CN112749998A

CN112749998A - Income information output method and device, electronic equipment and computer storage medium

Info

Publication number: CN112749998A
Application number: CN202110364787.XA
Authority: CN
Inventors: 李文靖; 赵轩
Original assignee: Shanghai Smk Network Technology Co ltd
Current assignee: Shanghai Smk Network Technology Co ltd
Priority date: 2021-04-06
Filing date: 2021-04-06
Publication date: 2021-05-04

Abstract

The application provides a method and a device for outputting income information, electronic equipment and a computer storage medium. The income information output method comprises the following steps: acquiring identification information of user equipment; inputting the identification information of the user equipment into a preset income prediction model, and outputting the income information of the user corresponding to the identification information of the user equipment; the income prediction model is obtained through model training based on WIFI common network information and a training sample set, and the WIFI common network information represents the relationship between different user equipment connected with the same WIFI network. According to the embodiment of the application, the income information can be more accurately output.

Description

Income information output method and device, electronic equipment and computer storage medium

Technical Field

The present application belongs to the technical field of revenue information output, and in particular, to a revenue information output method, apparatus, electronic device, and computer storage medium.

Background

When a merchant conducts marketing putting, the merchant hopes to accurately find out potential customers for putting, so that corresponding individual or family income positioning is often provided for target audiences of the merchant, people in a certain income range need to be selected for accurate putting, and income is difficult to acquire due to sensitive privacy information.

The existing income prediction method uses a regression model, combines the historical income information and the behaviors of a predicted object to predict, and is difficult to cover people without the historical income information. The existing income prediction model is usually to establish a classification model or a regression model on a small amount of samples with known income, to construct the online preference, the offline preference, the population information and the like of a user into multi-dimensional characteristics for training, to construct the characteristics of all the people in the same way and to predict by using the model.

However, the coverage rate and accuracy rate of the existing revenue prediction model are often low, and are embodied in the following stages: (1) a sample stage: the samples capable of acquiring accurate income are fewer, and especially the information of high-income crowds is more sensitive and difficult to acquire, so that the samples for modeling are insufficient or the reliability of the samples is questionable. (2) A modeling stage: the characteristics used for modeling have missing, and if the samples with missing values are deleted, the samples are further reduced; random values or zero or mean values are used for substitution, or missing values are used as characteristics alone, so that the actual situation of the sample cannot be expressed really, and the accuracy of the model is further reduced. (3) A prediction stage: effective characteristics capable of representing income cannot cover all people, so that the trained model cannot effectively predict all people; under the condition that a part of prediction samples obviously have deviation, an effective mechanism is lacked to systematically correct the predicted values.

Disclosure of Invention

The embodiment of the application provides a method and a device for outputting income information, electronic equipment and a computer storage medium, which can more accurately output the income information.

In a first aspect, an embodiment of the present application provides a method for outputting revenue information, including: acquiring identification information of user equipment; inputting the identification information of the user equipment into a preset income prediction model, and outputting the income information of the user corresponding to the identification information of the user equipment; the income prediction model is obtained through model training based on WIFI common network information and a training sample set, and the WIFI common network information represents the relationship between different user equipment connected with the same WIFI network.

Optionally, before the user equipment identification information is input into the preset revenue prediction model and the revenue information of the user corresponding to the user equipment identification information is output, the method further includes: obtaining a training sample; carrying out label propagation on the training samples by utilizing WIFI common network information to expand the training samples to obtain a training sample set; and carrying out model training based on the WIFI common network information and the training sample set to obtain a revenue prediction model.

Optionally, model training is performed based on the WIFI common network information and the training sample set to obtain a revenue prediction model, including: performing feature completion on each training sample in the training sample set by using WIFI common network information; and establishing a revenue prediction model by adopting a machine learning algorithm based on the training sample set after the characteristic completion.

Optionally, after the training sample set based on the feature completion is used to establish the revenue prediction model by using a machine learning algorithm, the method further includes: obtaining a test sample set; inputting the test samples in the test sample set into an income prediction model, and outputting a predicted value; and adjusting the predicted value by utilizing the WIFI common network information.

