CN115705584A - Method and device for predicting demand of housekeeper product and readable storage medium - Google Patents
Method and device for predicting demand of housekeeper product and readable storage medium Download PDFInfo
- Publication number
- CN115705584A CN115705584A CN202110916842.1A CN202110916842A CN115705584A CN 115705584 A CN115705584 A CN 115705584A CN 202110916842 A CN202110916842 A CN 202110916842A CN 115705584 A CN115705584 A CN 115705584A
- Authority
- CN
- China
- Prior art keywords
- user
- product
- housekeeping
- network model
- demand
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a device for predicting house keeping product requirements and a readable storage medium, wherein the method for predicting the house keeping product requirements comprises the following steps: acquiring user data of a user to be detected in a preset time period through a preset platform; determining characteristic data for predicting the housekeeping product demand of the user to be tested according to the user data of the user to be tested; and determining the housekeeping product requirements of the user to be tested according to the feature data and the deep neural network model. The invention aims to improve the prediction accuracy of the house-keeping product demand.
Description
Technical Field
The invention relates to the technical field of deep learning, in particular to a method and a device for predicting house product requirements and a readable storage medium.
Background
At present, the prediction model of the operator for the house-keeping product demand is less involved, and the models in some other product demand prediction technical schemes of the existing operators are mainly based on table statistics or artificially set weight of features, or are based on shallow machine learning algorithms such as logistic regression, decision trees, neural networks and random forests. However, in the context of big data, these static or shallow algorithms are difficult to obtain higher prediction accuracy in terms of demand prediction problems, cannot meet various personalized demands of users, and are difficult for operators to perform accurate marketing on users with house product demands.
In summary, the prior art has the technical problem of low prediction accuracy when predicting the needs of users for house-keeping products.
Disclosure of Invention
The invention mainly aims to provide a method and a device for predicting the needs of housekeeping products and a readable storage medium, aiming at improving the prediction precision of the needs of the housekeeping products.
In order to achieve the above object, the present invention provides a method for predicting a demand for a housekeeper product, comprising:
acquiring user data of a user to be detected in a preset time period through a preset platform;
determining characteristic data for predicting the housekeeping product demand of the user to be tested according to the user data of the user to be tested;
and determining the housekeeping product requirements of the user to be tested according to the feature data and the deep neural network model.
Optionally, the preset platform includes a mobile phone user tag platform, a broadband internet access depth message detection platform and a mobile phone internet access depth message detection platform; the user data comprises user label data, broadband internet access data and mobile phone internet access data of the user to be tested.
Optionally, the step of determining the housekeeping product demand of the user to be tested according to the feature data and the deep neural network model includes:
determining a predicted value of the housekeeping product demand of the user to be tested according to the feature data and the deep neural network model;
and when the predicted value is a preset value, determining that the user to be tested has the requirement of a housekeeping product.
Optionally, before the step of obtaining the user data of the user to be tested in the preset time period through the preset platform, the method further includes:
acquiring user data of a user with known housekeeping product requirements;
determining sample characteristic data according to user data of a user with known housekeeping product requirements;
and determining the deep neural network model according to the sample characteristic data and a preset network model.
Optionally, the sample feature data includes training feature data and testing feature data, and the step of determining the deep neural network model according to the sample feature data and a preset network model includes:
training the preset network model by adopting the training characteristic data to determine a target weight value of the preset network model;
setting the weight value of the preset network model as the target weight value;
testing the preset network model with the target weight value by adopting the test characteristic data so as to test the accuracy of predicting the house product demand of the preset network model with the target weight value;
and when the accuracy is greater than a preset threshold value, determining the preset network model with a target weight value as the deep neural network model.
Optionally, the preset network model is a deep neural network model built based on a deep learning framework Tensorflow and a Python algorithm, and the preset network model includes an input layer, a plurality of hidden layers and an output layer, wherein the number of neurons in the input layer is the same as the number of the feature data.
Optionally, after the step of determining the housekeeping product demand of the user to be tested according to the feature data and the deep neural network model, the method further includes:
outputting user data of a user to be tested with the requirement of a housekeeping product;
desensitizing the user data of the user to be tested with the requirement of the housekeeping product;
and sending push information of the housekeeping product to the terminal equipment of the user to be tested with the housekeeping product requirement according to the desensitized user data.
