WO2021031600A1 - 数据采集方法、装置、计算机装置及存储介质 - Google Patents
数据采集方法、装置、计算机装置及存储介质 Download PDFInfo
- Publication number
- WO2021031600A1 WO2021031600A1 PCT/CN2020/086798 CN2020086798W WO2021031600A1 WO 2021031600 A1 WO2021031600 A1 WO 2021031600A1 CN 2020086798 W CN2020086798 W CN 2020086798W WO 2021031600 A1 WO2021031600 A1 WO 2021031600A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- advertisement
- display platform
- target person
- target
- information
- Prior art date
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
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
-
- 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
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Definitions
- This application relates to the field of computer technology, and in particular to a data collection method, data collection device, computer device and computer-readable storage medium for advertising push.
- the form of advertising is mainly one-way instillation, the audience is passively received, and it is impossible to know whether the product is interested in it.
- the audience passively receives various types of advertisement information, and if it contains a large number of advertisement content that the audience is not interested in, it will reduce the user experience. Therefore, it is particularly important to be able to collect the audience's personalized preferences for various types of advertising information, so that advertisements can be targeted to different audiences in the later stage and the user experience can be improved.
- the first aspect of the application provides a data collection method for advertisement push, which is applied to a computer device capable of communicating with a plurality of advertisement display platforms, and the method includes: obtaining access to the front of at least one advertisement display platform The target person image of each target person in the specific area; for each target person image, perform the following steps: determine the advertisement display platform corresponding to the target person image as the target advertisement display platform, and obtain the target advertisement display platform The first identifier, the display area in which it is located, and the first advertisement information displayed by the target advertisement display platform at the time when the target person’s image is collected; the identity information of the target person is analyzed according to the target person’s image, so The identity information includes the face image area of the target person in the target person image; the behavior information of the target person is analyzed according to the face image area, and the target person is judged against the target person according to the behavior information.
- Personalized preferences of the first advertising information search in a preset database whether there is an advertising audience that matches the identity information of the target person, wherein the preset database stores the personal data of multiple advertising audiences, each The personal data of an advertisement audience includes the identity information of the advertisement audience, the personalized preference for at least one advertisement information, the first identifier of the advertisement display platform that displays the at least one advertisement information, the display area where it is located, and the The time when the advertising audience appears in the display area where the first advertising display platform is located; and when there is an advertising audience matching the identity information of the target person, determining that the matching advertising audience is the target advertising audience, Adding the target person’s personalized preference to the first advertisement information, the first identifier of the target advertisement display platform, the display area where the target person is located, and the collection time of the target person’s image to the target advertisement audience In your personal data.
- a second aspect of the present application provides a data collection device for advertisement push, wherein the device includes: a first acquisition module for acquiring information about each target person entering a specific area in front of at least one advertisement display platform A target person image; a second acquisition module for determining that the advertisement display platform corresponding to the target person image is the target advertisement display platform, and obtain the first identifier of the target advertisement display platform, the display area where it is located, and the target The first advertisement information displayed by the advertisement display platform at the collection time of the target person’s image; the first analysis module is used to analyze the target person’s identity information according to the target person’s image, and the identity information includes the target The face image area of the target person in the person image; the second analysis module is used to analyze the behavior information of the target person according to the face image area, and determine that the target person is against the target person according to the behavior information.
- Personalized preferences of advertising information a search module for searching whether there is a target advertising audience that matches the identity information of the target person in a preset database, wherein the preset database stores information about multiple advertising audiences Personal data.
- the personal data of each advertisement audience includes the identity information of the advertisement audience, the personalized preference for at least one advertisement information, the first identifier of the advertisement display platform that displays the at least one advertisement information, and the display location.
- the matched advertisement audience is the target advertisement audience, and the target person’s personalized preference for the first advertisement information, the first identifier of the target advertisement display platform, the display area where the target person is located, and the target person’s image
- the collection time is added to the personal data of the target advertising audience.
- a third aspect of the present application provides a computer device, the computer device includes a processor, and the processor is configured to execute the computer program stored in the memory to implement the aforementioned data collection method for advertisement push.
- the fourth aspect of the present application provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the aforementioned data collection method for advertisement push is implemented.
- This application enables targeted advertisements for different audiences in the later stage to improve user experience.
- FIG. 1 is a flowchart of a data collection method for advertisement push provided in Embodiment 1 of the present application.
- Fig. 2 is a schematic structural diagram of a data collection device for advertisement push provided in the second embodiment of the present application.
- FIG. 3 is a schematic diagram of a computer device provided in Embodiment 3 of the present application.
- FIG. 1 is a flowchart of a data collection method for advertisement push provided by the first embodiment of the present invention.
- the data collection method is applied to a computer device that can communicate with multiple advertising display platforms. According to different needs, the order of the steps in the flowchart can be changed, and some steps can be omitted.
- the method includes:
- Step S11 Obtain a target person image of each target person entering a specific area in front of at least one advertisement display platform.
- the computer device may be an advertisement management and control platform held by an advertiser, which can investigate all advertisement display platforms in a certain display area according to the needs, that is, only obtain a certain display area (for example, Shanghai Metro 2 The image of the target person collected by each advertising display platform in the Longyang Road Station of Line No.
- the advertising display platform may be a television, an advertising display screen, an advertising poster, and the like.
- at least one camera device is installed on each advertisement display platform, and the shooting range of the camera device of each advertisement display platform includes at least the specific area located on the advertisement display platform, and the camera device It is used to collect the image of the target person in the shooting range.
- the camera device may include a visible light camera, an infrared camera, a thermal imaging camera, and the like.
- people entering the shooting range may include people passing by the advertising display platform, people facing away from the advertising display platform (for example, when waiting for a public car, they may turn their backs to the advertising display platform), and The audience watching the advertisement display platform.
- the target person in this embodiment is limited to viewers watching the advertisement display platform.
- each camera device continuously collects images of people in a specific range in front of the corresponding advertisement display platform in real time or periodically.
- the computer device obtains all person images at each advertising display platform, and uses a deep convolutional neural network to detect whether each person image contains a face image area, and if so, it will further determine whether the face image area is Whether continuously appearing in the continuous image of the person and the duration of the continuous image of the person is greater than or equal to a first predetermined time period. If it is, it indicates that the corresponding person in the person image is the target person watching the advertisement display platform at this time, and the computer device determines that the person image is the target person image at this time.
- Step S12 Determine that the advertisement display platform corresponding to the target person image is the target advertisement display platform, obtain the first identifier of the target advertisement display platform, the display area where the target advertisement display platform is located, and where the target advertisement display platform is located on the target person The first advertisement information displayed at the time the image was collected.
- the target advertisement display platform refers to an advertisement display platform in a specific area entered by a target person.
- the first identifier may be an identification name or identification code that distinguishes the target advertisement display platform from other advertisement display platforms.
- each of the target person images includes a second identifier of the camera device used to capture the target image.
