CN107103485B - Automatic advertisement recommendation method and system according to cinema visitor information - Google Patents
Automatic advertisement recommendation method and system according to cinema visitor information Download PDFInfo
- Publication number
- CN107103485B CN107103485B CN201710007725.7A CN201710007725A CN107103485B CN 107103485 B CN107103485 B CN 107103485B CN 201710007725 A CN201710007725 A CN 201710007725A CN 107103485 B CN107103485 B CN 107103485B
- Authority
- CN
- China
- Prior art keywords
- advertisement
- cinema
- visitor
- time
- future
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0261—Targeted advertisements based on user location
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
Abstract
The invention discloses an automatic advertisement recommendation method and system according to cinema visitor information, which comprises the following steps: acquiring merchant advertisement information and classifying the merchant advertisement information; obtaining visitor identity information of a cinema in a certain period of time in the future, wherein the visitor identity information comprises any one or more of age, area and gender; acquiring consumption information data of users with different identities; according to the identity information of the visitors in the cinema in a certain period of time in the future and consumption information data of users with different identities, determining the interest degree of the visitors in the cinema in the certain period of time in the future for different advertisements; calculating the advertising effect of pushing different advertisements in the cinema in a certain period of time in the future according to the interest degree of visitors of the cinema in the certain period of time in the future on different advertisements; and according to the obtained advertisement effect, the advertisements are pushed in the cinema within a certain time period in the future. The method and the device can improve the intelligent level of advertisement recommendation and are suitable for advertisement recommendation under the background of big data.
Description
Technical Field
The invention discloses an automatic advertisement recommendation method and system according to cinema visitor information, and relates to the technical field of computational advertising.
Background
The number of digital movie screens in China has increased at a high speed in the last 5 years, and the growth situation will be maintained in the next 5 years, and the number of screens in 2019 is expected to reach 5 ten thousand. The total amount of the box office is steadily increased, and the total amount of income of a national large-screen advertisement year can reach 65 hundred million by 2019.
At present, the cinema advertisement system does not sufficiently utilize personal information of advertisement target groups in a certain time period in the future. The advertising effect still has a larger space for improvement.
Disclosure of Invention
The invention aims to provide an automatic advertisement recommendation method and system, which are used for solving the problem that the advertisement effect is influenced because the personal information of advertisement target crowds is not fully utilized in the conventional cinema advertisement system.
To achieve the above object, an automatic advertisement recommendation method and system according to cinema visitor information are provided. The technical scheme of the embodiment of the invention is as follows:
the embodiment of the invention provides an automatic advertisement recommendation method according to cinema visitor information, which comprises the following steps:
step 101: acquiring merchant advertisement information and classifying the merchant advertisement information;
step 102: obtaining visitor identity information of a cinema in a certain period of time in the future, wherein the visitor identity information comprises any one or more of age, area and gender;
step 103: acquiring consumption information data of users with different identities;
step 104: according to the identity information of the visitors in the cinema in a certain period of time in the future and consumption information data of users with different identities, determining the interest degree of the visitors in the cinema in the certain period of time in the future for different advertisements;
step 105: calculating the advertising effect of pushing different advertisements in the cinema in a certain period of time in the future according to the interest degree of visitors of the cinema in the certain period of time in the future on different advertisements;
step 106: and according to the obtained advertisement effect, the advertisements are pushed in the cinema within a certain time period in the future.
In one embodiment, the step 102 comprises:
acquiring movie ticket ordering information of a movie theater from a movie theater ticket ordering system, wherein the movie ticket ordering information comprises movie playing time corresponding to movie tickets and user identity information for purchasing the movie tickets, the movie playing time is in a certain period of time in the future, and the user identity information comprises any one or more of age, area and gender;
and determining the user identity information as the visitor identity information.
In one embodiment, the consumption information data in step 103 includes any one or more of age, location, sex, consumption time, consumption area, and consumption content.
