A method of determining an orientation of a tag and related apparatus

Abstract

The embodiment of the application discloses a method for determining a directional label of information and a related device. On the basis of determining a candidate directional label of information through a target group index label of a transformed object group corresponding to the information, a design variable for determining the candidate directional label is obtained. A maximum conversion rate of an information request object configured with the candidate directional label to the information is taken as an optimization target, and an optimization model is constructed through the design variable and the optimization target to determine the relationship between the design variable and the optimization target. The optimization model is solved through a constraint condition of the design variable to obtain an optimal solution of the design variable. The conversion rate of the information request object configured with the candidate directional label to the information is maximized under the condition that the design variable meets the constraint condition to find the optimal solution of the design variable. The optimal solution is used to determine a target directional label of the information, so that the target directional label can match the change of the delivery data related to the information in the history period.

Description

Technical Field

[0001] This application relates to the field of data processing, and in particular to a method and related apparatus for determining directional tags for information. Background Technology

[0002] With the rapid development of information delivery technology, intelligent targeting of information is becoming increasingly important. One method for determining targeting tags for information involves first identifying the target audience that has already been converted by the information, and then selecting the highest Target Group Index (TGI) tag for that audience as the targeting tag. Based on this, the information is then delivered to the target audience configured with the targeted tag, thereby improving the effectiveness of information delivery.

[0003] In related technologies, when statistically analyzing the converted target group, if the data for the converted target group is insufficient, it is necessary to backtrack from a fine-grained information dimension to a coarse-grained information dimension based on the corresponding backtracking information dimension, and continue to statistically analyze the converted target group until sufficient data is available; when selecting targeting tags, it is necessary to select some high TGI tags of the converted target group.

[0004] However, the above methods are not flexible enough in terms of identifying the converted target group and selecting targeting tags. The changes in the information-related delivery data over the historical period are not matched, resulting in inaccurate targeting tags and hindering the improvement of information delivery effectiveness. Summary of the Invention

[0005] To address the aforementioned technical issues, this application provides a method and related apparatus for determining targeted tags for information. The determined targeted tags are more flexible and accurate, and can match changes in information-related delivery data over historical periods, thereby improving the effectiveness of information delivery.

[0006] The embodiments of this application disclose the following technical solutions:

[0007] On the one hand, this application provides a method for determining the orientation label of information, the method comprising:

[0008] Obtain design variables for candidate targeting labels used to determine information; the candidate targeting labels are determined by the target group index labels of the converted object group corresponding to the information.

[0009] An optimization model is constructed based on the design variables and optimization objectives; the optimization objective is to maximize the conversion rate of the information request object configured with the candidate targeting labels for the information.

[0010] Determine the constraints for the design variables;

[0011] The optimization model is solved based on the constraints to obtain the optimal solution for the design variables;

[0012] The target orientation label for the information is determined based on the optimal solution.

[0013] On the other hand, this application provides an apparatus for determining the orientation label of information, the apparatus comprising: an acquisition unit, a construction unit, a determination unit, and a solution unit;

[0014] The acquisition unit is used to acquire design variables for candidate targeting labels used to determine information; the candidate targeting labels are determined by the target group index labels of the converted object group corresponding to the information.

[0015] The construction unit is used to construct an optimization model based on the design variables and the optimization objective; the optimization objective is to maximize the conversion rate of the information request object configured with the candidate targeting labels for the information.

[0016] The determining unit is used to determine the constraints of the design variables;

[0017] The solving unit is used to solve the optimization model based on the constraints to obtain the optimal solution for the design variables;

[0018] The determining unit is further configured to determine the target orientation label of the information based on the optimal solution.

[0019] On the other hand, this application provides a computer device for determining orientation tags of information, the computer device including a processor and a memory:

[0020] The memory is used to store program code and transmit the program code to the processor;

[0021] The processor is used to execute the method for determining the orientation label of the above-described aspect according to the instructions in the program code.

[0022] On the other hand, embodiments of this application provide a computer-readable storage medium for storing a computer program for executing the method for determining directional tags of information as described above.

[0023] On the other hand, embodiments of this application provide a computer program product, which includes a computer program or instructions; when the computer program or instructions are executed by a processor, the method for determining the orientation tag of information as described above is performed.

[0024] As can be seen from the above technical solution, based on determining the candidate targeting labels of the information through the target group index tags of the converted target groups corresponding to the information, design variables are obtained to determine the candidate targeting labels, so that the fixed parameters used to determine the candidate targeting labels are no longer fixed. Maximizing the conversion rate of the information requesting objects with the configured candidate targeting labels for the information is taken as the optimization objective. An optimization model is constructed through the design variables and the optimization objective to determine the relationship between the design variables and the optimization objective. First, the optimization model is solved through the constraints of the design variables to obtain the optimal solution for the design variables. This achieves the goal of maximizing the conversion rate of the information requesting objects with the configured candidate targeting labels for the information under the constraints, in order to find the optimal solution for the design variables. Then, the target targeting labels of the information are determined through the optimal solution, so that the target targeting labels can match the changes in the information-related delivery data over a historical period. Based on this, the targeting labels determined by this method are more flexible and accurate, thus improving the effectiveness of information delivery. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a schematic diagram illustrating the prediction of the matching degree between an object and information based on an artificial neural network model, as provided in an embodiment of this application.

[0027] Figure 2 A schematic diagram illustrating offline training and online prediction of an artificial neural network model provided in an embodiment of this application;

[0028] Figure 3 This is a schematic diagram illustrating the determination of the matching degree between an object and information based on a targeted tag, as provided in an embodiment of this application.

[0029] Figure 4 A schematic diagram of a targeting tag for determining information provided in an embodiment of this application;

[0030] Figure 5 A schematic diagram illustrating a TGI calculation for a tag, provided as an embodiment of this application;

[0031] Figure 6 This is a schematic diagram illustrating an application scenario of a method for determining directional tags for information provided in an embodiment of this application.