- the computer device stores a first correspondence between the unique identifiers of different advertising display platforms and the second identifiers of the camera devices installed on the advertising display platforms. After acquiring the target person image, the computer device determines the second identifier of the camera device that captured the target image, and determines the first identifier corresponding to the second identifier according to the first correspondence relationship. Identifier. In another embodiment, the computer device may also directly obtain the first identifier of the target advertisement display platform from the target advertisement display platform.
- the computer device also stores a second correspondence between the first identifiers of different advertising display platforms and the display areas where the advertising display platforms are located. After obtaining the first identifier of the target advertisement display platform, the computer device determines the display area corresponding to the first identifier according to the second correspondence relationship.
- each target person image further includes the collection time
- the collection time of the target person image reflects the appearance of the target customer on the target advertising display platform (or, the display area) time.
- the collection time may be identified in the target person image in the form of a time stamp.
- the computer device is preset with an original advertisement placement plan for each advertisement display platform, and the original advertisement placement plan includes the advertisement information that the target advertisement display platform plans to display in each advertisement time.
- the computer device may determine, according to the collection time of the target person image, that the advertisement information displayed by the target advertisement display platform at the same advertisement time as the collection time is the first advertisement information.
- the advertisement information includes the type of the displayed advertisement object (that is, the type of goods or services) and the specific characteristics of the advertisement object. For example, for a car advertisement, the advertisement information may include the car and the performance index of the car.
- Step S13 Analyze the identity information of the target person according to the target person image, where the identity information includes the face image area of the target person in the target person image.
- the face image area can reflect the unique identity of the target person. Further, the identity information may also include the gender, race, age, and occupation of the target person.
- the computer device uses a deep convolutional neural network to detect the face image region from the target person image, and performs cropping processing on the detected face image, thereby extracting all Describe the face image area.
- the convolutional neural network can learn the features of the face from the target person image, and then use a separator to distinguish the face image area from the non-face image area, so as to achieve the purpose of face detection.
- the computer device uses a trained deep learning classifier model to calculate the face image area to identify the gender, race, age, occupation, etc. of the target person. Taking the identification of the gender of the target person as an example, the calculation process includes:
- the gender feature parameters include hair (including beard) feature parameters, facial organ parameters, contour parameters, and sex feature parameters.
- hair including beard
- the facial feature parameters Taking the need to obtain facial feature parameters as an example, first locate the facial feature points, then perform skin color segmentation, use the active shape model algorithm to locate the facial feature points to obtain the chin area, and then use the skin color segmentation algorithm to separate the non-skin area of the chin. Finally, the beard color discrimination method is used to detect the beard in the non-skinned area of the chin, so as to extract the characteristics of the beard.
- a feature value can be assigned to the beard in the face image area according to the color of the beard, for example, an initial value can be assigned according to the color or density of the beard, so as to obtain the feature parameter of the beard according to the preset initial value.
- the feature extraction and classification of the face image region can be performed by the local binary pattern method (Local Binary Patterns), neural network method, and SVM (Support Vector Machine, Support Vector Machine), etc., to obtain the gender. Characteristic Parameters.
- the parameter model is compared with the face gender classifier model, so as to identify the gender corresponding to the face image region.
- Step S14 analyzing the behavior information of the target person according to the face image area, and judging the target person's personalized preference for the first advertisement information according to the behavior information.
- the behavior information includes at least one of the micro-expression of the target person and the length of attention to the first advertisement information.
- the computer device recognizes the characteristic area (such as the eye area, the eyebrow area, and the mouth area) in each face image area, and analyzes the user's behavior according to the changes in the characteristic areas of at least two consecutive face image areas.
- the micro expression For example, when the eye area becomes larger, the micro-expression is that the eyes are enlarged; when the corners of the mouth on both sides deviate upward, the micro-expression is the corners of the mouth rise; when the corners of the mouth deviate upward, the micro-expression The corners of the mouth are raised on one side. Then, the computer device determines the personalized preference of the target person for the first advertisement information according to the micro-expression.
- the micro-expression is that the corners of the mouth are raised on both sides, it can be determined that the target person prefers the first advertisement information (that is, more interested); and when the micro-expression is that the corners of the mouth are raised on one side, It can be determined that the target person does not prefer the first advertisement information (ie, is not interested).
- the protection scope of the present invention is not limited to the division of personalized preferences listed in this embodiment.
- the computer device recognizes the eye area in each face image area, and determines the length of time the target person pays attention to the first advertisement information according to the eye area of each face image area. Wherein, the length of time the target person pays attention to the first advertisement information needs to use the light spot formed by the light reflected by the eyes of the target person.
- the advertising display platform may also be provided with a collection lamp at a position close to the camera device. The collection lamp is used to emit light so that the camera device can collect the face image area and the face The eye area of the image area is formed by the light of the collecting lamp reflected by the eyeball of the target person.
- the attention duration is greater than or equal to a second preset duration, it is determined that the target person is more interested in the first advertisement information; conversely, when the attention duration is less than the second preset duration, Then it is determined that the target person is not interested in the first advertisement information.
- Step S15 Search in the preset database whether there is an advertisement audience that matches the identity information of the target person. If so, proceed to step S16; otherwise, proceed to step S17.
- the preset database stores the personal data of multiple advertisement audiences, and the personal data of each advertisement audience includes the identity information of the advertisement audience, the personalized preference for at least one advertisement information, and the display of the at least one advertisement.
- Step S16 Determine that the matched advertisement audience is a target advertisement audience, and compare the target person’s personalized preference for the first advertisement information, the first identifier of the target advertisement display platform, and the display area And the collection time of the target person image is added to the personal data of the target advertisement audience.
- the target person’s personalized preference for the first advertisement information actually reflects the point of interest of the target person
- the personalized preferences added to the personal data of the target advertising audience can be used to update the points of interest of the target advertising audience.
- the display area actually reflects the place where the target person appears
- adding the display area where the target advertisement display platform is located to the personal data of the target advertisement audience can be used to update the place where the target advertisement audience appears.
- the collection time of the target person's image actually reflects the time when the target person appears in the display area. Adding the collection time of the target person's image to the personal data of the target advertising audience can be used for Update the time when the advertisement audience appears in the display area.
- the computer device can push the preset database to offline marketers, so that offline marketers can track each advertising audience based on the personal data and target the products that the advertising audience is interested in. Or services to increase the probability of purchase.
- Step S17 Add the personal data of another advertisement audience to the preset database according to the identity information of the target person, and combine the target person’s personalized preference for the first advertisement information and the target advertisement
- the display area where the display platform is located and the collection time of the target person's image are added to the newly added personal data.
- the identity information of the advertisement audience includes the face image area of the advertisement audience.
- the computer device compares the face image area of the target person with the face image area of each advertisement audience in the preset database, and when the face image area of the target person matches that of one of the advertisement audiences When the difference value of the face image area is less than a preset difference value, the computer device determines that the advertisement audience matches the identity information of the target person.
- the computer device determines that there is no identity with the target person The advertising audience that matches the information.