In one embodiment, step 104 includes:
calculating interest degrees of visitors of the cinema in a certain period of time in the future for different advertisements according to a first calculation formula;
the first calculation formula is:
wherein R isUIThe interest degree of the visitor type U to the advertisement type I is 0-1, and represents the ratio of the number of people interested in the I type advertisement in the U type visitor to the total number of the U type visitor; pUkRepresenting the interest degree of the visitor category U in the potential category k; qkIRepresenting the weight occupied by the advertisement category I in the potential category k, wherein the higher the weight is, the more the advertisement category I can be represented as the potential category; after the number of the potential categories is appointed, the potential categories are obtained by the computer through counting and automatic clustering; the visitor type U is determined by visitor identity information; rUIThe middle part data is determined by consumption information data of visitors with different identities; the remaining part of data is composed of PUkAnd QkICalculating to obtain; pUkAnd QkIObtained by minimizing a loss function, the loss function being:
where C is a loss function and S is represented by RUIThe determined part and the random sampling assignment part, and lambda is a regularization factor and can be obtained through multiple tests.
In one embodiment, step 105 comprises:
calculating the advertising effect of pushing different advertisements in the cinema in a certain period of time in the future according to a second calculation formula;
the second calculation formula is:
wherein EF (I) indicates the advertising effectiveness of advertisement category I; n is the total number of visitor classes, the SGN () function represents the sign of the variable, RUIRepresenting the interest of the person in the U-th class in the advertisement I, with a value between 0 and 1, PUThe number of U-th visitors is adjustable interest threshold valueAn indication advertisement with a degree higher than this value is better for its effect; alpha and beta are adjustable adjusting factors respectively representing the nonlinear influence of the number of people and the influence of advertisements in non-interested people, wherein alpha is more than or equal to 1, beta is more than 0 and less than 1+, or beta is more than 0 and less than 1.
The embodiment of the invention provides an automatic advertisement recommendation system according to cinema visitor information, which comprises:
the advertisement information processing module is used for obtaining the advertisement information of the merchants and classifying the advertisement information of the merchants;
the system comprises a visitor information processing module, a data processing module and a data processing module, wherein the visitor information processing module is used for acquiring visitor identity information of a cinema in a certain period of time in the future, and the visitor identity information comprises any one or more of age, area and gender;
the consumption information processing module is used for acquiring consumption information data of users with different identities;
the interest degree calculation module is used for determining interest degrees of the visitors of the cinema in a certain period of time in the future for different advertisements according to the identity information of the visitors of the cinema in the certain period of time in the future and consumption information data of users with different identities;
the advertisement effect calculation module is used for calculating the advertisement effect of pushing different advertisements in the cinema in a certain period of time in the future according to the interest degree of visitors of the cinema in the certain period of time in the future on different advertisements;
and the advertisement pushing module is used for pushing the advertisements in the cinema within a certain time period in the future according to the obtained advertisement effect.
In one embodiment of the present invention,
the system comprises a visitor information processing module, a movie ticket ordering module and a movie ticket processing module, wherein the visitor information processing module is used for acquiring movie ticket ordering information of a movie theater from a movie theater ticket ordering system, the movie ticket ordering information comprises movie playing time corresponding to movie tickets and user identity information for purchasing the movie tickets, the movie playing time is in a certain period of time in the future, and the user identity information comprises any one or more of age, area and gender; and determining the user identity information as the visitor identity information.
In one embodiment, the consumption information data includes any one or more of age, location, sex, consumption time, consumption region, and consumption content.
In one embodiment, the interest level calculating module is used for calculating interest levels of visitors of the cinema in a certain period of time in the future for different advertisements according to a first calculation formula;
the first calculation formula is:
wherein R isUIThe interest degree of the visitor type U to the advertisement type I is 0-1, and represents the ratio of the number of people interested in the I type advertisement in the U type visitor to the total number of the U type visitor; pUkRepresenting the interest degree of the visitor category U in the potential category k; qkIRepresenting the weight occupied by the advertisement category I in the potential category k, wherein the higher the weight is, the more the advertisement category I can be represented as the potential category; after the number of the potential categories is appointed, the potential categories are obtained by the computer through counting and automatic clustering; the visitor type U is determined by visitor identity information; rUIThe middle part data is determined by consumption information data of visitors with different identities; the remaining part of data is composed of PUkAnd QkICalculating to obtain; pUkAnd QkIObtained by minimizing a loss function, the loss function being:
where C is a loss function and S is represented by RUIThe determined part and the random sampling assignment part, and lambda is a regularization factor and can be obtained through multiple tests.