In order to achieve the above object, the present invention provides a device for predicting a demand for a housekeeper product, comprising:
the acquisition module acquires user data of a user to be detected in a preset time period through a preset platform;
the determining module is used for determining and predicting the characteristic data of the housekeeping product demand of the user to be tested according to the user data;
and the prediction module is used for determining the housekeeping product requirement of the user to be detected according to the feature data and the deep neural network model.
In addition, in order to achieve the above object, the present invention further provides a device for predicting a demand for a housekeeper product, the device for predicting a demand for a housekeeper product comprising a memory, a processor and a program for predicting a demand for a housekeeper product stored in the memory and executable on the processor, wherein the program for predicting a demand for a housekeeper product, when executed by the processor, implements any one of the steps of the method for predicting a demand for a housekeeper product described above.
In addition, to achieve the above object, the present invention further provides a computer readable storage medium, having a prediction program of a housekeeping product demand stored thereon, where the prediction program of the housekeeping product demand, when executed by a processor, implements the steps of the prediction method of the housekeeping product demand described in any one of the above.
The invention provides a prediction method and device of housekeeping product requirements and a readable storage medium. According to the scheme, the house keeping product requirements of the users are predicted based on the deep neural network model, the model training is more sufficient, the feature extraction is more accurate, the potential product requirements of the users can be effectively mined, and the prediction precision of the house keeping product requirements is improved.
Drawings
Fig. 1 is a schematic diagram of a hardware architecture of a device for predicting demand of a housekeeper product according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart diagram illustrating a first embodiment of the method for predicting demand for housekeeping products according to the present invention;
FIG. 3 is a schematic flow chart diagram illustrating a second embodiment of the method for predicting demand for housekeeping products according to the present invention;
fig. 4 is a schematic block diagram of a device for predicting demand for a housekeeper product according to an embodiment of the present invention.
The implementation, functional features and advantages of the present invention will be further described with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As an implementation solution, referring to fig. 1, fig. 1 is a schematic diagram of a hardware architecture of a prediction apparatus of a housekeeping product requirement according to an embodiment of the present invention, as shown in fig. 1, the prediction apparatus of the housekeeping product requirement may include a processor 101, for example, a CPU, a memory 102, and a communication bus 103, where the communication bus 103 is used to implement connection communication between these modules.
The memory 102 may be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as a disk memory. As shown in fig. 1, a memory 102, which is a computer-readable storage medium, may include a prediction program of the demand of a housekeeping product; and the processor 101 may be configured to invoke the prediction program for the demand for the housekeeping product stored in the memory 102 and perform the following operations:
acquiring user data of a user to be detected in a preset time period through a preset platform;
determining characteristic data for predicting the housekeeping product demand of the user to be tested according to the user data of the user to be tested;
and determining the housekeeping product requirements of the user to be tested according to the feature data and the deep neural network model.
Further, the processor 101 may be configured to invoke a prediction program for the demand of the housekeeping product stored in the memory 102 and perform the following operations:
determining a predicted value of the housekeeping product demand of the user to be tested according to the feature data and the deep neural network model;
and when the predicted value is a preset value, determining that the user to be tested has the requirement of a housekeeping product.
Further, the processor 101 may be configured to invoke a prediction program for the demand of the housekeeping product stored in the memory 102 and perform the following operations:
acquiring user data of a user with known housekeeping product requirements;
determining sample characteristic data according to user data of a user with known housekeeping product requirements;
and determining the deep neural network model according to the sample characteristic data and a preset network model.
Further, the processor 101 may be configured to invoke a prediction program for the demand of the housekeeping product stored in the memory 102 and perform the following operations:
training the preset network model by adopting the training characteristic data to determine a target weight value of the preset network model;
setting the weight value of the preset network model as the target weight value;
testing the preset network model with the target weight value by adopting the test characteristic data so as to test the accuracy of predicting the house product demand of the preset network model with the target weight value;
and when the accuracy is greater than a preset threshold value, determining the preset network model with a target weight value as the deep neural network model.
Further, the processor 101 may be configured to invoke a prediction program for the demand of the housekeeping product stored in the memory 102 and perform the following operations:
outputting user data of a user to be tested with the requirement of a housekeeping product;
desensitizing the user data of the user to be tested with the requirement of the housekeeping product;
and sending push information of the housekeeping product to the terminal equipment of the user to be tested with the housekeeping product requirement according to the desensitized user data.
The mobile housekeeping product mainly refers to a housekeeping nursing product which is used for solving various conditions that a family user can still check old people, children, pets, abnormal action sound and the like in real time within 24 hours when going out. The prediction model of the mobile housekeeper product demand is a main means for finding whether a household user has the housekeeper product demand, and the prediction precision of the prediction model is very important for an operator to popularize and market housekeeper products.
At present, operators have fewer prediction models for house-keeping product demands, and models in some other product demand prediction technical schemes of the existing operators are mainly based on table statistics or weight of artificially set features, or are based on shallow machine learning algorithms such as logistic regression, decision trees, neural networks, random forests and the like. However, in the context of big data, these static or shallow algorithms are difficult to obtain higher prediction accuracy in terms of demand prediction problems, cannot meet various personalized demands of users, and are difficult for operators to perform accurate marketing on users who have demands for house-keeping products.
Based on the problems in the prior art, the invention provides a method for predicting the needs of housekeeping products, which has the core thought that: (1) building a deep neural network model; (2) Acquiring user data of a known housekeeper product demand from a mobile phone user label platform, a Deep Packet Inspection (DPI) platform and a mobile phone DPI platform, extracting characteristic data according to the user data of the known housekeeper product demand, and dividing the extracted characteristic data into training data and testing data; (3) Pre-training the built deep neural network model by using training data, obtaining a weight value of the deep neural network model after the model gradually converges, substituting the obtained weight value into the deep neural network model, carrying out accuracy test by using test data, and finishing the training of the deep neural network model when the accuracy meets the requirement; (4) Acquiring user data of a user to be tested with unknown housekeeping product requirements from a mobile phone user label platform, a broadband internet DPI platform and a mobile phone internet DPI platform, extracting characteristic data for predicting the housekeeping product requirements of the user to be tested according to the user data of the user to be tested, inputting the extracted characteristic data into a trained deep neural network model, and outputting a prediction result of the user to be tested on the housekeeping product requirements; (5) And outputting the user data of the user to be tested with the housekeeping product requirement so as to carry out accurate marketing on the user with the housekeeping product requirement. According to the scheme, the house keeping product requirements of the users are predicted based on the deep neural network model, the model training is more sufficient, the feature extraction is more accurate, the potential product requirements of the users can be effectively mined, and the prediction precision of the house keeping product requirements is improved. The prediction method of the demand of the housekeeping product proposed by the present invention is further explained by the following specific examples.
Referring to fig. 2, fig. 2 is a schematic flowchart illustrating a method for predicting a demand of a housekeeper product according to a first embodiment of the present invention, wherein the method for predicting the demand of the housekeeper product includes:
step S10, acquiring user data of a user to be detected in a preset time period through a preset platform;
the main execution body of the prediction method of the housekeeper product demand is a prediction device of the housekeeper product demand, wherein the prediction device of the housekeeper product demand can be a computer or a server, in other embodiments, the prediction device of the housekeeper product demand can also be determined according to actual needs, and the embodiment does not limit the prediction device of the housekeeper product demand.
The method comprises the steps that a prediction device of the demand of a housekeeper product obtains user data of a user to be detected in a preset time period through a preset platform, wherein the preset platform comprises a mobile phone user label platform, a Deep Packet Inspection (DPI) platform and a mobile phone DPI platform; the preset period of time may be 6 months; the user to be tested refers to a user with unknown housekeeping product requirements; the user data comprises user label data, broadband internet surfing data and mobile phone internet surfing data of the user to be detected, and the user data comprises data related to the requirement of the housekeeping product of the user to be detected.
Specifically, the prediction device for the house product demand obtains user data of the user to be tested by obtaining user tag data, broadband internet surfing data and mobile phone internet surfing data of the user to be tested in about 6 months through a mobile phone user tag platform, a broadband internet surfing DPI platform and a mobile phone internet surfing DPI platform.
It should be noted that, in other embodiments, the preset platform may also be one or two of the three platforms, and the preset platform may also be other data platforms that can be used for analyzing the needs of the user housekeeping product, which is not limited in this embodiment. It can be understood that when the preset platform changes, the corresponding user data obtained from the preset platform also changes. The preset time period may also be determined according to actual needs, which is not limited in this embodiment.
Step S20, determining characteristic data for predicting the housekeeping product demand of the user to be tested according to the user data of the user to be tested;
after acquiring user data of a user to be detected, a prediction device of the housekeeping product demand extracts characteristic data for predicting the housekeeping product demand of the user to be detected according to the user data of the user to be detected, wherein the characteristic data can comprise a mobile phone user value label grade of the user to be detected, a called old man frequency grade, a called child frequency grade, a mobile phone user high-conversation low-flow rate ratio, a broadband access competition product housekeeping product frequency, a mobile phone user age range grade, whether a mobile phone number is in-person, a consumption ratio of mobile phone flow in daytime and at night, whether the mobile phone number has attribution broadband service and the like. The number and specific types of feature data can be extracted as needed according to the acquired user data. It should be noted that, in general, the more feature data, the more features indicating the needs of the housekeeping products of the user to be tested are extracted, the more sufficient the feature extraction is, and the higher the prediction accuracy is.
And S30, determining the housekeeping product requirements of the user to be tested according to the feature data and the deep neural network model.
The prediction device of the housekeeping product demand takes the characteristic data as input data after acquiring the characteristic data, and inputs a deep neural network model to predict the housekeeping product demand of a user to be detected, wherein the deep neural network model is obtained by training user data of the user with the known housekeeping product demand, the housekeeping product demand of the user to be detected can be directly predicted, the deep neural network model comprises an input layer, a plurality of hidden layers and an output layer, the number of neurons of the input layer is the same as that of the characteristic data, the number of the hidden layers can be determined according to actual needs and can be selected into 4 layers, each hidden layer comprises a plurality of neuron numbers, the output layer comprises a neuron, the output result is 1-dimensional data and can be selected into 0 or 1, wherein the 0 can be used for representing that the user to be detected does not have the housekeeping product demand, and the 1 can be used for representing that the user to be detected has the housekeeping product demand.
Specifically, a predicted value of the housekeeping product demand of the user to be tested is determined according to the feature data and the deep neural network model, and when the predicted value is a preset value, the condition that the user to be tested has the housekeeping product demand is determined. The predicted value can be 0 or 1 of the output result of the output layer of the deep neural network model, the preset value can be output result 1, the characteristic data is input into the deep neural network model as input data to obtain the predicted value of the housekeeping product demand of the user to be tested, when the predicted value is the preset value 1, it is determined that the user to be tested has the housekeeping product demand, and it can be understood that when the predicted value is not the preset value 1 (when the predicted value is 0), it is determined that the user to be tested does not have the housekeeping product demand.
Further, the prediction device of the housekeeping product demand can output the user data of the user to be tested with the housekeeping product demand after determining the housekeeping product demand of the user to be tested, perform desensitization processing on the user data of the user to be tested with the housekeeping product demand, and send the push information of the housekeeping product to the terminal equipment of the user to be tested with the housekeeping product demand according to the user data after the desensitization processing. The desensitization treatment can be to hide or encrypt sensitive information of a user to be detected with a housekeeping product requirement, wherein the sensitive information can comprise a telephone number, an identity card number and the like; the terminal equipment can be a mobile phone terminal or a television terminal of a user to be tested with a requirement of a housekeeping product; the push information can be in the form of short messages, voice and video.
It should be noted that, after determining the housekeeping product demand of the user to be tested, the prediction device of the housekeeping product demand may also store the user data of the user to be tested having the housekeeping product demand, and after all the users to be tested have been predicted, the user data of all the users having the housekeeping product demand are collectively output in a data list manner, and desensitization processing and push information of the housekeeping product are collectively sent.
The embodiment can realize accurate marketing of the user with the house-keeping product requirement by sending the pushing information of the house-keeping product to the terminal equipment of the user to be tested with the house-keeping product requirement.
In the technical scheme provided by this embodiment, user data of a user to be tested in a preset time period is acquired through a preset platform, characteristic data used for predicting housekeeping product requirements of the user to be tested is determined according to the user data of the user to be tested, and the housekeeping product requirements of the user to be tested are determined according to the characteristic data and a deep neural network model. According to the scheme, the house keeping product requirements of the users are predicted based on the deep neural network model, the model training is more sufficient, the feature extraction is more accurate, the potential product requirements of the users can be effectively mined, and the prediction precision of the house keeping product requirements is improved.