- Step S18 Summarize all the advertisement information displayed on each advertisement display platform in the preset database, calculate the satisfaction index of the advertisement information according to the personalized preference of each advertisement audience for the advertisement information, and calculate the satisfaction index of the advertisement information according to the advertisement
- the satisfaction index of each advertisement information displayed by the display platform adjusts the original advertisement placement plan for the advertisement display platform to obtain a current advertisement placement plan, and transmits the current advertisement placement plan to the advertisement display platform.
- the satisfaction index represents the overall satisfaction of all advertising audiences of the advertising information with the advertising information, and can reflect the advertising effect of the advertising display platform.
- the satisfaction index is equal to the ratio between the number of advertising audiences who prefer the advertising information and the total number of all advertising audiences of the advertising information, and the computer device compares the satisfaction index with A preset satisfaction degree is compared, and when the satisfaction index is greater than or equal to the preset satisfaction degree, it is determined that all the advertisement audiences of the advertisement information have a higher overall satisfaction degree with the advertisement information. For example, for the advertisement "Jianghuai Automobile" displayed on the advertising display platform of Longyang Station on Shanghai Metro Line 2, according to statistics, 80% of all advertising audiences who watch the advertising information prefer the advertising information, which exceeds all advertising audiences. The preset satisfaction degree of 60% indicates that all the advertisement audiences of the advertisement information are highly satisfied with the advertisement information.
- the adjusting the original advertisement placement plan for the advertisement display platform according to the satisfaction index of each advertisement information displayed by the advertisement display platform includes: determining whether the satisfaction index of each advertisement information exceeds For the preset satisfaction degree, when the satisfaction index exceeds the preset satisfaction degree, the advertisement time of the advertisement information in the original advertisement placement plan is extended. On the contrary, the advertisement time of the advertisement information in the original advertisement delivery technology is shortened. For example, in the original advertising plan, the advertising time of the advertising display platform for the JAC automobile advertisement is 3 hours. If it is determined that the satisfaction index of the advertisement information exceeds the preset satisfaction degree, the computer device will correspondingly extend the advertisement time of the advertisement information in the original advertisement placement plan.
- step S18 the method can also determine the effect of advertisement placement in other ways.
- the following steps may also be included after step S18:
- Step S19 Summarize all the advertisement audiences corresponding to each advertisement display platform in the preset database and the appearance time of each advertisement audience to calculate the traffic index of the advertisement display platform, and adjust the traffic index according to the traffic index.
- the original advertisement placement plan of the advertisement display platform is used to obtain a current advertisement placement plan, and the current advertisement placement plan is transmitted to the advertisement display platform.
- the human flow indicator can also reflect the advertising effect of the advertising display platform from another aspect. It can be understood that the more human traffic, the better the advertising effect.
- the traffic indicator is the number of advertising audiences entering a specific area of the advertising display platform within a preset time interval (e.g., every hour), and the traffic indicator can be based on the forecast. Calculate the advertisement audience corresponding to each advertisement display platform in the database and the time when each advertisement audience appears. Wherein, if the same advertisement audience reappears at least twice within the preset time interval, calculation is performed based on the appearance of at least two advertisement audiences in the same advertisement display platform.
- the adjustment of the original advertisement placement plan for the advertisement display platform according to the human flow indicator includes: comparing the human flow indicator with a preset human flow, when the human flow indicator When the traffic is greater than or equal to the preset traffic, the advertising time of the advertisement information in the original advertisement placement plan is extended. On the contrary, the advertisement time of the advertisement information in the original advertisement delivery technology is shortened.
- FIG. 1 describes in detail the data collection method for advertising push of the present invention.
- Figures 2 and 3 the functional modules of the software device that implements the data collection method and the hardware device architecture that implements the data collection method Make an introduction.
- Fig. 2 is a structural diagram of a preferred embodiment of a data collection device for advertisement push according to the present invention.
- the data collection device 10 runs in a computer device.
- the data collection device 10 may include multiple functional modules composed of program code segments.
- the program code of each program segment in the data collection device 10 may be stored in the memory of the computer device and executed by the at least one processor to realize the data collection function.
- the data collection device 10 can be divided into multiple functional modules according to the functions it performs.
- the functional modules may include: a first acquisition module 101, a second acquisition module 102, a first analysis module 103, a second analysis module 104, a search module 105, an addition module 106, and a first summary module 107 And the second summary module 108.
- the module referred to in the present invention refers to a series of computer program segments that can be executed by at least one processor and can complete fixed functions, and are stored in a memory. In this embodiment, the function of each module will be described in detail in subsequent embodiments.
- the first acquiring module 101 is configured to acquire a target person image of each target person entering a specific area in front of at least one advertisement display platform.
- the computer device may be an advertisement management and control platform held by an advertiser, which can investigate all advertisement display platforms in a certain display area according to the needs, that is, only obtain a certain display area (for example, Shanghai Metro 2 The image of the target person collected by each advertising display platform in the Longyang Road Station of Line No.
- the advertising display platform may be a television, an advertising display screen, an advertising poster, and the like.
- at least one camera device is installed on each advertisement display platform, and the shooting range of the camera device of each advertisement display platform includes at least the specific area located on the advertisement display platform, and the camera device It is used to collect the image of the target person in the shooting range.
- the camera device may include a visible light camera, an infrared camera, a thermal imaging camera, and the like.
- people entering the shooting range may include people passing by the advertising display platform, people facing away from the advertising display platform (for example, when waiting for a public car, they may turn their backs to the advertising display platform), and The audience watching the advertisement display platform.
- the target person in this embodiment is limited to viewers watching the advertisement display platform.
- each camera device continuously collects images of people in a specific range in front of the corresponding advertisement display platform in real time or periodically.
- the first acquisition module 101 is used to acquire all the person images at each advertising display platform, and the first analysis module 103 is used to detect whether each person image contains a face image area using a deep convolutional neural network, If so, it will be further determined whether the face image area continues to appear in the continuous person images and whether the continuous person images last for a duration greater than or equal to a first predetermined duration. If so, it indicates that the corresponding person in the person image is the target person watching the advertisement display platform at this time, and it can be determined that the person image is the target person image at this time.
- the second obtaining module 102 is configured to determine that the advertisement display platform corresponding to the target person image is the target advertisement display platform, obtain the first identifier of the target advertisement display platform, the display area where it is located, and the target advertisement display The first advertisement information displayed by the platform at the collection time of the target person image.
- the target advertisement display platform refers to an advertisement display platform in a specific area entered by a target person.
- the first identifier may be an identification name or identification code that distinguishes the target advertisement display platform from other advertisement display platforms.
- each of the target person images includes a second identifier of the camera device used to capture the target image.
- the computer device stores a first correspondence between the unique identifiers of different advertising display platforms and the second identifiers of the camera devices installed on the advertising display platforms.
- the second acquisition module 102 is configured to determine the second identifier of the camera device that acquired the target image after acquiring the target person image, and determine the second identifier corresponding to the second identifier according to the first correspondence relationship The first identifier.
- the second obtaining module 102 may also directly obtain the first identifier of the target advertisement display platform from the target advertisement display platform.