[0032] Figure 7A flowchart illustrating a method for determining orientation tags for information, provided in an embodiment of this application;

[0033] Figure 8 A schematic diagram of a device for determining information using a directional tag, as provided in an embodiment of this application;

[0034] Figure 9 This application provides a schematic diagram of the structure of a server according to an embodiment of the present application.

[0035] Figure 10 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. Detailed Implementation

[0036] The embodiments of this application will now be described with reference to the accompanying drawings.

[0037] For information delivery, intelligent targeting is crucial. The essence of intelligent targeting is delivering information to the appropriate target audience; it's like recalling information that might interest someone after they've made a request. In practical applications, artificial neural network strategies and targeted labeling strategies can be used to measure the degree of match between the target audience and the information to achieve effective information delivery.

[0038] Artificial neural network strategies utilize pre-established artificial neural network models to match objects with information, such as... Figure 1 The diagram illustrates a method for predicting the matching degree between an object and information based on an artificial neural network model. The matching degree is determined by factors such as the conversion rate of the information when the object sees it in a context. See also... Figure 2 The diagram illustrates the offline training and online prediction of an artificial neural network model. It extracts context-based object features and information features, and performs offline training by combining the object's conversion rate for information. After the object issues an information request, it searches for information features that match the context-based object features in order to recall information that the corresponding object may be interested in.

[0039] Because relying solely on artificial neural network strategies leads to information concentration and the inability to adequately expose new information, a targeted labeling strategy is considered. This involves matching the targeted labels of information with the targeted labels of objects, such as... Figure 3 The diagram illustrates a method for determining the matching degree between an object and information based on targeted tags. It determines the matching degree between tags representing the object's behavioral targeting, interest targeting, intention targeting, application installation targeting, and custom target group targeting, and tags representing the information's creative content, application identifier, converted target group, and information identifier. Based on this, such as... Figure 4The diagram illustrates a targeted label for identifying information. It suggests that the target audience corresponding to the information can be identified first, and then the high TGI label of the target audience can be selected as the targeted label.

[0040] In related technologies, for example, when the information is an advertisement, if the data on the converted target audience of the advertisement is insufficient, i.e., the number of converted target audiences is less than the preset target audience number of 50, the data is rolled back according to the preset rollback information dimensions: Advertisement -> Target (including fingerprint) -> Advertiser (including fingerprint) -> Similar / Competitor Ads -> Advertiser Industry -> Advertiser Industry, rolling back from the advertisement to the target, and continuing to count the converted target audience of the target until the number of converted target audiences is greater than or equal to the preset target audience number of 50; when selecting targeting tags, firstly through, for example... Figure 5 The diagram shown illustrates a method for calculating the TGI of a tag, based on the formula. Calculate the TGI of tags in the converted target group, that is, calculate the ratio of the proportion of tags in the converted target group to the proportion of tags in the exposed target group (click target group). Tags with larger TGI are high TGI tags. Select the 20 high TGI tags that are preset as the targeting tags of the advertisement.

[0041] However, the preset dimensions of rollback information and the preset number of targets used to count the converted target groups in the above methods, as well as the preset number of tags used to select targeting tags, are all fixed and inflexible. The changes in the information-related delivery data during the historical period do not match, resulting in inaccurate targeting tags and hindering the improvement of information delivery effectiveness.

[0042] In view of this, this application proposes a method and related apparatus for determining the targeting labels of information. The determined targeting labels are more flexible and accurate, and can match the changes in information-related delivery data over a historical period, thereby improving the effectiveness of information delivery.

[0043] The method for determining information using directional tags provided in this application can be applied to devices with data processing capabilities for determining information using directional tags, such as servers and terminal devices. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smartphone, computer, personal digital assistant (PDA), tablet computer, laptop computer, desktop computer, smart speaker, smartwatch, smart voice interaction device, smart home appliance, in-vehicle terminal, etc., but is not limited to these. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, which is not limited herein.

[0044] It is understood that, in the specific implementation of the embodiments of this application, when the converted object group is the converted user group, considering the relevant user data involved, when the embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0045] To facilitate understanding of the technical solution of this application, the method for determining the orientation label of information provided in the embodiments of this application will be introduced below in conjunction with actual application scenarios.

[0046] See Figure 6 , Figure 6 This is a schematic diagram illustrating an application scenario of a method for determining directional tags for information provided in an embodiment of this application. Figure 6 The application scenario shown includes terminal device 601 and server 602, where server 602 serves as a device for determining the orientation tag of information.

[0047] Based on the target group index label of the transformed object group corresponding to the information, the terminal device 601 inputs the design variable used to determine the candidate orientation label of the information and sends the design variable to the server 602. Then the server 602 obtains the design variable used to determine the candidate orientation label of the information.

[0048] Server 602 will maximize the conversion rate of the information request object for the configuration candidate targeting labels as the optimization goal, and build an optimization model based on design variables and optimization goals.

[0049] Server 602 determines the constraints of the design variables; solves the optimization model based on the constraints to obtain the optimal solution for the design variables; and determines the target orientation label for the information based on the optimal solution.

[0050] As can be seen, based on determining candidate targeting labels for information through the target group index tags of the converted target audience corresponding to the information, design variables are obtained to determine the candidate targeting labels, making the fixed parameters used to determine the candidate targeting labels no longer fixed. Maximizing the conversion rate of information requesters with configured candidate targeting labels for the information is taken as the optimization objective. An optimization model is constructed through the design variables and the optimization objective to determine the relationship between the design variables and the optimization objective. First, the optimization model is solved by applying the constraints of the design variables to obtain the optimal solution for the design variables. This achieves the goal of maximizing the conversion rate of information requesters with configured candidate targeting labels for the information under the constraints, thus finding the optimal solution for the design variables. Then, the target targeting label for the information is determined using the optimal solution, ensuring that the target targeting label matches the changes in information-related delivery data over historical periods. Based on this, the targeting labels determined by this method are more flexible and accurate, thereby improving the effectiveness of information delivery.

[0051] The following describes in detail the method for determining the orientation tag of information provided in the embodiments of this application, using a server as the device for determining the orientation tag of information.

[0052] See Figure 7 This figure is a flowchart of a method for determining orientation tags for information provided in an embodiment of this application. Figure 7 As shown, the method for determining the orientation tag of the information is performed by the target terminal device and includes the following steps:

[0053] S701: Obtain design variables for determining candidate targeting labels for information; candidate targeting labels are determined by the target group index labels of the converted object group corresponding to the information.

[0054] In related technologies, based on the implementation method of selecting high TGI tags of the converted target group corresponding to statistical information as the targeting tags for determining information; wherein, when counting the converted target group, if the number of converted target groups is less than the preset number of target groups, it indicates that the data of the converted target group is insufficient, and it is necessary to backtrack from the fine-grained information dimension to the coarse-grained information dimension based on the preset backtracking information dimension, and continue to count the converted target group until the data is sufficient; when selecting targeting tags, it is necessary to select a preset number of high TGI tags from the high TGI tags of the converted target group as targeting tags.

[0055] Research has revealed that the preset dimensions of rollback information and the number of preset objects used to count the converted target groups in the aforementioned technologies, as well as the number of preset tags used to select targeting tags, are all fixed. For example, when the information is an advertisement, the preset number of objects is 50, the preset rollback information dimensions are advertisement -> promotion target (including fingerprint) -> advertiser (including fingerprint) -> similar / competitive advertisement -> advertising industry -> advertiser industry, and the preset number of tags is 20. This cannot flexibly match the changes that have occurred in the information-related delivery data over a historical period, resulting in inaccurate targeting tags and hindering the improvement of information delivery effectiveness.

[0056] In this embodiment of the application, analysis shows that the preset rollback information dimension and preset number of objects used to count the converted object group, as well as the preset number of tags used to select the targeting tags, are three parameters used to determine the targeting tags of the information. In order to solve the problem that the three parameters are fixed parameters in the related technology, it is necessary to obtain the design variables of the candidate targeting tags used to determine the information based on this, so that the fixed parameters used to determine the targeting tags are no longer fixed.

[0057] Among them, the information dimension representing the information-based rollback is used as the rollback information dimension, the number of objects used to measure whether the data of the converted target group of the information dimension is sufficient is used as the object number threshold, and the number of candidate targeting tags selected from the target group index tags is used as the tag number threshold. The above rollback information dimension, object number threshold and tag number threshold are all used to determine the candidate targeting tags of the information, and any one or more of them can be used as design variables.

[0058] Therefore, this application provides a possible implementation method, in which the design variables include one or more of the following: fallback information dimension, object number threshold, and tag number threshold; the fallback information dimension represents the information dimension based on information fallback, the object number threshold is used to measure whether the data of the converted object group in the information dimension is sufficient, and the tag number threshold is used to select candidate targeting tags from TGI tags.

[0059] As an example, the design variables for obtaining candidate orientation labels used to determine information can specifically be the fallback information dimensions x1, ..., x2. k The threshold values ​​are: object number N and tag number M; k is a positive integer greater than or equal to 2, and N and M are both positive integers. The dimensions of the rollback information are x1, ..., x2. k This indicates a sequential regression from information dimension x1 to information dimension x. k The object quantity threshold N represents the number of objects sequentially from information dimension x1 to information dimension x... kWhen the number of objects in the converted object group of the information dimension is greater than or equal to N, it means that the data of the converted object group of the information dimension is sufficient. Correspondingly, when the number of objects in the converted object group of the information dimension is less than N, it means that the data of the converted object group of the information dimension is insufficient. The tag number threshold M means selecting the top M high TGI tags from the TGI tags of the converted object group with sufficient data as candidate targeting tags.

[0060] S702: Construct an optimization model based on design variables and optimization objectives; the optimization objective is to maximize the conversion rate of information request objects with configured candidate targeting labels for information.

[0061] In this embodiment of the application, after the design variables are obtained by S701, the change of the design variables causes the candidate targeting labels of the determined information to change. The conversion rate of the information request objects with different candidate targeting labels is different. In order to maximize the conversion rate of the information after the information is delivered to the object group with the candidate targeting labels, it is necessary to take maximizing the conversion rate of the information request objects with the candidate targeting labels as the optimization objective. An optimization model is constructed through the design variables and the optimization objective to determine the relationship between the design variables and the optimization objective.

[0062] As an example, based on the design variables mentioned above, an optimization model built upon the design variables and the optimization objective can be as follows:

[0063] y = G(user,f(x1,……,x) k ,N,M))

[0064] The specific calculation steps for function f are as follows:

[0065] (1) If the number of objects in the converted object group is greater than or equal to the object number threshold N, then proceed to step (k+2); otherwise proceed to step (2).

[0066] (2) For the group of converted objects in the statistical information dimension x1, if the number of objects in the group of converted objects is greater than or equal to the object number threshold N, then proceed to step (k+2); otherwise proceed to step (3).

[0067] ...

[0068] (k+1) Statistical Information Dimension x k If the number of objects in the converted object group is greater than or equal to the object number threshold N, then proceed to step (k+2); otherwise, end.

[0069] (k+2) Determine the converted target group, calculate the TGI of each tag in the converted target group, the tag with the larger TGI is the high TGI tag, and select the top M high TGI tags as candidate targeting tags for information.

[0070] The specific calculation steps for function G are as follows:

[0071] (1) Based on the candidate targeting labels obtained by the function f, determine the information request object user that is configured with the candidate targeting labels;

[0072] (2) Calculate the conversion rate of the information requesting user for the information by using historical delivery data related to the information; for example, the exposure conversion rate or the click conversion rate, etc.

[0073] S703: Determine the constraints for design variables.

[0074] In this embodiment of the application, after the optimization model is constructed by S702, considering that the optimization objective depends on the design variables, and the design variables have a certain range of limitations, that is, the design variables have the characteristics of constraints, the premise of solving the optimization model is to determine the constraints of the design variables.

[0075] In the specific implementation of S703, based on the design variables including one or more of the following parameters: fallback information dimension, object quantity threshold, and tag quantity threshold, the constraints on the determined design variables also differ depending on the specific parameters included in the design variables. See below for details:

[0076] First, when the design variables include a fallback information dimension, considering that the fallback information dimension represents the information dimension for fallback based on information, the number and priority of information dimensions for fallback based on information need to be pre-defined; therefore, the fallback information dimension includes at least two information dimensions, namely, a first information dimension and a second information dimension; and the first information dimension has a finer granularity than the second information dimension. Based on this, the feasible information dimension range of the first information dimension can be analyzed as the first selection range and the feasible information dimension range of the second information dimension as the second selection range through each information dimension in the information attribution set, information audience set, and information content set, thereby determining the constraints of the first information dimension as the first selection range and the constraints of the second information dimension as the second selection range. Therefore, this application provides a possible implementation method in which, when the design variables include a fallback information dimension, the fallback information dimension includes at least a first information dimension and a second information dimension, and the granularity of the first information dimension is smaller than the granularity of the second information dimension; S703 may include, for example, the following S7031-S7032:

[0077] S7031: Based on the information dimensions in the information attribution set, information audience set, and information content set, determine the first selection range of the first information dimension and the second selection range of the second information dimension.

[0078] Among them, the information dimension in the information attribution set refers to the object to which the information belongs, the information dimension in the information audience set refers to the audience orientation of the information, and the information dimension in the information content set refers to the content of the information itself and the product corresponding to the information.

[0079] S7032: Determine the constraint conditions of the first information dimension as the first selection range and the constraint conditions of the second information dimension as the second selection range.

[0080] As an example, when the information is an advertisement, the advertisement dimension in the advertisement attribution set can include the advertiser, advertiser group, advertiser company, industry of the advertisement, sub-industry of the advertisement, first category of the advertisement, second category of the advertisement, third category of the advertisement, region of the advertisement, operation project group of the advertisement, operation team of the advertisement, size level of the advertiser, size level of the advertiser group, and size level of the advertiser company, etc.

[0081] The advertising dimensions within the advertising audience set can include the basic targeting subset, behavioral interest targeting subset, custom target group targeting subset, and audience extension factor targeting subset. The basic targeting subset can include dimensions such as gender, age, region, occupation, education level, and salary level. The behavioral interest targeting subset can include dimensions such as installed applications, ad interaction behavior, e-commerce browsing behavior, search click behavior, news browsing behavior, and interest-based industry categories. The custom target group targeting subset can include dimensions such as public account followers, installed application audiences, product purchase customers, similar audience expansion, and relationship chain expansion. The audience extension factor targeting subset can include dimensions such as brand.

[0082] The advertising dimensions in the advertising content collection can include advertising title information, advertising image information, advertising video information, product library identifiers, product industry type, advertising creative specifications, dynamic product advertising template identifiers, backend product identifiers, customer product identifiers, customer product names, product types, core product keywords, creative identifiers, custom product tags, and external product identifiers, etc.

[0083] Second, when the design variable includes an object quantity threshold, considering that the object quantity threshold is the number of objects that measure whether the data of the converted object group in the information dimension is sufficient, the feasible value range of the object quantity threshold can be pre-set as the first value range by combining relevant statistical data on the number of objects in the historical converted object group; thus, the constraint condition of the object quantity threshold can be determined as the first value range. Therefore, this application provides a possible implementation method. When the design variable includes an object quantity threshold, S703 may include, for example, the following S7033-S7034:

[0084] S7033: Determine the first range of values ​​for the object quantity threshold based on the number of objects in the historically converted object group.

[0085] S7034: The constraint for determining the threshold number of objects is the first range of values.

[0086] As an example, the constraints for the object quantity threshold are greater than or equal to the first lower limit of 40 and less than or equal to the first upper limit of 200. When the object quantity threshold is N, 40≤N≤200.

[0087] Third, when the design variable includes a tag number threshold, considering that the tag number threshold is the number of candidate targeting tags selected from the target group index tags, a feasible range of values ​​for the tag number threshold can be pre-set as a second value range by combining relevant statistical data on the number of target group index tags of historically converted target groups; thus, the constraint condition for the tag number threshold can be determined as the second value range. Therefore, this application provides a possible implementation method. When the design variable includes a tag number threshold, S703 may include, for example, the following S7035-S7036:

[0088] S7035: Determine the second range of values ​​for the tag number threshold based on the number of target group index tags of historically converted object groups.

[0089] S7036: The constraint condition for determining the threshold number of tags is the second value range.

[0090] As an example, the constraint condition for the number of tags is that it is greater than or equal to the second lower limit of 20 and less than or equal to the second upper limit of 100. When the number of objects is M, 20≤M≤100.

[0091] S704: Solve the optimization model based on constraints to obtain the optimal solution for the design variables.

[0092] In this embodiment, after the constraints are determined in S703, the optimization model constructed in S702 can be solved under the condition that the design variables meet the constraints. That is, the conversion rate of the information request object with the optimized configuration of the candidate targeting label is maximized to find the optimal solution of the design variables. The optimal solution of the design variables obtained in this way can change with the changes in the information-related delivery data during the historical period, thereby realizing the timely updating of the design variables.

[0093] In a specific implementation of S704, when solving the optimization model, it is necessary to determine the preset optimization algorithm to be used in the solution process, so that the optimal solution for the design variables can be obtained by using the preset optimization algorithm when solving the optimization model based on the constraints. Therefore, this application provides a possible implementation method, and S704 may include, for example, the following S7041-S7042:

[0094] S7041: Determine the preset optimization algorithm.

[0095] Among the optimization algorithms, genetic algorithms and particle swarm optimization (PSO) are heuristic algorithms. In the process of finding the optimal solution, there is no need to select or specify an initial solution; the initial solution is random, and the global optimal solution can be obtained subsequently. These algorithms are more suitable for solving the optimization model constructed by S702, and either one can be selected as the preset optimization algorithm. Therefore, this application provides a possible implementation method where the preset optimization algorithm includes a genetic algorithm or a particle swarm optimization algorithm. Of course, the embodiments of this application do not limit the preset optimization algorithm to a genetic algorithm or a particle swarm optimization algorithm; the preset optimization algorithm can also be other optimization algorithms besides genetic algorithms and particle swarm optimization algorithms.

[0096] S7042: Solve the optimization model based on constraints and a preset optimization algorithm to obtain the optimal solution for the design variables.

[0097] As an example, when the information is an advertisement, the design variables are the fallback information dimensions x1, x2, x3, the object quantity threshold N, and the tag quantity threshold M. The optimal solution may include, for example, the fallback information dimensions as Advertisement -> Advertiser -> Advertiser Industry, N=60, and M=10. Compared to the preset fallback information dimensions as Advertisement -> Promotion Target (including fingerprint) -> Advertiser (including fingerprint) -> Similar / Competitor Advertisement -> Advertisement Industry -> Advertiser Industry, the preset object quantity 50, and the preset tag quantity 20, this optimal solution can change with the changes in the advertising-related delivery data over a historical period, thereby achieving the updating of design variables.

[0098] Furthermore, in this embodiment, the delivery data related to the information changes continuously over time. Therefore, solving the optimization model based on constraints is not a one-time process and needs to be repeated. Considering that it is very easy to repeat, the frequency of solving the optimization model can be limited. By using this frequency to solve the optimization model based on constraints, the optimal solution of the design variables can be dynamically updated, further improving the accuracy and real-time performance of the optimal solution of the design variables. Therefore, this application provides a possible implementation method, which further includes the following S1-S2:

[0099] S1: Determine the frequency of solving the optimization model.

[0100] S2: Solve the optimization model based on the constraints according to the solution frequency, and dynamically update the optimal solution of the design variables.

[0101] S705: Target-oriented label based on information determined by the optimal solution.

[0102] In this embodiment of the application, after obtaining the optimal solution of the design variables in S704, since the design variables are used to determine the candidate targeting labels of the information, and different design variables determine different candidate targeting labels of the information, the optimal candidate qualitative label of the information can be determined through the optimal solution of the design variables, which serves as the target targeting label of the information; the target targeting label can match the changes that have occurred in the information-related delivery data during the historical period, and thus the target targeting label is more accurate.

[0103] Furthermore, in this embodiment, after the target targeting label of the information is determined in S705, since the target targeting label can match the changes in the information-related delivery data over a historical period, that is, compared to the fixed targeting label of the information determined by fixed parameters, the target targeting label is more accurate. Therefore, the information can be delivered to the target group with the configured target targeting label, thereby improving the effectiveness of information delivery. Thus, this application provides a possible implementation method, which further includes S3: delivering the information to the target group with the configured target targeting label.

[0104] Based on this, delivering information to a target audience with configured target tags results in a higher conversion rate for the target audience compared to delivering information to a fixed audience with configured fixed tags, thus improving the effectiveness of information delivery.

[0105] The method for determining targeted tags for information provided in the above embodiments, based on determining candidate targeted tags for information through the target group index tags of the converted target group corresponding to the information, obtains design variables for determining candidate targeted tags, so that the fixed parameters used to determine candidate targeted tags are no longer fixed; maximizing the conversion rate of information request objects with configured candidate targeted tags for information is taken as the optimization objective; an optimization model is constructed through design variables and optimization objective to determine the relationship between design variables and optimization objective. First, the optimization model is solved through the constraints of the design variables to obtain the optimal solution of the design variables; under the condition that the design variables meet the constraints, the conversion rate of information request objects with configured candidate targeted tags for information is maximized to find the optimal solution of the design variables; then, the target targeted tag of the information is determined through the optimal solution, so that the target targeted tag can match the changes that have occurred in the information-related delivery data during the historical period. Based on this, the targeted tags determined by this method are more flexible and more accurate, thus better improving the effectiveness of information delivery.

[0106] In addition to the method for determining information using directional tags provided in the above embodiments, this application also provides an apparatus for determining information using directional tags.

[0107] See Figure 8 , Figure 8 This is a schematic diagram of a device for determining the orientation tag of information, provided in an embodiment of this application. Figure 8 As shown, the device 800 for determining the orientation tag of the information includes an acquisition unit 801, a construction unit 802, a determination unit 803, and a solution unit 804;

[0108] The acquisition unit 801 is used to acquire design variables for determining candidate targeting labels for information; the candidate targeting labels are determined by the target group index labels of the converted object group corresponding to the information.

[0109] Building unit 802 is used to build an optimization model based on design variables and optimization objectives; the optimization objective is to maximize the conversion rate of information request objects with configured candidate targeting labels for information.

[0110] Unit 803 is used to determine the constraints of the design variables;

[0111] Solver 804 is used to solve the optimization model based on constraints to obtain the optimal solution for the design variables;

[0112] The determining unit 803 is also used to determine the target orientation label based on the optimal solution information.

[0113] As one possible implementation, the design variables include one or more of the following: fallback information dimension, object number threshold, and tag number threshold. The fallback information dimension represents the information dimension based on the information to fall back. The object number threshold is used to measure whether the data of the converted object group in the information dimension is sufficient. The tag number threshold is used to select candidate targeting tags from the target group index tags.

[0114] As one possible implementation, when the design variables include a fallback information dimension, the fallback information dimension includes at least a first information dimension and a second information dimension, where the granularity of the first information dimension is smaller than the granularity of the second information dimension; the determining unit 803 is used for:

[0115] Based on the information dimensions in the information attribution set, information audience set, and information content set, determine the first selection range of the first information dimension and the second selection range of the second information dimension.

[0116] The constraints of the first information dimension are defined as the first selection range, and the constraints of the second information dimension are defined as the second selection range.

[0117] As one possible implementation, when the design variable includes an object quantity threshold, the determining unit 803 is used for:

[0118] Based on the number of objects in the historically transformed object group, determine the first range of values ​​for the object number threshold;

[0119] The constraint for determining the threshold number of objects is the first range of values.

[0120] As one possible implementation, when the design variable includes a label quantity threshold, the determining unit 803 is used for:

[0121] Based on the number of target group index tags of historically converted target groups, determine the second range of values ​​for the tag number threshold.

[0122] The constraint condition for determining the threshold number of tags is the second range of values.

[0123] As one possible implementation, solver 804 is used for:

[0124] Determine the preset optimization algorithm;

[0125] The optimization model is solved based on constraints and a preset optimization algorithm to obtain the optimal solution for the design variables.

[0126] As one possible implementation method, the preset optimization algorithm includes genetic algorithm or particle swarm optimization algorithm.

[0127] As one possible implementation, the determining unit 803 is also used for:

[0128] Determine the solution frequency of the optimization model;

[0129] The device also includes an update unit;

[0130] The update unit is used to solve the optimization model based on the constraints according to the solution frequency, and dynamically update the optimal solution of the design variables.

[0131] As one possible implementation, the device also includes a dispensing unit;

[0132] The delivery unit is used to deliver information to the target audience with configured target targeting tags.

[0133] The apparatus for determining targeted tags for information provided in the above embodiments, based on determining candidate targeted tags for information through the target group index tags of the converted target group corresponding to the information, obtains design variables for determining candidate targeted tags, so that the fixed parameters used to determine candidate targeted tags are no longer fixed; maximizing the conversion rate of information request objects with configured candidate targeted tags for information is taken as the optimization objective; an optimization model is constructed through design variables and optimization objective to determine the relationship between design variables and optimization objective. First, the optimization model is solved through the constraints of the design variables to obtain the optimal solution of the design variables; it is achieved by maximizing the conversion rate of information request objects with configured candidate targeted tags for information under the condition that the design variables meet the constraints, in order to find the optimal solution of the design variables; then, the target targeted tag for information is determined through the optimal solution, so that the target targeted tag can match the changes that have occurred in the information-related delivery data during the historical period. Based on this, the targeted tags determined by this method are more flexible and more accurate, thereby improving the effectiveness of information delivery.

[0134] This application also provides a device for determining the orientation tag of information. The computer device provided in this application will be described below from the perspective of hardware physicalization.

[0135] See Figure 9 , Figure 9This is a schematic diagram of a server structure provided in an embodiment of this application. The server 900 can vary significantly due to different configurations or performance. It may include one or more central processing units (CPUs) 922 (e.g., one or more processors) and memory 932, and one or more storage media 930 (e.g., one or more mass storage devices) for storing application programs 942 or data 944. The memory 932 and storage media 930 can be temporary or persistent storage. The program stored in the storage media 930 may include one or more modules (not shown in the diagram), each module may include a series of instruction operations on the server. Furthermore, the CPU 922 may be configured to communicate with the storage media 930 and execute the series of instruction operations in the storage media 930 on the server 900.

[0136] Server 900 may also include one or more power supplies 926, one or more wired or wireless network interfaces 950, one or more input / output interfaces 958, and / or one or more operating systems 941, such as Windows Server. TM Mac OS X TM Unix TM Linux TM FreeBSD TM etc.

[0137] The steps performed by the server in the above embodiments can be based on this Figure 9 The server structure shown.

[0138] CPU 922 is used to perform the following steps:

[0139] Obtain design variables for candidate targeting labels to determine information; candidate targeting labels are determined by the target group index labels of the converted target group corresponding to the information.

[0140] An optimization model is constructed based on design variables and optimization objectives; the optimization objective is to maximize the conversion rate of information request objects with configured candidate targeting labels for information.

[0141] Determine the constraints for the design variables;

[0142] The optimization model is solved based on the constraints to obtain the optimal solution for the design variables;

[0143] The target-oriented label is determined based on the optimal solution.

[0144] In addition to the method for determining the orientation tag of information described above, this application also provides a terminal device for determining the orientation tag of information, so that the above method for determining the orientation tag of information can be implemented and applied in practice.

[0145] See Figure 10 , Figure 10 This is a schematic diagram of a terminal device provided in an embodiment of this application. For ease of explanation, only the parts related to the embodiment of this application are shown; for specific technical details not disclosed, please refer to the method section of the embodiment of this application. The terminal device can be any terminal device including mobile phones, tablets, PDAs, etc. Taking a mobile phone as an example:

[0146] Figure 10 This diagram illustrates a partial structural representation of a mobile phone related to the terminal device provided in this embodiment. (Reference) Figure 10 The mobile phone includes components such as a radio frequency (RF) circuit 1010, a memory 1020, an input unit 1030, a display unit 1040, a sensor 1050, an audio circuit 1060, a wireless Fidelity (WiFi) module 1070, a processor 1080, and a power supply 1090. Those skilled in the art will understand that... Figure 10 The mobile phone structure shown does not constitute a limitation on the mobile phone and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0147] The following is combined Figure 10 A detailed introduction to each component of a mobile phone:

[0148] The RF circuit 1010 can be used for receiving and transmitting signals during information transmission or calls. Specifically, it receives downlink information from the base station and processes it with the processor 1080; additionally, it transmits uplink data to the base station. Typically, the RF circuit 1010 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low-noise amplifier (LNA), and a duplexer. Furthermore, the RF circuit 1010 can also communicate wirelessly with networks and other devices. The aforementioned wireless communication can use any communication standard or protocol, including but not limited to Global System for Mobile Communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, and Short Messaging Service (SMS).