In a second aspect, an embodiment of the present application provides a revenue information output apparatus, including: the first acquisition module is used for acquiring the identification information of the user equipment; the first output module is used for inputting the user equipment identification information into a preset income prediction model and outputting income information of a user corresponding to the user equipment identification information; the income prediction model is obtained through model training based on WIFI common network information and a training sample set, and the WIFI common network information represents the relationship between different user equipment connected with the same WIFI network.

Optionally, the apparatus further comprises: the second acquisition module is used for acquiring a training sample; the expansion module is used for carrying out label propagation on the training samples by utilizing the WIFI common network information so as to expand the training samples and obtain a training sample set; and the model training module is used for carrying out model training based on the WIFI common network information and the training sample set to obtain a income prediction model.

Optionally, the model training module includes: the characteristic completion unit is used for performing characteristic completion on each training sample in the training sample set by utilizing the WIFI common network information; and the establishing unit is used for establishing a revenue prediction model by adopting a machine learning algorithm based on the training sample set after the characteristic completion.

Optionally, the apparatus further comprises: the third acquisition module is used for acquiring a test sample set; the second output module is used for inputting the test samples in the test sample set into the income prediction model and outputting predicted values; and the adjusting module is used for adjusting the predicted value by utilizing the WIFI common network information.

In a third aspect, an embodiment of the present application provides an electronic device, where the electronic device includes: a processor and a memory storing computer program instructions; the processor, when executing the computer program instructions, implements a revenue information output method as shown in the first aspect.

In a fourth aspect, embodiments of the present application provide a computer storage medium having computer program instructions stored thereon, where the computer program instructions, when executed by a processor, implement the revenue information output method as shown in the first aspect.

The income information output method, the income information output device, the electronic equipment and the computer storage medium can more accurately output income information. The income information output method acquires the identification information of the user equipment; and inputting the identification information of the user equipment into a preset income prediction model, and outputting the income information of the user corresponding to the identification information of the user equipment. The income prediction model is obtained through model training based on WIFI common network information and a training sample set, and the WIFI common network information represents the relationship between different user equipment connected with the same WIFI network, so that the income information can be more accurately output.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments of the present application will be briefly described below, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a schematic flow chart of a revenue information output method according to an embodiment of the present application.

Fig. 2 is a schematic diagram of a conventional method and the added steps of the present invention according to an embodiment of the present application.

FIG. 3 is a schematic diagram of feature completion logic provided in accordance with an embodiment of the present application.

Fig. 4 is a schematic structural diagram of a revenue information output apparatus according to an embodiment of the present application.

Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

Features and exemplary embodiments of various aspects of the present application will be described in detail below, and in order to make objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are intended to be illustrative only and are not intended to be limiting. It will be apparent to one skilled in the art that the present application may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present application by illustrating examples thereof.

It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus 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 apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

In order to solve the prior art problems, embodiments of the present application provide a method and an apparatus for outputting revenue information, an electronic device, and a computer storage medium. First, a method for outputting revenue information provided in the embodiment of the present application will be described below.

Fig. 1 is a flowchart illustrating a revenue information output method according to an embodiment of the present application. As shown in fig. 1, the revenue information output method includes: s101, obtaining user equipment identification information.

S102, inputting the identification information of the user equipment into a preset income prediction model, and outputting the income information of the user corresponding to the identification information of the user equipment; the income prediction model is obtained through model training based on WIFI common network information and a training sample set, and the WIFI common network information represents the relationship between different user equipment connected with the same WIFI network.

In one embodiment, before inputting the user equipment identification information into the preset revenue prediction model and outputting the revenue information of the user corresponding to the user equipment identification information, the method further comprises: obtaining a training sample; carrying out label propagation on the training samples by utilizing WIFI common network information to expand the training samples to obtain a training sample set; and carrying out model training based on the WIFI common network information and the training sample set to obtain a revenue prediction model.

In one embodiment, model training is performed based on WIFI common network information and a training sample set to obtain a revenue prediction model, including: performing feature completion on each training sample in the training sample set by using WIFI common network information; and establishing a revenue prediction model by adopting a machine learning algorithm based on the training sample set after the characteristic completion.