Referring to fig. 3, fig. 3 is a flowchart illustrating a method for predicting demand of housekeeping products according to a second embodiment of the present invention, wherein based on the first embodiment, before the step S10, the method further includes:
step S40, acquiring user data of users with known housekeeping product requirements;
the prediction device of the housekeeping product demand can set up a preset network model based on a deep learning framework Tensorflow and a Python algorithm, the set up preset network model is a not-yet-trained deep neural network model, the preset network model is the same as the network structure of the trained deep neural network model in the first embodiment, and the prediction device comprises an input layer, a plurality of hidden layers and an output layer, wherein the number of neurons of the input layer is the same as that of the feature data, the number of the hidden layers can be selected to be 4, wherein when the number of the hidden layers is 4, the 1 st hidden layer can contain 64 neurons, the 2 nd hidden layer can contain 32 neurons, the 3 rd hidden layer can contain 16 neurons, and the 4 th hidden layer can contain 8 neurons. It should be noted that all the activation functions used by the hidden layer are 'relu' functions, and the activation function used by the output layer is 'sigmoid'.
After a preset network model is built by the prediction device for the requirements of the housekeeping products, user data of users with known requirements of the housekeeping products are obtained from a preset platform. Of course, the user data of the user with known house product requirements can be obtained first, and then the preset network model is built.
Step S50, determining sample characteristic data according to user data of users with known housekeeping product requirements;
and S60, determining the deep neural network model according to the sample characteristic data and a preset network model.
The prediction device of the house keeping product demand extracts sample feature data according to the user data of the user who knows the house keeping product demand, the sample feature data being the same in type and number as the feature data in the first embodiment. The sample feature data includes training feature data and testing feature data.
And training the preset network model by adopting the training characteristic data to determine a target weight value of the preset network model. Specifically, training the set-up preset network model by using training characteristic data, calculating a loss function of the preset network model, judging whether the loss function of the trained preset network model is converged, and when the loss function of the trained preset network model is converged, determining a weight value corresponding to the convergence of the loss function of the preset network model as a target weight value of the preset network model. It can be understood that when the loss function of the trained preset network model is not converged, the training parameters of the preset network model are adjusted, and the training of the preset network model is continued by using the training characteristic data until the loss function of the preset network model is converged to obtain the target weight value of the preset network model.
After the target weight value of the preset network model is obtained, the weight value of the preset network model is set as the target weight value, the preset network model with the target weight value is tested by adopting test characteristic data, so that the accuracy of predicting the requirement of the housekeeping product by the preset network model with the target weight value is tested, when the accuracy is greater than a preset threshold value, the preset network model with the target weight value is determined as a deep neural network model, and the deep neural network model can be directly used for predicting whether a user to be tested has the requirement of the housekeeping product. It can be understood that, if the accuracy is less than or equal to the preset threshold, it indicates that the preset network model is not successfully trained, the training parameters are continuously adjusted, and the training characteristic data is used to train the preset network model until the accuracy is greater than the preset threshold. The preset threshold may be set according to the requirement of prediction accuracy, which is not limited in this embodiment.
In the technical scheme provided by this embodiment, the sample feature data is determined according to the user data of the user with the known housekeeping product requirement by acquiring the user data of the user with the known housekeeping product requirement, and the deep neural network model is determined according to the sample feature data and the preset network model. According to the scheme, the preset neural network model is trained through the user data of the user with known housekeeping product requirements to obtain the deep neural network model for predicting the housekeeping product requirements, the model training is more comprehensive and efficient, and the prediction accuracy of the deep neural network model on the housekeeping product requirements can be improved.
Based on the foregoing embodiment, referring to fig. 4, the present invention further provides a device for predicting a requirement of a housekeeper product, where the device for predicting a requirement of a housekeeper product includes:
the acquisition module 100 acquires user data of a user to be detected in a preset time period through a preset platform;
a determining module 200, configured to determine, according to the user data, feature data for predicting a requirement of a housekeeping product of the user to be tested;
and the prediction module 300 is configured to determine the housekeeping product demand of the user to be tested according to the feature data and the deep neural network model.