- the computer device also stores a second correspondence between the first identifiers of different advertising display platforms and the display areas where the advertising display platforms are located. After acquiring the first identifier of the target advertisement display platform, the second acquiring module 102 determines the display area corresponding to the first identifier according to the second correspondence.
- each target person image further includes the collection time
- the collection time of the target person image reflects the appearance of the target customer on the target advertising display platform (or, the display area) time.
- the collection time may be identified in the target person image in the form of a time stamp.
- the computer device is preset with an original advertisement placement plan for each advertisement display platform, and the original advertisement placement plan includes the advertisement information that the target advertisement display platform plans to display in each advertisement time.
- the computer device may determine, according to the collection time of the target person image, that the advertisement information displayed by the advertisement display platform corresponding to the target person image at the same advertisement time as the collection time is the first advertisement information.
- the advertisement information includes the type of the displayed advertisement object (that is, the type of goods or services) and the specific characteristics of the advertisement object. For example, for a car advertisement, the advertisement information may include the car and the performance index of the car.
- the first analysis module 103 is configured to analyze the identity information of the target person according to the target person image, and the identity information includes the face image area of the target person in the target person image.
- the face image area can reflect the unique identity of the target person. Further, the identity information may also include the gender, race, age, and occupation of the target person.
- the first analysis module 103 is configured to use a deep convolutional neural network to detect the face image area from the target person image, and perform cropping processing on the detected face image , So as to extract the face image area.
- the convolutional neural network can learn the features of the face from the target person image, and then use a separator to distinguish the face image area from the non-face image area, so as to achieve the purpose of face detection.
- the first analysis module 103 uses a trained deep learning classifier model to calculate the face image area to identify the gender, race, age, and occupation of the target person. Taking the identification of the gender of the target person as an example, the calculation process includes:
- the gender feature parameters include hair (including beard) feature parameters, facial organ parameters, contour parameters, and sex feature parameters.
- hair including beard
- the facial feature parameters Taking the need to obtain facial feature parameters as an example, first locate the facial feature points, then perform skin color segmentation, use the active shape model algorithm to locate the facial feature points to obtain the chin area, and then use the skin color segmentation algorithm to separate the non-skin area of the chin. Finally, the beard color discrimination method is used to detect the beard in the non-skinned area of the chin, so as to extract the characteristics of the beard.
- a feature value can be assigned to the beard in the face image area according to the color of the beard, for example, an initial value can be assigned according to the color or density of the beard, so as to obtain the feature parameter of the beard according to the preset initial value.
- the feature extraction and classification of the face image region can be performed by the local binary pattern method (Local Binary Patterns), neural network method, and SVM (Support Vector Machine, Support Vector Machine), etc., to obtain the gender. Characteristic Parameters.
- the parameter model is compared with the face gender classifier model, so as to identify the gender corresponding to the face image region.
- the second analysis module 104 is configured to analyze the behavior information of the target person according to the face image area, and determine the personalized preference of the target person for the advertisement information according to the behavior information.
- the behavior information includes at least one of the micro-expression of the target person and the length of attention to the first advertisement information.
- the second analysis module 104 is used to identify characteristic areas (such as eye area, eyebrow area, mouth area) in each face image area, based on the characteristic areas of at least two consecutive face image areas Analyze the micro-expression of the user. For example, when the eye area becomes larger, the micro-expression is that the eyes are enlarged; when the corners of the mouth on both sides deviate upward, the micro-expression is the corners of the mouth rise; when the corners of the mouth deviate upward, the micro-expression The corners of the mouth are raised on one side. Then, the computer device determines the personalized preference of the target person for the advertisement information according to the micro-expression.
- characteristic areas such as eye area, eyebrow area, mouth area
- the micro-expression is that the corners of the mouth are raised on both sides, it can be determined that the target person prefers the first advertisement information (that is, more interested); and when the micro-expression is that the corners of the mouth are raised on one side, It can be determined that the target person does not prefer the first advertisement information (ie, is not interested).
- the protection scope of the present invention is not limited to the division of personalized preferences listed in this embodiment.
- the second analysis module 104 identifies the eye area in each face image area, and judges the target person’s attention to the first advertisement information according to the eye area of each face image area duration. Wherein, the length of time the target person pays attention to the first advertisement information needs to use the light spot formed by the light reflected by the eyes of the target person.
- the advertising display platform may also be provided with a collection lamp at a position close to the camera device. The collection lamp is used to emit light so that the camera device can collect the face image area and the face The eye area of the image area is formed by the light of the collecting lamp reflected by the eyeball of the target person.
- the attention duration is greater than or equal to a second preset duration, it is determined that the target person is more interested in the first advertisement information; conversely, when the attention duration is less than the second preset duration, Then it is determined that the target person is not interested in the first advertisement information.
- the search module 105 is used to search a preset database for whether there is an advertisement audience that matches the identity information of the target person.
- the preset database stores the personal data of multiple advertisement audiences.
- the personal data of the audience includes the identity information of the advertisement audience, the personalized preference for at least one piece of advertisement information, the first identifier of the advertisement display platform that displays the at least one piece of advertisement information, the display area where it is located, and the advertisement audience The time of appearance in the display area where the first advertising display platform is located.
- the adding module 106 is used for determining that the matched advertising audience is the target advertising audience when there is an advertising audience that matches the identity information of the target person, and determining the target person’s contribution to the first advertising information Personalized preferences, the first identifier of the target advertisement display platform, the display area where it is located, and the collection time of the target person image are added to the personal data of the target advertisement audience.
- the target person’s personalized preference for the first advertisement information actually reflects the point of interest of the target person
- the personalized preferences added to the personal data of the target advertising audience can be used to update the points of interest of the target advertising audience.
- the display area actually reflects the place where the target person appears, and adding the obtained display area of the advertisement display platform to the personal data of the target advertisement audience can be used to update the appearance of the target advertisement audience location.
- the collection time of the target person's image actually reflects the time when the target person appears in the display area. Adding the collection time of the target person's image to the personal data of the target advertising audience can be used for Update the time when the advertisement audience appears in the display area.
- the computer device can push the preset database to offline marketers, so that offline marketers can track each advertising audience based on the personal data and target the products that the advertising audience is interested in. Or services to increase the probability of purchase.
- the identity information of the advertisement audience includes the face image area of the advertisement audience.
- the search module 105 is used to compare the face image area of the target person with the face image area of each advertisement audience in the preset database, when the face image area of the target person is equal to one of the When the difference value of the face image area of the advertisement audience is less than a preset difference value, it is determined that the advertisement audience matches the identity information of the target person.
- the difference between the face image area of the target person and the face image area of any advertising audience is less than the preset difference value, it is determined that there is no match with the identity information of the target person Advertising audience.
- the adding module 106 adds the personal data of another advertisement audience to the preset database according to the identity information of the target person, and adjusts the target person’s personalized preference for the first advertisement information
- the display area where the advertisement target display platform is located and the collection time of the target person's image are added to the newly added personal data.
- the first summary module 107 is used to summarize all the advertisement information displayed by each advertisement display platform in the preset database, and calculate the satisfaction degree of the advertisement information according to the personalized preference of each advertisement audience for the advertisement information Index, adjust the original advertisement placement plan for the advertisement display platform according to the satisfaction index of each advertisement information displayed by the advertisement display platform to obtain a current advertisement placement plan, and transmit the current advertisement placement plan to all The advertising display platform.
- the satisfaction index represents the overall satisfaction of all advertising audiences of the advertising information with the advertising information, and can reflect the advertising effect of the advertising display platform.
- the satisfaction index is equal to the ratio between the number of advertising audiences who prefer the advertising information to the total number of all advertising audiences of the advertising information, and the first aggregation module 107 calculates the satisfaction
- the degree index is compared with a preset satisfaction degree. When the satisfaction index is greater than or equal to the preset satisfaction degree, it is determined that all the advertising audiences of the advertisement information have a higher overall satisfaction degree with the advertisement information. .
- the first summary module 107 adjusts the original advertisement placement plan for the advertisement display platform according to the satisfaction index of each advertisement information displayed by the advertisement display platform, including: judging the performance of each advertisement information Whether the satisfaction index exceeds the preset satisfaction degree, and when the satisfaction index exceeds the preset satisfaction degree, the advertisement time of the advertisement information in the original advertisement placement plan is extended. On the contrary, the advertisement time of the advertisement information in the original advertisement delivery technology is shortened. For example, in the original advertising plan, the advertising time of the advertising display platform for the JAC automobile advertisement is 3 hours. If it is determined that the satisfaction index of the advertisement information exceeds the preset satisfaction degree, the computer device will correspondingly extend the advertisement time of the advertisement information in the original advertisement placement plan.
- the second summary module 108 is used to summarize all the advertisement audiences corresponding to each advertisement display platform in the preset database and the appearance time of each advertisement audience to calculate the human flow index of the advertisement display platform, according to the person
- the traffic indicator adjusts the original advertisement placement plan for the advertisement display platform to obtain a current advertisement placement plan, and transmits the current advertisement placement plan to the advertisement display platform.
- the human flow indicator can also reflect the advertising effect of the advertising display platform from another aspect. It can be understood that the more human traffic, the better the advertising effect.
- the traffic indicator is the number of advertising audiences entering a specific area of the advertising display platform within a preset time interval (e.g., every hour), and the traffic indicator can be based on the forecast. Calculate the advertisement audience corresponding to each advertisement display platform in the database and the time when each advertisement audience appears. Wherein, if the same advertisement audience reappears at least twice within the preset time interval, calculation is performed based on the appearance of at least two advertisement audiences in the same advertisement display platform.
- the adjustment of the original advertisement placement plan for the advertisement display platform according to the human flow indicator includes: comparing the human flow indicator with a preset human flow, when the human flow indicator When the traffic is greater than or equal to the preset traffic, the advertising time of the advertisement information in the original advertisement placement plan is extended. On the contrary, the advertisement time of the advertisement information in the original advertisement delivery technology is shortened.
- the collected information when collecting information, has a high degree of richness, including target person images, advertisement information, the first identifier of the advertisement display platform, the display area where the advertisement display platform is located, and the The acquisition time of the target person's image, etc., so as to determine the target person's identity information (including face image area, gender, race, age, occupation), behavior information (including micro-expression, attention time) and other characteristics of multiple dimensions, and then Determine the target person’s personalized preference for advertising information, appearing location, frequency, traffic information, advertising effect, etc.; furthermore, the continuously updated preset database can be pushed to offline marketers to make online Marketing personnel can track each advertising audience according to the personal data and target the products or services that the advertising audience is interested in to increase the purchase probability; finally, by quantifying the advertising effect of each advertising display platform, Subsequent advertisements provide reference to achieve accurate placement of advertisements by time period, and realize intelligent matching between advertisers, media and platform parties to maximize their benefits.
- target person's identity information including face image area, gender, race, age, occupation
- behavior information
- Fig. 3 is a schematic diagram of a preferred embodiment of the computer device of the present invention.
- the computer device 1 includes a memory 20, a processor 30, and a computer program 40 stored in the memory 20 and running on the processor 30, such as a data collection program for advertisement push.
- a computer program 40 stored in the memory 20 and running on the processor 30, such as a data collection program for advertisement push.
- the processor 30 executes the computer program 40, the steps in the foregoing embodiment of the data collection method are implemented, for example, steps S11 to S19 shown in FIG. 1.
- the processor 30 executes the computer program 40, the function of each module/unit in the embodiment of the data collection device is realized, for example, the modules 101-108 in FIG. 2.
- the computer program 40 may be divided into one or more modules/units, and the one or more modules/units are stored in the memory 20 and executed by the processor 30 to complete this invention.
- the one or more modules/units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program 40 in the computer device 1.
- the computer program 40 can be divided into the first acquisition module 101, the second acquisition module 102, the first analysis module 103, the second analysis module 104, the search module 105, the addition module 106, and the first summary in FIG. Module 107 and the second summary module 108. Refer to the second embodiment for the specific functions of each module.
- the computer device 1 may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server.
- a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server.
- the schematic diagram is only an example of the computer device 1 and does not constitute a limitation on the computer device 1. It may include more or fewer components than those shown in the figure, or a combination of certain components, or different components. Components, for example, the computer device 1 may also include input and output devices, network access devices, buses, and so on.
- the so-called processor 30 may be a central processing unit (Central Processing Unit, CPU), other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.
- the general-purpose processor may be a microprocessor or the processor 30 may also be any conventional processor, etc.
- the processor 30 is the control center of the computer device 1 and connects the entire computer device 1 with various interfaces and lines. Various parts.
- the memory 20 may be used to store the computer program 40 and/or modules/units.
- the processor 30 runs or executes the computer programs and/or modules/units stored in the memory 20 and calls the computer programs and/or modules/units stored in the memory.
- the data in 20 realizes various functions of the computer device 1.
- the memory 20 may mainly include a storage program area and a storage data area.
- the storage program area may store an operating system, an application program required by at least one function (such as a sound playback function, an image playback function, etc.), etc.; the storage data area may Data (such as audio data) created according to the use of the computer device 1 and the like are stored.
- the memory 20 may include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a Secure Digital (SD) card, a flash memory card (Flash Card), At least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device.
- non-volatile memory such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a Secure Digital (SD) card, a flash memory card (Flash Card), At least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device.
- the integrated modules/units of the computer device 1 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium, which may be non-easy. Loss of sex can also be volatile.
- the present invention implements all or part of the processes in the above-mentioned embodiments and methods, and can also be completed by instructing relevant hardware through a computer program.
- the computer program can be stored in a computer-readable storage medium. When the program is executed by the processor, the steps of the foregoing method embodiments can be implemented.
- the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file, or some intermediate forms.
- the computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory) .
- the disclosed computer device and method may be implemented in other ways.
- the computer device embodiments described above are merely illustrative.
- the division of the units is only a logical function division, and there may be other division methods in actual implementation.
- the functional units in the various embodiments of the present invention may be integrated in the same processing unit, or each unit may exist alone physically, or two or more units may be integrated in the same unit.
- the above-mentioned integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional modules.
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Controls And Circuits For Display Device (AREA)
Abstract
Description
Claims (21)
- 一种用于广告推送的数据采集方法,应用于一计算机装置中,所述计算机装置能够与多个广告展示平台进行通信,其中,所述方法包括:获取进入至少一广告展示平台前方的特定区域内的每一目标人物的目标人物图像;对每一目标人物图像,执行如下步骤:确定所述目标人物图像对应的广告展示平台为目标广告展示平台,获取所述目标广告展示平台的第一识别符、所处的展示区域以及所述目标广告展示平台在所述目标人物图像的采集时间所展示的第一广告信息;根据所述目标人物图像分析所述目标人物的身份信息,所述身份信息包括所述目标人物图像中所述目标人物的人脸图像区域;根据所述人脸图像区域分析所述目标人物的行为信息,并根据所述行为信息判断所述目标人物对所述第一广告信息的个性化偏好;在预置数据库中搜索是否存在与所述目标人物的身份信息相匹配的广告受众,其中,所述预置数据库中存储有多个广告受众的个人数据,每一广告受众的个人数据包括所述广告受众的身份信息、对至少一广告信息的个性化偏好、展示所述至少一广告信息的广告展示平台的第一识别符、所处的展示区域以及所述广告受众在所述第一广告展示平台所处的展示区域出现的时间;以及当存在与所述目标人物的身份信息相匹配的广告受众时,确定所述相匹配的广告受众为目标广告受众,将所述目标人物对所述第一广告信息的个性化偏好、所述目标广告展示平台的第一识别符、所处的展示区域以及所述目标人物图像的采集时间添加至所述目标广告受众的个人数据中。
- 如权利要求1所述的用于广告推送的数据采集方法,其中,所述计算机装置预置有针对每一广告展示平台的原始广告投放计划,所述方法还包括:汇总所述预置数据库中每一广告展示平台所展示的所有广告信息;根据每一广告受众对所述广告信息的个性化偏好计算所述广告信息的满意度指标;以及根据所述广告展示平台所展示的每一广告信息的满意度指标调整针对所述广告展示平台的原始广告投放计划以得到一当前广告投放计划,并将所述当前广告投放计划传输至所述广告展示平台。
- 如权利要求1所述的用于广告推送的数据采集方法,其中,所述计算机装置预置有针对每一广告展示平台的原始广告投放计划,所述方法还包括:汇总所述预置数据库中每一广告展示平台对应的所有广告受众以及每一广告受众出现的时间以计算所述广告展示平台的人流量指标;以及根据所述人流量指标调整针对所述广告展示平台的原始广告投放计划以得到一当前广告投放计划,并将所述当前广告投放计划传输至所述广告展示平台。
- 如权利要求1所述的用于广告推送的数据采集方法,其中,所述获取进入至少一广告展示平台前方的特定区域内的每一目标人物的目标人物图像包括:获取每一广告展示平台处的所有人物图像,并利用深度的卷积神经网络检测每一人物图像中是否包含人脸图像区域;当所述人物图像包括人脸图像区域时,判断所述人脸图像区域是否在连续的所述人物图像中持续出现且连续的所述人物图像所持续的时长是否大于或等于一第一预定时长;以及当所述人物图像所持续的时长大于或等于所述第一预设时长时,判断所述人物图像为所述目标人物图像。
- 如权利要求1所述的用于广告推送的数据采集方法,其中,每一广告展示平台上安装有至少一摄像装置,每一广告展示平台的所述摄像装置用于采集所述目标人物图像,其中,每一所述目标人物图像包含用于采集所述目标图像的摄像装置的第二识别符,所述计算机装置中存储有不同广告展示平台的第一识别符与安装于所述广告展示平台的摄像装置的第二识别符之间的第一对应关系,所述获取所述目标广告展示平台的第一识别符包括:在获取所述目标人物图像后,确定采集所述目标图像的摄像装置的第二识别符;以及根据所述第一对应关系确定与所述第二识别符对应的所述第一识别符。
- 如权利要求5所述的用于广告推送的数据采集方法,其中,每一所述目标人物图像还包含所述采集时间,所述目标人物图像的采集时间反映所述目标客户在所述目标广告展示平台出现的时间,所述计算机装置预置有针对每一广告展示平台的原始广告投放计划,所述原始广告投放计划包括所述目标广告展示平台在每一广告时间计划展示的广告信息,所述计算机装置根据所述目标人物图像的采集时间,确定所述目标广告展示平台在与所述采集时间相同的广告时间所展示的广告信息为所述第一广告信息。
- 如权利要求1所述的用于广告推送的数据采集方法,其中,所述行为信息包括所述目标人物的微表情以及对所述第一广告信息的关注时长中的至少一个。
- 一种计算机装置,其中:所述计算机装置包括处理器,所述处理器用于执行存储器中存储的计算机程序时获取进入至少一广告展示平台前方的特定区域内的每一目标人物的目标人物图像;并对每一目标人物图像,执行如下步骤:确定所述目标人物图像对应的广告展示平台为目标广告展示平台,获取所述目标广告展示平台的第一识别符、所处的展示区域以及所述目标广告展示平台在所述目标人物图像的采集时间所展示的第一广告信息;根据所述目标人物图像分析所述目标人物的身份信息,所述身份信息包括所述目标人物图像中所述目标人物的人脸图像区域;根据所述人脸图像区域分析所述目标人物的行为信息,并根据所述行为信息判断所述目标人物对所述第一广告信息的个性化偏好;在预置数据库中搜索是否存在与所述目标人物的身份信息相匹配的广告受众,其中,所述预置数据库中存储有多个广告受众的个人数据,每一广告受众的个人数据包括所述广告受众的身份信息、对至少一广告信息的个性化偏好、展示所述至少一广告信息的广告展示平台的第一识别符、所处的展示区域以及所述广告受众在所述第一广告展示平台所处的展示区域出现的时间;以及当存在与所述目标人物的身份信息相匹配的广告受众时,确定所述相匹配的广告受众为目标广告受众,将所述目标人物对所述第一广告信息的个性化偏好、所述目标广告展示平台的第一识别符、所处的展示区域以及所述目标人物图像的采集时间添加至所述目标广告受众的个人数据中。
- 如权利要求8所述的计算机装置,其中,所述计算机装置预置有针对每一广告展示平台的原始广告投放计划,所述处理器还用于执行:汇总所述预置数据库中每一广告展示平台所展示的所有广告信息;根据每一广告受众对所述广告信息的个性化偏好计算所述广告信息的满意度指标;以及根据所述广告展示平台所展示的每一广告信息的满意度指标调整针对所述广告展示平台的原始广告投放计划以得到一当前广告投放计划,并将所述当前广告投放计划传输至所述广告展示平台。
- 如权利要求8所述的计算机装置,其中,所述计算机装置预置有针对每一广告展示平台的原始广告投放计划,所述处理器还用于执行:汇总所述预置数据库中每一广告展示平台对应的所有广告受众以及每一广告受众出现的时间以计算所述广告展示平台的人流量指标;以及根据所述人流量指标调整针对所述广告展示平台的原始广告投放计划以得到一当前广告投放计划,并将所述当前广告投放计划传输至所述广告展示平台。
- 如权利要求8所述的计算机装置,其中,所述获取进入至少一广告展示平台前方的特定区域内的每一目标人物的目标人物图像包括:获取每一广告展示平台处的所有人物图像,并利用深度的卷积神经网络检测每一人物图像中是否包含人脸图像区域;当所述人物图像包括人脸图像区域时,判断所述人脸图像区域是否在连续的所述人物图像中持续出现且连续的所述人物图像所持续的时长是否大于或等于一第一预定时长;以及当所述人物图像所持续的时长大于或等于所述第一预设时长时,判断所述人物图像为所述目标人物图像。
- 如权利要求8所述的计算机装置,其中,每一广告展示平台上安装有至少一摄像装置,每一广告展示平台的所述摄像装置用于采集所述目标人物图像,其中,每一所述目标人物图像包含用于采集所述目标图像的摄像装置的第二识别符,所述计算机装置中存储有不同广告展示平台的第一识别符与安装于所述广告展示平台的摄像装置的第二识别符之间的第一对应关系,所述获取所述目标广告展示平台的第一识别符包括:在获取所述目标人物图像后,确定采集所述目标图像的摄像装置的第二识别符;以及根据所述第一对应关系确定与所述第二识别符对应的所述第一识别符。