In one embodiment, the advertisement effect calculation module is configured to calculate an advertisement effect of different advertisements pushed in a cinema in a certain period of time in the future according to a second calculation formula;
the second calculation formula is:
wherein EF (I) indicates the advertising effectiveness of advertisement category I; n is the total number of visitor classes, the SGN () function represents the sign of the variable, RUIRepresenting the interest of the person in the U-th class in the advertisement I, with a value between 0 and 1, PUThe number of the U-th visitors is an adjustable interest threshold, and the advertisement with the interest higher than the interest threshold has a good effect; alpha and beta are adjustable adjusting factors respectively representing the nonlinear influence of the number of people and the influence of advertisements in non-interested people, wherein alpha is more than or equal to 1, beta is more than 0 and less than 1+, or beta is more than 0 and less than 1.
The method provided by the embodiment of the invention can accurately predict which advertisements can realize better advertisement effect when being pushed in the cinema in a certain time period in the future in advance, so that the advertisements can be pushed in the cinema in time in the certain time period in the future, and the advertisement effect of the advertisements pushed in the cinema is improved.
Drawings
FIG. 1 is a flow diagram of a method of automatic advertisement recommendation, according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an automatic advertisement recommendation system according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
FIG. 1 is a flow chart of a method for automatic advertisement recommendation according to an embodiment of the present invention.
At step 101, merchant advertising information is obtained and classified. The business advertising information is mainly industry classification information, such as classifying the advertisements as: cultural media, vehicles, food and beverage, electronic computers, real estate, telecommunication services, financial insurance, fashion clothing, air travel, retail services, and the like. The more detailed the classification, the better the effect. In one embodiment of the invention, the merchant advertising information is divided into cultural media, vehicles, electronic computers, real estate.
In step 102, visitor identity information of the cinema in a certain period of time in the future is obtained, wherein the visitor identity information comprises any one or more of age, region and gender. Of course, other identity information, such as name, etc., may also be included.
In one embodiment, step 102 may be implemented as steps A1-A2:
step A1, acquiring movie ticket ordering information of a movie theater from a movie ticket ordering system, wherein the movie ticket ordering information comprises movie playing time corresponding to movie tickets and user identity information for purchasing the movie tickets, the movie playing time is in a certain period of time in the future, and the user identity information comprises any one or more of age, area and gender;
step a2, determining the user identity information as the visitor identity information.
At present, cinema has a corresponding cinema ticket booking system, users can purchase tickets in a remote network of the cinema ticket booking system, and the cinema ticket booking system can store user identity information of each user and a unique identity identification code of the user, such as a mobile phone number. When a user purchases a movie ticket through the movie theater ticket booking system, the user needs to provide the unique identification code for the movie theater ticket booking system, so that the movie theater ticket booking system can acquire the user identification information of the user according to the received unique identification code and can record the movie playing time corresponding to the movie ticket purchased by the user. The cinema ticket booking system can store the user identity information of the user and the movie playing time corresponding to the movie ticket purchased by the user as movie ticket booking information.
A user who purchases a movie ticket for a certain period of time in the future at a theater may be considered a visitor to the theater who will be present for a certain period of time in the future.
In step 103: and acquiring consumption information data of users with different identities.
When the consumption information data is acquired, the consumption information data of the user in the area where the theater is located may be acquired, for example, the consumption information data of the user in the area where the theater is located, and the consumption information data of the user in the area close to the area where the theater is located may be selected, and the consumption information data may include any one or more of age, area where the theater is located, sex, consumption time, consumption area, and consumption content. The area where the cinema is located can be a city, district, county, village and town or street where the cinema is located; the area may be an area within a preset kilometer range of a square circle centered at the theater, and the preset kilometer number may be set, for example, 20 kilometers of the square circle.
In step 104: according to the identity information of the visitors in the cinema in a certain period of time in the future and the consumption information data of users with different identities, the interest degree of the visitors in the cinema in the certain period of time in the future in different advertisements is determined.
In one embodiment, step 104 may be implemented as: calculating interest degrees of visitors of the cinema in a certain period of time in the future for different advertisements according to a first calculation formula;
the first calculation formula is:
wherein R isUIThe interest degree of the visitor type U to the advertisement type I is 0-1, and represents the ratio of the number of people interested in the I type advertisement in the U type visitor to the total number of the U type visitor; pUkRepresenting the interest degree of the visitor category U in the potential category k; qkIRepresenting the weight occupied by the advertisement category I in the potential category k, wherein the higher the weight is, the more the advertisement category I can be represented as the potential category; after the number of the potential categories is appointed, the potential categories are obtained by the computer through counting and automatic clustering; the visitor type U is determined by visitor identity information; rUIThe middle part data is determined by consumption information data of visitors with different identities; the remaining part of data is composed of PUkAnd QkICalculating to obtain; pUkAnd QkIObtained by minimizing a loss function, the loss function being:
where C is a loss function and S is represented by RUIThe determined part and the random sampling assignment part, and lambda is a regularization factor and can be obtained through multiple tests.
In another embodiment, step 104 may also be replaced by the following operational steps: and obtaining pre-stored interest degrees of the visitors in different advertisements from an external database.
In step 105: and calculating the advertising effect of pushing different advertisements in the cinema in a certain period of time in the future according to the interest degree of visitors of the cinema in the certain period of time in the future on different advertisements.
In one embodiment, step 105 may be implemented as: calculating the advertising effect of pushing different advertisements in the cinema in a certain period of time in the future according to a second calculation formula;
the second calculation formula is:
wherein EF (I) indicates the advertising effectiveness of advertisement category I; n is the total number of visitor classes, the SGN () function represents the sign of the variable, RUIRepresenting the interest of the person in the U-th class in the advertisement I, with a value between 0 and 1, PUThe number of the U-th visitors is an adjustable interest threshold, and the advertisement with the interest higher than the interest threshold has a good effect; alpha and beta are adjustable adjusting factors, alpha is more than or equal to 1, beta is more than 0 and less than 1+, or beta is more than 0 and less than 1, which respectively represent the nonlinear influence of the crowd quantity and the influence of the advertisement in the non-interested crowd.
In step 106: and according to the obtained advertisement effect, the advertisements are pushed in the cinema within a certain time period in the future.
In one embodiment, the advertisement with the highest advertisement effect or the advertisement with the advertisement effect reaching the preset standard can be pushed in the cinema in a certain period of time in the future. During pushing, the advertisement can be pushed on any equipment capable of issuing advertisements in the cinema, such as a screen for playing a movie, a self-service ticket purchasing machine and a self-service ticket fetching machine in the cinema, a television or an electronic display screen on the inner wall of the cinema and the like.
The method provided by the embodiment of the invention can accurately predict which advertisements can realize better advertisement effect when being pushed in the cinema in a certain time period in the future in advance, so that the advertisements can be pushed in the cinema in time in the certain time period in the future, and the advertisement effect of the advertisements pushed in the cinema is improved.
One embodiment of the invention is as follows:
at step 201, merchant advertising information is obtained and classified.
For example, merchant advertising information is classified as: cultural media, vehicles, electronic computers, real estate.
In step 202: visitor identity information for the theatre is obtained for a period of time in the future.
For example, when the current time is 2016, 11 and 15 days, the theater is a jinsong theater located in beijing, and the theater plays the movie "middle battle of belley and ryan" in a time period of 2016, 11 and 17 and 9:00 and 12:00 (i.e., a certain time period in the future), the statistical data of the visitor identity information appearing in the jinsong theater in the time period of 2016, 11 and 17 and 9:00 and 12:00 is obtained through the foregoing steps a1-a2 as follows:
15-25 years old: 100 persons
26-35 years old: 200 persons
And (4) the age of 36-45 years: 50 persons
In step 203: and acquiring consumption information data of users with different identities.
For example, the area where the jinsong cinema is located is the sunny area in beijing, and from a certain shopping website, the data of the goods concerned by the users in various age groups in the sunny area in beijing is obtained as follows:
| percentage of people concerned | Culture media | Transportation means | Electronic computer | Real estate |
| 15-25 years old | Is unknown | 0.2 | 0.75 | Is unknown |
| 26-35 years old | 0.2 | Is unknown | Is unknown | 0.35 |
| 36-45 years old | 0.3 | Is unknown | Is unknown | 0.3 |
In step 204: according to the identity information of the visitors in the cinema in a certain period of time in the future and the consumption information data of users with different identities, the interest degree of the visitors in the cinema in the certain period of time in the future in different advertisements is determined.
For example, according to the first calculation formula:
| RUI | culture media | Transportation means | Electronic computer | Real estate |
| 15-25 years old | 0.1 | 0.2 | 0.75 | 0.2 |
| 26-35 years old | 0.2 | 0.5 | 0.6 | 0.35 |
| 36-45 years old | 0.3 | 0.5 | 0.3 | 0.3 |
In step 205: and calculating the advertising effect of pushing different advertisements in the cinema in a certain period of time in the future according to the interest degree of visitors of the cinema in the certain period of time in the future on different advertisements.
