Data Promotion Method, Device, Equipment and Storage Medium

Abstract

The present application discloses a data promotion method, apparatus, device, and storage medium. The method includes: when a data promotion request is detected, classifying the data promotion request to obtain a classification result; determining the promotion channel pointed to by the classification result, and determining a target promotion strategy corresponding to the data promotion request according to the promotion channel; and performing targeted promotion processing on the data content corresponding to the data promotion request according to the target promotion strategy. The present application solves the technical problem in the prior art of performing data promotion by oneself with low promotion efficiency.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology in fintech, and particularly to a data promotion method, device, equipment, and storage medium. Background Art

[0002] With the continuous development of fintech, especially Internet technology finance, more and more technologies are applied in the financial field. However, the financial industry also poses higher requirements for technologies. For example, the financial industry also has higher requirements for data promotion.

[0003] Currently, it is often necessary to promote data such as advertisements. In the existing promotion process, enterprises, merchants, factories, etc. all promote by themselves. Self-promotion lacks pertinence, the promotion effect is not ideal, and resource consumption is high. The promotion convenience is difficult to meet the requirements. That is, there is a technical problem of low efficiency in data promotion such as advertisement content promotion in the existing technology. Summary of the Invention

[0004] The main purpose of this application is to provide a data promotion method, device, equipment, and storage medium, aiming to solve the technical problem of low promotion efficiency in self-conducted data promotion in the existing technology.

[0005] To achieve the above object, this application provides a data promotion method, and the data promotion method includes:

[0006] When a data promotion request is detected, classify the data promotion request to obtain a classification result;

[0007] Determine the promotion channel pointed to by the classification result, and determine the target promotion strategy corresponding to the data promotion request according to the promotion channel;

[0008] According to the target promotion strategy, perform targeted promotion processing on the data content corresponding to the data promotion request.

[0009] Optionally, the step of performing targeted promotion processing on the data content corresponding to the data promotion request according to the target promotion strategy includes:

[0010] Determine the target user of the data content corresponding to the data promotion request;

[0011] According to the target promotion strategy, push the data content corresponding to the data promotion request to the target user.

[0012] Optionally, the step of determining the target user of the data content corresponding to the data promotion request includes:

[0013] Obtain user data and input the user data into a preset recognition model to perform semantic encoding on the user data to obtain a user feature representation variable, where the preset recognition model is obtained by iterative training based on a preset federated process;

[0014] Calculate the user similarity result corresponding to the user feature representation variable, and generate a candidate set of similar users based on the similarity result and the data content corresponding to the data promotion request;

[0015] Obtain the target user based on the candidate set of similar users.

[0016] Optionally, the user feature representation variable includes a first feature representation and a second feature representation, and the preset recognition model includes a scoring model.

[0017] The step of calculating the user similarity result corresponding to the user feature representation variable includes:

[0018] Calculate the inner product of the first feature representation and the second feature representation to obtain data to be processed;

[0019] Input the data to be processed into the scoring model to score each candidate user corresponding to the user feature representation variable to obtain the user similarity result.

[0020] Optionally, the step of determining the promotion channel pointed to by the classification result and determining the target promotion strategy corresponding to the data promotion request according to the promotion channel includes:

[0021] Determine the promotion channel pointed to by the classification result, and determine whether there is bidding information for promotion positions in the promotion channel;

[0022] If there is bidding information for promotion positions in the promotion channel, determine the target promotion strategy corresponding to the data promotion request according to the target traffic carried in the data promotion request.

[0023] Optionally, the step of determining the target promotion strategy corresponding to the data promotion request according to the target traffic carried in the data promotion request includes:

[0024] Obtain the offline area to be covered pointed to by the data promotion request and the target traffic carried;

[0025] Obtain the traffic population types and traffic sizes in each time period corresponding to the offline area to be covered;

[0026] Determine the promotion time period corresponding to the data promotion request according to the traffic volume in each time period and the target traffic volume, and determine the promotion form corresponding to the data promotion request according to the traffic population type;

[0027] Set the promotion time period and the promotion form as the target promotion strategy.

[0028] Optionally, after the step of performing targeted promotion processing on the data content corresponding to the data promotion request according to the promotion channel, it includes:

[0029] Obtain the target click data of the data content that is greater than the preset click volume, and extract the same policy information in the target click data;

[0030] Perform feedback adjustment on the target promotion strategy based on the same policy information.

