user label, and pushing the message to be pushed to a corresponding client according to a matching result;
wherein the generating a user portrait of each client according to the prediction tag, the model tag and the fact tag comprises: according to the number of the prediction labels, the model labels and the fact labels in the current clients and all clients, calculating the actual weights of the prediction labels, the model labels and the fact labels to obtain the actual weights of the prediction labels, the actual weights of the model labels and the actual weights of the fact labels respectively; generating a user portrait of each client according to the actual weight of the prediction tag, the actual weight of the model tag and the actual weight of the fact tag;
Calculating the actual weights of the prediction tags, the model tags and the fact tags according to the number of the prediction tags, the model tags and the fact tags in the current clients and all clients to obtain the actual weights of the prediction tags, the actual weights of the model tags and the actual weights of the fact tags respectively, wherein the method comprises the following steps: counting the number of the predictive labels, the model labels and the fact labels of the clients to obtain the number of the predictive labels, the number of the model labels and the number of the fact labels respectively; calculating the duty ratios of the prediction tags, the model tags and the fact tags in all tags of the clients according to the number of the prediction tags, the number of the model tags and the number of the fact tags, and respectively obtaining a first weight of the prediction tags, a first weight of the model tags and a first weight of the fact tags; counting the label numbers of the prediction labels, the model labels and the fact labels of all clients to respectively obtain the total prediction label number, the total model label number and the total fact label number; calculating the duty ratios of the predictive label, the model label and the fact label in all labels of all clients according to the total predictive label number, the total model label number and the total fact label number to respectively obtain a second weight of the predictive label, a second weight of the model label and a second weight of the fact label; according to the first weight and the second weight of the prediction tag, the first weight and the second weight of the model tag, the first weight and the second weight of the fact tag, the actual weights of the prediction tag, the model tag and the fact tag are calculated by using a TF-IDF algorithm.
2. The user portrayal-based message pushing method of claim 1, wherein said determining one or more user tags for each of said clients based on the user portrayal of said client comprises:
matching the user portrait with a pre-constructed candidate word template to obtain a candidate word set in the user portrait;
carrying out key information classification judgment on the candidate word set by utilizing a pre-trained key information classification model to obtain key information in the user portrait;
and generating one or more user labels of the clients according to the key information.
3. The message pushing method based on user portraits of claim 1, wherein analyzing the category to which the message to be pushed belongs by using a pre-built multi-category model comprises:
acquiring a training data set consisting of a historical push message data set and a category to which the historical push message data set belongs, and constructing a first training set and a second training set based on the training data set;
acquiring a pre-constructed original multi-classification model, and carrying out model training on the original multi-classification model pair by utilizing the first training set to obtain an original multi-classification model;
Performing model test on the initial multi-classification model by using the second training set, and adjusting super parameters in the initial multi-classification model according to test results to obtain a trained multi-classification model;
and classifying the message to be pushed by using the trained multi-classification model to obtain the category of the message to be pushed.
4. The message pushing method based on user portraits of claim 3, wherein analyzing the category to which the message to be pushed belongs by using a pre-constructed multi-category model comprises:
performing word segmentation processing on the message to be pushed to obtain a word segmentation message set;
calculating the weight of each word in the word segmentation message set by using a TF-LDF algorithm to obtain the weight of the word;
extracting words in the word segmentation message set corresponding to the word weight being greater than a preset threshold value to obtain keywords in the word segmentation message set;
performing part-of-speech tagging on the keywords by searching a preset dictionary, and determining word senses of the keywords;
and determining the category of the message to be pushed according to the word meaning of the keyword.
5. The message pushing method based on user portraits according to any of claims 1 to 4, characterized in that, after said pushing the message to be pushed to the corresponding client according to the matching result, the method further comprises:
Collecting feedback information of the client to the message to be pushed;
identifying and classifying the feedback information to obtain negative feedback information;
and adjusting the corresponding user portrait of the client according to the negative feedback information.
6. A user portrayal based message pushing device for implementing a user portrayal based message pushing method according to any of claims 1 to 5, comprising:
the message label module to be pushed is used for acquiring a message to be pushed, analyzing the category to which the message to be pushed belongs by utilizing a pre-constructed multi-classification model, and setting one or more message labels for the message to be pushed according to the category;
the user portrait generation module is used for acquiring basic information of a client, carrying out statistical analysis on the basic information and the historical behavior data of the client according to the basic information, obtaining a fact label of the client, carrying out modeling analysis according to the fact label, obtaining a model label of the client, carrying out predictive analysis on the model label, obtaining a predictive label of the client, and generating a user portrait of each client according to the fact label, the model label and the predictive label;
And the message pushing module is used for determining one or more user labels of the clients according to the user portrait of each client, matching the message labels with the user labels, and pushing the message to be pushed to the corresponding client according to a matching result.
7. An electronic device, the electronic device comprising:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores computer program instructions executable by the at least one processor to enable the at least one processor to perform the user portrayal based message pushing method of any one of claims 1 to 5.
8. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the user portrayal based message pushing method according to any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210610313.3A CN115002200B (en) | 2022-05-31 | 2022-05-31 | Message pushing method, device, equipment and storage medium based on user portrait |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210610313.3A CN115002200B (en) | 2022-05-31 | 2022-05-31 | Message pushing method, device, equipment and storage medium based on user portrait |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115002200A CN115002200A (en) | 2022-09-02 |
| CN115002200B true CN115002200B (en) | 2023-08-22 |
Family
ID=83031476
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210610313.3A Active CN115002200B (en) | 2022-05-31 | 2022-05-31 | Message pushing method, device, equipment and storage medium based on user portrait |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115002200B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115983902B (en) * | 2023-01-10 | 2023-10-20 | 苏州盈天地资讯科技有限公司 | Information pushing method and system based on user real-time event |
| CN116319395B (en) * | 2023-03-21 | 2023-10-31 | 苏州利博特信息科技有限公司 | Big data-based computer information processing system and method |
| CN116823382B (en) * | 2023-05-17 | 2024-01-05 | 南京邮电大学 | Product popularization method based on big data |
| CN117216803B (en) * | 2023-11-09 | 2024-02-09 | 成都乐超人科技有限公司 | Intelligent finance-oriented user information protection method and system |
| CN117235586B (en) * | 2023-11-16 | 2024-02-09 | 青岛小帅智能科技股份有限公司 | Hotel customer portrait construction method, system, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6421751B1 (en) * | 1998-11-23 | 2002-07-16 | Advanced Micro Devices, Inc. | Detecting a no-tags-free condition in a computer system having multiple outstanding transactions |
| CN108427661A (en) * | 2018-03-19 | 2018-08-21 | 广州汇智通信技术有限公司 | A kind of new big data label manufacturing process and device |
| CN114387061A (en) * | 2022-01-12 | 2022-04-22 | 平安普惠企业管理有限公司 | Product pushing method and device, electronic equipment and readable storage medium |
-
2022
- 2022-05-31 CN CN202210610313.3A patent/CN115002200B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6421751B1 (en) * | 1998-11-23 | 2002-07-16 | Advanced Micro Devices, Inc. | Detecting a no-tags-free condition in a computer system having multiple outstanding transactions |
| CN108427661A (en) * | 2018-03-19 | 2018-08-21 | 广州汇智通信技术有限公司 | A kind of new big data label manufacturing process and device |
| CN114387061A (en) * | 2022-01-12 | 2022-04-22 | 平安普惠企业管理有限公司 | Product pushing method and device, electronic equipment and readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 基于模型融合的搜索引擎用户画像技术;郭梁 等;科技与创新(第07期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115002200A (en) | 2022-09-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115002200B (en) | Message pushing method, device, equipment and storage medium based on user portrait | |
| WO2017190610A1 (en) | Target user orientation method and device, and computer storage medium | |
| CN113095076B (en) | Sensitive word recognition method and device, electronic equipment and storage medium | |
| CN112380859A (en) | Public opinion information recommendation method and device, electronic equipment and computer storage medium | |
| CN107368521B (en) | Knowledge recommendation method and system based on big data and deep learning | |
| US20190080352A1 (en) | Segment Extension Based on Lookalike Selection | |
| CN115391669B (en) | Intelligent recommendation method and device and electronic equipment | |
| CN114722281B (en) | Training course configuration method and device based on user portrait and user course selection behavior | |
| CN114238573B (en) | Text countercheck sample-based information pushing method and device | |
| CN113592605B (en) | Product recommendation method, device, equipment and storage medium based on similar products | |
| CN110717597A (en) | Method and device for acquiring time sequence characteristics by using machine learning model | |
| CN113051480A (en) | Resource pushing method and device, electronic equipment and storage medium | |
| CN111400613A (en) | Article recommendation method, device, medium and computer equipment | |
| CN113886691A (en) | Intelligent recommendation method and device based on historical data, electronic equipment and medium | |
| CN115659008B (en) | Information pushing system, method, electronic equipment and medium for big data information feedback | |
| CN114663198A (en) | Product recommendation method, device and equipment based on user portrait and storage medium | |
| CN113886708A (en) | Product recommendation method, device, equipment and storage medium based on user information | |
| CN115018588A (en) | Product recommendation method and device, electronic equipment and readable storage medium | |
| CN111429161A (en) | Feature extraction method, feature extraction device, storage medium, and electronic apparatus | |
| CN115222433A (en) | Information recommendation method and device and storage medium | |
| CN115204971B (en) | Product recommendation method, device, electronic equipment and computer readable storage medium | |
| CN116340516A (en) | Entity relation cluster extraction method, device, equipment and storage medium | |
| CN115099680A (en) | Risk management method, device, equipment and storage medium | |
| CN114219367A (en) | User scoring method, device, equipment and storage medium | |
| CN114662005A (en) | Message pushing method, device, equipment and storage medium for user behavior track |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |