Method and apparatus for determining a delivery target, electronic device, and storage medium

Abstract

The application discloses a method and device for determining a delivery object, electronic equipment and a storage medium. The method comprises the following steps: obtaining a product to be delivered corresponding to an advertisement activity to be created; determining the detail information corresponding to the product to be delivered based on a preset database; performing text splitting processing on the detail information corresponding to the product to be delivered, and determining a set of delivery objects corresponding to the product to be delivered. Thus, the delivery object is quickly determined based on the key data corresponding to the product to be delivered in the preset database, the requirement for the experience of a merchant is reduced, the operation difficulty is reduced, and the operation efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of advertising data processing technology, and more specifically, to a method, apparatus, electronic device, and storage medium for determining the target audience. Background Technology

[0002] E-commerce platforms provide a platform for users and merchants to conduct online transactions. Users can enter relevant keywords of the products they want to buy on the e-commerce platform to find the products they need; merchants can set corresponding keywords for their products to create advertisements and promote their products so that when users enter keywords, the products can appear in a prominent position on the display page. Therefore, the selection of keywords is particularly important.

[0003] However, when creating ads, the search for keywords relies heavily on the merchant's experience, making the process difficult. Summary of the Invention

[0004] In view of the above problems, the present invention proposes a method, apparatus, electronic device and storage medium for determining the target of delivery.

[0005] In a first aspect, embodiments of this application provide a method for determining the target audience, the method comprising: obtaining the product to be placed corresponding to the advertising campaign to be created; determining the detailed information corresponding to the product to be placed based on a preset database; and performing text splitting processing on the detailed information corresponding to the product to be placed to determine the target audience set corresponding to the product to be placed.

[0006] Secondly, this application also provides a device for determining the target audience, which includes: a product acquisition module for acquiring products to be delivered corresponding to an advertising campaign to be created; an information determination module for determining the details of the products to be delivered based on a preset database; and a delivery determination module for performing text splitting processing on the details of the products to be delivered to determine the target audience set corresponding to the products to be delivered.

[0007] Thirdly, embodiments of this application also provide an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the object determination method as described in the first aspect above.

[0008] Fourthly, embodiments of this application also provide a computer-readable storage medium storing program code that can be called by a processor to execute the object determination method as described in the first aspect above.

[0009] The technical solution provided by this invention specifically includes: obtaining the products to be advertised corresponding to the advertising campaign to be created; determining the detailed information of the products to be advertised based on a preset database; and performing text splitting processing on the detailed information of the products to be advertised to determine the target audience set corresponding to the products to be advertised. Thus, the target audience can be quickly determined based on the key data corresponding to the products to be advertised in the preset database, reducing the requirement for merchant experience, reducing operational difficulty, and improving operational efficiency. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments and drawings obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0011] Figure 1 A flowchart illustrating a method for determining delivery targets provided in an embodiment of this application is shown.

[0012] Figure 2 A schematic diagram of the structure of a target determination device provided in an embodiment of this application is shown.

[0013] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown.

[0014] Figure 4 A schematic diagram of the structure of a computer-readable storage medium provided in an embodiment of this application is shown. Detailed Implementation

[0015] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0016] E-commerce platforms provide a platform for users and merchants to conduct online transactions. Users can enter relevant keywords of the products they want to buy on the e-commerce platform to find the products they need; merchants can set corresponding keywords for their products to create advertisements and promote their products so that when users enter keywords, the products can appear in a prominent position on the display page. Therefore, the selection of keywords is particularly important.

[0017] However, when creating ads, the search for keywords relies heavily on the merchant's experience, making the process difficult.

[0018] To address the aforementioned technical problems, the inventors have proposed a method, apparatus, electronic device, and storage medium for determining advertising targets, as provided in this application. The method includes: acquiring products to be advertised corresponding to an advertising campaign to be created; determining detailed information corresponding to the products to be advertised based on a preset database; and performing text splitting processing on the detailed information corresponding to the products to be advertised to determine the target audience set corresponding to the products to be advertised. Thus, by quickly determining the target audience based on key data corresponding to the products to be advertised in a preset database, the requirement for merchant experience is reduced, operational difficulty is decreased, and operational efficiency is improved.

[0019] Please refer to the following steps for specific implementation details.

[0020] Please see Figure 1 , Figure 1 The illustration shows a flowchart of a method for determining a delivery target according to an embodiment of this application. The method may include steps 110 to 130.

[0021] In step 110, the products to be launched corresponding to the advertising campaign to be created are obtained.

[0022] Users can create advertising campaigns on e-commerce platforms. In the embodiments of this application, the advertising campaign to be created is an example of an SP (Sponsored Products) advertisement, and the e-commerce platform is an example of the Amazon platform.

[0023] Among them, the products to be launched are the products that need to be promoted in the advertising campaign to be created.

[0024] When creating an ad to be delivered, users select the product to be delivered. For example, they can enter the ASIN (Amazon Standard Identification Number) code of the product to be delivered.

[0025] In step 120, based on a preset database, the detailed information corresponding to the product to be launched is determined.

[0026] In some implementations, the preset database may include product-related information, such as details, brand information, price information, star rating, category information, and ranking information.

[0027] The information in the default database can be obtained from the application programming interface (API) and report data provided by the e-commerce platform, or from the user's account information provided by the user on the e-commerce platform.

[0028] Users can pre-authorize the use of their e-commerce platform account information. The system can retrieve relevant information from the e-commerce platform system backend data associated with the user's account and save it to a preset database.

[0029] In some implementations, each product has a unique code, which allows information corresponding to that product to be found in a pre-defined database. For example, the product's detailed information can be retrieved from the pre-defined database based on its code.

[0030] The detailed information includes the product's title and description. A pre-set database can be used to find the corresponding product details page, where the title and description can be found.

[0031] Step 130: Perform text splitting on the details information of the product to be launched to determine the target audience set corresponding to the product.

[0032] In the embodiments of this application, the text splitting process includes splitting the details into individual objects, combining the individual objects into multiple delivery objects, and finally determining the delivery object set corresponding to the product to be delivered.

[0033] In some implementations, the method of splitting the detailed information into text and determining the target audience includes the following steps.

[0034] (1) Split the details into multiple objects with different preset word lengths.

[0035] (2) All the objects obtained from the splitting are assigned to the object set.

[0036] In some implementations, the title information is split into individual objects, and these individual objects are combined into objects of different word lengths and categorized into a set of delivery objects.

[0037] For example, if the title is "Strip Light Style", it can be broken down into individual objects "Strip", "Light", and "Style", and then combined into objects of different word lengths. For instance, combining individual objects into an object with a word length of 3 results in the object "Strip Light Style", which belongs to the target audience set; similarly, combining individual objects into an object with a word length of 2 results in the objects "Strip Light" and "Light Style", which are added to the target audience set.

[0038] In some implementations, the description information is split into multiple objects with different preset word lengths; and individual objects are combined into objects with different word lengths and categorized into a delivery object set.

[0039] For example, the description "RGB Color Changing LED Lights for home" can be broken down into individual objects: "RGB", "Color", "Changing", "LED", "Lights", "for", and "home". These individual objects can then be combined into objects of varying word lengths. For instance, combining individual objects into objects with a word length of 5 results in the set of objects "RGB Color Changing LED Lights", "Color Changing LED Lights for", and "Changing LEDLights for home". Similarly, combining individual objects into objects with a word length of 4 results in the set of objects "RGB Color Changing LED", "Color Changing LED Lights", "Changing LEDLights for", and "LED Lights for home".

[0040] In some implementations, the steps involve splitting the details into multiple objects of different preset word lengths; including the following steps.

[0041] (a) Filter the details.

[0042] (b) Split the filtered details into multiple objects with different preset word lengths.

[0043] In some implementations, the details can be filtered before splitting.

[0044] For example, special characters in the details information can be filtered out first. Special characters include commas, spaces, pause marks, parentheses, etc.

[0045] For example, part-of-speech analysis and semantic analysis can be used to filter the details information, such as filtering out prepositions, articles, conjunctions and interjections in the details information.

[0046] Further breaking down the filtered details can make the resulting objects more readable or reliable.

[0047] In some implementations, the target audience set can be displayed to the user by showing it on the ad creation interface.

[0048] In other implementations, when displaying the target product, other key information about the product to be advertised can also be displayed, such as price, star rating, number of reviews, average, maximum and minimum listing duration, etc., so that users can pay attention to the market situation of the product to be advertised and make horizontal comparisons.

[0049] In some implementations, the method for determining the delivery target provided in this application embodiment further includes the following steps.

[0050] (1) Based on brand analysis data and the advertising metrics of each advertising target in the target audience set corresponding to the product to be advertised, classify each advertising target in the target audience set corresponding to the product to be advertised.

[0051] (2) Determine the advertising campaign recommendation results based on the classification results of the target audience corresponding to the products to be advertised.

[0052] In the foregoing embodiments, by segmenting the details information, the system helps users determine the target audience set corresponding to the product to be advertised. Users can then select from the provided target audience set, reducing the need for merchant experience and simplifying the process. However, given the large number of target audiences in the set, to further assist users in selecting target audiences, the target audience determination method provided in this application embodiment can also categorize each target audience using brand analysis data to determine the recommended advertising results and assist users in selecting target audiences. This will be explained in detail below.

[0053] Brand analytics data is analytical data provided by e-commerce platforms. It includes the search objects entered by users through the e-commerce platform, the number of searches for the search objects, and the ranking of the search objects after sorting by the number of searches. Users can obtain brand analytics data provided by the e-commerce platform backend through their accounts and store it in a preset database.

[0054] In some implementations, brand analysis data for a preset time period can be obtained. For example, brand analysis data for the most recent week can be obtained.

[0055] By inputting an object into a pre-defined database, you can obtain information about that object in the brand analytics data, such as whether it exists in the brand analytics data, the corresponding product, the product's click-through rate, and the object's ranking. Taking the e-commerce platform Amazon as an example, the brand analytics data is Amazon Brand Analytics (ABA).

[0056] The metrics for ad placement are the inherent attributes of the ad placement itself. For example, ad placement metrics include the word frequency of each ad placement in the ad placement set, the word length of each ad placement, and the brand information of the product to which each ad placement belongs.

[0057] Among them, word frequency represents the frequency of the target object appearing in the target object set; for example, if the target object "RGBlight" appears 3 times in the target object set, then the word frequency of the target object "RGB light" is 3 times.

[0058] The word length of the target audience represents the length of the words contained in the target audience; for example, the target audience "RGB light" contains two words.

[0059] The brand information of the product corresponding to the target audience indicates the company name or product name, etc. The brand information can be queried in a preset database through the product's corresponding code information.

[0060] In some implementations, the steps involve classifying the target audience based on brand analytics data and the target audience's metrics, including: determining the target audience category for each target audience based on its keyword frequency, keyword length, and corresponding brand information.

[0061] In some implementations, the targeting categories include at least one of long-tail object categories, attribute object categories, and brand object categories. More specifically, this is further explained below with reference to Table 1, the targeting category allocation table.

[0062] Table 1 - Distribution Category Allocation Table

[0063]

[0064] If the target audience does not exist in the brand analysis data, and the target audience's keyword frequency is greater than the target quantity and the target audience's keyword length is greater than or equal to the first preset keyword length, then the target audience is determined to belong to the long-tail target audience category.

[0065] Alternatively, if the target audience exists in the brand analysis data and the keyword length of the target audience is greater than or equal to the first preset keyword length, then the target audience is determined to be a long-tail target audience; where the target quantity is the number of products to be targeted.

[0066] Alternatively, if the target audience exists in the brand analysis data, and the text information of the target audience contains preset attribute words and the word length of the target audience is less than or equal to the second preset word length, then the target audience is determined to belong to the attribute object class. The second preset word length is less than the first preset word length; the preset attribute words can be words that reflect the attributes of the candidate object, such as "APP", "RGB", or "number + ft".

[0067] Alternatively, if the text information of the target object contains brand information, then the candidate object is determined to belong to the brand object class.

[0068] In some implementations, the targeting category may also include a traffic object category, which refers to the targeting objects that rank high in the brand analysis data. For example, if the preset traffic ranking is 1000, then the targeting objects ranked within the top 1000 in the brand analysis data can be classified as traffic object categories.

[0069] In some implementations, the targeting category may also include other object categories, which are targeting objects whose corresponding word frequency is less than the target number and do not exist in the brand analysis data; and targeting objects whose corresponding text information does not contain preset attribute words, whose corresponding word length is less than or equal to the first preset word length and exist in the brand analysis data.

[0070] In some implementations, the recommended targeting results include the target audience and the corresponding targeting category. These recommended targeting results can be displayed on the ad creation interface to assist users in selecting target audiences.

[0071] In other implementations, the recommendation results may also include other information about the target audience, such as the word length and word frequency of the target audience.

[0072] In some other implementations, the ad placement recommendations can also be sorted according to the ranking of the target audience in the brand analytics data, such as by ranking order, so that users can understand the ranking of the target audience.

[0073] In some implementations, the categorization results for some poorly performing advertisers may not be displayed in the ad placement recommendation results. For example, if an advertiser does not exist in the brand analysis data or ranks low in the brand analysis data, these poorly performing advertisers can be filtered out, thereby providing users with more valuable ad placement categorization results.

[0074] In some implementations, the method for determining the target audience provided in this application further includes: determining the competing products corresponding to the product to be advertised based on brand analysis data and the target audience corresponding to the product to be advertised; wherein, the competing products do not include the product to be advertised.

[0075] To help users more comprehensively determine their target audience, information about competing products can be used to assist users in identifying these competitors.

[0076] In some implementations, users can also manually input the competing products corresponding to the product to be advertised, but this may not be comprehensive. To more comprehensively and accurately determine the competing products corresponding to the product to be advertised, in the embodiments of this application, brand analysis data and the target audience corresponding to the product to be advertised are used to help users obtain competing products. Specifically, the steps for determining the competing products corresponding to the product to be advertised based on brand analysis data and the target audience corresponding to the product to be advertised include the following steps.

[0077] (1) Select the target audience corresponding to the product to be launched that exists in the brand analysis data as the screening target.

[0078] (2) In the brand analysis data, determine the search products corresponding to each filter object.

[0079] (3) Based on the attention metrics of the search products corresponding to each filter object, identify the competing products in the search products corresponding to each filter object.

[0080] In the embodiments of this application, the advertising targets corresponding to the product to be advertised that exist in the brand analysis data can be used as the filtering targets first. Advertising targets that do not appear in the brand analysis data or are ranked lower are considered to be advertising targets with no traffic or low traffic, and their role in subsequent filtering of competing products is small.

[0081] In brand analytics data, each filter object corresponds to multiple search products, and different search products have corresponding attention metrics.

[0082] The metrics to be monitored may include, but are not limited to, clicks, impressions, and orders, in order to measure the effectiveness of the selected targets in advertising the search products.

[0083] Furthermore, based on the metrics of interest, search products with better campaign performance can be selected as competing products.

[0084] For example, if the focus metric is click-through rate, the search products with click-through rates ranking in a preset position among the search products corresponding to each filter object can be considered as competing products. The preset position can be selected according to actual needs; for example, the top three search products can be selected.

[0085] In this way, each screening target can identify multiple competing products, and all competing products corresponding to the screening targets are used as competing products corresponding to the product to be launched.

[0086] Furthermore, when there are a large number of screening targets, the number of identified competing products is also large, resulting in a large amount of data that needs to be processed. In order to obtain competing products that have a greater impact on the products to be launched, the steps can include the following steps: Based on the attention indicators of the search products corresponding to each screening target, the competing products are identified in the search products corresponding to each screening target.

[0087] (1) Based on the attention metrics of the search products corresponding to each filter object, determine the products to be determined for each filter object.

[0088] (2) Based on the ranking of the screening objects corresponding to the products to be determined in the brand analysis data, a preset number of products to be determined are selected as competing products.

[0089] Specifically, based on the attention metrics of the search products corresponding to each filter object, search products with better advertising performance can be selected as candidates for final selection. For example, search products ranked at a preset position can be selected as candidates for final selection based on the ranking of attention metrics.

[0090] Different filter objects may correspond to duplicate products to be identified. When duplicate products exist, filtering can be performed. Specifically, filtering can be based on the ranking of the filter object corresponding to the product to be identified in the brand analysis data. For example, products to be identified corresponding to filter objects with lower rankings can be filtered out. For instance, if the product to be identified corresponding to filter object A is P, and the product to be identified corresponding to filter object B is also P, but filter object A ranks higher than filter object B in the brand analysis data, then the product to be identified corresponding to filter object B with a lower ranking, P, can be filtered out.

[0091] Therefore, there are no duplicate products among the filtered products to be determined. The products to be determined can be sorted according to the ranking of the corresponding filter objects in the brand analysis data. The higher the ranking of the corresponding filter objects, the higher the ranking of the products to be determined. When the data of the competing products to be screened is limited, the products can be screened according to the ranking. For example, when only a preset number of competing products are screened, the top preset number of products to be determined can be used as competing products. In this way, the competing products with the greatest reference value to the products to be launched can be screened from the products to be determined.

[0092] In some implementations, the method for determining the delivery target provided in this application embodiment further includes the following steps.

[0093] (1) Based on the preset database, determine the detailed information of competing products.

[0094] (2) The detailed information of competing products is split into text to determine the target audience for competing products.

[0095] The target audience determined by splitting and processing the details of competing products can also be used as the target audience when creating an advertising campaign for the product to be advertised. Therefore, the target audience for competing products can also be determined simultaneously for users to choose from.

[0096] Specifically, the method for processing the text of the details of competing products is similar to the steps for the products to be launched. For details, please refer to the specific description in the foregoing embodiments, which will not be repeated here.

[0097] In some implementations, once competing products are identified, the detailed information corresponding to the competing products can be automatically split into text.

[0098] In some implementations, once competing products are identified, the detailed information corresponding to those products can be broken down in response to user triggers. For example, an analytics control can be included on the advertising campaign creation page. When a user has a need, they can click the analytics control, thereby triggering the breakdown of the detailed information corresponding to the competing products in response to the user's action on the analytics control.

[0099] In some implementations, the method for determining the delivery target provided in this application embodiment further includes the following steps.

[0100] (1) Based on brand analysis data and the advertising metrics of each advertising target in the advertising target set corresponding to the competing products, each advertising target in the advertising target set corresponding to the competing products is classified.

[0101] (2) Update the advertising campaign recommendation results based on the classification results of the target audience corresponding to competing products.

[0102] Specifically, the method for classifying and processing the target audience of competing products is similar to the steps for products to be launched. For details, please refer to the specific description in the foregoing embodiments, which will not be repeated here.

[0103] In the embodiments of this application, the classification results of the target audience for competing products are merged with the classification results of the target audience for the product to be advertised, thereby updating the advertising recommendation results for the advertising campaign to be created.

[0104] Specifically, the steps involve updating the advertising campaign's placement recommendations based on the classification results of the target audience corresponding to competing products, including the following steps.

[0105] (1) Select the target audiences that are different from those in the target audience recommendation results for competing products as the target audiences to be updated.

[0106] (2) Add the classification results of the objects to be updated to the delivery recommendation results to update the delivery recommendation results.

[0107] Among them, the target audience that is the same as the target audience recommendation result does not need to be updated again. The target audience corresponding to the competing products that is different from the target audience recommendation result is taken as the target audience to be updated, and the classification result of the target audience to be updated is added to the target audience recommendation result, thereby updating the target audience recommendation result.

[0108] Understandably, users can further identify competing products based on the target audience and the recommended results, thereby continuously providing users with more target audiences and recommended results. For example, if users want to identify more target audiences for reference, they can trigger the analysis button to further perform text splitting and classification processing on the competing products. The specific selection can be made according to actual needs, and this application does not impose any restrictions on this.

[0109] Please see Figure 2 This application provides a target determination device 200, which includes a product acquisition module 210, an information determination module 220, and a target determination module 230.

[0110] Product acquisition module 210 is used to acquire products to be deployed corresponding to the advertising campaign to be created.

[0111] The information determination module 220 is used to determine the detailed information corresponding to the product to be launched based on a preset database;

[0112] The delivery determination module 230 is used to perform text splitting processing on the details information of the product to be delivered, and to determine the delivery target set corresponding to the product to be delivered.

[0113] In some embodiments, the target determination device 200 further includes a classification processing module and a target recommendation module.

[0114] The classification processing module is used to classify each target in the target set corresponding to the product to be launched based on brand analysis data and the target metrics of each target in the target set corresponding to the product to be launched.

[0115] The ad placement recommendation module is used to determine the ad placement recommendation results for advertising campaigns based on the classification results of the target audience corresponding to the products to be advertised.

[0116] In some implementations, the target determination device 200 further includes a competition determination module.

[0117] The competition determination module is used to determine the competing products corresponding to the product to be launched based on brand analysis data and the target audience set corresponding to the product to be launched; among them, the competing products do not include the product to be launched.

[0118] In some implementations, the competition determination module includes a filtering unit, a search unit, and a competition unit.

[0119] The filtering unit is used to select the target audience corresponding to the products to be advertised from the brand analysis data.

[0120] The search unit is used to identify the search products corresponding to each filter object in the brand analytics data.

[0121] The competition unit is used to identify competing products among the search products corresponding to each filter object based on the attention metrics of the search products corresponding to each filter object.

[0122] In some implementations, the competition unit includes a determining subunit and a competition subunit.

[0123] The determination sub-unit is used to determine the product to be determined for each filter object based on the attention indicators of the search products corresponding to each filter object.

[0124] The competition sub-unit is used to determine a preset number of products as competition products based on the ranking of the corresponding screening objects in the brand analysis data.

[0125] In some implementations, the target determination device 200 further includes a competition details module and a competition delivery module.

[0126] The competition details module is used to determine the detailed information of competing products based on a preset database.

[0127] The competitive placement module is used to split the text of the details information of competing products and determine the target audience for the competing products.

[0128] In some implementations, the object determination device 200 further includes a competitive classification module and a competitive update module.

[0129] The competition classification module is used to classify each target in the target set corresponding to the competing products based on brand analysis data and the targeting metrics of each target in the target set corresponding to the competing products.

[0130] The competition update module is used to update the placement recommendation results of the advertising campaign to be created based on the classification results of the target audience corresponding to competing products.

[0131] It should be noted that, for the device-type embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and relevant details can be found in the descriptions of the method embodiments. Any processing method described in the method embodiments can be implemented in the device embodiments through corresponding processing modules, and will not be elaborated upon further in the device embodiments.

[0132] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0133] Please see Figure 3 Based on the above-described method for determining the target of delivery, this application also provides an electronic device 300 that can execute the aforementioned method for determining the target of delivery.

[0134] In embodiments of this application, the electronic device 300 includes one or more processors 310, a memory 320, and one or more application programs. The one or more application programs are stored in the memory 320, which stores programs capable of executing the contents of the foregoing embodiments, and the processor 310 can execute the programs stored in the memory.

[0135] The processor 310 may include one or more cores for data processing and message matrix units. The processor 310 connects to various parts of the electronic device using various interfaces and lines, and performs various functions of the cooking device and processes data by running or executing instructions, programs, code sets, or instruction sets stored in memory, and by calling data stored in memory. Optionally, the processor 310 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 310 may integrate one or more of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 310 and may be implemented separately using a communication chip.