The machine learning algorithm may be a neural network algorithm, a deep learning algorithm, or the like, and is not specifically limited herein, and model formulas corresponding to these machine learning algorithms are all the prior art and are not described herein again; the features of the training sample set can be various features such as online and offline behavior features and population attributes of the samples.

In one embodiment, after the revenue prediction model is built using a machine learning algorithm based on the feature complemented training sample set, the method further comprises: obtaining a test sample set; inputting the test samples in the test sample set into an income prediction model, and outputting a predicted value; and adjusting the predicted value by utilizing the WIFI common network information.

The income information output method acquires the identification information of the user equipment; and inputting the identification information of the user equipment into a preset income prediction model, and outputting the income information of the user corresponding to the identification information of the user equipment. The income prediction model is obtained through model training based on WIFI common network information and a training sample set, and the WIFI common network information represents the relationship between different user equipment connected with the same WIFI network, so that the income information can be more accurately output.

The above technical solution is explained below with a specific example.

The method and the device make full use of WIFI common network information, respectively supplement samples, supplement characteristics and correct the predicted values in a sample stage, a training stage and a prediction stage, and accordingly provide more accurate and credible income prediction results.

As shown in fig. 2, compared with the conventional method, in the stage of obtaining a sample, the method performs sample propagation through the common network information to expand the sample; in the training modeling stage, feature completion is carried out through the common network information, and the coverage rate of features is improved; and in the income prediction stage, correcting the prediction result through the common network information. The feature completion logic can be seen in fig. 3.

The specific system process based on the Spark platform in this embodiment is as follows: 1. and (3) carrying out label propagation on the samples according to the co-network relation among the devices: (a) the sample label is propagated to all the other devices connected to the same Bssid, and the propagation score is Xa/log2 (number of people connected to the Bssid), where Xa is the revenue propagation coefficient for each level, and the higher the revenue, the larger the coefficient setting. (b) The score propagated to each device by each type of sample is recorded.

The common network relationship among the devices means that the devices are connected to the same WIFI network (Bssid), and the devices can be connected to the same Bssid at the same time, in different time periods on the same day and at different times according to the connection time of the devices. Based on the co-networking relationship among the devices, all the other devices which are connected with one device through the same Bssid can be determined, the same label is marked for the devices, and the label propagation is realized.

2. For non-sample devices, the credible sample is selected according to the total score and the ratio of various scores, and is used as a sample supplement: (a) for high income crowds, the total score of the transmission is required to be not lower than a specified threshold value 1, and the score ratio transmitted by high income is not lower than a specified threshold value 2; (b) for the middle income crowd, the total score of the spread is required to be not higher than a specified threshold value 3, and the ratio of the score spread by the income crowd is not lower than a specified threshold value 4; (c) for low income groups, it is desirable that the total score of the spread is not higher than a specified threshold of 5, and the score spread by this type of income group is higher than a threshold of 4.

3. And calculating various characteristics such as online and offline behavior characteristics, population attributes and the like of the sample according to a traditional method.

4. And (3) performing characteristic completion according to the equipment and the connection bssid information: (a) calculating the average score of each bsid on the characteristics, wherein the average score is the average score of the equipment which is connected with the bsid and has scores; (b) and regarding the device lacking the characteristic value, taking the average value of the scores of the connected bssids on the characteristic as the score of the device on the characteristic.

5. And (4) establishing a classification model by adopting a machine learning method for the sample expanded in the step (2) through the characteristics supplemented in the step (4).

6. And (4) generating characteristics of the population needing to be predicted in a traditional mode, performing characteristic completion in the same mode as the step 4, and then performing prediction by using the model established in the step 5.

7. And (3) carrying out label propagation on the prediction result in the step (6) in the mode in the step (1), and adjusting the prediction value which does not accord with the logic: (a) if the total spread score and the spread percentage of the high income crowd of the equipment are very high, the predicted value of the equipment is increased by one level; (b) if the total score of the equipment to be transmitted is low and the transmission ratio of the equipment to be transmitted by the low-income crowd is high, the predicted value of the equipment is adjusted to be lower by one level.

The rules for adjusting the predicted values may include the rules shown in (a) and (b), which are configured in advance for the purpose of improving the accuracy of prediction.

According to the embodiment, under the condition that the income samples are seriously insufficient, the tags can be transmitted through the WIFI common network information, and the credible sample sources are effectively supplemented. And the modeling characteristics are supplemented through WIFI common network information, the prediction characteristics are supplemented, and the accuracy and the coverage rate of the income prediction model are improved. And correcting the deviation through WIFI common network information, and further perfecting a revenue prediction model.

Fig. 4 is a schematic structural diagram of a revenue information output apparatus according to an embodiment of the present application, and as shown in fig. 4, the revenue information output apparatus includes: a first obtaining module 401, configured to obtain user equipment identification information; a first output module 402, configured to input the user equipment identification information into a preset revenue prediction model, and output revenue information of a user corresponding to the user equipment identification information; the income prediction model is obtained through model training based on WIFI common network information and a training sample set, and the WIFI common network information represents the relationship between different user equipment connected with the same WIFI network.

In one embodiment, the apparatus further comprises: the second acquisition module is used for acquiring a training sample; the expansion module is used for carrying out label propagation on the training samples by utilizing the WIFI common network information so as to expand the training samples and obtain a training sample set; and the model training module is used for carrying out model training based on the WIFI common network information and the training sample set to obtain a income prediction model.

In one embodiment, a model training module, comprising: the characteristic completion unit is used for performing characteristic completion on each training sample in the training sample set by utilizing the WIFI common network information; and the establishing unit is used for establishing a revenue prediction model by adopting a machine learning algorithm based on the training sample set after the characteristic completion.

In one embodiment, the apparatus further comprises: the third acquisition module is used for acquiring a test sample set; the second output module is used for inputting the test samples in the test sample set into the income prediction model and outputting predicted values; and the adjusting module is used for adjusting the predicted value by utilizing the WIFI common network information.

Each module/unit in the apparatus shown in fig. 4 has a function of implementing each step in fig. 1, and can achieve the corresponding technical effect, and for brevity, the description is not repeated here.

Fig. 5 shows a schematic structural diagram of an electronic device provided in an embodiment of the present application.

The electronic device may comprise a processor 501 and a memory 502 in which computer program instructions are stored.

Specifically, the processor 501 may include a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or may be configured to implement one or more Integrated circuits of the embodiments of the present Application.

Memory 502 may include mass storage for data or instructions. By way of example, and not limitation, memory 502 may include a Hard Disk Drive (HDD), a floppy Disk Drive, flash memory, an optical Disk, a magneto-optical Disk, tape, or a Universal Serial Bus (USB) Drive or a combination of two or more of these. Memory 502 may include removable or non-removable (or fixed) media, where appropriate. The memory 502 may be internal or external to the electronic device, where appropriate. In particular embodiments, memory 502 may be non-volatile solid-state memory.

In one example, the Memory 502 may be a Read Only Memory (ROM). In one example, the ROM may be mask programmed ROM, programmable ROM (prom), erasable prom (eprom), electrically erasable prom (eeprom), electrically rewritable ROM (earom), or flash memory, or a combination of two or more of these.

The processor 501 reads and executes computer program instructions stored in the memory 502 to implement any one of the revenue information output methods in the above embodiments.

In one example, the electronic device can also include a communication interface 503 and a bus 510. As shown in fig. 5, the processor 501, the memory 502, and the communication interface 503 are connected via a bus 510 to complete communication therebetween.

The communication interface 503 is mainly used for implementing communication between modules, apparatuses, units and/or devices in the embodiments of the present application.

Bus 510 comprises hardware, software, or both to couple the components of the online data traffic billing device to each other. By way of example, and not limitation, a bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hypertransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an infiniband interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a video electronics standards association local (VLB) bus, or other suitable bus or a combination of two or more of these. Bus 510 may include one or more buses, where appropriate. Although specific buses are described and shown in the embodiments of the application, any suitable buses or interconnects are contemplated by the application.

