Advertisement pushing method and device, electronic equipment and storage medium

By analyzing user behavior information and family attribute information, calculating advertising attribute scores, and selecting the appropriate advertising type for pushing, the problem of low returns caused by random audiences in traditional TV advertising is solved, and precise advertising and revenue increase is achieved.

CN119027184APending Publication Date: 2024-11-26CHINA MOBILE (SUZHOU) SOFTWARE TECH CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410996789.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-24
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

In traditional TV advertising, the audience of advertisements is relatively random, resulting in low advertising revenue.

Method used

By obtaining local user behavior information, analyzing user portraits, calculating the attribute score of the ad type based on family attribute information, and selecting the corresponding ad type for pushing.

Benefits of technology

It realizes accurate advertising delivery to users and improves advertising delivery revenue.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119027184A_ABST
    Figure CN119027184A_ABST
Patent Text Reader

Abstract

The invention discloses an advertisement pushing method and device, electronic equipment and a storage medium, and the main technical scheme comprises the steps: firstly, obtaining the behavior information of a local user, carrying out the analysis according to the behavior information, and obtaining a user portrait of the local user; wherein the user portrait comprises personal attribute data and behavior attribute information of the user; secondly, calculating attribute scores of different advertisement types according to the user portraits and the family attribute information; wherein the family attribute information comprises the number of local users and intelligent equipment information; and finally, according to the attribute score, selecting a corresponding advertisement type for pushing. Wherein different attribute scores correspond to different advertisement types. Compared with the prior art, according to the embodiment of the invention, the user portrait is analyzed in the preferential time and space, and the corresponding advertisement type is matched for the user through the user portrait, so that accurate advertisement audience putting is provided, and the advertisement putting income is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to a method and device for pushing advertisements, an electronic device, and a storage medium. Background Art

[0002] With the upgrade of broadband service technology, TV boxes have realized functions that traditional TV services did not have in the past, such as video on demand, massive playback sources, home theater, and Internet surfing, enabling family entertainment, which is also something that the small screen of a mobile phone cannot bring.

[0003] At present, the traditional TV advertising business has the following delivery methods: advertising on TV stations, although the advertising coverage is wide, the target audience cannot be refined and the advertising cost is high; in TV boxes, the ads are pre-downloaded and stored in the box, and the ads are played when the box is turned on; when the video APP is started, the ads are played during the loading waiting time of the APP.

[0004] Although this method can achieve the delivery and push of advertisements, the audience of the advertisements is relatively random and the advertising revenue is not high. Summary of the invention

[0005] The present disclosure provides an advertisement push method, device, electronic device and storage medium, the main purpose of which is to solve the problem that the audience group of advertisements is relatively random and the advertisement revenue is not high.

[0006] According to a first aspect of the present disclosure, a method for pushing an advertisement is provided, comprising:

[0007] Obtaining behavior information of a local user, and analyzing the behavior information to obtain a user portrait of the local user; wherein the user portrait includes user personal attribute data and behavior attribute information;

[0008] Calculating attribute scores of different advertisement types according to the user portrait and family attribute information; wherein the family attribute information includes the number of local users and smart device information;

[0009] A corresponding advertisement type is selected for push according to the attribute score; wherein different attribute scores correspond to different advertisement types.

[0010] Optionally, before obtaining the behavior information of the local user and analyzing the behavior information to obtain the user portrait of the local user, the method further includes:

[0011] Get the network media access control address (MAC) and Bluetooth MAC of different devices;

[0012] Based on the network MAC and Bluetooth MAC of each device, determine the online time of different devices and identify home devices.

[0013] Optionally, the acquiring behavior information of the local user, and performing analysis based on the behavior information to acquire the user portrait of the local user includes:

[0014] Based on the network MAC and the Bluetooth MAC, the behavior information of the local user is obtained; wherein the behavior information at least includes the home time and network behavior; the home time includes the home time on weekdays and the home time on holidays;

[0015] Determining the work intensity and entertainment intensity of the user away from home according to the length of time spent at home;

[0016] The home working intensity and shopping intensity of the local user are determined based on the network behavior.

[0017] Optionally, before calculating the attribute score according to the user portrait and the family attribute information, the method further includes:

[0018] Acquire the number of local users, and determine the personal information of the local users according to the behavior information of the local users; wherein the personal information includes age and gender;

[0019] The type and brand of the smart device are determined based on the network MAC and the Bluetooth MAC of each device.

[0020] Optionally, the calculating of attribute scores of different advertisement types according to the user portrait and household attribute information; wherein the household attribute information includes the number of local users and smart device information including:

[0021] Calculating a household gender score based on different advertisement types and the gender of each of the local users;

[0022] Calculating a home work intensity score according to the home work intensity and away-from-home work intensity of each local user;

[0023] Calculating a family entertainment score according to the entertainment intensity of each of the local users;

[0024] Calculate a home brand score based on the type and brand of the home smart device;

[0025] The attribute scores of different advertisement types are calculated respectively according to the family gender score, the family work intensity score, the family entertainment score, the family brand score and a preset coefficient.

[0026] Optionally, after determining the type and brand of the smart device according to the network MAC and the Bluetooth MAC of each device, the method further includes:

[0027] Establishing an advertisement type set and a family set; wherein the family set includes family attribute information and viewing users; wherein the viewing users are determined by the Bluetooth MAC corresponding to the local user;

[0028] Establishing a bipartite graph according to the advertisement type set and the family set, and calculating edge weights;

[0029] The advertisement type set with the largest edge weight is determined as the target push advertisement type for the family set.

[0030] According to a second aspect of the present disclosure, there is provided an advertisement pushing device, comprising:

[0031] A first acquisition unit is used to acquire behavior information of a local user, and to analyze the behavior information to acquire a user portrait of the local user; wherein the user portrait includes user personal attribute data and behavior attribute information;

[0032] A first calculation unit, configured to calculate attribute scores of different advertisement types according to the user portrait and family attribute information; wherein the family attribute information includes the number of local users and smart device information;

[0033] The push unit is used to select a corresponding advertisement type for push according to the attribute score; wherein different attribute scores correspond to different advertisement types.

[0034] Optionally, the device further comprises:

[0035] A second acquisition unit is used to acquire the behavior information of the local user in the first acquisition unit, and analyze the behavior information before acquiring the user portrait of the local user, and acquire the network media access control address (MAC) and Bluetooth MAC of different devices based on the behavior information;

[0036] The first determining unit is used to determine the online time of different devices based on the network MAC and Bluetooth MAC of each device, and determine the home device.

[0037] Optionally, the first acquiring unit is further used for:

[0038] Based on the network MAC and the Bluetooth MAC, the behavior information of the local user is obtained; wherein the behavior information at least includes the home time and network behavior; the home time includes the home time on weekdays and the home time on holidays;

[0039] Determining the work intensity and entertainment intensity of the user away from home according to the length of time spent at home;

[0040] The home working intensity and shopping intensity of the local user are determined based on the network behavior.

[0041] Optionally, the device further comprises:

[0042] a third acquisition unit, configured to acquire the number of local users and determine the personal information of the local users according to the behavior information of the local users before the first calculation unit calculates the attribute score according to the user portrait and the family attribute information; wherein the personal information includes age and gender;

[0043] The second determining unit is used to determine the type and brand of the smart device according to the network MAC and the Bluetooth MAC of each device.

[0044] Optionally, the first computing unit is further used for:

[0045] Calculating a household gender score based on different advertisement types and the gender of each of the local users;

[0046] Calculating a home work intensity score according to the home work intensity and away-from-home work intensity of each local user;

[0047] Calculating a family entertainment score according to the entertainment intensity of each of the local users;

[0048] Calculate a home brand score based on the type and brand of the home smart device;

[0049] The attribute scores of different advertisement types are calculated respectively according to the family gender score, the family work intensity score, the family entertainment score, the family brand score and a preset coefficient.

[0050] Optionally, the device further comprises:

[0051] an establishing unit, configured to establish an advertisement type set and a family set after the second determining unit determines the type and brand of the smart device according to the network MAC and the Bluetooth MAC of each device; wherein the family set includes family attribute information and viewing users; wherein the viewing users are determined by the Bluetooth MAC corresponding to the local user;

[0052] A second calculation unit, used for establishing a bipartite graph according to the advertisement type set and the family set, and calculating edge weights;

[0053] The third determining unit is used to determine the advertisement type set with the largest edge weight as the target push advertisement type for the family set.

[0054] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0055] at least one processor; and

[0056] a memory communicatively connected to the at least one processor; wherein,

[0057] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect.

[0058] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method described in the first aspect.

[0059] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method as described in the first aspect above.

[0060] The main technical scheme of the advertisement push method, device, electronic device and storage medium provided by the present disclosure includes: first, obtaining the behavior information of the local user, and analyzing the behavior information to obtain the user portrait of the local user; wherein the user portrait includes the user's personal attribute data and behavior attribute information; second, calculating the attribute scores of different advertisement types according to the user portrait and family attribute information; wherein the family attribute information includes the number of local users and smart device information; finally, selecting the corresponding advertisement type for push according to the attribute score; wherein different attribute scores correspond to different advertisement types. Compared with the related art, the embodiment of the present application analyzes the user portrait in the preferred time and space, and matches the corresponding advertisement type to the user through the user portrait, so as to provide accurate advertisement audience delivery and improve the advertisement delivery revenue.