Optionally, in the aspect of determining the requirement of the housekeeping product of the user to be tested according to the feature data and the deep neural network model, the prediction module 300 is specifically applied to:
determining a predicted value of the housekeeping product demand of the user to be tested according to the feature data and the deep neural network model;
and when the predicted value is a preset value, determining that the user to be tested has the requirement of a housekeeping product.
Optionally, the device for predicting the demand of a housekeeper product further includes a training module 400, where the training module 400 is specifically applied to:
acquiring user data of a user with known housekeeping product requirements;
determining sample characteristic data according to user data of a user with known housekeeping product requirements;
and determining the deep neural network model according to the sample characteristic data and a preset network model.
Optionally, the training module 400 is specifically configured to, in the aspect of determining the deep neural network model according to the sample feature data and a preset network model:
training the preset network model by adopting the training characteristic data to determine a target weight value of the preset network model;
setting the weight value of the preset network model as the target weight value;
testing the preset network model with the target weight value by adopting the test characteristic data so as to test the accuracy of predicting the house product demand of the preset network model with the target weight value;
and when the accuracy is greater than a preset threshold value, determining the preset network model with a target weight value as the deep neural network model.
Optionally, the device for predicting the demand of a housekeeper product further includes an output module 500, where the output module 500 is specifically applied to:
outputting user data of a user to be tested with the requirement of a housekeeping product;
desensitizing the user data of the user to be tested with the requirement of the housekeeping product;
and sending the pushing information of the housekeeping product to the terminal equipment of the user to be tested with the housekeeping product requirement according to the desensitized user data.
Based on the foregoing embodiments, the present invention further provides a device for predicting a demand for a housekeeper product, where the device for predicting a demand for a housekeeper product may include a memory, a processor, and a program for predicting a demand for a housekeeper product stored in the memory and executable on the processor, and when the processor executes the program for predicting a demand for a housekeeper product, the steps of the method for predicting a demand for a housekeeper product according to any one of the foregoing embodiments are implemented.
Based on the foregoing embodiments, the present invention further provides a computer-readable storage medium, on which a prediction program of a housekeeping product demand is stored, and when the prediction program of the housekeeping product demand is executed by a processor, the steps of the prediction method of the housekeeping product demand according to any one of the foregoing embodiments are implemented.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of other like elements in a process, method, article, or system comprising the element.
The above-mentioned serial numbers of the embodiments of the present invention are only for description, and do not represent the advantages and disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention or the portions contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) as described above and includes several instructions for enabling a terminal device (which may be a smart television, a mobile phone, a computer, etc.) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention, and all equivalent structures or equivalent processes performed by the present invention or directly or indirectly applied to other related technical fields are also included in the scope of the present invention.
Claims (10)
1. A method for predicting demand for a housekeeper product, the method comprising:
acquiring user data of a user to be detected in a preset time period through a preset platform;
determining characteristic data for predicting the housekeeping product demand of the user to be tested according to the user data of the user to be tested;
and determining the housekeeping product requirements of the user to be tested according to the feature data and the deep neural network model.
2. The method for predicting the demand of a housekeeper product as claimed in claim 1, wherein the preset platform comprises a mobile phone user label platform, a broadband internet deep packet inspection platform and a mobile phone internet deep packet inspection platform; the user data comprises user label data, broadband internet access data and mobile phone internet access data of the user to be tested.
3. A method for predicting housekeeping product needs according to claim 1, wherein the step of determining the housekeeping product needs of the user to be tested according to the feature data and the deep neural network model comprises:
determining a predicted value of the housekeeping product demand of the user to be tested according to the feature data and the deep neural network model;
and when the predicted value is a preset value, determining that the user to be tested has the requirement of a housekeeping product.
4. The method for predicting demand of housekeeping products according to claim 1, wherein before the step of obtaining the user data of the user to be tested in the preset time period through the preset platform, the method further comprises:
acquiring user data of a user with known housekeeping product requirements;
determining sample characteristic data according to user data of a user with known housekeeping product requirements;
and determining the deep neural network model according to the sample characteristic data and a preset network model.
5. The method of claim 4, wherein the sample feature data comprises training feature data and testing feature data, and the step of determining the deep neural network model based on the sample feature data and a predetermined network model comprises:
training the preset network model by adopting the training characteristic data to determine a target weight value of the preset network model;
setting the weight value of the preset network model as the target weight value;
testing the preset network model with the target weight value by adopting the test characteristic data so as to test the accuracy of predicting the house product demand of the preset network model with the target weight value;
and when the accuracy is greater than a preset threshold value, determining the preset network model with a target weight value as the deep neural network model.