[0031] This application also provides a data promotion device, and the data promotion device includes:

[0032] A classification module, configured to classify the data promotion request when detecting a data promotion request, and obtain a classification result;

[0033] A determination module, configured to determine the promotion channel pointed to by the classification result, and determine the target promotion strategy corresponding to the data promotion request according to the promotion channel;

[0034] A promotion module, configured to perform targeted promotion processing on the data content corresponding to the data promotion request according to the target promotion strategy.

[0035] Optionally, the promotion module includes:

[0036] A first determination unit, configured to determine the target user of the data content corresponding to the data promotion request;

[0037] A first push unit, configured to push the data content corresponding to the data promotion request to the target user according to the target promotion strategy.

[0038] Optionally, the first determination unit includes:

[0039] A first acquisition subunit, configured to acquire user data, and input the user data into a preset recognition model to perform semantic encoding on the user data to obtain a user feature representation variable, where the preset recognition model is obtained by iterative training based on a preset federated process;

[0040] A calculation subunit, configured to calculate a user similarity result corresponding to the user feature representation variable, and generate a candidate set of similar users based on the similarity result and the data content corresponding to the data promotion request;

[0041] A second acquisition subunit, configured to obtain the target user based on the candidate set of similar users.

[0042] Optionally, the user feature representation variable includes a first feature representation and a second feature representation, and the preset recognition model includes a scoring model.

[0043] The calculation subunit is configured to:

[0044] Calculate the inner product of the first feature representation and the second feature representation to obtain data to be processed;

[0045] Input the data to be processed into the scoring model to score each candidate user corresponding to the user feature representation variable, and obtain the user similarity result.

[0046] Optionally, the determination module includes:

[0047] A second determination unit, configured to determine the promotion channel pointed to by the classification result, and determine whether there is bidding information for promotion positions in the promotion channel;

[0048] A third determination unit, configured to, when there is bidding information for promotion positions in the promotion channel, determine the target promotion strategy corresponding to the data promotion request according to the target traffic carried in the data promotion request.

[0049] Optionally, the third determination unit includes:

[0050] A third acquisition subunit, configured to acquire the offline area to be covered pointed to by the data promotion request and the target traffic carried;

[0051] A fourth acquisition subunit, configured to acquire the traffic population types and the traffic sizes in each time period corresponding to the offline area to be covered;

[0052] A determination subunit, configured to determine the promotion time period corresponding to the data promotion request according to the traffic sizes in each time period and the target traffic, and determine the promotion form corresponding to the data promotion request according to the traffic population types;

[0053] A setting subunit, configured to set the promotion time period and the promotion form as the target promotion strategy.

[0054] Optionally, the data promotion device further includes:

[0055] An acquisition module, configured to acquire target click data of the data content that is greater than a preset click volume, and extract the same policy information from the target click data;

[0056] An adjustment module, configured to perform feedback adjustment on the target promotion strategy based on the same policy information.

[0057] This application also provides a data promotion device, which is a physical device. The data promotion device includes: a memory, a processor, and a program of the data promotion method stored on the memory and executable on the processor. When the program of the data promotion method is executed by the processor, the steps of the data promotion method as described above can be implemented.

[0058] This application also provides a storage medium, on which a program for implementing the above data promotion method is stored. When the program of the data promotion method is executed by a processor, the steps of the data promotion method as described above are implemented.

[0059] In this application, when a data promotion request is detected, the data promotion request is classified to obtain a classification result; the promotion channel pointed to by the classification result is determined, and the target promotion strategy corresponding to the data promotion request is determined according to the promotion channel; according to the target promotion strategy, targeted promotion processing is performed on the data content corresponding to the data promotion request. Compared with the prior art where merchants promote data by themselves, the present invention uniformly receives promotion requests from merchants, and based on different classification results of the promotion requests, different promotion channels and corresponding different target promotion strategies are adopted for targeted promotion of corresponding data content. This means overcomes the deficiencies of the prior art in promoting data by themselves, such as lack of pertinence, low promotion convenience, and high resource consumption, which in turn lead to low efficiency in promoting data such as advertising content promotion, and improves the data promotion efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The accompanying drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with this application, and are used together with the specification to explain the principles of this application.

[0061] In order to more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following will briefly introduce the accompanying drawings required for describing the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0062] Figure 1 It is a schematic flowchart of the first embodiment of the data promotion method of this application;

[0063] Figure 2Schematic diagram of the refinement steps for generating adversarial data of the first data in the data promotion method of this application;

[0064] Figure 3 Schematic diagram of the device structure of the hardware operating environment involved in the solution of the embodiment of this application;

[0065] Figure 4 Schematic diagram of the scenario of the data promotion method of this application.

[0066] The realization of the purpose, functional features and advantages of this application will be further described with reference to the embodiments and the accompanying drawings. Detailed implementation manners

[0067] It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit this application.

[0068] The embodiment of this application provides a data promotion method. In the first embodiment of the data promotion method of this application, referring to Figure 1 , the data promotion method includes:

[0069] Step S10, when a data promotion request is detected, classify the data promotion request to obtain a classification result;

[0070] Step S20, determine the promotion channel pointed to by the classification result, and determine the target promotion strategy corresponding to the data promotion request according to the promotion channel;

[0071] Step S30, according to the target promotion strategy, perform targeted promotion processing on the data content corresponding to the data promotion request.

[0072] The specific steps are as follows:

[0073] Step S10, when a data promotion request is detected, classify the data promotion request to obtain a classification result;

[0074] In this embodiment, it should be noted that the data promotion method can be applied to a data promotion system. This data promotion system belongs to a data promotion device. For the data promotion system, it has a communication connection relationship with institutions such as enterprises, merchants, factories, etc. Therefore, when institutions such as enterprises, merchants, factories, etc. have advertising promotion needs, they can register and log in to the data promotion system and generate advertising promotion needs. The data promotion system receives the advertising promotion needs and processes the advertising promotion needs.

[0075] Among them, the data promotion system also communicates with online media, online official accounts, online websites, offline physical video service applications, search service applications, customer service systems, search promotion systems, etc., such as Figure 4As shown, that is, the data promotion system, as an intermediary, connects enterprises, merchants, etc. Specifically, when merchants, factories, etc. have advertising promotion needs, the data promotion system receives the advertising promotion needs and determines whether there are corresponding data idle positions, such as corresponding idle advertising positions, in various online media, online official accounts, online websites, offline entities, customer service systems, search promotion systems, etc. If there are corresponding idle advertising positions, based on the corresponding idle advertising positions and the corresponding advertising promotion needs, determine promotion forms, promotion timings, etc., so as to perform targeted promotion processing on the promotion content corresponding to the data promotion request.

[0076] It should be noted that the data promotion system can have user data of all online media, online official accounts, online websites, offline entities, etc., and the user data between these different online media, online official accounts, online websites, offline entities, etc. are not interconnected with each other.

[0077] When a data promotion request is detected, classify the data promotion request to obtain a classification result. The purpose of classifying the data promotion request is to perform targeted processing based on the merchant's demand type and at the same time realize the orderly management of the promotion request.

[0078] When a data promotion request is detected, the ways to classify the data promotion request to obtain a classification result include:

[0079] Way 1: When a data promotion request is detected, classify the data promotion request based on the product type and service type to obtain a classification result;

[0080] Specifically, for example, if what needs to be promoted is a product, then classify the data promotion request into the first category, and if what needs to be promoted is a service, then classify the data promotion request into the second category. Among them, the type of the data promotion request can be further subdivided according to the specific type of the product or service.

[0081] Way 2: When a data promotion request is detected, classify the data promotion request based on the target site to be promoted to obtain a classification result.

[0082] Specifically, for example, if the target site to be promoted is an online website, then classify the data promotion request into the first category, if the target site to be promoted is an official account, then classify the data promotion request into the second category, and if the target site to be promoted is an offline building area, then classify the data promotion request into the third category, etc.

[0083] It should be noted that in this embodiment, the data promotion request carries content such as the promotion product type, promotion requirements, promotion time period, promotion target traffic, promotion result, promotion cost, etc.

[0084] Among them, the ways to determine the promoted product type, promotion requirements, promotion time period, target traffic for promotion, promotion results, promotion costs, etc. can be: manual input by the merchant or selection by the merchant on the data promotion system based on existing options.

[0085] Step S20: Determine the promotion channels pointed to by the classification result, and determine the target promotion strategy corresponding to the data promotion request according to the promotion channels.

[0086] In this embodiment, taking the classification of the data promotion request based on the target site to be promoted to obtain a classification result as an example for specific description, after obtaining the classification result, determine the promotion channels pointed to by the classification result. Specifically, the promotion channels can be types such as WeChat official accounts, WeChat Moments, website videos, blogger text promotions, offline videos, offline advertising slogans, etc. After obtaining the promotion channels, determine the target promotion strategy corresponding to the data promotion request according to the promotion channels. Among them, the promotion strategy includes promotion form, promotion timing, promotion creativity, promotion mode, etc.