Setting the second calculation formula to 0.15, α to 1, and β to 0.1, the advertisement effectiveness of different advertisements can be obtained by using the second calculation formula:
in step 206: and according to the obtained advertisement effect, the advertisements are pushed in the cinema within a certain time period in the future. Because the advertisement effect of the electronic computer product is better, the advertisements of the electronic computer are pushed in the cinema in a certain time period in the future.
FIG. 2 is a schematic diagram of an automatic advertisement recommendation system according to an embodiment of the present invention;
an automatic advertisement recommendation system according to the present invention includes:
the advertisement information processing module 301 is configured to obtain merchant advertisement information and classify the merchant advertisement information; the visitor information processing module 302 is used for obtaining merchant advertisement information and classifying the merchant advertisement information; a consumption information processing module 303, configured to obtain consumption information data of users with different identities; the interestingness calculating module 304 is used for determining the interestingness of the visitors of the cinema in a certain period of time in the future on different advertisements according to the identity information of the visitors of the cinema in a certain period of time in the future and consumption information data of users with different identities; the advertisement effect calculating module 305 is configured to calculate, according to interest degrees of visitors of the cinema in a certain future time period for different advertisements, advertisement effects of different advertisements pushed in the cinema in the certain future time period; and the advertisement pushing module 306 is configured to push an advertisement in a cinema within a certain time period in the future according to the obtained advertisement effect.
The visitor information processing module 302 is configured to acquire movie ticket ordering information of a movie theater from a movie theater ticket ordering system, where the movie ticket ordering information includes movie playing time corresponding to a movie ticket and user identity information for purchasing the movie ticket, the movie playing time is within a certain period of time in the future, and the user identity information includes any one or more of age, location, and gender; and determining the user identity information as the visitor identity information.
The consumption information data comprises any one or more of age, region, gender, consumption time, consumption area and consumption content.
The interestingness calculating module 304 is configured to calculate interestingness of visitors of the cinema in a certain period of time in the future for different advertisements according to a first calculation formula;
the first calculation formula is:
wherein R isUIThe interest degree of the visitor type U to the advertisement type I is 0-1, and represents the ratio of the number of people interested in the I type advertisement in the U type visitor to the total number of the U type visitor; pUkRepresenting the interest degree of the visitor category U in the potential category k; qkIRepresenting the weight occupied by the advertisement category I in the potential category k, wherein the higher the weight is, the more the advertisement category I can be represented as the potential category; after the number of the potential categories is appointed, the potential categories are obtained by the computer through counting and automatic clustering; the visitor type U is determined by visitor identity information; rUIThe middle part data is determined by consumption information data of visitors with different identities; the remaining part of data is composed of PUkAnd QkICalculating to obtain; pUkAnd QkIObtained by minimizing a loss function, the loss function being:
where C is a loss function and S is represented by RUIThe determined part and the random sampling assignment part, and lambda is a regularization factor and can be obtained through multiple tests.
The advertisement effect calculating module 305 is configured to calculate, according to a second calculation formula, an advertisement effect of different advertisements pushed to the cinema in a certain period of time in the future;
the second calculation formula is:
wherein EF (I) indicates the advertising effectiveness of advertisement category I; n is the total number of visitor classes, the SGN () function represents the sign of the variable, RUIRepresenting the interest of the person in the U-th class in the advertisement I, with a value between 0 and 1, PUThe number of the U-th visitors is an adjustable interest threshold, and the advertisement with the interest higher than the interest threshold has a good effect; alpha and beta are adjustable adjusting factors respectively representing the nonlinear influence of the number of people and the influence of advertisements in non-interested people, wherein alpha is more than or equal to 1, beta is more than 0 and less than 1+, or beta is more than 0 and less than 1.
In light of the foregoing description of the preferred embodiments of the present invention, those skilled in the art will be able to make numerous alterations and modifications without departing from the spirit and scope of the invention. The technical scope of the present invention is not limited to the content of the specification, and must be determined according to the scope of the claims.
Claims (6)
1. An automatic advertisement recommendation method according to cinema visitor information, comprising the steps of:
step 101: acquiring merchant advertisement information and classifying the merchant advertisement information;
step 102: obtaining visitor identity information of a cinema in a certain period of time in the future, wherein the visitor identity information comprises any one or more of age, area and gender;
step 103: acquiring consumption information data of users with different identities;
step 104: according to the identity information of the visitors in the cinema in a certain period of time in the future and consumption information data of users with different identities, determining the interest degree of the visitors in the cinema in the certain period of time in the future for different advertisements;
step 105: calculating the advertising effect of pushing different advertisements in the cinema in a certain period of time in the future according to the interest degree of visitors of the cinema in the certain period of time in the future on different advertisements;
step 106: according to the obtained advertisement effect, the advertisements are pushed in the cinema within a certain time period in the future;
step 104 comprises:
calculating interest degrees of visitors of the cinema in a certain period of time in the future for different advertisements according to a first calculation formula;
the first calculation formula is:
wherein R isUIThe interest degree of the visitor type U to the advertisement type I is 0-1, and represents the ratio of the number of people interested in the I type advertisement in the U type visitor to the total number of the U type visitor; pUkRepresenting the interest degree of the visitor category U in the potential category k; qkIRepresenting the weight occupied by the advertisement category I in the potential category k, wherein the higher the weight is, the more the advertisement category I can be represented as the potential category; after the number of the potential categories is appointed, the potential categories are obtained by the computer through counting and automatic clustering; the visitor type U is determined by visitor identity information; rUIThe middle part data is determined by consumption information data of visitors with different identities; the remaining part of data is composed of PUkAnd QkICalculating to obtain; pUkAnd QkIObtained by minimizing a loss function, the loss function being:
where C is a loss function and S is represented by RUIThe determined part and the random sampling assignment part are combined, and lambda is a regularization factor and can be obtained through multiple tests;
step 105 comprises:
calculating the advertising effect of pushing different advertisements in the cinema in a certain period of time in the future according to a second calculation formula;
the second calculation formula is:
wherein EF (I) indicates the advertising effectiveness of advertisement category I; n is the total number of visitor classes, the SGN () function represents the sign of the variable, RUIRepresenting the interest of the person in the U-th class in the advertisement I, with a value between 0 and 1, PUThe number of the U-th visitors is an adjustable interest threshold, and the advertisement with the interest higher than the interest threshold has a good effect; alpha and beta are adjustable adjusting factors respectively representing the nonlinear influence of the number of people and the influence of advertisements in non-interested people, wherein alpha is more than or equal to 1, beta is more than 0 and less than 1+, or beta is more than 0 and less than 1.
2. The method of claim 1, wherein the step 102 comprises:
acquiring movie ticket ordering information of a movie theater from a movie theater ticket ordering system, wherein the movie ticket ordering information comprises movie playing time corresponding to movie tickets and user identity information for purchasing the movie tickets, the movie playing time is in a certain period of time in the future, and the user identity information comprises any one or more of age, area and gender;
and determining the user identity information as the visitor identity information.
3. The method of claim 1,
the consumption information data in step 103 includes any one or more of age, location, sex, consumption time, consumption area, and consumption content.
4. An automatic advertisement recommendation system according to theater visitor information, the system comprising:
the advertisement information processing module is used for obtaining the advertisement information of the merchants and classifying the advertisement information of the merchants;
the system comprises a visitor information processing module, a data processing module and a data processing module, wherein the visitor information processing module is used for acquiring visitor identity information of a cinema in a certain period of time in the future, and the visitor identity information comprises any one or more of age, area and gender;
the consumption information processing module is used for acquiring consumption information data of users with different identities;
the interest degree calculation module is used for determining interest degrees of the visitors of the cinema in a certain period of time in the future for different advertisements according to the identity information of the visitors of the cinema in the certain period of time in the future and consumption information data of users with different identities;
the advertisement effect calculation module is used for calculating the advertisement effect of pushing different advertisements in the cinema in a certain period of time in the future according to the interest degree of visitors of the cinema in the certain period of time in the future on different advertisements;
the advertisement pushing module is used for pushing advertisements in the cinema within a certain time period in the future according to the obtained advertisement effect;
the interest degree calculating module is used for calculating interest degrees of visitors of the cinema in a certain period of time in the future for different advertisements according to a first calculation formula;
the first calculation formula is:
wherein R isUIThe interest degree of the visitor type U to the advertisement type I is 0-1, and represents the ratio of the number of people interested in the I type advertisement in the U type visitor to the total number of the U type visitor; pUkRepresenting the interest degree of the visitor category U in the potential category k; qkIRepresenting the weight occupied by the advertisement category I in the potential category k, wherein the higher the weight is, the more the advertisement category I can be represented as the potential category; after the number of the potential categories is appointed, the potential categories are obtained by the computer through counting and automatic clustering; the visitor type U is determined by visitor identity information; rUIConsumption letter of visitor with middle part data passing different identitiesDetermining data; the remaining part of data is composed of PUkAnd QkICalculating to obtain; pUkAnd QkIObtained by minimizing a loss function, the loss function being:
where C is a loss function and S is represented by RUIThe determined part and the random sampling assignment part are combined, and lambda is a regularization factor and can be obtained through multiple tests;
the advertisement effect calculation module is used for calculating the advertisement effect of pushing different advertisements in the cinema in a certain period of time in the future according to a second calculation formula;
the second calculation formula is:
wherein EF (I) indicates the advertising effectiveness of advertisement category I; n is the total number of visitor classes, the SGN () function represents the sign of the variable, RUIRepresenting the interest of the person in the U-th class in the advertisement I, with a value between 0 and 1, PUThe number of the U-th visitors is an adjustable interest threshold, and the advertisement with the interest higher than the interest threshold has a good effect; alpha and beta are adjustable adjusting factors respectively representing the nonlinear influence of the number of people and the influence of advertisements in non-interested people, wherein alpha is more than or equal to 1, beta is more than 0 and less than 1+, or beta is more than 0 and less than 1.
5. The system of claim 4,
the visitor information processing module is used for acquiring movie ticket ordering information of the cinema from a cinema ticket ordering system, wherein the movie ticket ordering information comprises movie playing time corresponding to movie tickets and user identity information for purchasing the movie tickets, the movie playing time is in a certain period of time in the future, and the user identity information comprises any one or more of age, area and gender; and determining the user identity information as the visitor identity information.
6. The system of claim 4,
the consumption information data comprises any one or more of age, region, gender, consumption time, consumption area and consumption content.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710007725.7A CN107103485B (en) | 2017-01-05 | 2017-01-05 | Automatic advertisement recommendation method and system according to cinema visitor information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710007725.7A CN107103485B (en) | 2017-01-05 | 2017-01-05 | Automatic advertisement recommendation method and system according to cinema visitor information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107103485A CN107103485A (en) | 2017-08-29 |
| CN107103485B true CN107103485B (en) | 2020-12-25 |
Family
ID=59676481
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710007725.7A Expired - Fee Related CN107103485B (en) | 2017-01-05 | 2017-01-05 | Automatic advertisement recommendation method and system according to cinema visitor information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107103485B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107798567B (en) * | 2017-11-21 | 2023-06-20 | 成都高德唯斯科技股份有限公司 | Brand information pushing method and device and electronic equipment |
| CN108460125A (en) * | 2018-02-26 | 2018-08-28 | 影核（北京）网络科技有限公司 | A method of carrying out displaying labeling classification for movie theatre user |
| CN108766278B (en) * | 2018-05-15 | 2020-06-05 | 三星电子（中国）研发中心 | Electronic guideboard information display method and device |
| CN109118270B (en) * | 2018-07-12 | 2021-04-06 | 北京猫眼文化传媒有限公司 | Data extraction method and device |
| CN111695009B (en) * | 2019-03-11 | 2023-06-30 | 浙江莲荷科技有限公司 | Information display method and device |
| CN113781124B (en) * | 2020-09-18 | 2024-04-02 | 北京智能广宣科技有限公司 | Intelligent adjustment method for cinema advertisement play list |
| CN112333483A (en) * | 2020-10-27 | 2021-02-05 | 北京智能广宣科技有限公司 | Intelligent adjustment method and system for cinema advertisement play list |
| CN112767015A (en) * | 2021-01-07 | 2021-05-07 | 上海鸿研物流技术有限公司 | Information charging method and system based on logistics appliances |
| CN113269594A (en) * | 2021-06-08 | 2021-08-17 | 绍兴市壹点通传媒有限公司 | Cinema advertisement management method and system based on big data |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105355158A (en) * | 2015-11-12 | 2016-02-24 | 日立电梯（中国）有限公司 | Elevator advertisement posting method and system |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001013301A2 (en) * | 1999-08-13 | 2001-02-22 | Cinecast, Llc | System and method for digitally providing and displaying advertisement information to cinemas and theaters |
| US7680796B2 (en) * | 2003-09-03 | 2010-03-16 | Google, Inc. | Determining and/or using location information in an ad system |
| US20100042501A1 (en) * | 2008-08-12 | 2010-02-18 | Hsiu-Ling Lee | Method and apparatus for controlling content within a network |
| PL2268025T3 (en) * | 2009-06-22 | 2015-10-30 | Cinvolve Bvba | Method for interactive digital cinema system |
| CN102201187A (en) * | 2010-03-23 | 2011-09-28 | 深圳华北工控股份有限公司 | Method for directionally advertising |
| CN101951441A (en) * | 2010-09-16 | 2011-01-19 | 中国联合网络通信集团有限公司 | Mobile telephone advertisement delivery method and equipment |
| KR101459871B1 (en) * | 2012-01-18 | 2014-11-10 | 현대자동차주식회사 | Method for providing advertisement based on location and system for providing advertisement |