[0061] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0063] Figure 1 A flowchart of an advertisement push method provided by an embodiment of the present disclosure;

[0064] Figure 2 A flowchart of an advertisement push method provided by an embodiment of the present disclosure;

[0065] Figure 3A flowchart of an advertisement push method provided by an embodiment of the present disclosure;

[0066] Figure 4 A schematic diagram of a bipartite graph provided by an embodiment of the present disclosure;

[0067] Figure 5 A schematic diagram of the structure of an advertisement push device provided by an embodiment of the present disclosure;

[0068] Figure 6 A schematic diagram of the structure of an advertisement push device provided by an embodiment of the present disclosure;

[0069] Figure 7 A schematic block diagram of an exemplary electronic device provided for an embodiment of the present disclosure. DETAILED DESCRIPTION

[0070] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0071] The following describes the advertising push method, device, electronic device and storage medium of the embodiments of the present disclosure with reference to the accompanying drawings. In some embodiments, the method can be applied to small electronic devices such as TV boxes and routers. The embodiments of the present application are described by taking the TV box as the execution subject as an example.

[0072] Figure 1 A flowchart of an advertisement push method provided by an embodiment of the present disclosure is provided.

[0073] like Figure 1 As shown, the method comprises the following steps:

[0074] Step 101, obtain the behavior information of the local user, and analyze the behavior information to obtain the user portrait of the local user; wherein the user portrait includes the user's personal attribute data and behavior attribute information.

[0075] In some embodiments, the local user can be set in advance for the user and obtained by binding the electronic device, or can be determined by identifying the mobile device, such as by the device type (mobile phone, computer) and the length of stay (such as the length of time at home in a week) (by binding the local user by device, one device is a local user by default). The behavior information of the local user is the network behavior information, such as the type of browsing information, such as entertainment information, shopping information, work information, etc., which is not limited in the embodiments of the present application.

[0076] In some embodiments, after collecting the behavior information of local users, a user portrait of the local users is generated by analyzing the behavior information, such as determining the user's entertainment preferences, shopping preferences, gender, age range, etc. by browsing information types. Specifically, the embodiments of the present application do not limit the specific content of the user portrait.

[0077] In some embodiments, a local embedded model can be inserted into the TV box to analyze the behavior information of local users, refuse to upload it to the cloud, and protect user privacy and security.

[0078] Step 102, calculating attribute scores of different advertisement types based on the user portrait and household attribute information; wherein the household attribute information includes the number of local users and smart device information.

[0079] In some embodiments, the family attributes include relevant information of local users, such as the number of local users, the associated devices of each local user, and basic information of the local users, such as age, gender, etc. The smart device information is the type and brand of the devices in the user's home. Specifically, relevant information can be collected according to actual needs. The embodiments of this application do not limit the specific content of the family attribute information.

[0080] In some embodiments, different user attribute scores are given different scores depending on the type of advertisement. For example, when the advertisement type is women's products or men's products, the corresponding score ratios are different depending on the gender of the local user. Therefore, before calculating the attribute scores, the score ratios of different types of users are set in advance according to the advertisement type, such as setting them to 3:7 or 4:6. In actual applications, they can be set according to actual needs, and the embodiments of the present application do not limit this.

[0081] Step 103: Select a corresponding advertisement type for push according to the attribute score; different attribute scores correspond to different advertisement types.

[0082] In some embodiments, data monitoring and advertisement updating can be performed while the machine is powered on or soft-shut down, and determined advertisement types can be cached in advance so that targeted advertisements can be pushed to the user when the machine is started during the user's frequently used time period.

[0083] In some embodiments, when determining the type of advertisement to be pushed, several advertisement types with higher attribute scores may be determined for push based on the attribute scores, such as determining the five advertisement types with the highest attribute scores for push, etc. Specifically, the embodiments of the present application do not limit this.

[0084] The main technical scheme of the advertisement push method provided by the present disclosure includes: first, obtaining the behavior information of the local user, and analyzing the behavior information to obtain the user portrait of the local user; wherein the user portrait includes the user's personal attribute data and behavior attribute information; second, calculating the attribute scores of different advertisement types according to the user portrait and family attribute information; wherein the family attribute information includes the number of local users and smart device information; finally, selecting the corresponding advertisement type for push according to the attribute score; wherein different attribute scores correspond to different advertisement types. Compared with the related art, the embodiment of the present application analyzes the user portrait in the preferred time and space, and matches the corresponding advertisement type for the user through the user portrait, so as to provide accurate advertisement audience delivery and improve the advertisement delivery revenue.

[0085] In some embodiments, before obtaining the behavior information of the local user in step 101 and analyzing the behavior information to obtain the user portrait of the local user, the method further includes:

[0086] Get the network media access control address (MAC) and Bluetooth MAC of different devices;

[0087] Based on the network MAC and Bluetooth MAC of each device, determine the online time of different devices and identify home devices.

[0088] In some embodiments, after the TV box network is connected to the home LAN, the network MAC addresses of all devices in the LAN are recorded, the home mobile gateway information is obtained, and Bluetooth is used to detect surrounding Bluetooth MAC addresses.

[0089] The TV box filters the devices that are online for 72 hours in the local area network, excluding other home smart devices and obtaining the device type and brand, such as smart speakers and smart camera devices.

[0090] During the daily LAN and Bluetooth scanning device process, a scan is performed every 5 minutes. If no LAN MAC address and Bluetooth MAC address are detected within the time interval, or a newly detected LAN MAC address and Bluetooth MAC address are determined to be the same user and bound.

[0091] In some embodiments, when a user uses a TV box for the first time, the hardware function status of the TV box can be tested. The user specifies a password and controls the box by voice. The box uses a local embedded model to analyze the voice and identify the user's gender and age. The voice data is processed locally and deleted after analysis. The embedded model can be upgraded later, but the data refuses to be analyzed online. The specified voice of the box can set a voiceprint lock. The user enables the voiceprint lock and performs recognition based on the recorded voiceprint. Only users who have enabled the lock permission can control the device with voice.

[0092] In some embodiments, the user's behavior information includes not only the user's browsing information content, but also the user's home time. Figure 2 , Figure 2 A flowchart of a method for pushing advertisements provided by an embodiment of the present disclosure; comprising:

[0093] Step 201, based on the network MAC and the Bluetooth MAC, obtain the behavior information of the local user; wherein the behavior information at least includes the home time and network behavior; the home time includes the home time on weekdays and the home time on holidays.

[0094] In some embodiments, the TV box can be used to detect whether the user's mobile phone or wearable device such as a bracelet is present in the local area network, or to monitor whether the Bluetooth signal of the device exists, so as to determine the time when the user leaves home and returns home; the TV box analyzes the user behavior data obtained through the TV APP of the TV itself or from the mobile gateway, such as the user's movie viewing information, the browsing information of the user's mobile device, etc., to collect the user's behavior information. Specifically, the embodiments of the present application do not limit the method of collecting information.

[0095] Step 202, determining the intensity of the user's work and entertainment away from home according to the length of time spent at home.

[0096] In some embodiments, the present application classifies the user's work intensity into three categories, the lower the level, the more time the user has at his / her disposal, and the higher the level, the less time the user has at his / her disposal. The office work intensity here is limited to the user's work away from home.

[0097] a. The total time away from home on working days is less than 10 hours, the frequency is greater than or equal to 3 days, and the work intensity is level I.

[0098] b. The total time away from home on working days is greater than or equal to 10 hours and less than 12 hours, the frequency is greater than or equal to 3 days, and the work intensity is Level II.

[0099] c. The total time away from home on working days is greater than or equal to 12 hours, the frequency is greater than or equal to 3 days, and the work intensity is level III.

[0100] Here, the user's entertainment behavior is classified into two levels: user entertainment at home and user entertainment away from home. The user's entertainment method also determines the user's consumption method, which is also an important user behavior label. The higher the user's entertainment level, the more active the user's outdoor activities are and the more active their consumption behavior will be.

[0101] a. On weekends, the time spent at home during the day is greater than or equal to 16 hours, the frequency is greater than or equal to 2 times a month, and the entertainment level is Level I.

[0102] b. On weekends, the time spent at home during the day is greater than or equal to 8 hours and less than 16 hours, the frequency is greater than or equal to 2 times a month, and the entertainment level is II.

[0103] c. On weekends, the time spent at home during the day is greater than or equal to 4 hours and less than 8 hours, the frequency is greater than or equal to 2 times a month, and the entertainment level is Level III.

[0104] d. On weekends, the time spent at home during the day is less than 4 hours, the frequency is greater than or equal to 2 times a month, and the entertainment level is IV.

[0105] Step 203: Determine the home working intensity and shopping intensity of the local user according to the network behavior.

[0106] In some embodiments, for people engaged in mental work, after returning home, they will also work from home. The TV box detects the MAC address and Bluetooth signal through the local area network and obtains the mobile gateway data, so as to analyze the user's home office situation. Analyzing the behavior of mental workers can have a certain reference value for determining the user's income. The TV box can communicate with the mobile home gateway to obtain the usage time and traffic information of mobile office applications or web pages. The lower the work intensity level at home, the lower the intensity of the user's work at home after returning home.

[0107] a. Working from home for less than or equal to 1 hour on weekdays, with a frequency of more than or equal to 3 days, and the intensity of work at home is level I.

[0108] b. The working hours after returning home on weekdays are greater than 1 hour and less than or equal to 2 hours, and the frequency is greater than or equal to 3 days. The intensity of work after returning home is level II.

[0109] c. Working hours after returning home on weekdays are greater than 2 hours, the frequency is greater than or equal to 3 days, and the work intensity is level III.

[0110] These shopping behaviors also affect the user's consumption tag data. The TV box analyzes user behavior data through the TV APP of the TV itself or obtained from the mobile gateway. If the user uses the TV-side shopping APP, the Bluetooth signal can be detected, and the user with the strongest signal distance from the box is used as the user. If the user has multiple overlapping levels, the next level after the highest level is used as the final judgment level. For example, if a user uses shopping platform a with a higher average price and platform b with a medium average price at the same time, the level of platform a is used as the user's consumption ability level. At this time, the user has uncertain consumption ability behavior.

[0111] a. The frequency of using the platform with the lowest average price d is greater than or equal to 3 days in a week, and the online shopping consumption capacity is level I.

[0112] b. The frequency of using platform c, whose average price is only higher than platform d, is greater than or equal to 3 days within a week, and the online shopping consumption capacity is level II.

[0113] c. The frequency of using platform b, whose average price is second only to platform a, is greater than or equal to 3 days within a week, and the online shopping consumption capacity is level III.

[0114] d. The user uses platform A, which has the highest average price, for more than 3 days in a week, and his online shopping consumption capacity is level IV.

[0115] In some embodiments, the user's home dining behavior is also a good behavior label. The user's dining includes three ways: purchasing ingredients and cooking, ordering takeout, and dining out. The TV box can obtain whether the category of the video watched by the user includes food programs during the daily dining time period. The food here can include homemade food and dining out programs. The box will also obtain the data of the mobile home gateway during the same time period to check the APP information currently browsed by the user. The APP here can include fresh food APPs and takeout APPs.

[0116] a. If the user likes food programs, the user's consumption ability is level I and he is a potential consumer user.

[0117] b. If the user uses fresh food apps three days or more a week, his / her internet dining consumption capacity is Level II.

[0118] c. The user uses food delivery apps for three days or more a week, and the user's internet dining consumption capacity is Level III.

[0119] If a user has multiple tags, the highest level is taken as the user's dietary consumption capacity. Dividing users into these three categories can push relevant advertising information more accurately.

[0120] In some embodiments, it may be possible to determine whether there are children in a household by browsing the following information types:

[0121] a. On weekdays, between 16:00 and 18:00 in the afternoon, broadcast programs for infants and young children. The frequency is 3 days or more per week, and the family has children in kindergarten.

[0122] b. Children's programs are played between 18:00 and 21:00 on weekdays. The frequency is 3 days or more per week and there are teenagers or children in the family.

[0123] Step 204, obtaining the number of local users, and determining the personal information of the local users according to the behavior information of the local users; wherein the personal information includes age and gender.

[0124] In some embodiments, the TV box can form a family list based on the user data detected daily, and determine the gender and approximate age range of the local user based on the behavior information of each local user and the type of browsing information.

[0125] In some embodiments, user personal information may include the following: 1. Random user ID, used to distinguish home users; 2. LAN MAC address, Bluetooth MAC address; 3. Gender, age; 4. Work intensity; 5. Entertainment intensity; 6. Video viewing preferences, labeled according to the user's daily video viewing categories; 7. Frequent video viewing time periods, calculated based on the user's frequent video viewing time periods; 8. Wearable Bluetooth device type and brand; 9. Mobile phone model and brand.

[0126] Step 205: determine the type and brand of the smart device according to the network MAC and the Bluetooth MAC of each device.

[0127] By filtering devices that are online for 72 hours in the local area network, other home smart devices are excluded and the device type and brand are obtained, such as smart speakers and smart camera devices.

[0128] See also Figure 3 , Figure 3 A flowchart of a method for pushing advertisements provided by an embodiment of the present disclosure; comprising:

[0129] Step 301, calculating a household gender score according to different advertisement types and the gender of each local user.

[0130] The family gender score provides a gender score calculation method for advertising suppliers. By default, the female score is 1.0, the male score is 1.0, and the total is 2.0. Suppliers can set different scores for gender. For example, if the target gender of the advertisement is male and the non-target gender is female, the male score can be set to 1.6 and the non-target score to 0.4, but the sum of the target gender score and the non-target gender score must be 2.0. Then the family gender score can be expressed as follows:

[0131] Target family gender score = number of target gender * target gender score + number of non-target gender * non-target family score.

[0132] Step 302: Calculate a home work intensity score based on the home work intensity and away-from-home work intensity of each of the local users.

[0133] The work intensity score of the family, the work intensity of the whole family, will affect the family's shopping decisions. Therefore, work intensity is also an important factor affecting advertising recommendations. If the work intensity is level I, the individual will get 3.0 points; if the work intensity is level II, the individual will get 2.0 points; if the work intensity is level III, the individual will get 1.0 points. Then the total work intensity score of the family can be expressed as follows:

[0134] Total work intensity score of the family = number of people with level I work intensity * 3.0 + number of people with level II work intensity * 2.0 + number of people with level III work intensity * 1.0

[0135] Average household work intensity score = total household work intensity score / total number of working people in the household

[0136] The above scores can be artificially enlarged or reduced to reasonably magnify the score gap between different families.

[0137] Step 303: Calculate a family entertainment score according to the entertainment intensity of each local user.

[0138] Family entertainment intensity score. Generally speaking, a family with strong entertainment also indicates that they have good consumption capacity. Therefore, this is also an important means of evaluating family consumption capacity. If the entertainment level is level I, the individual score is 1.0 points; if the entertainment level is level II, the individual score is 2.0 points; if the entertainment level is level III, the individual score is 3.0 points; if the entertainment level is level IV, the individual score is 4.0 points. The total entertainment intensity score of the family can be expressed as follows:

[0139] The total family entertainment intensity score = the number of people with level I entertainment intensity*1.0+the number of people with level II entertainment intensity*2.0+the number of people with level III entertainment intensity*3.0+the number of people with level IV entertainment intensity*4.0.

[0140] Average family entertainment intensity score = total family entertainment intensity score / total number of family entertainment persons.

[0141] Step 304: Calculate a household brand score according to the type and brand of the household smart device.

[0142] The family brand value score, the brand value here, can be calculated by all the detectable equipment brands in the home, so as to analyze the level of consumption capacity of the family. The brand value score of a family can be obtained by the number of brand equipment in the home * the brand value of the online market. Then the brand value score of the whole family is equal to the sum of all the brand scores in the home.

[0143] Step 305 , calculating attribute scores of different advertisement types according to the family gender score, the family work intensity score, the family entertainment score, the family brand score and preset coefficients.

[0144] In some embodiments, the final attribute score may be obtained by calculating based on different preset coefficients and the scores calculated in steps 301 to 304.

[0145] In some embodiments, when determining to push an advertisement, the following steps are also included:

[0146] Establishing an advertisement type set and a family set; wherein the family set includes family attribute information and viewing users; wherein the viewing users are determined by the Bluetooth MAC corresponding to the local user;

[0147] Establishing a bipartite graph according to the advertisement type set and the family set, and calculating edge weights;

[0148] The advertisement type set with the largest edge weight is determined as the target push advertisement type for the family set.

[0149] Update advertising data in real time based on the data monitoring of people at home. Perform data monitoring and advertising updates when the machine is powered on or soft-shut down. Push targeted ads to this user when the machine is started during the user's usual time period. During APP startup or video playback, prioritize targeted ads to users with strong Bluetooth signals from the TV box. Play ads with family attributes when using the app for the first time or when the current user cannot be analyzed. This allows for a combination of family and personal attributes, resulting in accurate targeting of users and families. The optimal ad selection strategy is as follows:

[0150] Advertisements are played in households, but the best match for this ad is to analyze the customer currently watching the program, and then the customer's attributes must be included in the calculation to maximize the value of the ad. Advertisement and household matching specifically includes:

[0151] Map the set of advertisements and the set of households (including the personal attributes of the currently watched program) into a bipartite graph, see Figure 4 , Figure 4 A schematic diagram of a bipartite graph provided by an embodiment of the present application, wherein the left side is X with m, and the right side is Y with n. The left side X1, X2, and X3 are a set of advertisements, and the right side Y1, Y2, and Y3 are a set of households (including personal attributes of the current program being watched), and the edge weights between them are shown in the connecting lines. Based on the generated bipartite graph, the edge weights are calculated, and the optimal correspondence between advertisements and households is obtained according to the calculated edge weights.

[0152] Edge Weights of Bipartite Graphs<Xi,Yj> The calculation method of the calculated value is: the number of labels matching the advertisement label and the family label + the family consumption score * 0.5 + the number of labels matching the advertisement label and the personal label. Among them, the consumption score of the whole family can be obtained by summing up the calculation method in the above content, or the score can be set for targeting to reach the advertiser's target family.