[0087] Step S30: Perform targeted promotion processing on the data content corresponding to the data promotion request according to the target promotion strategy.

[0088] In this embodiment, perform targeted promotion processing on the data content corresponding to the data promotion request according to the target promotion strategy. Specifically, push the data content corresponding to the data promotion request to the target users according to the target promotion strategy to achieve targeted promotion.

[0089] Among them, the step of performing targeted promotion processing on the data content corresponding to the data promotion request according to the target promotion strategy includes:

[0090] Step S31: Determine the target users of the data content corresponding to the data promotion request.

[0091] In this embodiment, first determine the target users of the data content corresponding to the data promotion request, and then the content can be promoted targeted.

[0092] Among them, the ways to determine the target users of the data content corresponding to the data promotion request include:

[0093] Method 1: Obtain similar content of the data content corresponding to the data promotion request, and determine the target users based on the users of the similar content.

[0094] Method 2: The step of determining the target users of the data content corresponding to the data promotion request includes:

[0095] Step S311: Obtain user data and input the user data into a preset recognition model to perform semantic encoding on the user data and obtain a user feature representation variable, where the preset recognition model is obtained through iterative training based on a preset federated process;

[0096] In this embodiment, it should be noted that the user data includes all users who have been connected to the data promotion system through a certain channel. Specifically, the user data includes first-type user data from users to items and second-type user data from users to users. Among them, both the first-type user data and the second-type user data include user tags, where the user tags are used to identify the types of users. For example, using the number 1 to identify a user as a first-type user and using the number 0 to identify a user as a second-type user, etc. And both the first-type user data and the second-type user data are represented by large sparse vectors (one-hot encoding). Among them, the first-type user data records the data of the target user regarding items. For example, the rating of the target user for a movie, the click volume of the target user on a certain web page, etc. The second-type user data records the data of the target user regarding other users to be selected. For example, the number of times the target user and the user to be selected jointly click on a certain web page, the number of the same TV series watched by the target user and the user to be selected, etc. The user feature representation corresponding to the user feature representation variable can be represented by a string of real numbers. The user feature representation can uniquely represent a certain thing. The user feature representation variable is usually to convert a large sparse vector into a low-dimensional space representation that retains semantic relationships. For example, assuming that a certain sparse vector is 010000000000000 and represents that the user's click volume on a certain web page is 10 times, the user feature representation variable can be set to the real number 10 to represent that the user's click volume on a certain web page is 10 times. That is, perform semantic encoding on the sparse vector and convert the large sparse vector into a low-dimensional space representation that retains semantic relationships. Specifically, the means of encoding can be: obtain user data and input the user data into a preset recognition model to perform semantic encoding on the user data and obtain a user feature representation variable, where the preset recognition model is obtained through iterative training based on a preset federated process. That is, the preset recognition model has been trained.

[0097] Among them, the preset recognition model is obtained through the preset federated process to perform iterative training by combining multi-party data, and then obtain a first user feature representation variable corresponding to the first-type user data and a second user feature representation variable corresponding to the second-type user data. That is, obtain the user feature representation variable.

[0098] Step S312: Calculate the user similarity result corresponding to the user feature representation variable, and generate a candidate set of similar users based on the similarity result and the data content corresponding to the data promotion request;

[0099] In this embodiment, the user similarity is the degree of similarity between users. Calculate the user similarity result corresponding to the user feature representation variable, and generate a candidate set of similar users based on the similarity result and the data promotion request. Specifically, first determine a reference user based on the data content corresponding to the data promotion request. Based on the user feature representation variable, use the scoring model to score each candidate user corresponding to the reference user to obtain the candidate user scores corresponding to each candidate user. The higher the candidate user score, the higher the user similarity between the reference user and the candidate user. Then, based on the candidate user scores, sort each candidate user to obtain a list of candidate users, that is, obtain the user similarity result, and select the candidate set of similar users from the list of candidate users.

[0100] The user feature representation variable includes a first feature representation and a second feature representation, and the preset recognition model includes a scoring model.

[0101] The step of calculating the user similarity result corresponding to the user feature representation variable includes:

[0102] Step A1: Calculate the inner product of the first feature representation and the second feature representation to obtain data to be processed;

[0103] In this embodiment, it should be noted that the inner product is a vector operation. For example, assume that the first feature representation is (a, b, c) and the second feature representation is (A, B, C). Then the inner product of the first feature representation and the second feature representation is Aa + Bb + Cc, that is, the data to be input is Aa + Bb + Cc.

[0104] Step A2: Input the data to be processed into the scoring model to score each candidate user corresponding to the user feature representation variable to obtain the user similarity result.

[0105] In this embodiment, the to-be-processed data is input into the scoring model to calculate the similarity of each user, obtain a similarity result, and generate a candidate set of similar users based on the similarity result. Specifically, the to-be-processed data is input into the scoring model to calculate the similarity between the reference user and each to-be-selected user through a preset similarity calculation method, and then score each to-be-selected user to obtain the similarity score corresponding to each to-be-selected user. Based on each similarity score, to-be-selected users with similarity scores lower than the preset similarity score threshold are excluded from each to-be-selected user, and then the remaining to-be-selected features are sorted to obtain a list of to-be-selected users, that is, the user similarity result is obtained.

[0106] Step S313, obtain the target user based on the candidate set of similar users.

[0107] For example, select the top 10,000 to-be-selected users with the highest scores in the to-be-selected user list to form the candidate set of similar users, and set the candidate set of similar users as the target user.

[0108] Step S32, push the data content corresponding to the data promotion request to the target user according to the target promotion strategy.

[0109] Push the data content corresponding to the data promotion request to the target user according to the target promotion strategy.

[0110] In this application, when a data promotion request is detected, the data promotion request is classified to obtain a classification result; the promotion channel pointed to by the classification result is determined, and the target promotion strategy corresponding to the data promotion request is determined according to the promotion channel; according to the target promotion strategy, targeted promotion processing is performed on the data content corresponding to the data promotion request. Compared with the prior art where merchants promote data independently, the present invention uniformly receives promotion requests from merchants and, based on different classification results of the promotion requests, adopts different promotion channels and corresponding different target promotion strategies to perform targeted promotion of the corresponding data content. This means overcomes the deficiencies in the prior art, such as the lack of pertinence in the independent promotion of data by enterprises, merchants, and factories, low promotion convenience, high resource consumption, and thus low efficiency in data promotion such as advertising content promotion, and improves the data promotion efficiency.

[0111] Further, based on the first embodiment of this application, another embodiment is provided. In this embodiment, the step of determining the promotion channel pointed to by the classification result and determining the target promotion strategy corresponding to the data promotion request according to the promotion channel includes:

[0112] Step B1, determine the promotion channels pointed to by the classification result, and determine whether there is tender information for promotion positions in the promotion channels;

[0113] In this embodiment, it is necessary to first determine whether there is tender information for promotion positions in the promotion channels pointed to by the classification result to avoid the situation where the data promotion request cannot be processed in a timely manner after being received.

[0114] Step B2, if there is tender information for promotion positions in the promotion channel, determine the target promotion strategy corresponding to the data promotion request according to the target traffic carried in the data promotion request.

[0115] Only when there is tender information for promotion positions in the promotion channel, determine the target promotion strategy corresponding to the data promotion request according to the target traffic carried in the data promotion request.

[0116] The step of determining the target promotion strategy corresponding to the data promotion request according to the target traffic carried in the data promotion request includes:

[0117] Step C1, obtain the offline area to be covered pointed to by the data promotion request and the target traffic carried;

[0118] In this embodiment, it is a specific way to determine the target promotion strategy. First, obtain the offline area to be covered pointed to by the data promotion request and the target traffic carried. For example, the offline area to be covered is the elevator TV promotion area of certain determined buildings in first-tier cities, and the target traffic carried is preset, specifically it can be a.

[0119] Step C2, obtain the types of traffic people in each time period corresponding to the offline area to be covered, and the traffic volume in each time period;

[0120] Step C3, determine the promotion time period corresponding to the data promotion request according to the traffic volume in each time period and the target traffic, and determine the promotion form corresponding to the data promotion request according to the type of traffic people;

[0121] Obtain the types of traffic people in each time period corresponding to the offline area to be covered. For example, the types of people can be young people or children. Obtain the traffic volume in each time period corresponding to the offline area to be covered. For example, the throughput of the people in the building elevator in each time period.

[0122] Determine the promotion time period corresponding to the data promotion request according to the traffic volume in each time period and the target traffic. For example, if the target traffic is 2,000 people and the traffic volume of the elevator TV promotion area in a building during the working hours is 6,000 people, the promotion time period can be one-third of the working hours. Determine the promotion form corresponding to the data promotion request according to the traffic population type. Specifically, if the traffic population type is young people, the promotion form can be the most popular creative form at present.

[0123] Step C4, set the promotion time period and the promotion form as the target promotion strategy.

[0124] Set the promotion time period and the promotion form as the target promotion strategy. In particular, set it as the offline target promotion strategy.

[0125] In this embodiment, determining the target promotion strategy corresponding to the data promotion request according to the target traffic carried in the data promotion request further includes:

[0126] Method 1:

[0127] Obtain the online section pointed to by the data promotion request and the target traffic carried;

[0128] Obtain the traffic population type corresponding to the online section and the node traffic volume;

[0129] Determine the promotion node time period corresponding to the data promotion request according to the node traffic volume and the target traffic, and determine the promotion form corresponding to the data promotion request according to the traffic population type;

[0130] Set the promotion node time period and the promotion form as the target promotion strategy.

[0131] The above target promotion strategy can be applied to website promotion.

[0132] In this embodiment, determining the target promotion strategy corresponding to the data promotion request according to the target traffic carried in the data promotion request further includes:

[0133] Method 2:

[0134] Obtain the public account type pointed to by the data promotion request and the target traffic carried;

[0135] Obtain the traffic population type corresponding to the public account type and the public account follow-up volume;

[0136] Determine the official account promotion node corresponding to the data promotion request according to the number of followers of the official account and the target traffic, and determine the promotion form corresponding to the data promotion request according to the type of traffic population;

[0137] Set the official account promotion node and the promotion form as the target promotion strategy.

[0138] The above target promotion strategy can be applied to the promotion of WeChat sites.

[0139] In this embodiment, determining the target promotion strategy corresponding to the data promotion request according to the target traffic carried in the data promotion request further includes:

[0140] Method 3:

[0141] Obtain the media type pointed to by the data promotion request and the target traffic carried;

[0142] Obtain the type of traffic population corresponding to the media type and the size of media attention;

[0143] Determine the media promotion node corresponding to the data promotion request according to the size of media attention and the target traffic, and determine the promotion form corresponding to the data promotion request according to the type of traffic population;

[0144] Set the media promotion node and the promotion form as the target promotion strategy.

[0145] The above target promotion strategy can be applied to the promotion of media sites.

[0146] In this embodiment, the target promotion strategy can also be applied to video promotion applications, search engines, etc., and no specific examples are given here.

[0147] In this embodiment, by determining the promotion channel pointed to by the classification result, determine whether there is bidding information for promotion positions in the promotion channel; if there is bidding information for promotion positions in the promotion channel, determine the target promotion strategy corresponding to the data promotion request according to the target traffic carried in the data promotion request. In this embodiment, the target promotion strategy is accurately determined.

[0148] Further, based on the first embodiment and the second embodiment in the present application, after the step of performing targeted promotion processing on the data content corresponding to the data promotion request according to the promotion channel, it includes:

[0149] Step D1, obtain the target click data of the data content that is greater than the preset click volume, and extract the same strategy information in the target click data;

[0150] In this embodiment, the same data content can have different promotion forms and different promotion channels. After promotion, various click data of the data content corresponding to the data promotion request are also obtained, such as click data of different promotion forms for the same promotion content, or click data of different promotion channels for the same promotion content. Target click data greater than a preset click volume of the data content is obtained, and the same policy information in the target click data is extracted. For example, the policy information of the target click data greater than the preset click volume is all through a certain promotion form.

[0151] Step D2: Perform feedback adjustment on the target promotion strategy based on the same policy information.

[0152] Perform feedback adjustment on the target promotion strategy based on the same policy information. For example, if the policy information of the target click data greater than the preset click volume is all through promotion form b, then adjust the data content of other promotion forms to this promotion form b.

[0153] In this embodiment, by obtaining target click data greater than a preset click volume of the data content, the same policy information in the target click data is extracted; and feedback adjustment is performed on the target promotion strategy based on the same policy information. In this embodiment, feedback adjustment is performed on the target promotion strategy to improve the promotion efficiency.

[0154] Refer to Figure 3 , Figure 3 It is a schematic diagram of the device structure of the hardware operating environment involved in the solution of the embodiment of the present application.

[0155] As Figure 3 shown, the data promotion device may include: a processor 1001, such as a CPU, a memory 1005, and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between the processor 1001 and the memory 1005. The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0156] Optionally, the data promotion device may further include a rectangular user interface, a network interface, a camera, an RF (Radio Frequency) circuit, sensors, an audio circuit, a WiFi module, etc. The rectangular user interface may include a display screen (Display) and an input sub-module such as a keyboard (Keyboard). Optionally, the rectangular user interface may further include a standard wired interface and a wireless interface. The network interface may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0157] Those skilled in the art can understand that Figure 3 the structure of the data promotion device shown in Figure 3 does not constitute a limitation on the data promotion device, and it may include more or fewer components than shown in the figure, or combine some components, or have different component arrangements.

[0158] As Figure 3 shown, in the memory 1005 as a storage medium, it may include an operating system, a network communication module, and a data promotion program. The operating system is a program that manages and controls the hardware and software resources of the data promotion device, and supports the operation of the data promotion program and other software and / or programs. The network communication module is used to implement communication between the components inside the memory 1005, as well as communication with other hardware and software in the data promotion system.

[0159] In Figure 3 the data promotion device shown in Figure 3 , the processor 1001 is used to execute the data promotion program stored in the memory 1005 to implement the steps of the data promotion method described in any one of the above.

[0160] The specific implementation manners of the data promotion device of this application are basically the same as those of the above embodiments of the data promotion method, and will not be elaborated here.

[0161] This application also provides a data promotion device, which includes:

[0162] a classification module, configured to classify the data promotion request when detecting a data promotion request, and obtain a classification result;

[0163] a determination module, configured to determine the promotion channel pointed to by the classification result, and determine the target promotion strategy corresponding to the data promotion request according to the promotion channel;

[0164] a promotion module, configured to perform targeted promotion processing on the data content corresponding to the data promotion request according to the target promotion strategy.

[0165] Optionally, the promotion module includes:

[0166] a first determination unit, configured to determine the target user of the data content corresponding to the data promotion request;

[0167] a first push unit, configured to push the data content corresponding to the data promotion request to the target user according to the target promotion strategy.

[0168] Optionally, the first determination unit includes:

[0169] A first acquisition subunit, configured to acquire user data and input the user data into a preset recognition model to perform semantic encoding on the user data, so as to obtain a user feature representation variable, where the preset recognition model is obtained by iterative training based on a preset federated process;

[0170] A calculation subunit, configured to calculate a user similarity result corresponding to the user feature representation variable, and generate a candidate set of similar users based on the similarity result and the data content corresponding to the data promotion request;

[0171] A second acquisition subunit, configured to obtain the target user based on the candidate set of similar users.

[0172] Optionally, the user feature representation variable includes a first feature representation and a second feature representation, and the preset recognition model includes a scoring model.

[0173] The calculation subunit is configured to:

[0174] Calculate the inner product of the first feature representation and the second feature representation to obtain data to be processed;

[0175] Input the data to be processed into the scoring model to score each candidate user corresponding to the user feature representation variable, so as to obtain the user similarity result.

[0176] Optionally, the determination module includes:

[0177] A second determination unit, configured to determine the promotion channel pointed to by the classification result, and determine whether there is bidding information for promotion positions in the promotion channel;

[0178] A third determination unit, configured to, when there is bidding information for promotion positions in the promotion channel, determine the target promotion strategy corresponding to the data promotion request according to the target traffic carried in the data promotion request.

[0179] Optionally, the third determination unit includes:

[0180] A third acquisition subunit, configured to acquire the offline area to be covered pointed to by the data promotion request and the target traffic carried;

[0181] A fourth acquisition subunit, configured to acquire the traffic population types and traffic sizes in each time period corresponding to the offline area to be covered;

[0182] A determination subunit, configured to determine the promotion time period corresponding to the data promotion request according to the traffic sizes in each time period and the target traffic, and determine the promotion form corresponding to the data promotion request according to the traffic population types.

[0183] A sub-unit is provided for setting the promotion time period and the promotion form as the target promotion strategy.

[0184] Optionally, the data promotion device further includes:

[0185] An acquisition module for acquiring target click data of the data content that is greater than a preset click volume, and extracting the same strategy information from the target click data;

[0186] An adjustment module for performing feedback adjustment on the target promotion strategy based on the same strategy information.

[0187] The specific implementation manner of the data promotion device of the present application is basically the same as that of the above-mentioned embodiments of the data promotion method, and will not be elaborated herein.

[0188] The embodiments of the present application provide a storage medium, and the storage medium stores one or more programs, and the one or more programs can also be executed by one or more processors to be used to implement the steps of the data promotion method described in any one of the above.

[0189] The specific implementation manner of the storage medium of the present application is basically the same as that of the above-mentioned embodiments of the data promotion method, and will not be elaborated herein.