| CN105303998A (en) * | 2014-07-24 | 2016-02-03 | 北京三星通信技术研究有限公司 | Method, device and equipment for playing advertisements based on inter-audience relevance information |
| CN105574730A (en) * | 2014-10-10 | 2016-05-11 | 中兴通讯股份有限公司 | Internet of Things big data platform-based intelligent user portrait method and device |
| CN105989374B (en) * | 2015-03-03 | 2019-12-24 | 阿里巴巴集团控股有限公司 | Method and equipment for training model on line |
| CN106022865A (en) * | 2016-05-10 | 2016-10-12 | 江苏大学 | Goods recommendation method based on scores and user behaviors |
| CN105844502A (en) * | 2016-05-20 | 2016-08-10 | 广州市莱麦互联网科技有限公司 | Information release method, device and system based on cloud and positioning technology |
-
2017
- 2017-01-05 CN CN201710007725.7A patent/CN107103485B/en not_active Expired - Fee Related
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105355158A (en) * | 2015-11-12 | 2016-02-24 | 日立电梯（中国）有限公司 | Elevator advertisement posting method and system |
Non-Patent Citations (2)
| Title |
|---|
| "一种基于学习自动机的推荐算法改进";荆羽纯;《计算机应用研究》;20160131;第33卷(第1期);第32-34页 * |
| "基于位置的移动社会化网络推荐技术研究";刘树栋;《中国博士学位论文全文数据库（电子期刊）信息科技辑》;20160315;第I138-210页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107103485A (en) | 2017-08-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107103485B (en) | Automatic advertisement recommendation method and system according to cinema visitor information | |
| Pötzschke et al. | Migrant sampling using Facebook advertisements: A case study of polish migrants in four European countries | |
| Kang et al. | Validating activity, time, and space diversity as essential components of urban vitality | |
| US8781897B2 (en) | Media targeting system and method | |
| Dawar et al. | Marketing universals: Consumers’ use of brand name, price, physical appearance, and retailer reputation as signals of product quality | |
| CN106570718B (en) | Information delivery method and delivery system | |
| US20160203211A1 (en) | Geolocation data analytics on multi-group populations of user computing devices | |
| US20110208586A1 (en) | Leveraging Demographic Data for Advertising Purposes | |
| US8255392B2 (en) | Real time data collection system and method | |
| CN103177384A (en) | Network advertisement putting method based on user interest spectrum | |
| CN109408712A (en) | A kind of construction method of travel agency user multidimensional information portrait | |
| CN101454771A (en) | System and method of segmenting and tagging entities based on profile matching using a multi-media survey | |
| Cui et al. | Travel behavior classification: an approach with social network and deep learning | |
| US10424029B2 (en) | Method and system for providing a housing recommendation | |
| CN109191181B (en) | Digital signage advertisement audience and crowd classification method based on neural network and Huff model | |
| JP6731826B2 (en) | Extraction device, extraction method, and extraction program | |
| Yu et al. | AI-based targeted advertising system | |
| Duchessi et al. | Decision tree models for profiling ski resorts’ promotional and advertising strategies and the impact on sales | |
| US10909553B1 (en) | Systems and methods for generating an affinity graph | |
| Ibarra et al. | Electronic Commerce as a Business Strategy: Impact in Consumption Habits in Hermosillo, Sonora's Inhabitants. | |
| US20150066743A1 (en) | System and method for socially connecting payment card holders | |
| Aday et al. | Competitive advantage or market saturation: An in-depth comparison of flash-sale sites through content analysis | |
| Grubert | Every door direct mail in US survey research: an anonymous census approach to mail survey sampling | |
| CN110264244B (en) | Advertisement user trajectory tracking management system and method | |
| US20160249083A1 (en) | Tabulation system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20201225 Termination date: 20220105 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |