Advertising word determination method based on flow analysis, terminal and storage medium

Abstract

The invention discloses an advertising word determination method based on flow analysis, a terminal and a storage medium, and relates to the technical field of electronic commerce. According to the method, the overall flow distribution condition of the category is obtained by analyzing the flow condition of each search word in the category to which the product belongs. By combining the search word with a flow source lacked by our product and a flow source lacked by competitive products, the search word capable of effectively occupying the flow can be accurately screened as the advertising word, and the advertisement management efficiency of the user is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of e-commerce, and in particular to a method for determining advertisement words based on flow analysis, a terminal and a storage medium. Background Art

[0002] With the popularization of the Internet and the continuous development of online shopping platforms, online shopping has gradually become one of the mainstream shopping methods, and the popularity and usage rate of online shopping platforms are also increasing year by year. Common online shopping platforms basically have search functions, and buyers can find the products they need by searching keywords. Therefore, advertising based on search terms has become an important way for merchants to increase product sales.

[0003] At present, advertising based on search terms usually involves merchants determining relevant search terms as advertising terms based on product features. However, the advertising terms determined in this way lack a traffic analysis process, resulting in the advertising terms only fitting the products and failing to accurately occupy traffic, leading to poor advertising results.

[0004] Therefore, the existing technology still needs to be improved and developed. Summary of the invention

[0005] The technical problem to be solved by the present invention is that, in response to the above-mentioned defects of the prior art, a method, terminal and storage medium for determining advertising words based on traffic analysis are provided, aiming to solve the problem in the prior art that merchants usually determine relevant search words as advertising words based on product characteristics, lack of a traffic analysis process, resulting in the advertising words only fitting the products and failing to accurately occupy traffic, resulting in poor advertising delivery effects.

[0006] The technical solution adopted by the present invention to solve the problem is as follows: In a first aspect, an embodiment of the present invention provides a method for determining an advertisement word based on traffic analysis, the method comprising: Obtain search term ranking information of the target category to which our product belongs on the target platform; wherein the search term ranking information includes a number of search terms and the traffic ranking of each of the search terms; Determine the word label of each of the search words, and determine the overall traffic distribution information of the target category according to the word label of each of the search words and the search word ranking information; wherein the word label categories include my product brand words, competitor brand words and category words; Taking our product and several competitive products as analysis products, for each of the analysis products, obtaining the traffic source information of the analysis product; wherein the traffic source information is used to reflect the traffic obtained by the analysis product through search words of different word tag categories; Determine the own traffic difference information and relative traffic difference information of the product according to the traffic source information of each analyzed product; The advertising words of the product are determined according to the overall traffic distribution information, the own traffic difference information and the relative traffic difference information.

[0007] In one embodiment, determining the overall traffic distribution information of the target category according to the word label of each search word and the search word ranking information includes: For each of the search terms, determine the word level of the search term according to a preset ranking interval and the traffic ranking of the search term; According to the word label and word level of each of the search words, the overall traffic distribution information of the target category is determined.

[0008] In one embodiment, the overall traffic distribution information and / or each of the traffic source information is presented in the form of a pivot table.

[0009] In one implementation, determining the own traffic difference information and relative traffic difference information of the product according to the traffic source information of each analyzed product includes: Perform vertical analysis based on the traffic source information corresponding to our product to obtain the traffic difference information of our product; A horizontal analysis is performed based on the traffic source information of each analyzed product to obtain relative traffic difference information of our products.

[0010] In one embodiment, the traffic source information is also used to reflect the advertising traffic and natural traffic obtained by the analysis product through search terms of different word tag categories; The self-traffic difference information is used to reflect: the difference in traffic obtained by our product through search terms of different word tag categories under each type of traffic, natural traffic and advertising traffic; The relative traffic difference information is used to reflect: under each type of natural traffic and advertising traffic, the difference in traffic obtained by the product and each of the competing products through search terms of the same word tag category.

[0011] In one implementation, determining a number of advertising words for the product according to the overall traffic distribution information, the own traffic difference information, and the relative traffic difference information includes: Determine the target word label category in the traffic concentration according to the overall traffic distribution information; Determine the first word label category of the lack of traffic of the product according to the own traffic difference information; Determine, based on the relative traffic difference information, the second word tag category in which the product lacks traffic compared to the competing product; According to the target word label category, the first word label category and the second word label category, several advertising words of the product are determined.

[0012] In one implementation, determining the advertising words of the product according to the target word label category, the first word label category, and the second word label category includes: Determining a number of target search words from the search word ranking information according to the target word label category, the first word label category, and the second word label category; For each of the target search words, performing word root splitting on the target search word to obtain a number of word roots corresponding to the target search word; For each of the root words, the flow information of the root word is obtained according to the search word ranking information, and a number of target root words are determined according to the flow information of each of the root words; An advertisement word for the product is determined based on at least one of the target search words and / or the target word root.

[0013] In one embodiment, the method further comprises: According to the advertising words of our product, the product page of our product on the target platform is optimized.

[0014] In a second aspect, an embodiment of the present invention further provides a terminal, comprising a memory and one or more processors; the memory stores one or more programs; the program includes instructions for executing any of the above-described methods for determining advertising words based on traffic analysis; and the processor is used to execute the program.

[0015] In a third aspect, an embodiment of the present invention further provides a computer-readable storage medium on which a plurality of instructions are stored, wherein the instructions are suitable for being loaded and executed by a processor to implement the steps of any of the above-mentioned methods for determining advertising words based on traffic analysis.

[0016] Beneficial effects of the present invention: The embodiment of the present invention obtains the overall traffic distribution of the category by analyzing the traffic of various search terms in the category to which our product belongs. By combining it with the traffic sources that our product itself lacks and the traffic sources that are lacking compared with competing products, it is possible to accurately select search terms that can effectively occupy traffic as advertising terms, thereby improving the user's advertising management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is a flow chart of a method for determining advertisement words based on traffic analysis provided by an embodiment of the present invention.

[0019] Figure 2 It is a principle block diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The present invention discloses a method, terminal and storage medium for determining advertisement words based on traffic analysis. To make the purpose, technical solution and effect of the present invention clearer and more specific, the present invention is further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0021] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be intermediate elements. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0022] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as generally understood by those skilled in the art in the art to which the present invention belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as herein.

[0023] In view of the above-mentioned defects of the prior art, the present invention provides a method for determining advertising words based on traffic analysis, the method obtains the search word ranking information of the target category to which our product belongs on the target platform; wherein the search word ranking information includes several search words and the traffic ranking of each of the search words; determines the word label of each of the search words, and determines the overall traffic distribution information of the target category according to the word label of each of the search words and the search word ranking information; wherein the word label categories include our product brand words, competitive product brand words and category words; takes our product and several competitive products as analysis products, and obtains the traffic source information of the analysis product for each of the analysis products; wherein the traffic source information is used to reflect the traffic obtained by the analysis product through search words of different word label categories; according to the traffic source information of each of the analysis products, determines the self-traffic difference information and relative traffic difference information of the product; according to the overall traffic distribution information, the self-traffic difference information and the relative traffic difference information, determines the advertising words of the product. The present invention obtains the overall traffic distribution of the category by analyzing the traffic of various search words in the category to which our product belongs. By combining it with the traffic sources that our products lack and the traffic sources that our products lack compared to competing products, we can accurately screen out search terms that can effectively occupy traffic as advertising terms, thereby improving users' advertising management efficiency.

[0024] like Figure 1 As shown, the method specifically comprises the following steps: Step S100, obtaining search term ranking information of a target category to which our product belongs on a target platform; wherein the search term ranking information includes a number of search terms and a traffic ranking of each of the search terms.

[0025] Specifically, the search term ranking may include the top several search terms in the target category, such as the top 100 search terms. The specific ranking of each search term may reflect the importance or search popularity of the search term in the target category. Taking search popularity as an example, the search popularity of each search term is calculated by dividing 1 by the corresponding specific ranking.

[0026] Step S200, determine the word label of each of the search terms, and determine the overall traffic distribution information of the target category according to the word label of each of the search terms and the search term ranking information; wherein the word label categories include my product brand words, competitor brand words and category words.

[0027] Specifically, all search terms will be divided into three categories: one is our brand terms, one is competitor brand terms, and the other is category terms, and they will be tagged with words, thus obtaining a label system that can be used multiple times. Among them, category terms can be understood as search terms that do not contain any brand name, such as water cups. By analyzing the word labels and search term ranking information of each search term, we can know the traffic share or search popularity of different search terms. From the perspective of category insights, in order to obtain better advertising results, advertising words should choose search terms with higher search popularity, so that our products can occupy more search traffic.

[0028] In one implementation, determining the overall traffic distribution information of the target category according to the word label of each search word and the search word ranking information includes: For each of the search terms, determine the word level of the search term according to a preset ranking interval and the traffic ranking of the search term; According to the word label and word level of each of the search words, the overall traffic distribution information of the target category is determined.

[0029] Specifically, a traffic analysis strategy adopted in this embodiment is category-related traffic analysis. The overall traffic distribution of different categories is different. For example, the traffic of some categories is concentrated in certain brand words, so the traffic of these brand words should be given priority when advertising; the overall traffic of some categories is not very concentrated, and most of the traffic still comes from category words searched by users, such as water cups. In actual application, according to the ranking of different search terms, the word level of each search term is determined according to the preset ranking interval. For example, the search terms with relatively high rankings are given a word level of P0; the search terms ranked in the middle are given a word level of P1, and the search terms of P1 are usually relatively fine words; the search terms ranked at the bottom are given a word level of P2, and the search terms of P2 are usually relatively long-tail words. The preset ranking interval is set by the user according to his own needs. Each word level can include multiple search terms, and the search terms of each word level are updated regularly, for example, the word level can be updated on a monthly basis.

[0030] Step S300: Take our product and several competing products as analysis products, and obtain the traffic source information of each analysis product; wherein the traffic source information is used to reflect the traffic obtained by the analysis product through search terms of different word tag categories.

[0031] Specifically, this embodiment will not only analyze the traffic sources of our products, but also analyze the traffic sources of other competing products that are in competition with our products. Therefore, both our products and competing products are used as analysis products. Taking an analysis product as an example, it is necessary to reversely check which search terms the traffic of the analysis product comes from. For example, the main traffic source of analysis product A is category words, and our product brand words and competitor brand words account for a very small proportion as traffic sources; the main traffic source of analysis product B is our product brand words, that is, the brand power of the product is very strong, and most of the traffic comes from its own brand traffic, not category traffic. By analyzing the traffic sources of our products and other competing products, we can clearly know the distribution of our own and competitors' traffic sources, which will help to determine the advertising strategy for our products in the future.

[0032] In one implementation, the overall traffic distribution information and / or each of the traffic source information is presented in the form of a pivot table.

[0033] Specifically, in order to facilitate comparative analysis, after adding a new task order, this embodiment will integrate the traffic data provided by some third-party software and the label system established by itself, and generate a pivot table. Pivot tables can be associated with each other and can also be associated with target platform data. The pivot table can intuitively present the overall traffic distribution information of the target category and / or the traffic source information of each analyzed product. Therefore, through the pivot table, we can quickly analyze the type of traffic that our products lack, as well as the traffic gap with other competitors, which will help to formulate subsequent advertising strategies. In actual applications, pivot tables can be generated with the help of data analysis tools.

[0034] Step S400: Determine the own traffic difference information and relative traffic difference information of the product according to the traffic source information of each analyzed product.

[0035] Specifically, the other two traffic analysis strategies adopted in this embodiment are product-related traffic analysis, which are specifically divided into vertical comparison and horizontal comparison traffic analysis. By vertically comparing the proportion of different traffic sources of our own products, we can obtain our own traffic difference information, that is, the traffic type we lack. By horizontally comparing the proportion of different traffic sources of our products and competing products, we can obtain relative traffic difference information, that is, the traffic type we lack relative to our competitors.

[0036] In one implementation, determining the own traffic difference information and relative traffic difference information of the own product according to the traffic source information of each of the analyzed products includes: Perform vertical analysis based on the traffic source information corresponding to our product to obtain the traffic difference information of our product; A horizontal analysis is performed based on the traffic source information of each analyzed product to obtain relative traffic difference information of our products.

[0037] Specifically, by comparing the traffic source information of our products vertically, we can learn which types of search terms our own traffic sources mainly rely on, and then combine the search terms with larger traffic in the target category to learn which search terms in the target category our products lack traffic for, and we need to seize the traffic of these search terms when advertising. By comparing the traffic source information of our products and competing products horizontally, we can learn the difference in traffic between us and our competitors, and then learn which search terms our products lack traffic from our competitors, and we need to seize the traffic of these search terms when advertising. For example, our brand strength is not enough, and we lack traffic sources for our brand terms. If our competitors belong to the same category as us, and their brand strength is very strong and their brand traffic is large, then our products can consider seizing the search traffic of their competitors' brand terms when advertising.

[0038] In one implementation, the traffic source information is also used to reflect the advertising traffic and natural traffic obtained by the analysis product through search terms of different word tag categories; The self-traffic difference information is used to reflect: the difference in traffic obtained by our product through search terms of different word tag categories under each type of traffic, natural traffic and advertising traffic; The relative traffic difference information is used to reflect: under each type of natural traffic and advertising traffic, the difference in traffic obtained by the product and each of the competing products through search terms of the same word tag category.

[0039] Specifically, the traffic sources of the product are divided into two types of traffic: natural traffic and advertising traffic. For each type of traffic, the two analysis strategies of vertical analysis and horizontal analysis will be used to obtain the traffic difference information of our product itself and the relative traffic difference information. In other words, this embodiment needs to analyze which types of search word traffic our product itself lacks under natural traffic, and which types of search word traffic it lacks under advertising traffic. And it is necessary to analyze which types of search word traffic our product lacks under natural traffic, and which types of search word traffic it lacks under advertising traffic compared to competing products.

[0040] For example, each column of data in the pivot table is used to reflect the traffic obtained by an analysis product through different search terms, and each row of data is used to reflect the traffic obtained by different analysis products through a certain search term. By analyzing each column of data vertically, you can get the information about the difference in traffic. By analyzing each row of data horizontally, you can get the information about the difference in relative traffic, that is, when the traffic of the same search term is divided by different products, each product can occupy what percentage of the traffic of the search term. The traffic in the pivot table will distinguish between natural traffic and advertising traffic.

[0041] Step S500: Determine the advertising words of the product according to the overall traffic distribution information, the own traffic difference information and the relative traffic difference information.

[0042] Specifically, our products can be new products launched online or old products to be optimized. When optimizing the advertisements of our products, we need to combine the overall traffic distribution information of the category to which the product belongs, the traffic sources it lacks, and the traffic sources it lacks relative to competing products, and make a comprehensive decision on what advertising words to use, so as to effectively optimize the advertising effect.

[0043] In one implementation, based on the overall traffic distribution information, the own traffic difference information, and the relative traffic difference information, several advertising words of the product are determined, including: Determine the target word label category in the traffic concentration according to the overall traffic distribution information; Determine the first word label category of the lack of traffic of the product according to the own traffic difference information; Determine, based on the relative traffic difference information, the second word tag category in which the product lacks traffic compared to the competing product; According to the target word label category, the first word label category and the second word label category, several advertising words of the product are determined.

[0044] Specifically, through the overall traffic distribution information of the target category to which our product belongs, we can analyze which types of search words the natural traffic and advertising traffic under the target category are concentrated, that is, obtain the target word label category. Through the own traffic difference information, we can analyze which types of search words the natural traffic and advertising traffic of our product are concentrated, and which types of natural traffic and advertising traffic are lacking, that is, obtain the first word label category. Through the relative traffic difference information, we can analyze which types of search words the natural traffic and advertising traffic of competing products are concentrated, and which types of natural traffic and advertising traffic our product lacks compared with competing products, that is, obtain the second word label category. Through all the analysis results, the most appropriate advertising words are comprehensively selected for the advertising of our products.

[0045] For example, our product has strong brand power, that is, the natural traffic of our brand words is large, but if the advertising traffic of our brand words is small, it is possible that the search traffic of our brand words will be seized by competing products. In this case, when our product is advertising, we can use our brand words as advertising words to occupy the search traffic of our brand words. For another example, if there are no products with strong brand power in the target category where our product is located, then when our product is advertising, we can use the category words corresponding to the target category as advertising words. For another example, if the natural traffic of the brand words of competing products is large, but the competitor has not placed advertisements for its own brand words, then when our product is advertising, we can consider seizing the search traffic of the brand words of competing products.

[0046] In one implementation, determining the advertisement word of the product according to the target word label category, the first word label category, and the second word label category includes: Determining a number of target search words from the search word ranking information according to the target word label category, the first word label category, and the second word label category; For each of the target search words, performing word root splitting on the target search word to obtain a number of word roots corresponding to the target search word; For each of the root words, the flow information of the root word is obtained according to the search word ranking information, and a number of target root words are determined according to the flow information of each of the root words; An advertisement word for the product is determined based on at least one of the target search words and / or the target word root.

[0047] Specifically, in addition to the analysis of the word dimension, this embodiment also performs an analysis of the root dimension, and the analysis and display of the root dimension can be implemented based on the graffiti board tool. Root analysis first requires root splitting. Root splitting is to split a long word into multiple words to obtain multiple roots of the long word. Then, traffic analysis is performed on each root, and finally the traffic analysis results of all roots are summarized to obtain the traffic analysis results of the long word. Through root analysis, effective roots can be accurately screened out as the direction of advertising optimization.

[0048] In one implementation, the method further includes: According to the advertising words of our product, the product page of our product on the target platform is optimized.

[0049] Specifically, after determining the appropriate advertising words, in addition to using the advertising words for advertising, you can also use the advertising words to optimize the product pages of our products on the target platform, for example, you can optimize the title of the product page.

[0050] Based on the above embodiment, the present invention further provides a terminal, whose principle block diagram can be shown as follows: Figure 2 As shown. The terminal includes a processor, a memory, a network interface, and a display screen connected through a system bus. Among them, the processor of the terminal is used to provide computing and control capabilities. The memory of the terminal includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the terminal is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an advertising word determination method based on traffic analysis is implemented. The display screen of the terminal can be a liquid crystal display screen or an electronic ink display screen.

[0051] Those skilled in the art will understand that Figure 2 The principle block diagram shown in the figure is only a block diagram of a partial structure related to the scheme of the present invention, and does not constitute a limitation on the terminal to which the scheme of the present invention is applied. The specific terminal may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0052] In one implementation, the memory of the terminal stores one or more programs, and is configured to be executed by one or more processors. The one or more programs include instructions for performing a method for determining advertisement words based on traffic analysis.

[0053] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0054] In summary, the present invention discloses a method, terminal and storage medium for determining advertising words based on traffic analysis, and relates to the technical field of e-commerce. The method comprises: obtaining search word ranking information of a target category to which our product belongs on a target platform; wherein the search word ranking information comprises several search words and traffic rankings of each of the search words; determining the word label of each of the search words, and determining the overall traffic distribution information of the target category according to the word label of each of the search words and the search word ranking information; wherein the word label categories comprise our product brand words, competitor brand words and category words; taking our product and several competitor products as analysis products, for each of the analysis products, obtaining the traffic source information of the analysis product; wherein the traffic source information is used to reflect the traffic obtained by the analysis product through search words of different word label categories; according to the traffic source information of each of the analysis products, determining the self-traffic difference information and relative traffic difference information of the product; and determining the advertising words of the product according to the overall traffic distribution information, the self-traffic difference information and the relative traffic difference information. The present invention analyzes the traffic of various search terms in the category to which our product belongs, and obtains the traffic distribution of the category as a whole. Combining it with the traffic sources that our product itself lacks and the traffic sources that it lacks compared with competing products, we can accurately select search terms that can effectively occupy traffic as advertising terms, thereby improving the user's advertising management efficiency.

[0055] It should be understood that the application of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. A method for determining advertising words based on traffic analysis, characterized in that: The method comprises: Obtain search term ranking information of the target category to which our product belongs on the target platform; wherein the search term ranking information includes a number of search terms and the traffic ranking of each of the search terms; Determine the word label of each of the search words, and determine the overall traffic distribution information of the target category according to the word label of each of the search words and the search word ranking information; wherein the word label categories include my product brand words, competitor brand words and category words; Taking our product and several competitive products as analysis products, for each of the analysis products, obtaining the traffic source information of the analysis product; wherein the traffic source information is used to reflect the traffic obtained by the analysis product through search words of different word tag categories; Determine the own traffic difference information and relative traffic difference information of the product according to the traffic source information of each analyzed product; The advertising words of the product are determined according to the overall traffic distribution information, the own traffic difference information and the relative traffic difference information.

2. The method for determining advertisement words based on traffic analysis according to claim 1, characterized in that: Determining the overall traffic distribution information of the target category according to the word tags of each of the search words and the search word ranking information includes: For each of the search terms, determine the word level of the search term according to a preset ranking interval and the traffic ranking of the search term; According to the word label and word level of each of the search words, the overall traffic distribution information of the target category is determined.

3. The method for determining advertisement words based on traffic analysis according to claim 1, characterized in that: The overall traffic distribution information and / or each of the traffic source information is presented in the form of a pivot table.

4. The method for determining advertisement words based on traffic analysis according to claim 1, characterized in that: Determine the own traffic difference information and relative traffic difference information of the product according to the traffic source information of each of the analyzed products, including: Perform vertical analysis based on the traffic source information corresponding to our product to obtain the traffic difference information of our product; A horizontal analysis is performed based on the traffic source information of each analyzed product to obtain relative traffic difference information of our products.

5. The method for determining advertisement words based on traffic analysis according to claim 4, characterized in that: The traffic source information is also used to reflect the advertising traffic and natural traffic obtained by the analysis product through search terms in different word tag categories; The self-traffic difference information is used to reflect: the difference in traffic obtained by our product through search terms of different word tag categories under each type of traffic, natural traffic and advertising traffic; The relative traffic difference information is used to reflect: under each type of natural traffic and advertising traffic, the difference in traffic obtained by the product and each of the competing products through search terms of the same word tag category.

6. The method for determining advertisement words based on traffic analysis according to claim 1, characterized in that: According to the overall traffic distribution information, the own traffic difference information and the relative traffic difference information, several advertising words of the product are determined, including: Determine the target word label category in the traffic concentration according to the overall traffic distribution information; Determine the first word label category of the lack of traffic of the product according to the own traffic difference information; Determine, based on the relative traffic difference information, the second word tag category in which the product lacks traffic compared to the competing product; According to the target word label category, the first word label category and the second word label category, several advertising words of the product are determined.

7. The method for determining advertisement words based on traffic analysis according to claim 6, characterized in that: Determining the advertising words of the product according to the target word label category, the first word label category, and the second word label category includes: Determining a number of target search words from the search word ranking information according to the target word label category, the first word label category, and the second word label category; For each of the target search words, performing word root splitting on the target search word to obtain a number of word roots corresponding to the target search word; For each of the root words, the flow information of the root word is obtained according to the search word ranking information, and a number of target root words are determined according to the flow information of each of the root words; An advertisement word for the product is determined based on at least one of the target search words and / or the target word root.

8. The method for determining advertisement words based on traffic analysis according to claim 1, characterized in that: The method further comprises: According to the advertising words of our product, the product page of our product on the target platform is optimized.

9. A terminal, characterized in that: The terminal includes a memory and one or more processors; the memory stores one or more programs; the program includes instructions for executing the advertising word determination method based on traffic analysis as described in any one of claims 1-8; and the processor is used to execute the program.

10. A computer-readable storage medium having a plurality of instructions stored thereon, characterized in that: The instructions are suitable for being loaded and executed by a processor to implement the steps of the method for determining advertising words based on traffic analysis as described in any one of claims 1-8.

Images