- 如权利要求12所述的计算机装置,其中,每一所述目标人物图像还包含所述采集时间,所述目标人物图像的采集时间反映所述目标客户在所述目标广告展示平台出现的时间,所述计算机装置预置有针对每一广告展示平台的原始广告投放计划,所述原始广告投放计划包括所述目标广告展示平台在每一广告时间计划展示的广告信息,所述计算机装置根据所述目标人物图像的采集时间,确定所述目标广告展示平台在与所述采集时间相同的广告时间所展示的广告信息为所述第一广告信息。
- 如权利要求8所述的计算机装置,其中,所述行为信息包括所述目标人物的微表情以及对所述第一广告信息的关注时长中的至少一个。
- 一种计算机可读存储介质,其上存储有计算机程序,其中,执行存储器中存储的计算机程序时获取进入至少一广告展示平台前方的特定区域内的每一目标人物的目标人物图像;并对每一目标人物图像,执行如下步骤:确定所述目标人物图像对应的广告展示平台为目标广告展示平台,获取所述目标广告展示平台的第一识别符、所处的展示区域以及所述目标广告展示平台在所述目标人物图像的采集时间所展示的第一广告信息;根据所述目标人物图像分析所述目标人物的身份信息,所述身份信息包括所述目标人物图像中所述目标人物的人脸图像区域;根据所述人脸图像区域分析所述目标人物的行为信息,并根据所述行为信息判断所述目标人物对所述第一广告信息的个性化偏好;在预置数据库中搜索是否存在与所述目标人物的身份信息相匹配的广告受众,其中,所述预置数据库中存储有多个广告受众的个人数据,每一广告受众的个人数据包括所述广告受众的身份信息、对至少一广告信息的个性化偏好、展示所述至少一广告信息的广告展示平台的第一识别符、所处的展示区域以及所述广告受众在所述第一广告展示平台所处的展示区域出现的时间;以及当存在与所述目标人物的身份信息相匹配的广告受众时,确定所述相匹配的广告受众为目标广告受众,将所述目标人物对所述第一广告信息的个性化偏好、所述目标广告展示平台的第一识别符、所处的展示区域以及所述目标人物图像的采集时间添加至所述目标广告受众的个人数据中。
- 如权利要求15所述的计算机可读存储介质,其中,所述计算机可读存储介质内预置有针对每一广告展示平台的原始广告投放计划,所述处理器还用于执行:汇总所述预置数据库中每一广告展示平台所展示的所有广告信息;根据每一广告受众对所述广告信息的个性化偏好计算所述广告信息的满意度指标;以及根据所述广告展示平台所展示的每一广告信息的满意度指标调整针对所述广告展示平台的原始广告投放计划以得到一当前广告投放计划,并将所述当前广告投放计划传输至所述广告展示平台。
- 如权利要求15所述的计算机可读存储介质,其中,所述计算机可读存储介质预置有针对每一广告展示平台的原始广告投放计划,所述处理器还用于执行:汇总所述预置数据库中每一广告展示平台对应的所有广告受众以及每一广告受众出现的时间以计算所述广告展示平台的人流量指标;以及根据所述人流量指标调整针对所述广告展示平台的原始广告投放计划以得到一当前广告投放计划,并将所述当前广告投放计划传输至所述广告展示平台。
- 如权利要求15所述的计算机可读存储介质,其中,所述获取进入至少一广告展示平台前方的特定区域内的每一目标人物的目标人物图像包括:获取每一广告展示平台处的所有人物图像,并利用深度的卷积神经网络检测每一人物图像中是否包含人脸图像区域;当所述人物图像包括人脸图像区域时,判断所述人脸图像区域是否在连续的所述人物图像中持续出现且连续的所述人物图像所持续的时长是否大于或等于一第一预定时长;以及当所述人物图像所持续的时长大于或等于所述第一预设时长时,判断所述人物图像为所述目标人物图像。
- 如权利要求15所述的计算机可读存储介质,其中,每一广告展示平台上安装有至少一摄像装置,每一广告展示平台的所述摄像装置用于采集所述目标人物图像,其中,每一所述目标人物图像包含用于采集所述目标图像的摄像装置的第二识别符,所述计算机装置中存储有不同广告展示平台的第一识别符与安装于所述广告展示平台的摄像装置的第二识别符之间的第一对应关系,所述获取所述目标广告展示平台的第一识别符包括:在获取所述目标人物图像后,确定采集所述目标图像的摄像装置的第二识别符;以及根据所述第一对应关系确定与所述第二识别符对应的所述第一识别符。
- 如权利要求19所述的计算机可读存储介质,其中,每一所述目标人物图像还包含所述采集时间,所述目标人物图像的采集时间反映所述目标客户在所述目标广告展示平台出现的时间,所述计算机装置预置有针对每一广告展示平台的原始广告投放计划,所述原始广告投放计划包括所述目标广告展示平台在每一广告时间计划展示的广告信息,所述计算机装置根据所述目标人物图像的采集时间,确定所述目标广告展示平台在与所述采集时间相同的广告时间所展示的广告信息为所述第一广告信息。
- 如权利要求15所述的计算机可读存储介质,其中,所述行为信息包括所述目标人物的微表情以及对所述第一广告信息的关注时长中的至少一个。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910772280.0 | 2019-08-21 | ||
CN201910772280.0A CN110689367A (zh) | 2019-08-21 | 2019-08-21 | 数据采集方法、装置、计算机装置及存储介质 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021031600A1 true WO2021031600A1 (zh) | 2021-02-25 |
Family
ID=69108453
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2020/086798 WO2021031600A1 (zh) | 2019-08-21 | 2020-04-24 | 数据采集方法、装置、计算机装置及存储介质 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN110689367A (zh) |
WO (1) | WO2021031600A1 (zh) |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110689367A (zh) * | 2019-08-21 | 2020-01-14 | 深圳壹账通智能科技有限公司 | 数据采集方法、装置、计算机装置及存储介质 |
CN111311303A (zh) * | 2020-01-17 | 2020-06-19 | 北京市商汤科技开发有限公司 | 一种信息投放方法及装置、电子设备、存储介质 |
CN111339420A (zh) * | 2020-02-28 | 2020-06-26 | 北京市商汤科技开发有限公司 | 图像处理方法、装置、电子设备及存储介质 |
CN111582956A (zh) * | 2020-06-29 | 2020-08-25 | 成都新潮传媒集团有限公司 | 一种广告推送方法、装置及计算机设备 |
CN112926177B (zh) * | 2020-12-24 | 2024-06-04 | 南京城建隧桥智慧管理有限公司 | 一种户外多媒体平台中异质信息显示时长自适应确定方法 |
CN112633935A (zh) * | 2020-12-29 | 2021-04-09 | 厦门理工学院 | 一种基于cmf的交互性展示方法和装置 |
CN114012746B (zh) * | 2021-10-28 | 2023-07-14 | 深圳市普渡科技有限公司 | 一种机器人、信息播放的方法、控制装置以及介质 |
CN117876029B (zh) * | 2024-03-12 | 2024-05-07 | 南京摆渡人网络信息技术有限公司 | 一种基于商品推广的人机交互优化系统、方法及装置 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100318419A1 (en) * | 2009-06-12 | 2010-12-16 | Riccardo Vieri | Pay per audience for digital signage advertising |
US20180032997A1 (en) * | 2012-10-09 | 2018-02-01 | George A. Gordon | System, method, and computer program product for determining whether to prompt an action by a platform in connection with a mobile device |
CN109543575A (zh) * | 2018-11-09 | 2019-03-29 | 深圳市云兴科技有限公司 | 基于行为轨迹和动态多维度信息反馈激发大数据的方法和区域多维度探测反馈组合设备 |
CN110033296A (zh) * | 2018-11-09 | 2019-07-19 | 阿里巴巴集团控股有限公司 | 一种数据处理方法和装置 |