[0153] As shown in the figure above, there are two combinations of current edge weights, such as<X1,Y1> ,<X2,Y2> ,<X3,Y3> , the sum of their edge weights is 1+7+1=9, and the other is<X1,Y2> ,<X2,Y3> ,<X3,Y1> , the sum of their edge weights is 2+3+8=13. The best combination is the one with the largest sum of edge weights. For example, 13 is greater than 9, so the best combination is<X1,Y2> ,<X2,Y3> ,<X3,Y1> That is, the suitable households for advertisement X1 are Y2, the suitable households for advertisement X2 are Y3, and the suitable households for advertisement X3 are Y1.

[0154] Corresponding to the above-mentioned advertisement push method, the present invention also provides an advertisement push device. Since the device embodiment of the present invention corresponds to the above-mentioned method embodiment, details not disclosed in the device embodiment can be referred to the above-mentioned method embodiment, and will not be repeated in the present invention.

[0155] Figure 5 A schematic diagram of a structure of an advertisement push device provided by an embodiment of the present disclosure, such as Figure 5 As shown, including:

[0156] The first acquisition unit 41 is used to acquire the behavior information of the local user, and analyze the behavior information to acquire the user portrait of the local user; wherein the user portrait includes the user's personal attribute data and behavior attribute information;

[0157] A first calculation unit 42 is used to calculate attribute scores of different advertisement types according to the user portrait and family attribute information; wherein the family attribute information includes the number of local users and smart device information;

[0158] The push unit 43 is used to select a corresponding advertisement type for push according to the attribute score; wherein different attribute scores correspond to different advertisement types.

[0159] The main technical scheme of the advertisement push device provided by the present disclosure includes: first, obtaining the behavior information of the local user, and analyzing the behavior information to obtain the user portrait of the local user; wherein the user portrait includes the user's personal attribute data and behavior attribute information; second, calculating the attribute scores of different advertisement types according to the user portrait and family attribute information; wherein the family attribute information includes the number of local users and smart device information; finally, selecting the corresponding advertisement type for push according to the attribute score; wherein different attribute scores correspond to different advertisement types. Compared with the related art, the embodiment of the present application analyzes the user portrait in the preferred time and space, and matches the corresponding advertisement type for the user through the user portrait, so as to provide accurate advertisement audience delivery and improve the advertisement delivery revenue.

[0160] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 6 As shown, the device also includes:

[0161] The second acquisition unit 44 is used to acquire the behavior information of the local user in the first acquisition unit 41, and analyze the behavior information before acquiring the user portrait of the local user, and acquire the network media access control address (MAC) and Bluetooth MAC of different devices based on the behavior information;

[0162] The first determining unit 45 is used to determine the online time of different devices and determine the home devices based on the network MAC and Bluetooth MAC of each device.

[0163] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 6 As shown, the first acquisition unit 41 is further used for:

[0164] Based on the network MAC and the Bluetooth MAC, the behavior information of the local user is obtained; wherein the behavior information at least includes the home time and network behavior; the home time includes the home time on weekdays and the home time on holidays;

[0165] Determining the work intensity and entertainment intensity of the user away from home according to the length of time spent at home;

[0166] The home working intensity and shopping intensity of the local user are determined based on the network behavior.

[0167] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 6 As shown, the device also includes:

[0168] The third acquisition unit 46 is used to acquire the number of local users and determine the personal information of the local users according to the behavior information of the local users before the first calculation unit 42 calculates the attribute score according to the user portrait and the family attribute information; wherein the personal information includes age and gender;

[0169] The second determining unit 47 is configured to determine the type and brand of a smart device according to the network MAC and the Bluetooth MAC of each device.

[0170] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 6 As shown, the first calculation unit 42 is also used for:

[0171] Calculating a household gender score based on different advertisement types and the gender of each of the local users;

[0172] Calculating a home work intensity score according to the home work intensity and away-from-home work intensity of each local user;

[0173] Calculating a family entertainment score according to the entertainment intensity of each of the local users;

[0174] Calculate a home brand score based on the type and brand of the home smart device;

[0175] The attribute scores of different advertisement types are calculated respectively according to the family gender score, the family work intensity score, the family entertainment score, the family brand score and a preset coefficient.

[0176] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 6 As shown, the device also includes:

[0177] The establishing unit 48 is used to establish an advertisement type set and a family set after the second determining unit 47 determines the type and brand of the smart device according to the network MAC and the Bluetooth MAC of each device; wherein the family set includes family attribute information and viewing users; wherein the viewing users are determined by the Bluetooth MAC corresponding to the local user;

[0178] A second calculation unit 49 is used to establish a bipartite graph according to the advertisement type set and the family set, and calculate edge weights;

[0179] The third determining unit 410 is configured to determine the advertisement type set with the largest edge weight as the target push advertisement type for the family set.

[0180] It should be noted that the above explanation of the method embodiment is also applicable to the device of the embodiment of the present disclosure, and the principle is the same, which is no longer limited in the embodiment of the present disclosure.