[0136] The memory 320 may include random access memory (RAM) or read-only memory (ROM). The memory 320 can be used to store instructions, programs, code, code sets, or instruction sets. The memory may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function, instructions for implementing the various method embodiments described below, etc. The data storage area may also store data created by the terminal during use.

[0137] Please refer to Figure 4 This diagram illustrates a structural block diagram of a computer-readable storage medium 400 provided in an embodiment of this application. The computer-readable storage medium 400 stores program code 410, which can be called by a processor to execute the object determination method described in the above method embodiments.

[0138] The computer-readable storage medium 400 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Optionally, the computer-readable storage medium includes a non-transitory computer-readable storage medium. The computer-readable storage medium 400 has storage space for program code that performs any of the method steps of the above-described anti-counterfeiting identification method. This program code 410 can be read from or written to one or more computer program products. The program code may, for example, be compressed in a suitable form.

[0139] In summary, this application provides a method, apparatus, electronic device, and storage medium for determining advertising targets. The method includes: acquiring the products to be advertised corresponding to an advertising campaign to be created; determining the detailed information corresponding to the products to be advertised based on a preset database; and performing text splitting processing on the detailed information corresponding to the products to be advertised to determine the target audience set corresponding to the products to be advertised. Therefore, by quickly determining the target audience based on key data corresponding to the products to be advertised in a preset database, the requirement for merchant experience is reduced, operational difficulty is decreased, and operational efficiency is improved.

[0140] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for determining the target of delivery, characterized in that, The method includes: Retrieve the products to be deployed for the advertising campaign to be created; Based on a pre-set database, the detailed information corresponding to the product to be deployed is determined; The detailed information of the product to be deployed is split into text to determine the target audience set corresponding to the product to be deployed. Based on brand analysis data and the targeting metrics of each target in the target set corresponding to the products to be advertised, each target in the target set corresponding to the products to be advertised is categorized. The recommended placement result of the advertising campaign is determined based on the classification and processing results of the target audience corresponding to the products to be placed. The targeting metrics include the word frequency of each target in the target set, the word length of each target, and the brand information of the product corresponding to each target; wherein, the word frequency represents the frequency of the target in the target set. The process of categorizing each target audience in the target audience set corresponding to the products to be advertised, based on brand analysis data and the advertising metrics of each target audience in the target audience set corresponding to the products to be advertised, includes: The targeting category for each target in the target set corresponding to the product to be targeted is determined based on the word frequency, word length, corresponding brand information, and brand analysis data of each target in the target set corresponding to the product to be targeted.

2. The method according to claim 1, characterized in that, The method further includes: Based on brand analysis data and the target audience set corresponding to the product to be launched, the competing products corresponding to the product to be launched are determined; wherein, the competing products do not include the product to be launched.

3. The method according to claim 2, characterized in that, The process of determining the competing products corresponding to the product to be advertised, based on brand analysis data and the target audience set corresponding to the product to be advertised, includes: The target audience corresponding to the product to be advertised, which exists in the brand analysis data, is used as the filtering object; In the brand analysis data, the search products corresponding to each filter object are determined respectively; Based on the attention metrics of the search products corresponding to each filter object, identify competing products among the search products corresponding to each filter object.

4. The method according to claim 3, characterized in that, The step of determining competing products based on the attention metrics of the search products corresponding to each filter object includes: Based on the attention metrics of the search products corresponding to each filter object, determine the products to be determined for each filter object; Based on the ranking of the screening objects corresponding to the products to be determined in the brand analysis data, a preset number of the products to be determined are identified as competing products.

5. The method according to claim 2, characterized in that, The method further includes: Based on the preset database, the detailed information corresponding to the competing products is determined; The detailed information of the competing products is split into text to determine the target audience for the competing products.

6. The method according to claim 5, characterized in that, The method further includes: Based on brand analysis data and the advertising metrics of each advertising target in the target set corresponding to the competing products, each advertising target in the target set corresponding to the competing products is classified. The placement recommendation results for the advertising campaign to be created are updated based on the classification results of the target audience corresponding to the competing products.

7. The method according to claim 6, characterized in that, The step of updating the advertising campaign's recommendation results based on the classification results of the target audience corresponding to the competing products includes: The target audiences that are different from those in the target recommendation results for the competing products are designated as the target audiences to be updated. The classification results of the objects to be updated are added to the delivery recommendation results to update the delivery recommendation results.

8. The method according to any one of claims 1 to 7, characterized in that, The method for performing text splitting on the details information corresponding to the product to be deployed, and determining the target audience set corresponding to the product to be deployed, includes: The detailed information corresponding to the product to be deployed is split into multiple objects with different preset word lengths; All the objects obtained from the splitting are assigned to the target object set corresponding to the product to be deployed.

9. The method according to claim 8, characterized in that, The step of splitting the details information corresponding to the product to be deployed into multiple objects with different preset word lengths includes: The detailed information corresponding to the product to be deployed is filtered; The filtered details are split into multiple objects with different preset word lengths.

10. The method according to claim 6, characterized in that, The process of categorizing each target audience in the target audience set corresponding to the competing products, based on brand analysis data and the targeting metrics of each target audience in the target audience set corresponding to the competing products, includes: The targeting category for each target in the targeting set corresponding to the competing products is determined based on the word frequency, word length, corresponding brand information, and brand analysis data of each target in the targeting set corresponding to the competing products.

11. The method according to claim 1, characterized in that, The target categories include at least one of long-tail object categories, attribute object categories, and brand object categories; The step of determining the advertising category for each advertising target based on the keyword frequency, keyword length, and corresponding brand information of each advertising target in the advertising target set corresponding to each product to be advertised includes: If the target object does not exist in the brand analysis data, and the word frequency of the target object is greater than the target number and the word length of the target object is greater than or equal to the first preset word length, then the target object is determined to belong to the long-tail object class. Alternatively, if the target audience exists in the brand analysis data, and the keyword length of the target audience is greater than or equal to the first preset keyword length, then the target audience is determined to belong to the long-tail object class; wherein, the target quantity is the quantity of the products to be targeted. Alternatively, if the target object exists in the brand analysis data, and the text information of the target object contains preset attribute words and the word length of the target object is less than or equal to the second preset word length, then the target object is determined to belong to the attribute object class; wherein, the second preset word length is less than the first preset word length; Alternatively, if the text information of the target object contains the brand information, then the target object is determined to belong to the brand object class.

12. A device for determining the target of delivery, characterized in that, The device includes: The product acquisition module is used to acquire the products to be deployed for the advertising campaign to be created. The information determination module is used to determine the detailed information corresponding to the product to be deployed based on a preset database; The delivery determination module is used to perform text splitting processing on the details information corresponding to the product to be delivered, and to determine the delivery target set corresponding to the product to be delivered. The placement determination module is further configured to classify each placement object in the placement object set corresponding to the product to be placed based on brand analysis data and placement metrics of each placement object in the placement object set corresponding to the product to be placed; and to determine the placement recommendation result of the advertising campaign based on the classification results of the placement objects corresponding to the product to be placed; the placement metrics include the word frequency, word length of each placement object, and brand information of the product to which each placement object belongs in the placement object set; wherein, the word frequency represents the frequency of the placement object appearing in the placement object set; the classification of each placement object in the placement object set corresponding to the product to be placed based on brand analysis data and placement metrics of each placement object in the placement object set corresponding to the product to be placed includes: determining the placement category corresponding to each placement object in the placement object set corresponding to the product to be placed based on the word frequency, word length, corresponding brand information, and brand analysis data of each placement object in the placement object set corresponding to the product to be placed.

13. An electronic device, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the delivery target determination method according to any one of claims 1-10.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium contains program code, which can be called by a processor to execute the object determination method as described in any one of claims 1-10.

Images