CN110689367A (zh) * | 2019-08-21 | 2020-01-14 | 深圳壹账通智能科技有限公司 | 数据采集方法、装置、计算机装置及存储介质 |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102129644A (zh) * | 2011-03-08 | 2011-07-20 | 北京理工大学 | 一种具有受众特性感知与统计功能的智能广告系统 |
CN102881239A (zh) * | 2011-07-15 | 2013-01-16 | 鼎亿数码科技(上海)有限公司 | 基于图像识别的广告投播系统及方法 |
CN104573619A (zh) * | 2014-07-25 | 2015-04-29 | 北京智膜科技有限公司 | 基于人脸识别的智能广告大数据分析方法及系统 |
CN108764986A (zh) * | 2018-05-18 | 2018-11-06 | 汕头市智美科技有限公司 | 一种广告受众信息处理方法、装置及系统 |
CN208225374U (zh) * | 2018-06-14 | 2018-12-11 | 湖南超能机器人技术有限公司 | 精确统计受众情况的广告宣传装置 |
-
2019
- 2019-08-21 CN CN201910772280.0A patent/CN110689367A/zh active Pending
-
2020
- 2020-04-24 WO PCT/CN2020/086798 patent/WO2021031600A1/zh active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100318419A1 (en) * | 2009-06-12 | 2010-12-16 | Riccardo Vieri | Pay per audience for digital signage advertising |
US20180032997A1 (en) * | 2012-10-09 | 2018-02-01 | George A. Gordon | System, method, and computer program product for determining whether to prompt an action by a platform in connection with a mobile device |
CN109543575A (zh) * | 2018-11-09 | 2019-03-29 | 深圳市云兴科技有限公司 | 基于行为轨迹和动态多维度信息反馈激发大数据的方法和区域多维度探测反馈组合设备 |
CN110033296A (zh) * | 2018-11-09 | 2019-07-19 | 阿里巴巴集团控股有限公司 | 一种数据处理方法和装置 |
CN110689367A (zh) * | 2019-08-21 | 2020-01-14 | 深圳壹账通智能科技有限公司 | 数据采集方法、装置、计算机装置及存储介质 |
Also Published As
Publication number | Publication date |
---|---|
CN110689367A (zh) | 2020-01-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021031600A1 (zh) | 数据采集方法、装置、计算机装置及存储介质 | |
US10255505B2 (en) | Augmenting video data to present real-time sponsor metrics | |
US10799168B2 (en) | Individual data sharing across a social network | |
US9672535B2 (en) | System and method for communicating information | |
US20160321256A1 (en) | System and method for generating a facial representation | |
US9324006B2 (en) | System and method for displaying contextual supplemental content based on image content | |
JP2023036898A (ja) | 視聴者エンゲージメントを評価するためのシステムおよび方法 | |
US20150242707A1 (en) | Method and system for predicting personality traits, capabilities and suggested interactions from images of a person | |
US7760917B2 (en) | Computer-implemented method for performing similarity searches | |
WO2020143156A1 (zh) | 热点视频标注处理方法、装置、计算机设备及存储介质 | |
US20120140069A1 (en) | Systems and methods for gathering viewership statistics and providing viewer-driven mass media content | |
US20200118168A1 (en) | Advertising method, device and system, and computer-readable storage medium | |
US20150042953A1 (en) | Measurement Method and System | |
US20130067513A1 (en) | Content output device, content output method, content output program, and recording medium having content output program recorded thereon | |
CN104573619A (zh) | 基于人脸识别的智能广告大数据分析方法及系统 | |
US20160019411A1 (en) | Computer-Implemented System And Method For Personality Analysis Based On Social Network Images | |
US20110208593A1 (en) | Electronic advertisement apparatus, electronic advertisement method and recording medium | |
JP2015509218A (ja) | デジタル広告システム | |
CN103493068A (zh) | 个性化广告选择系统和方法 | |
JP2004227158A (ja) | 情報提供装置および情報提供方法 | |
US11631110B2 (en) | Audience-based optimization of communication media | |
Farinella et al. | Face re-identification for digital signage applications | |
Yu et al. | AI-based targeted advertising system | |
WO2008138144A1 (en) | Method and system for audience measurement and targeting media | |
CN105938603A (zh) | 一种基于机器视觉的人员感兴趣程度检测系统及方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20855586 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20855586 Country of ref document: EP Kind code of ref document: A1 |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 23.08.2022) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20855586 Country of ref document: EP Kind code of ref document: A1 |