6. The method for predicting the demand of housekeeping products according to any one of claims 4 to 5, wherein the preset network model is a deep neural network model built based on deep learning framework Tensorflow and Python algorithm, the preset network model comprises an input layer, a plurality of hidden layers and an output layer, wherein the number of neurons of the input layer is the same as the number of the characteristic data.
7. The method for predicting the demand of housekeeping products according to claim 1, wherein after the step of determining the demand of housekeeping products of the user to be tested according to the feature data and the deep neural network model, the method further comprises:
outputting user data of a user to be tested with the requirement of a housekeeping product;
desensitizing the user data of the user to be tested with the requirement of the housekeeping product;
and sending push information of the housekeeping product to the terminal equipment of the user to be tested with the housekeeping product requirement according to the desensitized user data.
8. A device for predicting a demand for a housekeeper product, comprising:
the acquisition module acquires user data of a user to be detected in a preset time period through a preset platform;
the determining module is used for determining and predicting the characteristic data of the housekeeping product demand of the user to be tested according to the user data;
and the prediction module is used for determining the housekeeping product demand of the user to be tested according to the feature data and the deep neural network model.
9. A prediction device of a demand for a housekeeper product, comprising a memory, a processor and a prediction program of a demand for a housekeeper product stored on the memory and executable on the processor, wherein the prediction program of a demand for a housekeeper product, when executed by the processor, implements the steps of the prediction method of a demand for a housekeeper product according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a prediction program of a demand for housekeeping products, which, when executed by a processor, implements the steps of the prediction method of a demand for housekeeping product according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110916842.1A CN115705584A (en) | 2021-08-10 | 2021-08-10 | Method and device for predicting demand of housekeeper product and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110916842.1A CN115705584A (en) | 2021-08-10 | 2021-08-10 | Method and device for predicting demand of housekeeper product and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115705584A true CN115705584A (en) | 2023-02-17 |
Family
ID=85179998
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110916842.1A Pending CN115705584A (en) | 2021-08-10 | 2021-08-10 | Method and device for predicting demand of housekeeper product and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115705584A (en) |
-
2021
- 2021-08-10 CN CN202110916842.1A patent/CN115705584A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107566358B (en) | Risk early warning prompting method, device, medium and equipment | |
| CN109922032B (en) | Method, device, equipment and storage medium for determining risk of logging in account | |
| CN111061874B (en) | Sensitive information detection method and device | |
| CN109509021B (en) | Behavior track-based anomaly identification method and device, server and storage medium | |
| CN109902833B (en) | Machine learning model interpretation method and device | |
| CN108810642B (en) | Bullet screen display method and device and electronic equipment | |
| CN108021934B (en) | Method and device for recognizing multiple elements | |
| CN109976995B (en) | Method and apparatus for testing | |
| CN108399482B (en) | Contract evaluation method and device and electronic equipment | |
| CN109194689B (en) | Abnormal behavior recognition method, device, server and storage medium | |
| CN110288085B (en) | Data processing method, device and system and storage medium | |
| CN112131578A (en) | Method and device for training attack information prediction model, electronic equipment and storage medium | |
| CN110619528A (en) | Behavior verification data processing method, behavior verification data processing device, behavior verification equipment and storage medium | |
| CN112560545B (en) | Method and device for identifying form direction and electronic equipment | |
| CN117409419A (en) | Image detection method, device and storage medium | |
| CN109753561B (en) | Automatic reply generation method and device | |
| CN115130536A (en) | Training method of feature extraction model, data processing method, device and equipment | |
| CN109299592B (en) | Man-machine behavior characteristic boundary construction method, system, server and storage medium | |
| CN110797046B (en) | Method and device for establishing prediction model of voice quality MOS value | |
| CN111488950B (en) | Classification model information output method and device | |
| CN110704614B (en) | Information processing method and device for predicting user group type in application | |
| CN116431912A (en) | User portrait pushing method and device | |
| CN115705584A (en) | Method and device for predicting demand of housekeeper product and readable storage medium | |
| CN110765352A (en) | User interest identification method and device | |
| CN113850670A (en) | Bank product recommendation method, device, equipment and storage medium |
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 |