In addition, the embodiment of the application can be realized by providing a computer storage medium. The computer storage medium having computer program instructions stored thereon; the computer program instructions, when executed by a processor, implement any of the revenue information output methods of the above embodiments.

It is to be understood that the present application is not limited to the particular arrangements and instrumentality described above and shown in the attached drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present application are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications, and additions or change the order between the steps after comprehending the spirit of the present application.

The functional blocks shown in the above-described structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the present application are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of a machine-readable medium include electronic circuits, semiconductor memory devices, ROM, flash memory, Erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, Radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.

It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed simultaneously.

Aspects of the present application are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions/acts specified in the flowchart and/or block diagram block or blocks. Such a processor may be, but is not limited to, a general purpose processor, a special purpose processor, an application specific processor, or a field programmable logic circuit. It will also be understood that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware for performing the specified functions or acts, or combinations of special purpose hardware and computer instructions.

As described above, only the specific embodiments of the present application are provided, and it can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system, the module and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present application, and these modifications or substitutions should be covered within the scope of the present application.

Claims

1. A method for outputting revenue information, comprising:

acquiring identification information of user equipment;

inputting the user equipment identification information into a preset income prediction model, and outputting income information of a user corresponding to the user equipment identification information; the income prediction model is obtained through model training based on WIFI common network information and a training sample set, and the WIFI common network information represents the relationship between different user equipment connected with the same WIFI network.

2. The revenue information output method of claim 1, wherein before the inputting the user equipment identification information into a preset revenue prediction model and outputting the revenue information of the user corresponding to the user equipment identification information, the method further comprises:

obtaining a training sample;

performing label propagation on the training samples by using the WIFI common network information to expand the training samples to obtain the training sample set;

and performing model training based on the WIFI common network information and the training sample set to obtain the income prediction model.

3. The revenue information output method of claim 2, wherein the model training based on the WIFI common network information and the training sample set to obtain the revenue prediction model comprises:

performing feature completion on each training sample in the training sample set by using the WIFI common network information;

and establishing the income prediction model by adopting a machine learning algorithm based on the training sample set after the characteristic completion.

4. The revenue information output method of claim 3, wherein after the training sample set based on feature completion, the revenue prediction model is built using a machine learning algorithm, the method further comprises:

obtaining a test sample set;

inputting the test samples in the test sample set into the income prediction model, and outputting predicted values;

and adjusting the predicted value by utilizing the WIFI common network information.

5. A revenue information output apparatus, comprising:

the first acquisition module is used for acquiring the identification information of the user equipment;

the first output module is used for inputting the user equipment identification information into a preset income prediction model and outputting income information of a user corresponding to the user equipment identification information; the income prediction model is obtained through model training based on WIFI common network information and a training sample set, and the WIFI common network information represents the relationship between different user equipment connected with the same WIFI network.

6. The revenue information output apparatus of claim 5, wherein the apparatus further comprises:

the second acquisition module is used for acquiring a training sample;

the expansion module is used for carrying out label propagation on the training samples by utilizing the WIFI common network information so as to expand the training samples to obtain the training sample set;

and the model training module is used for carrying out model training based on the WIFI common network information and the training sample set to obtain the income prediction model.

7. The revenue information output apparatus of claim 6, wherein the model training module comprises:

the characteristic completion unit is used for performing characteristic completion on each training sample in the training sample set by utilizing the WIFI common network information;

and the establishing unit is used for establishing the income prediction model by adopting a machine learning algorithm based on the training sample set after the characteristic completion.

8. The revenue information output apparatus of claim 7, wherein the apparatus further comprises:

the third acquisition module is used for acquiring a test sample set;

the second output module is used for inputting the test samples in the test sample set into the income prediction model and outputting predicted values;

and the adjusting module is used for adjusting the predicted value by utilizing the WIFI common network information.

9. An electronic device, characterized in that the electronic device comprises: a processor and a memory storing computer program instructions;

the processor, when executing the computer program instructions, implements the revenue information output method of any of claims 1 to 4.

10. A computer storage medium having computer program instructions stored thereon, which when executed by a processor, implement the revenue information output method of any one of claims 1 to 4.