[0181] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0182] Figure 7 A schematic block diagram of an example electronic device 500 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0183] like Figure 7 As shown, the device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 502 or a computer program loaded from a storage unit 508 to a RAM (Random Access Memory) 503. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An I / O (Input / Output) interface 505 is also connected to the bus 504.

[0184] A number of components in the device 500 are connected to the I / O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0185] The computing unit 501 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a CPU (Central Processing Unit), a GPU (Graphic Processing Units), various dedicated AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, a DSP (Digital Signal Processor), and any appropriate processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as the method for pushing advertisements. For example, in some embodiments, the method for pushing advertisements may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to execute the aforementioned advertisement pushing method in any other appropriate manner (for example, by means of firmware).

[0186] Various embodiments of the systems and techniques described above herein may be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application Specific Standard Products), SOCs (System On Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that may be executed and / or interpreted on a programmable system including at least one programmable processor that may be a dedicated or general-purpose programmable processor that may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0187] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0188] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a RAM, a ROM, an EPROM (Electrically Programmable Read-Only-Memory) or a flash memory, an optical fiber, a CD-ROM (Compact Dis sc Read-Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0189] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0190] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: LAN (Local Area Network), WAN (Wide Area Network), the Internet, and blockchain networks.

[0191] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0192] It should be noted that artificial intelligence is a discipline that studies how computers can simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), and includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, as well as machine learning / deep learning, big data processing technology, knowledge graph technology, and other major directions.

[0193] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0194] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for pushing advertisements, characterized in that: include: Obtaining behavior information of a local user, and analyzing the behavior information to obtain a user portrait of the local user; wherein the user portrait includes user personal attribute data and behavior attribute information; Calculating attribute scores of different advertisement types according to the user portrait and family attribute information; wherein the family attribute information includes the number of local users and smart device information; A corresponding advertisement type is selected for push according to the attribute score; wherein different attribute scores correspond to different advertisement types.

2. The method according to claim 1, characterized in that: Before obtaining the behavior information of the local user and analyzing the behavior information to obtain the user portrait of the local user, the method further includes: Get the network media access control address (MAC) and Bluetooth MAC of different devices; Based on the network MAC and Bluetooth MAC of each device, determine the online time of different devices and identify home devices.

3. The method according to claim 2, characterized in that The obtaining of the behavior information of the local user and performing analysis based on the behavior information to obtain the user profile of the local user includes: Based on the network MAC and the Bluetooth MAC, the behavior information of the local user is obtained; wherein the behavior information at least includes the home time and network behavior; the home time includes the home time on weekdays and the home time on holidays; Determining the work intensity and entertainment intensity of the user away from home according to the length of time spent at home; The home working intensity and shopping intensity of the local user are determined based on the network behavior.

4. The method according to claim 2, characterized in that: Before calculating the attribute score according to the user portrait and the family attribute information, the method further includes: Acquire the number of local users, and determine the personal information of the local users according to the behavior information of the local users; wherein the personal information includes age and gender; The type and brand of the smart device are determined based on the network MAC and the Bluetooth MAC of each device.

5. The method according to claim 3 or 4, characterized in that: The calculating of attribute scores of different advertisement types according to the user portrait and family attribute information; wherein the family attribute information includes the number of local users and smart device information including: Calculating a household gender score based on different advertisement types and the gender of each of the local users; Calculating a home work intensity score according to the home work intensity and away-from-home work intensity of each local user; Calculating a family entertainment score according to the entertainment intensity of each of the local users; Calculate a home brand score based on the type and brand of the home smart device; The attribute scores of different advertisement types are calculated respectively according to the family gender score, the family work intensity score, the family entertainment score, the family brand score and a preset coefficient.

6. The method according to claim 4, characterized in that After determining the type and brand of the smart device according to the network MAC and the Bluetooth MAC of each device, the method further includes: Establishing an advertisement type set and a family set; wherein the family set includes family attribute information and viewing users; wherein the viewing users are determined by the Bluetooth MAC corresponding to the local user; Establishing a bipartite graph according to the advertisement type set and the family set, and calculating edge weights; The advertisement type set with the largest edge weight is determined as the target push advertisement type for the family set.

7. An advertisement push device, characterized in that: include: A first acquisition unit is used to acquire behavior information of a local user, and to analyze the behavior information to acquire a user portrait of the local user; wherein the user portrait includes user personal attribute data and behavior attribute information; A first calculation unit, configured to calculate attribute scores of different advertisement types according to the user portrait and family attribute information; wherein the family attribute information includes the number of local users and smart device information; The push unit is used to select a corresponding advertisement type for push according to the attribute score; wherein different attribute scores correspond to different advertisement types.

8. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-6.

10. A computer program product, characterized in that The invention comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 6.