Search engine optimization method, device, electronic device and storage medium

Abstract

The present disclosure relates to a search engine optimization method, device, electronic device and storage medium, including: obtaining associated search engines associated with the functions of a target search engine; for each associated search engine, determining a search model corresponding to the associated search engine according to a search keyword input into the associated search engine and a search result corresponding to the search keyword; determining a search score of the search model in different search scenarios according to the search model; determining a target search model of the target search engine according to the search models corresponding to each associated search engine and the search scores of each search model in different search scenarios, so as to improve search efficiency.

Description

Technical Field

[0001] The present disclosure relates to the field of data search technology, and in particular to a search engine optimization method, device, electronic device and storage medium. Background Art

[0002] Search engines are a type of search technology that uses specific strategies to retrieve information from the Internet and feed it back to users based on user needs and certain algorithms. Search engines rely on a variety of technologies, such as web crawler technology, search and ranking technology, web page processing technology, big data processing technology, natural language processing technology, etc., to provide fast and highly relevant information services to information retrieval users. The core modules of search engine technology generally include crawlers, indexing, retrieval and ranking, etc., and a series of other auxiliary modules can be added to create a better network usage environment for users.

[0003] In the existing search engine optimization strategy, various search terms are manually input into other search engines to obtain search results of related products, which are manually analyzed and the advantages and disadvantages are summarized. Then, an optimization strategy for the search engine itself is formulated and implemented by technical personnel.

[0004] Since existing search engine optimization solutions involve a lot of manual analysis, strategy formulation and implementation, they are not only inefficient, but the search results of search engines depend to a large extent on the experience of technical personnel, making it difficult to continuously optimize search algorithms in a high-quality and fast manner. Summary of the invention

[0005] In order to solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides a search engine optimization method, device, electronic device and storage medium to improve search results.

[0006] In a first aspect, an embodiment of the present disclosure provides a search engine optimization method, comprising:

[0007] Obtaining associated search engines associated with the functionality of the target search engine;

[0008] For each of the associated search engines, determine a search model corresponding to the associated search engine according to a search keyword input into the associated search engine and a search result corresponding to the search keyword; determine a search score of the search model in different search scenarios according to the search model;

[0009] A target search model of a target search engine is determined according to the search models corresponding to the associated search engines and the search scores of the search models in different search scenarios.

[0010] Optionally, before determining the target search model of the target search engine according to the search models corresponding to the associated search engines and the search scores of the search models in different search scenarios, the method further includes:

[0011] For each of the associated search engines, based on the search scenario, determining the correlation between the search model of the associated search engine and the search model of the target search engine;

[0012] Determining the target search model of the target search engine according to the search models corresponding to the associated search engines and the search scores of the associated search models in different search scenarios includes:

[0013] The target search model of the target search engine is determined according to the search models corresponding to the associated search engines, the search scores of the target search models in different scenarios, and the correlation between the search models of the associated search engines and the search model of the target search engine.

[0014] Optionally, the determining, based on the search scenario, the correlation between the search model of the associated search engine and the search model of the target search engine includes:

[0015] The correlation between the search model of the associated search engine and the search model of the target search engine is determined according to the correlation between the search scenario of the target search engine and the search scenario of the associated search engine.

[0016] Optionally, determining the target search model of the target search engine according to the search models corresponding to the associated search engines, the search scores of the target search models in different scenarios, and the correlation between the search models of the associated search engines and the search model of the target search engine includes:

[0017] Calculate the weight values ​​of the search models in the associated search engines in different search scenarios according to the search scores of the search models corresponding to the associated search engines in different scenarios and the correlation between the search models of the associated search engines and the search model of the target search engine;

[0018] The target search model of the target search engine is determined according to the search models corresponding to the associated search engines and the weight values ​​of the search models corresponding to the associated search engines.

[0019] Optionally, before determining, for each of the associated search engines, based on the search classification and the search scenario, the correlation between the search model of the associated search engine and the search model of the target search engine, the method further includes:

[0020] Based on the search attribute extraction function, the attribute information of each relevant search engine is obtained, wherein the attribute information includes the search scenario.

[0021] Optionally, determining a search model corresponding to the associated search engine according to a search keyword input into the associated search engine and a search result corresponding to the search keyword includes:

[0022] Inputting the search keyword of the associated search engine and the search results corresponding to the search keyword into the candidate search model;

[0023] Based on a preset loss function, the candidate search model is trained to obtain a trained search model corresponding to the associated search engine.

[0024] Optionally, determining, according to the search model, a search score of the search model in different search scenarios includes:

[0025] Obtaining target search keywords corresponding to the target search scenario;

[0026] Inputting the target search keyword into the search model, and outputting predicted search results corresponding to the target search keyword;

[0027] Determine a relevance score corresponding to the predicted search result;

[0028] The search score of the search model in the target search scenario is determined according to the relevance score corresponding to the predicted search results of the search keyword.

[0029] In a second aspect, an embodiment of the present disclosure provides a search engine optimization device, including:

[0030] An associated search engine acquisition module is used to acquire an associated search engine that is functionally associated with a target search engine;

[0031] A search model parameter acquisition module is used to determine, for each of the associated search engines, a search model corresponding to the associated search engine based on a search keyword input into the associated search engine and a search result corresponding to the search keyword; and to determine a search score of the search model in different search scenarios based on the search model;

[0032] The target search engine determination module is used to determine the target search model of the target search engine according to the search models corresponding to the associated search engines and the search scores of the search models in different search scenarios.

[0033] In a third aspect, an embodiment of the present disclosure provides an electronic device, including:

[0034] one or more processors;

[0035] a storage device for storing one or more programs,

[0036] When the one or more programs are executed by the one or more processors, the one or more processors implement any method as described in the first aspect.

[0037] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any method described in the first aspect.

[0038] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:

[0039] The search engine optimization method, device, electronic device and storage medium provided by the embodiments of the present disclosure obtain associated search engines associated with the functions of the target search engine, and for each associated search engine, determine a search model corresponding to the associated search engine according to a search keyword input into the associated search engine and a search result corresponding to the search keyword; determine a search score of the search model in different search scenarios according to the search model; determine a target search model of the target search engine according to the search models corresponding to each associated search engine and the search scores of each search model in different search scenarios; evaluate the search pros and cons of the associated search engines by learning the search characteristics of the associated search engines and the search differences of each associated search engine in different scenarios, and then organically combine the advantages of the associated search engines, thereby realizing intelligent optimization of the target search engine. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0041] 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, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0042] Figure 1 It is a flowchart of a search engine optimization method provided by an embodiment of the present disclosure;

[0043] Figure 2 It is a flowchart of another search engine optimization method provided by an embodiment of the present disclosure;

[0044] Figure 3It is a flowchart of another search engine optimization method provided by an embodiment of the present disclosure;

[0045] Figure 4 It is a flowchart of another search engine optimization method provided by an embodiment of the present disclosure;

[0046] Figure 5 It is a flowchart of another search engine optimization method provided by an embodiment of the present disclosure;

[0047] Figure 6 It is a structural schematic diagram of a search engine optimization device provided by an embodiment of the present disclosure;

[0048] Figure 7 It is a structural schematic diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0049] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0050] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0051] Exemplarily, the present disclosure provides a search engine optimization method, device, electronic device and storage medium, which obtain associated search engines associated with the functions of a target search engine, and for each associated search engine, determine a search model corresponding to the associated search engine based on a search keyword input into the associated search engine and a search result corresponding to the search keyword; determine a search score of the search model in different search scenarios based on the search model; determine a target search model of the target search engine based on the search models corresponding to each associated search engine and the search scores of each search model in different search scenarios, and evaluate the search pros and cons of different search engines by learning the search characteristics of other search engines and the search differences of each search engine in different scenarios, and then organically combine the advantages of different search engines, thereby realizing intelligent optimization of the target search engine.

[0052] The search engine optimization method disclosed in the present invention is executed by an electronic device or an application, web page, public account, etc. in the electronic device. The electronic device can be a tablet computer, mobile phone, wearable, vehicle-mounted, augmented reality (AR) / virtual reality (VR), laptop, ultra-mobile personal computer (UMPC), netbook, personal digital assistant (PDA), smart TV, smart screen, high-definition TV, 4K TV, smart speaker, smart projector, etc. The present disclosure does not impose any restrictions on the specific type of electronic device.

[0053] The present disclosure does not limit the type of operating system of the electronic device, for example, Android system, Linux system, Windows system, iOS system, etc.

[0054] The technical solution of the present disclosure is described in detail below with reference to several specific embodiments.

[0055] Figure 1 A schematic diagram of a search engine optimization method provided by the present disclosure, such as Figure 1 As shown, the method of this embodiment is as follows:

[0056] S10: Obtain an associated search engine that is functionally associated with the target search engine.

[0057] Specifically, the target search engine can be a search engine that covers all information sources (such as websites, applications, devices, etc.), or it can be an in-site search engine of any information source (such as a search function within an App or a voice search on a smart device, etc.).

[0058] Functional association refers to the same partial functions or the same partial usage scenarios. When a search engine has the same partial functions and / or partial usage scenarios, the search engine is an associated search engine that is functionally associated with the target search engine.

[0059] When the target search engine is a search engine with a browser function, the associated search engines related to the function of the target search engine may be, for example, Baidu search engine, 60 search engine, etc. When the target search engine is a search engine with a shopping function, the associated search engines related to the function of the target search engine may be, for example, Baidu product search engine, Taobao search engine, JD search engine, etc.

[0060] By obtaining search engines that are functionally associated with the target search engine, based on the learning of the associated search engines, the search pros and cons of the associated search engines are evaluated according to the search characteristics of the associated search engines and the search differences of each associated search engine in different scenarios, and then the advantages of the associated search engines are organically combined to achieve intelligent optimization of the target search engine.

[0061] S20. For each associated search engine, determine a search model corresponding to the associated search engine based on a search keyword input into the associated search engine and a search result corresponding to the search keyword; and determine a search score for the search model in different search scenarios based on the search model.

[0062] Specifically, the search keywords of each associated search engine and the search results corresponding to the search keywords are learned through a machine learning algorithm to obtain a search model corresponding to the associated search engine.

[0063] Exemplarily, when the target search engine is a shopping search engine, the associated search engines associated with the function of the target search engine include Taobao or JD.com, etc. Search keywords related to shopping are input into Taobao to obtain search results corresponding to the currently input search keywords. Different search keywords correspond to different search results. The search keywords and the search results of Taobao corresponding to each search keyword are input into the machine learning algorithm. The search model of Taobao is learned through the machine learning algorithm, and the search model of JD.com is learned in this way.

[0064] It should be noted that the machine learning algorithm provided in the embodiments of the present disclosure can be used on any information source.

[0065] After the search model of each associated search engine is obtained, the search scores of the search models corresponding to each associated search engine in different search scenarios are determined.

[0066] Specifically, search scenarios include content classification, user usage scenarios, etc. In each dimensional search scenario, the search results of the search models corresponding to different associated search engines are scored. This score can be the score automatically scored by the technical module according to certain relevance rules, or it can be the manual evaluation score of the search results in this scenario.

[0067] For example, when scoring a Taobao search model in the fashion shopping category and home use scenario, some search results for each search keyword are obtained by randomly selecting some of the popular search keywords in this scenario and sending them to the Taobao search model. The relevance of the search results to the search keywords is scored using an automatic scoring system, and the average score of the relevance corresponding to all the selected search keywords is used as the search score of the Taobao search model in the fashion shopping category and home use scenario.

[0068] S50: Determine a target search model of a target search engine according to the search models corresponding to the associated search engines and the search scores of the search models in different search scenarios.

[0069] After determining the search models corresponding to each associated search engine and the search scores of each search model in different search scenarios, the target search model of the target search engine is determined based on the search models corresponding to each associated search engine and the search scores of each search model in different search scenarios.

[0070] For example, when Taobao's search model has a higher search score in the fashion shopping category and home use scenario, and JD.com's search model has a higher search score in the e-shopping category and travel use scenario, the search model of Taobao in the fashion shopping category and home use scenario and the search model of JD.com in the e-shopping category and travel use scenario are fused and determined as the target search model of the target search engine.

[0071] The search engine optimization method provided by the embodiment of the present disclosure obtains associated search engines associated with the functions of the target search engine, and for each associated search engine, determines a search model corresponding to the associated search engine according to a search keyword input into the associated search engine and a search result corresponding to the search keyword; determines a search score of the search model in different search scenarios according to the search model, determines a target search model of the target search engine according to the search models corresponding to each associated search engine and the search scores of each search model in different search scenarios, evaluates the search pros and cons of the associated search engines by learning the search characteristics of the associated search engines and the search differences of each associated search engine in different scenarios, and then organically combines the advantages of the associated search engines, thereby realizing intelligent optimization of the target search engine.

[0072] Figure 2 is a flow chart of another search engine optimization method provided by an embodiment of the present disclosure. The embodiment of the present disclosure is based on the above embodiment. Figure 2 As shown, before step S50, it also includes:

[0073] S40: For each associated search engine, based on the search scenario, determine the correlation between the search model of the associated search engine and the search model of the target search engine.

[0074] Specifically, the correlation between the search model of the associated search engine and the search model of the target search engine is determined according to the correlation between the search scenario of the target search engine and the search scenario of the associated search engine.

[0075] The relevance includes the similarities and differences in the search scenarios.

[0076] For example, the search model of the target search engine is applicable to the search category of shopping and the applicable search scenarios of home scenarios and travel scenarios. The search model of the learned associated search engine 1 is applicable to the search category of fashion shopping and the applicable search scenario of home scenarios. The search model of the learned associated search engine 2 is applicable to the search category of e-shopping and the applicable search scenario of travel scenarios. The search model of the learned associated search engine 3 is applicable to the search category of current news and the applicable search scenario of home scenarios.

[0077] By calculating the correlation between the search scenario of the target search engine and the search scenario of the associated search engine, a correlation score between the search model of the associated search engine and the search model of the target search engine is determined.

[0078] When the search engine optimization method includes step S40, a possible implementation of step S50 includes:

[0079] S51, determining a target search model of the target search engine according to the search models corresponding to the associated search engines, the search scores of the target search models in different scenarios, and the correlation between the search models of the associated search engines and the search model of the target search engine.

[0080] When determining the search models corresponding to each associated search engine, the search scores of each search model in different search scenarios, and the correlation between the search models of each associated search engine and the search model of the target search engine, determine the target search model of the target search engine based on the search models corresponding to each associated search engine, the search scores of each search model in different search scenarios, and the correlation between the search models of each associated search engine and the search model of the target search engine.

[0081] Exemplarily, when the search model of the target search engine is applicable to the search category of shopping and the applicable search scenarios of home and travel, the search model of the associated search engine 1 has a higher search score in the fashion shopping category and the home use scenario, and the search model of the associated search engine 2 has a higher search score in the e-shopping category and the travel use scenario, it is learned that the search model of the associated search engine 1 is applicable to the search category of fashion shopping and the applicable search scenario is the home scenario, the learned search model of the associated search engine 2 is applicable to the search category of e-shopping and the applicable search scenario is the travel scenario, and the learned search model of the associated search engine 3 is applicable to the search category of current news and the applicable search scenario is the home scenario, among which the search model of the associated search engine 1 has a high correlation with the search model of the target search engine, and the search model of the associated search engine 2 has a high correlation with the search model of the target search engine, then the search model of the associated search engine 1 in the fashion shopping category and the home use scenario and the search model of a certain Dong in the e-shopping category and the office use scenario are fused to determine the target search model of the target search engine.

[0082] The search engine optimization method provided by the embodiment of the present disclosure determines, for each associated search engine, the correlation between the search model of the associated search engine and the search model of the target search engine based on the search classification and the search scenario, and determines the target search of the target search engine according to the search models corresponding to the associated search engines, the search scores of the target search models in different scenarios, and the correlation between the search models of the associated search engines and the search model of the target search engine, thereby increasing the correlation between the search models of the associated search engines and the search models of the target search engine, and can better achieve intelligent optimization of the target search engine.

[0083] Figure 3 is a flow chart of another search engine optimization method provided by the embodiment of the present disclosure. Figure 2 Based on the corresponding embodiments, Figure 3 As shown, one possible implementation of step S51 includes:

[0084] S510: Calculate the weight values ​​of the search models in each associated search engine in different search scenarios according to the search scores of the search models corresponding to each associated search engine in different scenarios and the correlation between the search models of each associated search engine and the search model of the target search engine.

[0085] Based on the search score and correlation, the weight value of the search model in each associated search engine in different search scenarios is determined. The higher the weight value, the higher the search score of the search model in the associated search engine in the search scenario, and the higher the correlation between the search model of the associated search engine and the search model of the target search engine.

[0086] S511 : Determine a target search model of a target search engine according to the search models corresponding to the associated search engines and the weight values ​​of the search models corresponding to the associated search engines.

[0087] According to the correlation between the search model of each associated search engine and the search model of the target search engine in the search scenario, and the search score of each associated search engine in different search scenarios, the weight of each search model is calculated according to certain rules, and the search models of all associated search engines and the search model of the target search engine are fused according to the weights to generate a target search model of the target search engine.

[0088] Figure 4 is a flow chart of another search engine optimization method provided by the embodiment of the present disclosure. Figure 2 Based on the corresponding embodiments, Figure 4 As shown, before step S40, the following steps are also included:

[0089] S30. Based on the search attribute extraction function, obtain attribute information of each relevant search engine.

[0090] Among them, the attribute information includes search scenarios and search categories.

[0091] After obtaining the associated search engines associated with the functions of the target search engine, these associated search engines are input into the search attribute extraction function, and the search attribute extraction function is used to extract the attribute information of each associated search engine. Exemplarily, the attribute information includes search classification attributes, search scenario attributes, etc., and various attribute information of related search engines can be manually or automatically extracted from application stores, description pages of target products, content of target products, etc.

[0092] Figure 5 is a flow chart of another search engine optimization method provided by an embodiment of the present disclosure. The embodiment of the present disclosure is based on the above embodiment. Figure 5 As shown, step S20 includes:

[0093] S21. For each associated search engine, determine a search model corresponding to the associated search engine according to a search keyword input into the associated search engine and a search result corresponding to the search keyword.

[0094] By inputting the search keywords and the search results corresponding to the search keywords into the machine learning algorithm, the search model of the associated search engine in different search scenarios is learned through the machine learning algorithm.

[0095] Specifically, when learning the search model of the associated search engine in different search scenarios through the machine learning algorithm, the search keyword corresponding to the current search scenario and the search result corresponding to the search keyword are input into the machine learning algorithm.

[0096] S22. Determine the search score of the search model in different search scenarios according to the search model.

[0097] After learning the search models of each associated search engine in different search scenarios through machine learning algorithms, the search effects of the search models in different search scenarios are scored. Specifically, some are randomly selected from the set of popular search keywords corresponding to this search scenario and sent to the learned search model of the associated search engine in the current search scenario to obtain the search results for each search keyword. The relevance of the search results to the search keywords is scored using an automatic scoring system, and the average score of the relevance corresponding to all the selected search keywords is used as the search score corresponding to the search model of the associated search engine in the current search scenario.

[0098] Specifically, according to the search keyword input into the associated search engine and the search result corresponding to the search keyword, determining the search model corresponding to the associated search engine includes:

[0099] S210: Input the search keyword of the associated search engine and the search results corresponding to the search keyword into the candidate search model.

[0100] A test sample set is selected from a search library corresponding to an associated search engine, wherein the test sample set includes a search keyword and a search result corresponding to the search keyword, and the search keyword and the search result corresponding to the search keyword are input into a candidate search model.

[0101] S211. Based on a preset loss function, the candidate search model is trained to obtain a trained search model corresponding to the associated search engine.

[0102] After the search keyword and the search results corresponding to the search keyword are input into the candidate search model, the predicted search results corresponding to the search keyword output by the candidate search model are obtained, the loss value between the predicted search results and the search results in the test sample set is determined, and the candidate search model is trained based on the loss value until the loss value meets the preset loss value, thereby obtaining a trained search model corresponding to the associated search engine.

[0103] Specifically, features are extracted from the search keywords and the search results corresponding to the search keywords, such as the relevance of the search keywords and the search results corresponding to the search keywords, the labels corresponding to the search keywords and the search results corresponding to the search keywords, the semantic vectors corresponding to the search keywords and the search results corresponding to the search keywords, and the intentions corresponding to the search keywords and the search results corresponding to the search keywords, etc., and based on the extracted features of the search keywords and the search results corresponding to the search keywords, they are input into the candidate search model.

[0104] It should be noted that, for each associated search engine, when inputting the search keywords of the associated search engine and the search results corresponding to the search keywords into the candidate search model, the search keywords and the search results corresponding to the search keywords in the same search scenario can be input into the candidate search model, and then the search model of the associated search engine in the current search scenario can be trained, and then the search models of the associated search engine in other search scenarios can be obtained in turn. The search keywords and the search results corresponding to the search keywords in different search scenarios can also be input into the candidate search model, and then the search models of the associated search engine in different search scenarios can be trained. The embodiment of the present disclosure does not specifically limit this process.

[0105] Specifically, according to the search model, the search score of the search model in different search scenarios is determined, including:

[0106] S220: Obtain a target search keyword corresponding to the target search scenario.

[0107] It should be noted that, in this embodiment, the target search scenario corresponds to one search scenario, and different search scenarios correspond to different search keywords, that is, different target search scenarios have different target search keywords.

[0108] Exemplarily, when the target search scenario is a shopping search scenario, the target search keywords include clothes, food, furniture, electronic products, etc. When the target search scenario is a current news scenario, the target search keywords include: political news, real-time messages, etc.

[0109] S221. Input the target search keyword into the search model, and output the predicted search results corresponding to the target search keyword.

[0110] S222: Determine the relevance score corresponding to the predicted search result.

[0111] When the target search keyword is input into the search model, the search model will output the predicted search results corresponding to the target search keyword. The relevance of the predicted search results to the search keyword will be scored through the automatic scoring system to determine the relevance score corresponding to the predicted search results.

[0112] S223. Determine a search score of the search model in the target search scenario according to a relevance score corresponding to the search results of the search keyword.

[0113] The average score of the relevance scores corresponding to all selected search keywords is used as the search score of the search model in the current usage scenario.

[0114] Figure 6 is a schematic diagram of the structure of a search engine optimization device provided by an embodiment of the present disclosure, such as Figure 6 As shown, the optimization device includes:

[0115] The associated search engine acquisition module 610 is used to acquire associated search engines associated with the function of the target search engine;

[0116] The search model parameter acquisition module 620 is used to determine, for each associated search engine, a search model corresponding to the associated search engine based on a search keyword input to the associated search engine and a search result corresponding to the search keyword; and determine a search score of the search model in different search scenarios based on the search model;

[0117] The target search engine determination module 630 is used to determine the target search model of the target search engine according to the search models corresponding to the associated search engines and the search scores of the search models in different search scenarios.

[0118] The search engine optimization device provided by the embodiment of the present disclosure comprises an associated search engine acquisition module that acquires associated search engines associated with the functions of a target search engine, a search model parameter acquisition module that determines, for each associated search engine, a search model corresponding to the associated search engine according to a search keyword input into the associated search engine and a search result corresponding to the search keyword; and a search score of the search model in different search scenarios is determined according to the search model; and a target search engine determination module that determines a target search model of the target search engine according to the search models corresponding to each associated search engine and the search scores of each search model in different search scenarios, and evaluates the search pros and cons of the associated search engines by learning the search characteristics of the associated search engines and the search differences of each associated search engine in different scenarios, thereby organically combining the advantages of the associated search engines, thereby realizing intelligent optimization of the target search engine.

[0119] Optionally, also include:

[0120] A relevance determination module, for determining, for each associated search engine, the relevance of the search model of the associated search engine with the search model of the target search engine based on the search scenario;

[0121] The first target search engine determination module is used to determine the target search of the target search engine according to the search models corresponding to the associated search engines, the search scores of the target search models in different scenarios, and the correlation between the search models of the associated search engines and the search model of the target search engine.

[0122] Optionally, the relevance determination module includes a relevance determination unit, which is used to determine the relevance between the search model of the associated search engine and the search model of the target search engine according to the relevance between the search scenario of the target search engine and the search scenario of the associated search engine.

[0123] Optionally, the first target search engine determination module includes:

[0124] A weight value determination unit, used to calculate the weight values ​​of the search models in each associated search engine in different search scenarios according to the search scores of the search models corresponding to each associated search engine in different scenarios and the correlation between the search models of each associated search engine and the search model of the target search engine;

[0125] The target search engine determination unit is used to determine the target search model of the target search engine according to the search models corresponding to the associated search engines and the weight values ​​of the search models corresponding to the associated search engines.

[0126] Optionally, also include:

[0127] The attribute information determination unit is used to obtain attribute information of each relevant search engine based on the search attribute extraction function, wherein the attribute information includes the search scenario.

[0128] Optionally, search for model parameter acquisition module, specifically used for:

[0129] inputting the search keyword of the associated search engine and the search results corresponding to the search keyword into the candidate search model;

[0130] Based on a preset loss function, the candidate search model is trained to obtain a trained search model corresponding to the associated search engine; and,

[0131] Obtaining target search keywords corresponding to the target search scenario;

[0132] Input the target search keyword into the search model, and output the predicted search results corresponding to the target search keyword;

[0133] Determine a relevance score corresponding to the predicted search result;

[0134] The search score of the search model in the target search scenario is determined based on the relevance score corresponding to the search results of the search keyword.

[0135] The device provided by the embodiment of the present invention can execute the method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0136] It is worth noting that in the embodiment of the above-mentioned device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0137] Figure 7 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure, such as Figure 7 As shown, the electronic device includes a processor 710, a memory 720, an input device 730, and an output device 740; the number of processors 710 in the computer device can be one or more. Figure 7 A processor 710 is taken as an example; the processor 710, the memory 720, the input device 730 and the output device 740 in the electronic device can be connected via a bus or other means. Figure 7 The example of connecting through bus is taken in the following.

[0138] The memory 720 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the method in the embodiment of the present invention. The processor 710 executes various functional applications and data processing of the computer device by running the software programs, instructions and modules stored in the memory 720, that is, implementing the method provided in the embodiment of the present invention.

[0139] The memory 720 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 720 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 720 may further include a memory remotely arranged relative to the processor 710, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0140] The input device 730 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the electronic device, and may include a keyboard, a mouse, etc. The output device 740 may include a display device such as a display screen.

[0141] The embodiment of the present disclosure also provides a storage medium containing computer executable instructions, and the computer executable instructions are used to implement the method provided by the embodiment of the present disclosure when executed by a computer processor.

[0142] Of course, the computer executable instructions of a storage medium including computer executable instructions provided by an embodiment of the present invention are not limited to the operations of the method described above, but can also execute related operations in the method provided by any embodiment of the present invention.

[0143] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (FLASH), a hard disk or an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0144] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0145] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A search engine optimization method, characterized in that: include: Obtaining associated search engines associated with the functionality of the target search engine; For each of the associated search engines, determining a search model corresponding to the associated search engine according to a search keyword input into the associated search engine and a search result corresponding to the search keyword; Determining, according to the search model, a search score of the search model in different search scenarios; A target search model of a target search engine is determined according to the search models corresponding to the associated search engines and the search scores of the search models in different search scenarios.

2. The method according to claim 1, characterized in that: Before determining the target search model of the target search engine according to the search models corresponding to the associated search engines and the search scores of the search models in different search scenarios, the method further includes: For each of the associated search engines, based on the search scenario, determining the correlation between the search model of the associated search engine and the search model of the target search engine; Determining the target search model of the target search engine according to the search models corresponding to the associated search engines and the search scores of the associated search models in different search scenarios includes: The target search model of the target search engine is determined according to the search models corresponding to the associated search engines, the search scores of the target search models in different scenarios, and the correlation between the search models of the associated search engines and the search model of the target search engine.

3. The method according to claim 2, characterized in that The determining, based on the search scenario, the correlation between the search model of the associated search engine and the search model of the target search engine includes: The correlation between the search model of the associated search engine and the search model of the target search engine is determined according to the correlation between the search scenario of the target search engine and the search scenario of the associated search engine.

4. The method according to claim 2, characterized in that: Determining the target search model of the target search engine according to the search models corresponding to the associated search engines, the search scores of the target search models in different scenarios, and the correlation between the search models of the associated search engines and the search model of the target search engine includes: Calculate the weight values ​​of the search models in the associated search engines in different search scenarios according to the search scores of the search models corresponding to the associated search engines in different scenarios and the correlation between the search models of the associated search engines and the search model of the target search engine; The target search model of the target search engine is determined according to the search models corresponding to the associated search engines and the weight values ​​of the search models corresponding to the associated search engines.

5. The method according to claim 2, characterized in that: Before determining the correlation between the search model of the associated search engine and the search model of the target search engine based on the search scenario for each associated search engine, the method further includes: Based on the search attribute extraction function, the attribute information of each relevant search engine is obtained, wherein the attribute information includes the search scenario.

6. The method according to claim 1, characterized in that The step of determining a search model corresponding to the associated search engine according to a search keyword input into the associated search engine and a search result corresponding to the search keyword comprises: Inputting the search keyword of the associated search engine and the search results corresponding to the search keyword into the candidate search model; Based on a preset loss function, the candidate search model is trained to obtain a trained search model corresponding to the associated search engine.

7. The method according to claim 1, characterized in that Determining the search score of the search model in different search scenarios according to the search model includes: Obtaining target search keywords corresponding to the target search scenario; Inputting the target search keyword into the search model, and outputting predicted search results corresponding to the target search keyword; Determine a relevance score corresponding to the predicted search result; The search score of the search model in the target search scenario is determined according to the relevance score corresponding to the predicted search results of the search keyword.

8. A search engine optimization device, characterized in that: include: An associated search engine acquisition module is used to acquire an associated search engine that is functionally associated with a target search engine; A search model parameter acquisition module, for determining, for each of the associated search engines, a search model corresponding to the associated search engine according to a search keyword input to the associated search engine and a search result corresponding to the search keyword; Determining, according to the search model, a search score of the search model in different search scenarios; The target search engine determination module is used to determine the target search model of the target search engine according to the search models corresponding to the associated search engines and the search scores of the search models in different search scenarios.

9. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images