[0149] The memory 1020 can be used to store software programs and modules. The processor 1080 runs the software programs and modules stored in the memory 1020 to realize various functions and data processing of the mobile phone. The memory 1020 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, applications required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory 1020 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0150] The input unit 1030 can be used to receive input numerical or character information, and to generate key signal inputs related to user settings and function control of the mobile phone. Specifically, the input unit 1030 may include a touch panel 1031 and other input devices 1032. The touch panel 1031, also known as a touch screen, can collect touch operations performed by the user on or near it (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near the touch panel 1031), and drive the corresponding connection devices according to a pre-set program. Optionally, the touch panel 1031 may include two parts: a touch detection device and a touch controller. The touch detection device detects the user's touch position and the signal generated by the touch operation, and transmits the signal to the touch controller; the touch controller receives touch information from the touch detection device, converts it into touch point coordinates, and sends it to the processor 1080, and can also receive and execute commands sent by the processor 1080. In addition, the touch panel 1031 can be implemented using various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch panel 1031, the input unit 1030 may also include other input devices 1032. Specifically, other input devices 1032 may include, but are not limited to, one or more of the following: physical keyboard, function keys (such as volume control buttons, power buttons, etc.), trackball, mouse, joystick, etc.

[0151] The display unit 1040 can be used to display information input by the user or information provided to the user, as well as various menus of the mobile phone. The display unit 1040 may include a display panel 1041, which may optionally be configured as a Liquid Crystal Display (LCD), Organic Light-Emitting Diode (OLED), or similar display panel. Furthermore, a touch panel 1031 may cover the display panel 1041. When the touch panel 1031 detects a touch operation on or near it, it transmits the information to the processor 1080 to determine the type of touch event. Subsequently, the processor 1080 provides corresponding visual output on the display panel 1041 based on the type of touch event. Although in Figure 10 In this embodiment, the touch panel 1031 and the display panel 1041 are two separate components to realize the input and output functions of the mobile phone. However, in some embodiments, the touch panel 1031 and the display panel 1041 can be integrated to realize the input and output functions of the mobile phone.

[0152] The mobile phone may also include at least one sensor 1050, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor. The ambient light sensor can adjust the brightness of the display panel 1041 according to the ambient light level, and the proximity sensor can turn off the display panel 1041 and / or the backlight when the phone is moved to the ear. As a type of motion sensor, an accelerometer sensor can detect the magnitude of acceleration in various directions (generally three axes). When stationary, it can detect the magnitude and direction of gravity and can be used for applications that recognize the phone's posture (such as landscape / portrait switching, related games, magnetometer posture calibration), vibration recognition-related functions (such as pedometer, taps), etc. Other sensors that may be configured in the mobile phone, such as gyroscopes, barometers, hygrometers, thermometers, and infrared sensors, will not be described in detail here.

[0153] The audio circuit 1060, speaker 1061, and microphone 1062 provide an audio interface between the user and the mobile phone. The audio circuit 1060 converts the received audio data into electrical signals and transmits them to the speaker 1061, where the speaker 1061 converts them into sound signals for output. On the other hand, the microphone 1062 converts the collected sound signals into electrical signals, which are then received by the audio circuit 1060, converted into audio data, and then processed by the processor 1080 before being transmitted via the RF circuit 1010 to, for example, another mobile phone, or the audio data can be output to the memory 1020 for further processing.

[0154] WiFi is a short-range wireless transmission technology. Through the WiFi module 1070, mobile phones can help users send and receive emails, browse web pages, and access streaming media, providing users with wireless broadband internet access. Although Figure 10 The WiFi module 1070 is shown, but it is understood that it is not an essential component of a mobile phone and can be omitted as needed without changing the essence of the invention.

[0155] The processor 1080 is the control center of the mobile phone, connecting various parts of the phone through various interfaces and lines. It executes various functions and processes data by running or executing software programs and / or modules stored in the memory 1020 and calling data stored in the memory 1020. Optionally, the processor 1080 may include one or more processing units; preferably, the processor 1080 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 1080.

[0156] The mobile phone also includes a power supply 1090 (such as a battery) that supplies power to various components. Preferably, the power supply can be logically connected to the processor 1080 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system.

[0157] Although not shown, mobile phones may also include a camera, Bluetooth module, etc., which will not be described in detail here.

[0158] In this embodiment of the application, the memory 1020 included in the mobile phone can store program code and transmit the program code to the processor.

[0159] The processor 1080 included in the mobile phone can execute the method for determining information using the orientation tag provided in the above embodiments according to the instructions in the program code.

[0160] This application also provides a computer-readable storage medium for storing a computer program for executing the method for determining information using a directional tag provided in the above embodiments.

[0161] This application also provides a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. A processor of a device for determining the orientation tag of information reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the device for determining the orientation tag of information to perform the method for determining the orientation tag of information provided in the various optional implementations of the above aspects.

[0162] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium can be at least one of the following media: read-only memory (ROM), RAM, magnetic disk, or optical disk, etc., and other media capable of storing program code.

[0163] It should be noted that the various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for the device and system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiments. The device and system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of the solution in this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0164] The above description is merely one specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for determining orientation tags for information, characterized in that, The method includes: Design variables are obtained to determine candidate targeting labels for information; the candidate targeting labels are determined by the target group index labels of the converted target group corresponding to the information; the design variables include one or more of the following: fallback information dimension, object number threshold, and label number threshold; the fallback information dimension represents the information dimension for fallback based on the information, the object number threshold is used to measure whether the data of the converted target group of the information dimension is sufficient, and the label number threshold is used to select the candidate targeting labels from the target group index labels; An optimization model is constructed based on the design variables and optimization objectives; the optimization objective is to maximize the conversion rate of the information request object configured with the candidate targeting labels for the information. Determine the constraints for the design variables; The optimization model is solved based on the constraints to obtain the optimal solution for the design variables; The target orientation label for the information is determined based on the optimal solution.

2. The method according to claim 1, characterized in that, When the design variable includes the fallback information dimension, the fallback information dimension includes at least a first information dimension and a second information dimension, and the granularity of the first information dimension is smaller than the granularity of the second information dimension; the constraints for determining the design variable include: Based on the information dimensions in the information attribution set, information audience set, and information content set, determine the first selection range of the first information dimension and the second selection range of the second information dimension; The constraint condition for the first information dimension is determined as the first selection range, and the constraint condition for the second information dimension is determined as the second selection range.

3. The method according to claim 1, characterized in that, When the design variable includes the object quantity threshold, the constraints for determining the design variable include: Based on the number of objects in the historically transformed object group, a first range of values ​​for the object quantity threshold is determined; The constraint condition for determining the threshold number of objects is the first value range.

4. The method according to claim 1, characterized in that, When the design variable includes the label quantity threshold, the constraints for determining the design variable include: Based on the number of target group index tags of historically converted object groups, a second range of values ​​for the tag number threshold is determined. The constraint condition for determining the threshold number of tags is the second value range.

5. The method according to any one of claims 1-4, characterized in that, The step of solving the optimization model based on the constraints to obtain the optimal solution for the design variables includes: Determine the preset optimization algorithm; The optimization model is solved based on the constraints and the preset optimization algorithm to obtain the optimal solution for the design variables.

6. The method according to claim 5, characterized in that, The preset optimization algorithm includes a genetic algorithm or a particle swarm optimization algorithm.

7. The method according to any one of claims 1-4, characterized in that, The method further includes: Determine the solution frequency of the optimization model; The optimization model is solved according to the stated solution frequency and based on the stated constraints, and the optimal solution of the design variables is dynamically updated.

8. The method according to any one of claims 1-4, characterized in that, The method further includes: The information is delivered to the target group configured with the target targeting label.

9. A device for determining the orientation of information using a directional tag, characterized in that, The device includes: an acquisition unit, a construction unit, a determination unit, and a solution unit; The acquisition unit is used to acquire design variables for determining candidate targeting labels for information; the candidate targeting labels are determined by the target group index labels of the converted object group corresponding to the information; the design variables include one or more of the following: fallback information dimension, object number threshold, and label number threshold; the fallback information dimension represents the information dimension for fallback based on the information, the object number threshold is used to measure whether the data of the converted object group of the information dimension is sufficient, and the label number threshold is used to select the candidate targeting labels from the target group index labels; The construction unit is used to construct an optimization model based on the design variables and the optimization objective; the optimization objective is to maximize the conversion rate of the information request object configured with the candidate targeting labels for the information. The determining unit is used to determine the constraints of the design variables; The solving unit is used to solve the optimization model based on the constraints to obtain the optimal solution for the design variables; The determining unit is further configured to determine the target orientation label of the information based on the optimal solution.

10. The apparatus according to claim 9, characterized in that, When the design variable includes the fallback information dimension, the fallback information dimension includes at least a first information dimension and a second information dimension, wherein the granularity of the first information dimension is smaller than the granularity of the second information dimension; the determining unit is used for: Based on the information dimensions in the information attribution set, information audience set, and information content set, determine the first selection range of the first information dimension and the second selection range of the second information dimension; The constraint condition for the first information dimension is determined as the first selection range, and the constraint condition for the second information dimension is determined as the second selection range.

11. The apparatus according to claim 9, characterized in that, When the design variable includes the object quantity threshold, the determining unit is used to: Based on the number of objects in the historically transformed object group, a first range of values ​​for the object quantity threshold is determined; The constraint condition for determining the threshold number of objects is the first value range.

12. The apparatus according to claim 9, characterized in that, When the design variable includes the label quantity threshold, the determining unit is used to: Based on the number of target group index tags of historically converted object groups, a second range of values ​​for the tag number threshold is determined. The constraint condition for determining the threshold number of tags is the second value range.

13. The apparatus according to any one of claims 9-12, characterized in that, The solving unit is used for: Determine the preset optimization algorithm; The optimization model is solved based on the constraints and the preset optimization algorithm to obtain the optimal solution for the design variables.

14. The apparatus according to claim 13, characterized in that, The preset optimization algorithm includes a genetic algorithm or a particle swarm optimization algorithm.

15. The apparatus according to any one of claims 9-12, characterized in that, The determining unit is further configured to: Determine the solution frequency of the optimization model; The device further includes: The update unit is used to solve the optimization model based on the constraints according to the solution frequency, and dynamically update the optimal solution of the design variables.

16. The apparatus according to any one of claims 9-12, characterized in that, The device further includes: The delivery unit is used to deliver the information to the target group configured with the target targeting tag.

17. A computer device, characterized in that, The device includes a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is configured to execute the method for determining information using a directional tag as described in any one of claims 1-8, according to instructions in the program code.

18. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program for performing the method of determining the orientation tag of information as described in any one of claims 1-8.

19. A computer program product, characterized in that, Includes a computer program or instructions; when the computer program or instructions are executed by a processor, the method for determining the orientation tag of information as described in any one of claims 1-8 is performed.

Images