[0190] It should be noted that in this article, the terms "include", "comprise" or any other variant thereof are intended to cover a non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the phrase "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the element.

[0191] The serial numbers of the above-mentioned embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0192] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation manner. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc), and includes several instructions for causing a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0193] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be similarly included in the patent protection scope of the present invention.

Claims

1. A data promotion method, characterized in that, The data promotion method includes: When a data promotion request is detected, classify the data promotion request to obtain a classification result; Determine the promotion channel pointed to by the classification result, and determine the target promotion strategy corresponding to the data promotion request according to the promotion channel; The step of determining the promotion channel pointed to by the classification result and determining the target promotion strategy corresponding to the data promotion request according to the promotion channel includes: Determine the promotion channel pointed to by the classification result, and determine whether there is bidding information for promotion positions in the promotion channel to avoid being unable to process the data promotion request after receiving it; When there is bidding information for promotion positions in the promotion channel, determine the target promotion strategy corresponding to the data promotion request according to the target traffic carried in the data promotion request; According to the target promotion strategy, perform targeted promotion processing on the data content corresponding to the data promotion request.

2. The data promotion method according to claim 1, wherein The step of performing targeted promotion processing on the data content corresponding to the data promotion request according to the target promotion strategy includes: Determine the target users of the data content corresponding to the data promotion request; According to the target promotion strategy, push the data content corresponding to the data promotion request to the target users.

3. The data promotion method according to claim 2, wherein The step of determining the target users of the data content corresponding to the data promotion request includes: Obtain user data, and input the user data into a preset recognition model to perform semantic encoding on the user data to obtain a user feature representation variable, where the preset recognition model is obtained by iterative training based on a preset federated process; Calculate the user similarity result corresponding to the user feature representation variable, and generate a candidate set of similar users based on the similarity result and the data content corresponding to the data promotion request; Obtain the target users based on the candidate set of similar users.

4. The data promotion method according to claim 3, characterized in that The user feature representation variable includes a first feature representation and a second feature representation, and the preset recognition model includes a scoring model. The step of calculating the user similarity result corresponding to the user feature representation variable includes: Calculate the inner product of the first feature representation and the second feature representation to obtain data to be processed; Input the data to be processed into the scoring model to score each user to be selected corresponding to the user feature representation variable, and obtain the user similarity result.

5. The data promotion method according to claim 1, wherein The step of determining the target promotion strategy corresponding to the data promotion request according to the target traffic carried in the data promotion request includes: Obtain the offline area to be covered pointed to by the data promotion request and the target traffic carried; Obtain the traffic population types and traffic sizes in each time period corresponding to the offline area to be covered; According to the traffic sizes in each time period and the target traffic, determine the promotion time period corresponding to the data promotion request, and according to the traffic population type, determine the promotion form corresponding to the data promotion request; Set the promotion time period and the promotion form as the target promotion strategy.

6. The data promotion method according to claim 1, wherein After the step of performing targeted promotion processing on the data content corresponding to the data promotion request according to the promotion channel, the following steps are included: Obtain target click data of the data content that is greater than a preset click volume, and extract the same policy information from the target click data; Based on the same policy information, perform feedback adjustment on the target promotion strategy.

7. A data promotion device, characterized in that, The data promotion device includes: A classification module, configured to classify the data promotion request when detecting a data promotion request, and obtain a classification result; A determination module, configured to determine the promotion channel pointed to by the classification result, and determine the target promotion strategy corresponding to the data promotion request according to the promotion channel; The determination module includes: A second determination unit, configured to determine the promotion channel pointed to by the classification result, and determine whether there is tender information for a promotion position in the promotion channel, so as to avoid being unable to process after receiving a data promotion request; A third determination unit, configured to, when there is tender information for a promotion position in the promotion channel, determine the target promotion strategy corresponding to the data promotion request according to the target traffic carried in the data promotion request; A promotion module, configured to perform targeted promotion processing on the data content corresponding to the data promotion request according to the target promotion strategy.

8. A data promotion device, characterized in that, The data promotion device includes: a memory, a processor, and a program stored on the memory for implementing the data promotion method, The memory is used to store a program for implementing the data promotion method; The processor is configured to execute the program for implementing the data promotion method to implement the steps of the data promotion method according to any one of claims 1 to 6.

9. A storage medium, characterized in that, A program for implementing the data promotion method is stored on the storage medium, and the program for implementing the data promotion method is executed by the processor to implement the steps of the data promotion method according to any one of claims 1 to 6.

Images