CN114638629A - Information pushing method and device - Google Patents
Information pushing method and device Download PDFInfo
- Publication number
- CN114638629A CN114638629A CN202011476417.7A CN202011476417A CN114638629A CN 114638629 A CN114638629 A CN 114638629A CN 202011476417 A CN202011476417 A CN 202011476417A CN 114638629 A CN114638629 A CN 114638629A
- Authority
- CN
- China
- Prior art keywords
- information
- payment
- terminal
- payment terminal
- push
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 80
- 239000000463 material Substances 0.000 claims abstract description 61
- 238000001514 detection method Methods 0.000 claims description 28
- 230000007613 environmental effect Effects 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 8
- 230000000474 nursing effect Effects 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 230000000875 corresponding effect Effects 0.000 description 48
- 238000010801 machine learning Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 11
- 238000013461 design Methods 0.000 description 8
- 239000013598 vector Substances 0.000 description 8
- 230000001680 brushing effect Effects 0.000 description 7
- 230000002596 correlated effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 241000257303 Hymenoptera Species 0.000 description 3
- 230000009471 action Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000001737 promoting effect Effects 0.000 description 2
- 241000237858 Gastropoda Species 0.000 description 1
- 206010061991 Grimacing Diseases 0.000 description 1
- 230000004397 blinking Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/30—Payment architectures, schemes or protocols characterised by the use of specific devices or networks
- G06Q20/32—Payment architectures, schemes or protocols characterised by the use of specific devices or networks using wireless devices
-
- 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
- G06Q30/0277—Online advertisement
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the specification provides an information pushing method for pushing information about a preset payment mode at a payment terminal, and according to one embodiment, the method comprises the following steps: generating a plurality of candidate push information about a preset payment mode according to the combination of a plurality of meta-materials in a material library; the candidate push information is pushed at the payment terminals based on the terminal information of the payment terminals; determining the association relationship between the terminal information of the payment terminal and the candidate push information according to the validity of each push result corresponding to each payment terminal; and determining push information from the candidate push information for each payment terminal based on the association relation so as to push corresponding push information when a single payment terminal detects a preset target body. The implementation mode can improve the effectiveness of information pushing.
Description
Technical Field
One or more embodiments of the present specification relate to the field of computer technologies, and in particular, to a method and an apparatus for pushing information.
Background
Offline advertising is one of the common ways of advertising. The device for offline advertising may be, for example, a billboard, a promotional page, etc. The advertisement putting of common offline equipment usually adopts manual operation, and the putting usually has certain randomness. Traditional offline advertising typically can only measure advertising effectiveness from the overall conversion. Therefore, how to improve the relevance of the links from the display to the payment (and later), shorten the conversion link, and realize intelligent and personalized advertisement push is a considerable problem.
Disclosure of Invention
One or more embodiments of the present specification describe an information pushing method and apparatus to solve one or more of the problems mentioned in the background.
According to a first aspect, an information pushing method is provided for pushing pushed information based on a predetermined payment mode at a payment terminal, and includes: generating a plurality of candidate push information about the preset payment mode according to the combination of a plurality of meta-materials in a material library; pushing the candidate push information at a plurality of payment terminals based on terminal information of the payment terminals, wherein the terminal information comprises one or more of the following items: geographic position, surrounding environment, shop operation information, terminal setting duration and a crowd portrait of a corresponding geographic position; determining an incidence relation between the terminal information of the payment terminal and the candidate push information according to the validity of each push result corresponding to each payment terminal; and respectively determining corresponding push information from the candidate push information for each payment terminal based on the association relation, so that when a single payment terminal detects a preset target body, the corresponding push information is pushed.
According to a second aspect, there is provided a method of information push for a payment terminal; the method comprises the following steps: acquiring images according to a preset time interval to detect whether the acquired current image is an image containing a preset target body; displaying push information about a predetermined payment mode under the condition that the current image is an image containing a predetermined target body, wherein the push information is determined based on terminal information of the payment terminal, and the terminal information comprises one or more of the following items: geographic position, surrounding environment, store operation information, terminal setting duration and people figure of corresponding geographic position.
In one embodiment, the predetermined target body is a human body, the payment terminal stores a human body detection model in advance, and the current image is detected by the payment terminal through the human body detection model to determine whether the current image is a human body part image.
In one embodiment, the predetermined target is a human body, and the acquiring the images at the predetermined time interval to detect whether the acquired current image is an image including the predetermined target includes: and the payment terminal sends the current image to a human body detection server so that the human body detection server detects whether the current image is an image containing a human body part according to a human body detection model trained in advance and feeds back a detection result.
In one embodiment, the push information of the predetermined payment mode is generated according to the combination of a plurality of meta-materials in the material library.
In one embodiment, the push information is determined based on a pre-trained information model, which is trained by: determining the incidence relation between the terminal information of the payment terminal and candidate push information according to the effectiveness of each push result corresponding to each payment terminal, wherein the single candidate push information is generated according to the combination of a plurality of meta-materials in a material library; and constructing a training sample by utilizing the incidence relation so as to train an information model, wherein the information model is used for selecting the push information used for a single payment terminal from the plurality of candidate push information according to the terminal information of the single payment terminal.
In one embodiment, the ambient environment includes at least one of the following environmental factors: business super, subway station, railway station, bus station, residential area, office building, park, scenic spot, school, nursing home, hospital.
In one embodiment, the people profile is determined based on one or more of the amount of people detected by the payment terminal, the payment method when payment is made using the payment terminal, the number of people making payments using a predetermined payment method, and the type of goods purchased.
According to a third aspect, an information pushing apparatus is provided, which is disposed at a server and is used for pushing information based on a predetermined payment method at a payment terminal, and includes:
the information generation unit is configured to generate a plurality of candidate push information about the preset payment mode according to the combination of a plurality of meta-materials in the material library;
an information pushing unit configured to push the candidate push information at a plurality of payment terminals based on terminal information of the plurality of payment terminals, wherein the terminal information includes one or more of the following: geographic position, surrounding environment, store operation information, terminal setting duration and crowd portrayal of corresponding geographic position;
the association unit is configured to determine an association relation between the terminal information of the payment terminal and the candidate push information according to the validity of each push result corresponding to each payment terminal;
and the information determining unit is configured to determine corresponding push information from the candidate push information for each payment terminal based on the association relation, so that the corresponding push information can be pushed when a single payment terminal detects a preset target body.
According to a fourth aspect, an information pushing device is provided and is arranged at a payment terminal; the device comprises:
the image acquisition unit is configured to acquire images at preset time intervals so as to detect whether the acquired current image is an image containing a preset target body;
an information pushing unit configured to present pushing information about a predetermined payment mode in a case that a current image is an image including a predetermined target, wherein the pushing information is determined based on terminal information of the payment terminal, and the terminal information includes one or more of the following: geographic location, surrounding environment, store operation information, set duration and a crowd portrait of the corresponding geographic location.
According to a fifth aspect, there is provided a computer readable storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform the method of the first or second aspect.
According to a sixth aspect, there is provided a computing device comprising a memory and a processor, wherein the memory has stored therein executable code, and wherein the processor, when executing the executable code, implements the method of the first or second aspect.
According to the method and the device provided by the embodiment of the specification, the combination of the meta-materials is utilized to autonomously generate the plurality of candidate push information, and the candidate push information with better effectiveness in various scenes is determined to be used as the corresponding push information based on the practical data pushed by the plurality of candidate push information at each payment terminal, so that the effectiveness of information pushing can be improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic diagram of a specific implementation architecture under the technical concept of the present specification;
fig. 2 shows a flow diagram of a method of information push according to an embodiment;
fig. 3 shows a flow chart of a method of information push according to another embodiment;
FIG. 4 shows a schematic block diagram of an apparatus for information push according to one embodiment;
fig. 5 shows a schematic block diagram of an apparatus for information push according to another embodiment.
Detailed Description
The scheme provided by the specification is described below with reference to the accompanying drawings.
First, a description will be given with reference to an embodiment shown in fig. 1. The technical scheme provided by the specification is suitable for a scene of information pushing through the payment terminal. Fig. 1 shows a specific implementation scenario of information push at a payment terminal. The payment terminal can be arranged in various scenes such as shops, supermarkets, self-service vending machines, hotels, tourist attractions and the like, which can generate payment.
The payment terminal can be connected with the payment server through a network, and can download corresponding push information from the server. The payment terminal can also support payment operation of a preset payment mode. The predetermined payment method may include a predetermined route and/or a predetermined payment form, etc. Wherein, the predetermined route may be, for example: unions of bank, network financial platforms, and the like. The predetermined payment form is, for example, card payment, code payment, face payment, etc.
The payment terminal may include at least a presentation device (e.g., a display screen or a projector), a processor, and may further include at least one of: voice acquisition device (like microphone), image acquisition device (like camera), voice broadcast device (like bee calling organ), detecting device (like infrared detector etc.) etc.. When the display device is a touch screen, the display equipment can be used for collecting character information, click information and the like input by a user through the screen, and the processor can be used for processing interactive operation (such as payment operation selection) among terminal users and carrying out data interaction with a server. Alternatively, in case the payment terminal includes an image capture device, the image capture device may use a 3D structured light camera for faster and more accurate image capture. On the other hand optionally, the image acquisition device can also adopt a stereo scanner to acquire a human body at an ultra-large wide angle, and clear images can be obtained no matter the backlight side light, so that the human body identification efficiency and accuracy are improved.
The information content pushed on each payment terminal can be specified by the server side or determined based on the effectiveness of information pushing carried out on each payment terminal by the server side. For example, the user may be further guided to pay by the predetermined payment method by pushing relevant information about the predetermined payment method on the payment terminal. For example, the user is guided to pay by using a face brushing payment mode of the network financial platform A. Therefore, a new payment technology can be popularized through information pushing at the payment terminal, and the payment efficiency is improved.
In order to improve the effectiveness of information pushing, an information pushing strategy can be determined for a user in a targeted manner, so that a better user experience is provided in the information pushing process. The effectiveness of information pushing can be measured by the utilization rate of the predetermined payment method used by the user, the improvement rate of the utilization rate of the user, the increment of the user using the predetermined payment method and the like. The push policy may include, for example, what push information is pushed, what manner push information is replaced, and the like. In an optional embodiment, in order to save network resources, the payment terminal may further provide a plurality of push policies, for example, determine the content of the push information to be displayed according to whether the user is detected (e.g., whether the acquired image includes an image of a human body part). As a specific example, the presentation may be with fixed pre-positioned material (e.g., a static flyer, picture, animation, etc.) when no user is detected, which may remain unchanged or may be updated at predetermined time intervals (e.g., 5 minutes). When the human body part is detected to appear, push information, such as scene-related animation (e.g., face brushing payment animation in a travel scene) can be adjusted to attract the attention of the user, so that guidance is provided for the user in a targeted manner. Wherein the purpose of detecting the human body part is to sense a real person (e.g. a biological person). The method of sensing a real person may be, for example, infrared detection, image recognition, etc. Under the image recognition method, any part of the human body, such as a palm, a finger, a head, a face, an ear, an eye, hair, a trunk, an arm, a leg, and the like, may be recognized. In some embodiments, the user herein may be understood to be an internet user.
It should be noted that the information pushing policy may be determined by the payment terminal (for example, by the terminal user, by a machine learning model preset in the terminal, etc.), or may be determined by a server providing a service for the payment terminal, which is not limited herein.
The technical idea of the present specification is described in detail below.
Fig. 2 shows a flow diagram of information pushing according to an embodiment of the present specification. The flow of pushing the information is described with reference to fig. 1. The process may be executed by a server as shown in fig. 1, or may be executed by any device with certain computing capability. The payment terminal to which the procedure relates may be a payment terminal as shown in fig. 1. The process can be used for pushing information related to the preset payment mode to the user at the payment terminal, so that the preset payment mode is automatically recommended to the user.
In the flow, first, through step 201, several candidate push information about a predetermined payment method are generated according to a combination of several meta-materials in the material library.
The meta-material may be pre-stored on the execution subject and may include, for example, a cartoon head, a cartoon body, voice, a copy, a picture, etc., which are generated in advance by the emulation software. Alternatively, the elemental material may be transparent video material. Transparent video material is an animation material distinguished from conventional video material, and has advantages such as the following, compared to a 3D animation package: rendering is not needed, what you see is what you get, and the communication cost is lower; and the method does not contain codes, so that the test flow can be saved, and the online flow is shorter.
Each type of element material may have multiple selectable material items, for example, the cartoon head may have multiple selectable material items such as smiling, grimacing, peeling, etc., the cartoon leg may have multiple selectable material items such as walking, running, jumping, etc. For the predetermined payment method, there may be an element material of a type related to the predetermined payment method, such as a face-brushing payment device, a face-brushing payment action inside the body/head of a cartoon (e.g., blinking blink), and so on.
The selectable material items in different types can be combined at will to generate related animations or images as candidate push information. For example, a candidate push message about a face brushing payment method obtained through combination is an animation that ants of a cartoon image pull a suitcase with one hand and carry a luggage bag with the other hand, complete face brushing payment and walk away quickly through face recognition. The animation can be further superposed with voice source materials and used for dubbing operation in the animation or promoting the advantages of payment modes displayed in the animation. For example, the voice element material is used for broadcasting and swiping face payment and has the characteristics of rapidness, safety, novelty, science and technology and the like.
Next, in step 202, the candidate push information is pushed to the plurality of payment terminals based on the terminal information of the plurality of payment terminals. In this step, several candidate push information generated in step 201 may be actually pushed at each payment terminal for sampling.
It can be understood that different payment terminals are located at different geographical positions, and the target users are different in orientation, so that the acceptance of the push information is different. Therefore, according to another possible design, the candidate push information may be classified, the correspondence between the payment terminal and the candidate push information may be determined according to the surrounding environment of the payment terminal, and the push information may be configured according to the correspondence. For example, for a train station scene, candidate push information related to travel can be corresponded (for example, a cartoon image has characteristics of carrying luggage and the like). At this time, candidate push information related to the scene may be pushed on the payment terminal of the corresponding scene. For example, different candidate push information may be configured for each payment terminal near a train station (e.g., within 1 km). In addition, the store operation information, for example, store operation goods, and the operation property of the store itself (for example, a supermarket, a canteen, and an unmanned store), may affect consumer groups, payment methods, and the like. The set duration of the payment terminal may also affect the way of payment for the consumer. Thus, the candidate push information may be pushed according to one or more of these information of the payment terminal. Since these pieces of information are all pieces of information related to the terminal, they may be referred to as terminal information. Specifically, the terminal information may include, but is not limited to, at least one of: geographic location, surrounding environment, store operation information, terminal setting duration, people figure of corresponding geographic location, and the like.
According to one possible design, the candidate push messages may be broadcast in turn at a single payment terminal and switched periodically, for example, one candidate push message per day.
According to yet another possible design, the candidate push information may also be specified by a user of the payment terminal (e.g. a store operator). In an alternative embodiment, the candidate push information may also be manually switched.
In other possible designs, there may be other possible candidate push information configuration modes, which are not described herein again.
Under the implementation framework of the present specification, validity of a push result corresponding to each piece of push information may also be counted for each payment terminal. The validity here may be determined based on, for example, the usage rate of the user using the predetermined payment means, the number of users using the predetermined payment means, and the like. Further, in step 203, the association relationship between the terminal information of the payment terminal and the candidate push information is determined according to the validity of each push result corresponding to each payment terminal.
It can be understood that the terminal information (such as the geographic location, the surrounding environment, the store operation information, the terminal setting duration, the crowd portrayal of the corresponding geographic location, etc.) of the payment terminal has personalized features for the payment terminal. However, under the condition that each candidate push message is displayed by a single terminal, different performances may occur, for example, validity of the push result is different. That is, the validity may be used to measure the association between the terminal information of the payment terminal and the candidate push information.
In one embodiment, whether an association exists between the terminal information of the payment terminal and the candidate push information may be determined according to a condition that validity is met. For example, in the case that the increment of the user amount using the predetermined payment method is larger than a predetermined value (e.g., 100) or a predetermined ratio (e.g., 1%), it indicates that the candidate push information is more effective on the payment terminal having the corresponding terminal information, and there is a correlation. On the contrary, in the case that the increment of the user amount using the predetermined payment method is smaller than the predetermined numerical value (e.g. 1) or the predetermined proportion (e.g. 0.01%), it indicates that the candidate push information is less effective on the payment terminal having the corresponding terminal information, and there is no correlation.
In another embodiment, the quantitative result of the effectiveness of the push result may be used as a measure of the association. For example, the increment of the user amount using a predetermined payment method is used as an index for measuring the strength of the association relationship. Further, the strength of the association relationship may be positively correlated with the increment of the user amount using a predetermined payment method. For another example, the amount of users who use a predetermined payment method is used as an index for measuring the strength of the association relationship. At this time, the strength of the association relationship may be positively correlated with the amount of the user who uses the predetermined payment method.
In another embodiment, payment terminals with similar terminal information may be used as a class, and the candidate push information with the best push effectiveness in the class of payment terminals may be used as the candidate push information associated with the class of payment terminals.
In other embodiments, the association relationship between the terminal information of the payment terminal and the candidate push information may also be determined in other manners, which is not described herein again.
Then, in step 204, based on the above-mentioned association relationship, corresponding push information is determined from the candidate push information for each payment terminal. In this way, when a single payment terminal detects a predetermined target body, the corresponding candidate push information can be pushed. It will be appreciated that a better recommendation effect is desirable for a single payment terminal. Therefore, the candidate push information can be configured for the payment terminal according to the incidence relation determined based on the validity of the recommendation result.
In one embodiment, the candidate push information may be configured for the payment terminal according to the level of validity. For example, the candidate push information with the highest effectiveness on all the payment terminals can be uniformly configured to each payment terminal.
In another embodiment, for a single payment terminal, one candidate push message may be selected from candidate push messages having an association relationship with the payment terminal of the corresponding class, and configured to the single payment terminal.
In yet another embodiment, the information model may be trained by constructing training samples using the association relationship. The information model can be used for selecting the push information for a single payment terminal from a plurality of candidate push information according to the terminal information of the single payment terminal.
According to the analysis, the characteristics can be extracted according to the terminal information of the payment terminal (such as one or more items of the geographic position, the surrounding environment, the shop operation information, the terminal setting duration and the crowd portrait of the corresponding geographic position of the payment terminal), the sample label is determined according to the association relationship, and the training sample is constructed, so that the information model is trained. The determination mode of the sample label may be different according to the determination mode of the association relationship. For example, when the association is "association", the sample label may indicate whether to associate (for example, 1 indicates association, and 0 indicates no association), and when the association is indicated by the association degree (association strength), the sample label may be positively correlated with the association degree, for example, a normalized value of the association degree. In an embodiment, the sample tag may be in a vector form, each dimension of the vector corresponds to each candidate push information, and an element value of a single dimension may be an association relationship between the payment terminal and the corresponding candidate push information. In another embodiment, the candidate push information with the best push effectiveness in a class of payment terminals is used as the candidate push information associated with the class of payment terminals, and at this time, the candidate push information itself or a corresponding identifier (such as a code, etc.) may also be used as the sample tag. In another embodiment, the candidate push information may be displayed at the corresponding payment terminal, and the user amount of the predetermined payment method may be used as the sample label within the predetermined time period.
In the process of extracting the features from the terminal information of the payment terminal, the features can be extracted according to human definition, or the features can be automatically extracted by using a deep neural network, which is not limited herein. For example, the geographic location may be represented using codes, such as different codes according to jurisdictions (e.g., provinces, cities, etc.), or different codes according to regional nature (e.g., towns, rural areas, etc.). As another example, different environmental factors may be represented by different characters in the ambient environment. Typical environmental factors may include, but are not limited to, at least one of the following: business continents, subway stations, railway stations, bus stations, residential areas, office buildings, parks, scenic spots, schools, retirement homes, hospitals, etc., which are not exhaustive herein. In some cases, the surrounding environment may also be a relatively isolated environment, e.g., in a remote village, the surrounding may not have the various environmental factors listed above, and the environmental factors at this time may be considered as "islands," represented by corresponding characters. The crowd portrayal may include, for example, the age of the user using the payment terminal as a whole, shopping preferences, payment methods, payment amounts, and so forth. Similarly, the business object, the business duration and the like in the store business information can be represented in a symbolized mode, and the terminal set duration can directly serve as the characteristic or obtain the symbolized characteristic according to the duration.
In practice, a machine learning model that determines push information from terminal information of a payment terminal may also be referred to as an information model. The information model may be various machine learning models for prediction, such as a deep neural network, and the like. When model training is carried out, the terminal information of the payment terminal or the terminal characteristics extracted based on the terminal information can be processed through the selected information model, an output result is obtained, model parameters are adjusted by taking model loss reduction as a target based on the sample label, and therefore the information model is trained. The method for determining the model loss can be determined according to the sample label, for example, in the case that the sample label is a vector, the model loss can be negatively correlated with the similarity between the following vectors or positively correlated with the variance between the following vectors: a model prediction vector and a sample label vector. In the case where the sample label is the amount of users using a predetermined payment method for a predetermined period of time, the model loss may also be determined from the residuals between the model output results (predicted values) and the sample labels (true values) in the plurality of training samples.
In yet another embodiment, each candidate push message having an association relationship with a single payment terminal may be sent to a user (e.g., a merchant) corresponding to the payment terminal, so that the user may manually configure the corresponding candidate push message.
For the payment terminal, in order to avoid resource waste, the corresponding push information may be presented only under a predetermined condition. For example, the predetermined condition is detection of a predetermined target. The predetermined target may be a generic term for the target that triggers the information push of the payment terminal. It may be, for example, a human body part or any shade. In the case that the predetermined target is a human body part, the human body detection model may be trained in advance, and the human body part (such as the human face, head, finger, eye, and the like listed above) may be detected using the image acquired by the image acquisition device of the payment terminal. Under the condition that the preset target body is any shielding object, an infrared device of the payment terminal can be used for sensing the object in the preset range, or the shielding object can be sensed by the change of pixels in an image acquired by an image acquisition device of the payment terminal.
The single payment terminal can detect the human body image in real time and display the candidate push information under the condition that the human body image is detected. Such as playing animation through the presentation device, playing voice through a voice announcement device, and so forth.
Under the condition that the candidate push information of the payment terminal is selected by the information model, a user portrait of a user in an acquired image can be added according to the terminal information of the payment terminal, for example, the user portrait replaces a crowd portrait, the candidate push information is predicted, and the predicted candidate push information is used as the push information to be displayed currently.
In a word, in the above process, a plurality of candidate push information are autonomously generated by using a combination of meta-materials, and the candidate push information with better effectiveness in various scenes is determined based on the practical data pushed by the plurality of candidate push information at each payment terminal, so that the effectiveness of information push can be improved.
Referring now to fig. 3, fig. 3 illustrates a flow of information push of a payment terminal according to an embodiment. The executing body of the flow may be a computer, a device, a server, etc. with certain computing power, such as the payment terminal shown in fig. 1. The flow of fig. 3 shows a case where the payment terminal includes an image capture device, and a predetermined target body is determined by image recognition. As shown in fig. 3, the process includes: step 301, collecting images at a preset time interval to detect whether the collected current image is an image containing a preset target body; step 302, in the case that the current image is an image containing a predetermined target, presenting push information about a predetermined payment method, wherein the push information is determined based on terminal information of the payment terminal, and the terminal information includes one or more of the following: geographic location, surrounding environment, store operation information, set duration and the people figure of the corresponding geographic location.
First, in step 301, images are captured at predetermined time intervals to detect whether the current captured image is a human body image. It can be understood that the payment terminal can detect whether an image including a predetermined target body appears in real time, and thus, it is necessary to acquire images at predetermined time intervals and analyze whether the acquired images are human body images. Alternatively, only an image may be acquired for recognizing a human body in detecting an image of the human body without storing the image.
The predetermined time interval here may be, for example, 0.1 second, 0.5 second, 1 second, or the like. In order to ensure real-time human body image acquisition within the allowable range of the terminal processing capacity, the predetermined time interval may be determined experimentally, or may be determined by manual experience, and may also be determined according to the terminal processing capacity, for example, in negative correlation with the terminal processing efficiency, which is not limited herein.
The payment terminal may previously store an identification model of a predetermined target body for detecting whether the predetermined target body appears from the captured image. For example, in the case that the predetermined target body is a human body part, the corresponding recognition model may be a human body recognition model for recognizing the predetermined part of the human body, such as the aforementioned human face, arm, palm, finger, torso, and so on. Under the condition that the network connection can meet the real-time performance, the payment terminal can also send the acquired image to a recognition service end of a preset target body, such as a human body recognition service end, the recognition service end of the preset target body detects whether the preset target body, such as a human body, exists in the image according to a pre-trained recognition model, and the detection result is fed back to the payment terminal. The identification model of the predetermined target volume may be implemented by an image processing model such as a convolutional neural network, which will not be described in detail herein.
According to one possible design, the payment terminal may be in a standby state before detecting an image containing a predetermined target volume. Such as screen blanking, keeping only the image capture device and processor active, etc.
According to another possible design, before the image containing the predetermined target body is detected, the payment terminal can also display candidate materials which are manually designated or matched with the terminal information of the payment terminal according to a predetermined display strategy. The candidate material may be, for example, an image, a text or a video, an animation, or the like. The displayed candidate materials can be updated periodically (for example, updated once in 1 minute), or manually switched, or kept unchanged, or played sequentially.
In one embodiment, the candidate materials presented may be determined empirically or may be determined by machine learning. It will be appreciated that since payment terminals are typically used in fixed locations and the various surrounding facilities are typically fixed, the presentation of candidate materials may take into account the following factors: peripheral facilities such as hospitals, subway stations, business supermarkets, residential areas, and the like; consumption habits of surrounding people, such as periodic large-quantity buying of living goods, or low-frequency buying of a small quantity of needed goods (such as fruit baskets, flowers and the like which look at patients), and the like. In one implementation, candidate materials to be displayed can be determined according to historical experience, for example, each payment terminal with similar facilities around is counted, and one of candidate materials with the highest information pushing effectiveness is obtained. In another implementation, corresponding features can be extracted from the facility information and the consumption habit information to train the machine learning model. These characteristics can reflect the surrounding environment and crowd characteristics. In the training process of the machine learning model, a plurality of candidate materials with high effectiveness in historical information pushing can be used as sample labels, or sample label vectors are generated by the displayed candidate materials according to effectiveness (such as success rate) to train the machine learning model. Therefore, the personalized display strategy can be determined according to the specific position of the payment equipment, and the candidate materials are displayed.
Wherein, according to one possible design, the candidate materials may be generated from a plurality of meta-materials acquired in advance. For example, for a picture or animation, the elemental material may include animation heroes, animation actions, animation effects, and the like. Optionally, the animation pivot may be further split, and is not limited herein. For example, the selectable meta-materials of the animation hero may be characters of the animated figure, ants, snails, kittens, etc. For one of the animation actors, such as ants, the selectable meta-materials may also be candidate face materials, candidate body type materials, candidate action materials, and the like. These elemental materials may be combined to generate candidate materials in various combinations. For example, a candidate material generated includes an animation that a traveler of an ant image pulls the trunk, completes the face-brushing payment conveniently and quickly, and completes the voice description of the psychological activities recognized by the animation actors for the payment process during the face-brushing payment operation.
Then, according to step 302, in the case that the current image is an image containing a predetermined target, push information for making payment in a predetermined payment manner is presented. The predetermined payment method may include, for example, a payment form such as a code scanning payment, a face swiping payment, a card swiping payment, a payment route such as a unionpay payment, a network financial platform payment, and the like. The push information can be used for describing convenience, safety, efficiency, novelty, special interest and the like of a certain payment mode, so that a user is guided to use the corresponding payment mode.
It is worth mentioning that the predetermined target object here can be a human body part or any other obstruction present in the payment terminal accessory. The human body part can be any part of the human body, and can also be a complete human body, and the human body part can be any part of the human body, such as fingers, a human face, a body and the like. At this time, in the case where any part of the human body such as a finger, a face, an arm, a torso, or the like is recognized, it can be determined that the predetermined target body is detected. The image recognition method is as described above, and is not described herein again.
The push information can be provided to the user in one or more of a file, animation, and voice. In the case that the providing form of the push information includes a plurality of forms, according to one embodiment, the push information in different forms may include similar contents, for example, the voice broadcast is consistent with the content of the file, only the form is different, or the animation is played while the character language in the animation is simultaneously displayed by using the voice/file; according to another embodiment, the different forms of push information may be independent of each other and generated by a multitasking model, or each by a corresponding predictive model (information model).
In the process of determining the push information, in addition to the terminal characteristics mentioned above, the characteristics can be extracted according to the payment habits of big data statistics related to age and gender, or according to the historical consumption records, the payment habits and the like of the user, so as to optimize a machine learning model for determining the displayed images, characters, videos, animations and the like. When the machine learning model is a supervised machine learning model, the machine learning model can be trained by taking whether the user finally selects the payment mode related in the push information as a label. For example, under the condition that the pushing information is a face brushing payment mode, whether the user uses a payment platform corresponding to the face brushing payment to complete payment or not and whether the user uses the face brushing payment mode to complete payment on the corresponding payment platform can be used as a sample label to construct a training sample.
In an alternative embodiment, the targeted image, text, animation, video, etc. may not be displayed in step 301, and when an image containing a predetermined target is detected, the display is switched to the targeted image, text, animation, video display.
In an optional embodiment, whether the images, the characters, the animations, the videos, and the like displayed in step 301 are targeted or not is not limited, and after an image including a predetermined target is detected, in the case that the detected image is a face image, information such as consumption records and payment habits related to a corresponding user can be extracted according to the face image, and corresponding features can be extracted for determining push information, so that more specific and targeted push information is provided.
The push information may include at least one form of video, animation, images, literature, voice, etc. For example, the push information may be displayed in the form of an image + a document, in which case, the image and the document may be displayed on the display screen together with one copy, or a combination of a plurality of images and a plurality of documents may be displayed on the display screen with one copy selected from the images and the documents. For another example, the push information may be presented in the form of animation + voice, and at this time, the animation may be presented through the display screen, and the voice case may be presented through the voice broadcasting device.
Therefore, in the process of information pushing, based on the terminal information of the payment terminal and the user information of the corresponding user in the image, the pushing information is determined according to the personalized characteristics of the payment terminal and the user, so that the information pushing process is rich in targeted pushing information, and the effectiveness of information pushing is further improved.
According to an embodiment of another aspect, an apparatus for pushing information is also provided. Fig. 4 shows an information pushing apparatus 400, provided at a server, for pushing, at a payment terminal, enforcement information based on a predetermined payment method in one embodiment. The apparatus 400 comprises:
an information generating unit 41 configured to generate several candidate push information about a predetermined payment manner according to a combination of several meta-materials in the material library;
an information push unit 42 configured to push the candidate push information at a plurality of payment terminals based on terminal information of the plurality of payment terminals; wherein, the terminal information may include one or more of the following: geographic position, surrounding environment, store operation information, terminal setting duration and crowd portrayal of corresponding geographic position;
an association unit 43 configured to determine an association relationship between the terminal information of the payment terminal and the candidate push information according to validity of each push result corresponding to each payment terminal;
and the information determining unit 44 is configured to determine corresponding push information from the candidate push information for each payment terminal based on the association relation, so that the corresponding push information can be pushed when a single payment terminal detects a preset target body.
According to an embodiment of another aspect, an apparatus for pushing information provided in a payment terminal is also provided. As shown in fig. 5, an apparatus 500 for pushing information provided to a payment terminal according to one embodiment includes:
an image capturing unit 51 configured to capture images at predetermined time intervals to detect whether the captured current image is an image containing a predetermined target volume;
an information push unit 52 configured to present push information on a predetermined payment means in a case where the current image is an image including a predetermined target; wherein the push information is determined based on terminal information of the payment terminal, which may include one or more of: geographic location, surrounding environment, store operation information, set duration and a crowd portrait of the corresponding geographic location.
In one embodiment, the predetermined target body is a human body, the payment terminal stores a human body detection model in advance, and the current image is detected by the payment terminal through the human body detection model to determine whether the current image is a human body part image.
According to one embodiment, the predetermined target body is a human body, and the image capturing unit 51 is further configured to:
the payment terminal sends the current image to the human body detection server side, so that the human body detection server side detects whether the current image is an image containing a human body part according to a pre-trained human body detection model, and feeds back a detection result.
In one embodiment, the push information for the predetermined payment method is generated from a combination of meta-materials in the materials library.
According to one possible design, the apparatus 500 is further configured with a pre-trained information model for determining push information based on terminal information of the payment terminal.
In one embodiment, the ambient environment includes at least one of the following environmental factors: business super, subway station, railway station, bus station, residential area, office building, park, scenic spot, school, nursing home, hospital.
According to one embodiment, the people profile is determined based on one or more of the amount of people detected by the payment terminal, the payment method when using the payment terminal to pay, the number of people using a predetermined payment method to pay, and the type of goods purchased.
It should be noted that the apparatuses 400 and 500 shown in fig. 4 and 5 are apparatus embodiments corresponding to the method embodiments shown in fig. 2 and 3, respectively, and the corresponding descriptions in the method embodiments shown in fig. 2 and 3 are also applicable to the apparatuses 400 and 500, and are not repeated herein.
According to an embodiment of another aspect, there is also provided a computer-readable storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform the method described in connection with fig. 2 or fig. 3.
According to an embodiment of yet another aspect, there is also provided a computing device comprising a memory and a processor, the memory having stored therein executable code, the processor, when executing the executable code, implementing the method described in connection with fig. 2 or fig. 3.
Those skilled in the art will recognize that, in one or more of the examples described above, the functions described in the embodiments of this specification may be implemented in hardware, software, firmware, or any combination thereof. When implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium.
The above-mentioned embodiments, objects, technical solutions and advantages of the technical concepts of the present specification are further described in detail, it should be understood that the above-mentioned embodiments are only specific embodiments of the technical concepts of the present specification, and do not limit the scope of the technical concepts of the present specification, and any modifications, equivalent substitutions, improvements and the like made on the basis of the technical solutions of the embodiments of the present specification should be included in the scope of the technical concepts of the present specification.
Claims (18)
1. An information pushing method is used for pushing information based on a preset payment mode at a payment terminal and comprises the following steps:
generating a plurality of candidate push information about the preset payment mode according to the combination of a plurality of meta-materials in a material library;
pushing the candidate push information at a plurality of payment terminals based on terminal information of the payment terminals, wherein the terminal information comprises one or more of the following items: geographic position, surrounding environment, store operation information, terminal setting duration and crowd portrayal of corresponding geographic position;
determining an association relation between the terminal information of the payment terminal and the candidate push information according to the validity of each push result corresponding to each payment terminal;
and respectively determining corresponding push information from the candidate push information for each payment terminal based on the association relation so as to push the corresponding push information when a single payment terminal detects a preset target body.
2. A method for information push is used for a payment terminal; the method comprises the following steps:
acquiring images according to a preset time interval to detect whether the acquired current image is an image containing a preset target body;
displaying push information about a predetermined payment mode under the condition that the current image is an image containing a predetermined target body, wherein the push information is determined based on terminal information of the payment terminal, and the terminal information comprises one or more of the following items: geographic position, surrounding environment, store operation information, terminal setting duration and people figure of corresponding geographic position.
3. The method of claim 2, wherein the predetermined target is a human body, the payment terminal stores a human body detection model in advance, and the current image is detected by the payment terminal through the human body detection model to determine whether the current image is a human body part image.
4. The method according to claim 2, wherein the predetermined target is a human body, and the acquiring images at predetermined time intervals to detect whether the acquired current image is an image including the predetermined target comprises:
and the payment terminal sends the current image to a human body detection server so that the human body detection server detects whether the current image is an image containing a human body part according to a human body detection model trained in advance and feeds back a detection result.
5. The method of claim 2, wherein the push information for the predetermined payment method is generated from a combination of meta-materials in a materials library.
6. The method of claim 2, wherein the push information is determined based on a pre-trained information model, the information model being trained by:
determining the association relationship between the terminal information of the payment terminal and candidate push information according to the effectiveness of each push result corresponding to each payment terminal, wherein the single candidate push information is generated according to the combination of a plurality of meta-materials in a material library;
and constructing a training sample by utilizing the incidence relation so as to train an information model, wherein the information model is used for selecting the push information used for a single payment terminal from the candidate push information according to the terminal information of the single payment terminal.
7. The method of claim 2, the ambient environment comprising at least one of the following environmental factors: business super, subway station, railway station, bus station, residential area, office building, park, scenic spot, school, nursing home, hospital.
8. The method of claim 2, wherein the people profile is determined based on one or more of a flow of people detected by the payment terminal, a payment method when using the payment terminal to pay, a number of people paying using a predetermined payment method, a type of goods purchased.
9. The utility model provides a device of information propelling movement, locates the server-side for at payment terminal propelling movement information based on predetermined payment mode, include:
the information generation unit is configured to generate a plurality of candidate push information about the preset payment mode according to the combination of a plurality of meta-materials in the material library;
an information pushing unit configured to push the candidate push information at a plurality of payment terminals based on terminal information of the plurality of payment terminals, wherein the terminal information includes one or more of the following: geographic position, surrounding environment, store operation information, terminal setting duration and crowd portrayal of corresponding geographic position;
the association unit is configured to determine an association relation between the terminal information of the payment terminal and the candidate push information according to the validity of each push result corresponding to each payment terminal;
and the information determining unit is configured to determine corresponding push information from the candidate push information for each payment terminal based on the association relation, so that when a single payment terminal detects a preset target body, the corresponding push information is pushed.
10. An information pushing device is arranged on a payment terminal; the device comprises:
the image acquisition unit is configured to acquire images at preset time intervals so as to detect whether the acquired current image is an image containing a preset target body;
an information pushing unit configured to present pushing information about a predetermined payment mode in a case that a current image is an image including a predetermined target, wherein the pushing information is determined based on terminal information of the payment terminal, and the terminal information includes one or more of the following: geographic location, surrounding environment, store operation information, set duration and a crowd portrait of the corresponding geographic location.
11. The apparatus of claim 10, the predetermined target is a human body, the payment terminal stores a human body detection model in advance, and the current image is detected by the payment terminal through the human body detection model to be a human body part image.
12. The apparatus of claim 10, the predetermined target being a human body, the image acquisition unit being further configured to:
and the payment terminal sends the current image to a human body detection server so that the human body detection server detects whether the current image is an image containing a human body part according to a human body detection model trained in advance and feeds back a detection result.
13. The apparatus of claim 10, wherein the push information for the predetermined payment method is generated from a combination of meta-materials in a materials library.
14. The apparatus of claim 10, wherein the apparatus is further configured with a pre-trained information model to determine push information based on terminal information of the payment terminal.
15. The apparatus of claim 10, the ambient environment comprising at least one of the following environmental factors: business super, subway station, railway station, bus station, residential area, office building, park, scenic spot, school, nursing home, hospital.
16. The apparatus of claim 10, the people profile determined from one or more of a flow of people detected by the payment terminal, a payment method when paying using the payment terminal, a number of people paying using a predetermined payment method, a type of goods purchased.
17. A computer-readable storage medium, on which a computer program is stored which, when executed in a computer, causes the computer to carry out the method of any one of claims 1-8.
18. A computing device comprising a memory and a processor, wherein the memory has stored therein executable code that, when executed by the processor, performs the method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011476417.7A CN114638629A (en) | 2020-12-15 | 2020-12-15 | Information pushing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011476417.7A CN114638629A (en) | 2020-12-15 | 2020-12-15 | Information pushing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114638629A true CN114638629A (en) | 2022-06-17 |
Family
ID=81945634
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011476417.7A Pending CN114638629A (en) | 2020-12-15 | 2020-12-15 | Information pushing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114638629A (en) |
Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110066491A1 (en) * | 2009-09-16 | 2011-03-17 | Telefonaktiebolaget L M Ericsson (Publ) | Method and Communication Device for Using a First Service Based on an Account Chargeable with the Use of a Second Service |
| CN104200360A (en) * | 2014-09-04 | 2014-12-10 | 深圳市腾讯计算机系统有限公司 | Information process method, system and terminal |
| CN106855982A (en) * | 2016-12-16 | 2017-06-16 | 天脉聚源（北京）科技有限公司 | The recommendation method and device of advertisement |
| US20170323337A1 (en) * | 2015-06-30 | 2017-11-09 | Tencent Technology (Shenzhen) Company Limited | Advertisement push system, apparatus, and method |
| US20170358003A1 (en) * | 2015-02-11 | 2017-12-14 | Sk Planet Co., Ltd. | Object recognition based retargeting advertisement product recommending server, control method thereof, and non-transitory computer readable storage medium having computer program recorded thereon |
| CN107563794A (en) * | 2017-08-14 | 2018-01-09 | 广州创维平面显示科技有限公司 | A kind of advertisement delivery method and system |
| US20180227617A1 (en) * | 2016-02-01 | 2018-08-09 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for pushing information |
| US20180308079A1 (en) * | 2017-04-21 | 2018-10-25 | Hangzhou Zongs Intelligent Technology Co., Ltd. | Vending machine, method and device for controlling the same and system thereof |
| CN108734460A (en) * | 2018-04-02 | 2018-11-02 | 阿里巴巴集团控股有限公司 | A kind of means of payment recommends method, apparatus and equipment |
| CN109191090A (en) * | 2018-07-27 | 2019-01-11 | 阿里巴巴集团控股有限公司 | Means of payment recommended method, device, equipment and computer readable storage medium |
| CN109711900A (en) * | 2018-12-29 | 2019-05-03 | 北京金山安全软件有限公司 | Information display method and device based on face recognition, terminal equipment and storage medium |
| CN109858900A (en) * | 2019-01-21 | 2019-06-07 | 中国平安财产保险股份有限公司 | A kind of payment information method for pushing, device and terminal device |
| CN110049094A (en) * | 2019-02-28 | 2019-07-23 | 阿里巴巴集团控股有限公司 | The method and offline exhibition terminal of information push |
| CN110298671A (en) * | 2018-03-22 | 2019-10-01 | 前海哆啦阿梦（深圳）数据服务有限公司 | The monitoring system and method for e-payment |
| CN110580640A (en) * | 2019-09-05 | 2019-12-17 | 大有智能科技(嘉兴)有限公司 | Information pushing and receiving method, terminal, data processing server and system |
| CN111311339A (en) * | 2020-05-09 | 2020-06-19 | 支付宝(杭州)信息技术有限公司 | Target object display method and device and electronic equipment |
| CN111340575A (en) * | 2020-05-22 | 2020-06-26 | 支付宝(杭州)信息技术有限公司 | Resource pushing method and device and electronic equipment |
| CN111353094A (en) * | 2018-12-20 | 2020-06-30 | 北京嘀嘀无限科技发展有限公司 | Information pushing method and device |
| WO2020133438A1 (en) * | 2018-12-29 | 2020-07-02 | 深圳市欢太科技有限公司 | Method for determining information content and related product |
| CN111489208A (en) * | 2020-04-17 | 2020-08-04 | 支付宝(杭州)信息技术有限公司 | Matching management method, device and processing equipment for service promotion information |
| CN111951047A (en) * | 2020-08-10 | 2020-11-17 | 中国平安人寿保险股份有限公司 | Advertisement effect evaluation method based on artificial intelligence, terminal and storage medium |
| CN112035736A (en) * | 2020-07-31 | 2020-12-04 | 北京达佳互联信息技术有限公司 | Information pushing method and device and server |
-
2020
- 2020-12-15 CN CN202011476417.7A patent/CN114638629A/en active Pending
Patent Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110066491A1 (en) * | 2009-09-16 | 2011-03-17 | Telefonaktiebolaget L M Ericsson (Publ) | Method and Communication Device for Using a First Service Based on an Account Chargeable with the Use of a Second Service |
| CN104200360A (en) * | 2014-09-04 | 2014-12-10 | 深圳市腾讯计算机系统有限公司 | Information process method, system and terminal |
| US20170358003A1 (en) * | 2015-02-11 | 2017-12-14 | Sk Planet Co., Ltd. | Object recognition based retargeting advertisement product recommending server, control method thereof, and non-transitory computer readable storage medium having computer program recorded thereon |
| US20170323337A1 (en) * | 2015-06-30 | 2017-11-09 | Tencent Technology (Shenzhen) Company Limited | Advertisement push system, apparatus, and method |
| US20180227617A1 (en) * | 2016-02-01 | 2018-08-09 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for pushing information |
| CN106855982A (en) * | 2016-12-16 | 2017-06-16 | 天脉聚源（北京）科技有限公司 | The recommendation method and device of advertisement |
| US20180308079A1 (en) * | 2017-04-21 | 2018-10-25 | Hangzhou Zongs Intelligent Technology Co., Ltd. | Vending machine, method and device for controlling the same and system thereof |
| CN107563794A (en) * | 2017-08-14 | 2018-01-09 | 广州创维平面显示科技有限公司 | A kind of advertisement delivery method and system |
| CN110298671A (en) * | 2018-03-22 | 2019-10-01 | 前海哆啦阿梦（深圳）数据服务有限公司 | The monitoring system and method for e-payment |
| CN108734460A (en) * | 2018-04-02 | 2018-11-02 | 阿里巴巴集团控股有限公司 | A kind of means of payment recommends method, apparatus and equipment |
| CN109191090A (en) * | 2018-07-27 | 2019-01-11 | 阿里巴巴集团控股有限公司 | Means of payment recommended method, device, equipment and computer readable storage medium |
| CN111353094A (en) * | 2018-12-20 | 2020-06-30 | 北京嘀嘀无限科技发展有限公司 | Information pushing method and device |
| CN109711900A (en) * | 2018-12-29 | 2019-05-03 | 北京金山安全软件有限公司 | Information display method and device based on face recognition, terminal equipment and storage medium |
| WO2020133438A1 (en) * | 2018-12-29 | 2020-07-02 | 深圳市欢太科技有限公司 | Method for determining information content and related product |
| CN109858900A (en) * | 2019-01-21 | 2019-06-07 | 中国平安财产保险股份有限公司 | A kind of payment information method for pushing, device and terminal device |
| CN110049094A (en) * | 2019-02-28 | 2019-07-23 | 阿里巴巴集团控股有限公司 | The method and offline exhibition terminal of information push |
| CN110580640A (en) * | 2019-09-05 | 2019-12-17 | 大有智能科技(嘉兴)有限公司 | Information pushing and receiving method, terminal, data processing server and system |
| CN111489208A (en) * | 2020-04-17 | 2020-08-04 | 支付宝(杭州)信息技术有限公司 | Matching management method, device and processing equipment for service promotion information |
| CN111311339A (en) * | 2020-05-09 | 2020-06-19 | 支付宝(杭州)信息技术有限公司 | Target object display method and device and electronic equipment |
| CN111340575A (en) * | 2020-05-22 | 2020-06-26 | 支付宝(杭州)信息技术有限公司 | Resource pushing method and device and electronic equipment |
| CN112035736A (en) * | 2020-07-31 | 2020-12-04 | 北京达佳互联信息技术有限公司 | Information pushing method and device and server |
| CN111951047A (en) * | 2020-08-10 | 2020-11-17 | 中国平安人寿保险股份有限公司 | Advertisement effect evaluation method based on artificial intelligence, terminal and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105224075B (en) | Sensor-based mobile search, correlation technique and system | |
| KR101854431B1 (en) | Concierge robot | |
| US20190320056A1 (en) | Intuitive computing methods and systems | |
| US7174029B2 (en) | Method and apparatus for automatic selection and presentation of information | |
| JP4165095B2 (en) | Information providing apparatus and information providing method | |
| JP6267861B2 (en) | Usage measurement techniques and systems for interactive advertising | |
| CN102893327A (en) | Intuitive computing methods and systems | |
| KR101643915B1 (en) | Construction system for big data reflect regional characteristics tailored ads | |
| US20160203504A1 (en) | Game-based advertising system and method | |
| CN108494836A (en) | Information-pushing method, device and equipment | |
| CN105022773B (en) | Image processing system including picture priority | |
| CN105005982B (en) | Image procossing including Object Selection | |
| JP2009151408A (en) | Marketing data analyzing method, marketing data analysis system, data analyzing server device, and program | |
| CN105183739B (en) | Image processing method | |
| CN104376427A (en) | Urban supermarket informant distribution method | |
| TWI565339B (en) | Method for dynamic management of context awareness service to multiple users | |
| CN104484745A (en) | City supermarket information publishing system | |
| CN116684688A (en) | Live broadcast mode switching method and related device based on emotion of audience | |
| CN114638629A (en) | Information pushing method and device | |
| KR102493920B1 (en) | Apparatus and method for measuring performance of outdoor advertising | |
| CN108960904A (en) | Promotion method and system, equipment and storage medium | |
| CN111143698B (en) | Content recommendation method and system | |
| CN108573056B (en) | Content data processing method and device, electronic equipment and storage medium | |
| CN113763123A (en) | Commodity recommendation and search method, commodity recommendation and search equipment and storage medium | |
| CN108205526A (en) | A kind of method and apparatus of determining Technique Using Both Text information |
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 |