Vertical search engine fine arrangement method and system based on multi-dimensional features

Abstract

The invention relates to the technical field of computer software, in particular to a vertical search engine fine arrangement method and system based on multi-dimensional features. The method comprises the steps of obtaining recalled resource information, and performing feature extraction based on the obtained resource information, including extracting document features, resource popularity features, column features and user behavior features of the resource information; performing classification model weighting according to the extracted resource information features, and performing resource popularity weighting according to the extracted resource information features, including setting a resource popularity hyper-parameter for adjusting the weight of the resource popularity; and carrying out model integration on the classification model weighting result and the resource popularity weighting result, carrying out fine arrangement scoring by utilizing the weight after model integration, and sorting the recalled resources according to the final scoring result. According to the method, multi-dimensional features are comprehensively considered, and the search results are reasonably weighted, so that accurate search result display is realized.

Description

Technical Field

[0001] The present invention relates to the field of computer software technology, and in particular to a vertical search engine ranking method and system based on multi-dimensional features. Background Art

[0002] Vertical search is a search engine technology that is specifically targeted at specific fields or topics. Unlike general search engines (such as Google and Baidu), vertical search engines focus on indexing and retrieving specific types of information, such as real estate, travel, shopping, government services, or data in specific industries. With the rapid development of information technology, search engines play a vital role in people's access to information. However, traditional general search engines often fail to provide sufficiently accurate and relevant search results when faced with search needs in specific fields or topics. In order to solve this problem, vertical search engines have emerged. Vertical search engines focus on information indexing and retrieval in specific fields or topics, and can better meet users' search needs in specific fields. For example, in the fields of real estate, travel, shopping, government services, etc., vertical search engines can provide more accurate and targeted search results.

[0003] In vertical search engines, the BM25 algorithm is a commonly used information retrieval and web page ranking algorithm. It evaluates the relevance of a document to a user query by considering the frequency of the query term in the document and the frequency of the query term in all documents. However, the traditional BM25 algorithm has some limitations in vertical search, such as not considering factors such as resource popularity, column weight, and business focus. In addition, feature extraction is a key link in search engines. Effective feature extraction can capture the key information and potential semantics of a document, but existing feature extraction methods may not be able to fully cover multi-dimensional features, resulting in the relevance and accuracy of search results being affected. At this stage, a vertical search engine ranking method and system based on multi-dimensional features is needed. Summary of the invention

[0004] In order to solve the problems of poor performance and low search accuracy of vertical search engines, the present invention provides a vertical search engine ranking method and system based on multi-dimensional features. It can comprehensively consider resource popularity, column weight, user behavior and user portrait factors, deeply mine the characteristics of documents, and thus provide more accurate and personalized search results.

[0005] In the first aspect, the present invention provides a vertical search engine ranking method based on multi-dimensional features, which adopts the following technical solution: A vertical search engine ranking method based on multi-dimensional features, comprising: Obtain the recalled resource information, including document information, resource popularity, column information, and user behavior data; Feature extraction is performed based on the acquired resource information, including document features, resource popularity features, column features, and user behavior features of the resource information; Weighting the classification model according to the extracted resource information features, including calculating the classification model weight by combining chi-square feature extraction and Bayesian classification; Perform resource heat weighting according to the extracted resource information features, including setting resource heat hyperparameters to adjust the weight of resource heat; The weighted results of the classification model and the weighted results of the resource heat are integrated into a model, including taking the weighted results of the classification model as the basic weight and combining the results of the resource heat weight through multiplication operation; Use the weights after model integration to perform precise ranking and scoring, and sort the recalled resources according to the final scoring results.

[0006] Furthermore, the classification model is weighted according to the extracted resource information features, including calculating the frequency of occurrence and chi-square statistics of each feature in different categories, screening out features with distinguishing ability, calculating the prior probability and posterior probability of each word in different categories by Bayesian classification, and selecting the category with the largest posterior probability as the classification of the document. The calculation formula of the Bayesian classification is: , in, Represented as keywords, Represented as categories, Represented as category The prior probability of Represented as in category Next, the word appears in the document The joint probability of Represents the word that appears in the document , the posterior probability that the document belongs to the category.

[0007] Furthermore, the weighting of the classification model according to the extracted resource information features also includes setting a column coefficient according to the importance of the column information to the business, and obtaining a preliminary weight of each document by multiplying the Bayesian posterior probability with the column coefficient.

[0008] Furthermore, the resource heat weighting according to the extracted resource information features includes obtaining the search log statistics of the recent resource visits, and setting the resource heat hyperparameters to adjust the weight of the resource heat, and calculating the resource heat weighting based on the recent resource visits and the heat hyperparameters. The calculation formula is: , in, Represented as a resource heat hyperparameter, Represents the number of recent resource visits. Indicates the weight after resource heat is weighted.

[0009] Furthermore, the weighted results of the classification model and the weighted results of resource heat are integrated into a model, including the initial weight obtained by weighting the classification model As the basic weight, the result of combining the resource heat weight by multiplication operation The final weight after integration is obtained, and the final weight is expressed as: , in, Represents the weight of the classification model after weighting, is represented as the final weight.

[0010] Furthermore, the weights after model integration are used to perform fine ranking and scoring, including calculating the scores in the rough ranking results according to the matching rules, calculating the final fine ranking scores using the weights after model integration, and sorting the recalled resources according to the final scoring results. The formula for calculating the final fine ranking score is: , in, It is expressed as the score in the rough sorting result. Indicates the final refined score.

[0011] Furthermore, the score in the rough sorting results is calculated according to the matching rules, including selecting the matching rules and determining the matching score according to the matching rules, converting the documents and keywords into vectors using word frequency-inverse document frequency, calculating the relevance score through cosine similarity, determining the score in the rough sorting results according to the matching score and the relevance score, setting a score threshold and eliminating resource information with a score less than the threshold.

[0012] In the second aspect, a vertical search engine ranking system based on multi-dimensional features includes: The data acquisition module is configured to: acquire user resource information, including document information, resource popularity, column information and user behavior data; The feature extraction module is configured to: perform feature extraction based on the acquired resource information, including extracting document features, resource popularity features, column features, and user behavior features of the resource information; The preliminary weighting module is configured to: perform classification model weighting according to the extracted resource information features, including calculating the classification model weighting by combining chi-square feature extraction and Bayesian classification; The heat weighting module is configured to: weight the resource heat according to the extracted resource information features, including setting resource heat hyperparameters for adjusting the weight of the resource heat; The integration module is configured to: perform model integration on the weighted result of the classification model and the weighted result of the resource heat, including taking the weighted result of the classification model as a basic weight and combining the result of the weighted result of the resource heat through a multiplication operation; The refined ranking module is configured to: perform refined ranking scoring using the weights after model integration, and sort the recalled resources according to the final scoring results.

[0013] In a third aspect, the present invention provides a computer-readable storage medium storing a plurality of instructions, wherein the instructions are suitable for being loaded and executed by a processor of a terminal device, for example, a vertical search engine ranking method based on multi-dimensional features.

[0014] In a fourth aspect, the present invention provides a terminal device including a processor and a computer-readable storage medium, wherein the processor is used to implement various instructions; the computer-readable storage medium is used to store multiple instructions, wherein the instructions are suitable for being loaded by the processor and executed by the vertical search engine ranking method based on multi-dimensional features.

[0015] In summary, the present invention has the following beneficial technical effects: 1. The present invention can more accurately determine the category of a document by calculating the frequency of occurrence of features, chi-square statistics and Bayesian classification, thereby improving the accuracy and reliability of classification. By setting a column coefficient and multiplying it with the Bayesian posterior probability, the importance of the column to the business can be fully considered, making the classification results more in line with actual business needs. Based on the search log statistics of recent resource visits and heat weighting, popular resources can have more advantages in sorting and meet users' needs for popular information.

[0016] 2. The present invention reasonably weights the search results by comprehensively considering document features, resource popularity features, column features and user behavior features, thereby achieving accurate search result display and avoiding the problem of low search accuracy caused by the inability to fully cover multi-dimensional features. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the overall process of a vertical search engine precise ranking method based on multi-dimensional features according to an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The present invention is further described in detail below in conjunction with the accompanying drawings.

[0019] Example 1 Reference Figure 1 , a vertical search engine ranking method based on multi-dimensional features in this embodiment includes: Obtain the recalled resource information, including document information, resource popularity, column information, and user behavior data; Feature extraction is performed based on the acquired resource information, including document features, resource popularity features, column features, and user behavior features of the resource information; Weighting the classification model according to the extracted resource information features, including calculating the classification model weight by combining chi-square feature extraction and Bayesian classification; Perform resource heat weighting according to the extracted resource information features, including setting resource heat hyperparameters to adjust the weight of resource heat; The weighted results of the classification model and the weighted results of the resource heat are integrated into a model, including taking the weighted results of the classification model as the basic weight and combining the results of the resource heat weight through multiplication operation; Use the weights after model integration to perform precise ranking and scoring, and sort the recalled resources according to the final scoring results.

[0020] Specifically, a vertical search engine ranking method based on multi-dimensional features in this embodiment includes the following steps: S1. Obtain the recalled resource information, including document information, resource popularity, column information and user behavior data; Based on the user's search intent and related conditions, determine the scope of resources to be searched, such as a specific website, database or index, extract keywords from the user's search query, and use these keywords to match and retrieve in the resources. Use the extracted keywords to search within the determined search scope to find resources related to the keywords. According to preset conditions and rules, filter the retrieved resources to remove irrelevant or non-compliant resources. For the filtered resources, collect relevant information, including document content, resource popularity, column information, user behavior data, and user portrait data.

[0021] S2. Extracting features based on the acquired resource information, including extracting document features, resource popularity features, column features, and user behavior features of the resource information; Among them, document features include key words or phrases in the document, resource popularity features include visits and clicks, column features include column categories such as news, entertainment, technology, etc., the level of the column hierarchy, whether it is a first-level column or a second-level or third-level column, etc., user behavior features include search keywords, browsing history and preferences, etc.

[0022] S3, weighting the classification model according to the extracted resource information features, including calculating the classification model weight by combining chi-square feature extraction and Bayesian classification; First, the documents need to be classified to determine different categories. Then, for each feature, the number of times it appears in each category is counted, that is, the frequency of occurrence of each feature in different categories is calculated. The chi-square statistic of each feature is calculated according to the chi-square statistic calculation formula. The chi-square statistic calculation formula is: , in, is the observed frequency, that is, the number of times the characteristic actually occurs in the category; is the expected frequency, which is the number of times the feature is expected to appear in the category based on the overall distribution. The expected frequency can be calculated by the total sample size, row sum, and column sum: , Among them, the row sum is the sum of the observed frequencies of a specific row (such as a certain category), and the column sum is the sum of the observed frequencies of a specific column (such as a certain feature). According to the size of the chi-square statistic, select features with higher distinguishing ability. The larger the chi-square statistic, the stronger the distinguishing ability of the feature for different categories. By selecting these features, the accuracy and effect of subsequent Bayesian classification can be improved.

[0023] For example, in a vertical search engine, suppose we have two categories: technology and entertainment. For a certain feature "artificial intelligence", we count the number of times it appears in technology and entertainment documents to get the observed frequency. Then, based on the total sample size and the number of documents in each category, we calculate the expected frequency. By calculating the chi-square statistic, we can determine the ability of the feature "artificial intelligence" to distinguish between technology and entertainment documents. If the chi-square statistic is large, it means that its distribution difference in the two categories is large, and it is a feature with high discrimination ability and can be used for subsequent classification.

[0024] Based on the above-screened distinguishing features, the prior probability and posterior probability of each word with distinguishing features in different categories are calculated by Bayesian classification, and the category with the largest posterior probability is selected as the category of the document. The calculation formula of the Bayesian classification is: , in, Represented as keywords, Represented as categories, Represented as category The prior probability of Represented as in category Next, the word appears in the document The joint probability of Represents the word that appears in the document , the posterior probability that the document belongs to the category, Represented as category The prior probability can be estimated by counting the frequency of the categories in all documents. For example, if among all documents, technology documents account for 40% and entertainment documents account for 60%, then the prior probability P(technology) = 0.4, P(entertainment) = 0.6. For the words "artificial intelligence" and "algorithm" in the new document, their conditional probabilities in the technology category are calculated to be P(artificial intelligence|technology) = 0.7, P(algorithm|technology) = 0.6, and their conditional probabilities in the entertainment category are calculated to be P(artificial intelligence|entertainment) = 0.2, P(algorithm|entertainment) = 0.1. Then the posterior probability in the technology category is: P(technology|artificial intelligence, algorithm) P(Technology) P(Artificial Intelligence|Technology) P(Algorithm|Technology) 0.4 0.7 0.6. Similarly, the posterior distribution of the entertainment category is calculated. Obviously, the technology category is larger than the entertainment category, so the document is classified as the technology category.

[0025] Calculate the Bayesian posterior probability, which indicates the probability that a document belongs to a certain category, and reflects the possible distribution of the document in each category. Then, set the column coefficient according to the importance of the column to the business. Different columns may have different importance in the business. By setting the column coefficient, the difference in importance can be reflected. The column coefficient is set by collecting document data, classifying and labeling these data, recording the column where each document is located, and determining the indicators for evaluating the importance of the column according to business goals and actual needs. A certain score range is set for each indicator, that is, the indicator is quantified, and the quantified indicator is normalized to obtain the column coefficient, and then weighted by calculating the classification model: , in, represents the probability that a document belongs to a certain category, Expressed as column coefficient, It is expressed as the preliminary weight of each document, which takes into account the classification probability and column coefficient of the document. The classification probability of a document indicates its possibility in different categories, while the column coefficient reflects the importance of the column to the business. By multiplying the two, the preliminary weight obtained can better reflect the importance of the document in the entire classification system. This preliminary weight provides a basis for subsequent weighting. In subsequent steps such as resource heat weighting, the weight of the document is further adjusted on this basis to achieve more accurate search result sorting and recommendation.

[0026] S4. performing resource heat weighting according to the extracted resource information features, including setting resource heat hyperparameters to adjust the weight of resource heat; First, the recent access volume of resources is counted through search logs, which means that the system will record the number of times or frequency of each resource accessed by users within a period of time (such as the last week, month, etc.). This kind of statistics can intuitively reflect the user's attention to and demand for different resources. Then, a resource heat hyperparameter is set to control the importance of resource heat in the entire weight calculation. By analyzing the resource access situation and user behavior in historical data, the hyperparameter value range is determined. For example, if it is found that the resource access volume is usually concentrated within a certain range, the hyperparameter is set within this range. By adjusting the value of this hyperparameter to adapt to different application scenarios and business needs, the resource heat weighted calculation is performed based on the recent resource access volume and heat hyperparameter. The calculation formula is: , in, Represented as a resource heat hyperparameter, Represents the number of recent resource visits. It is expressed as the weight after resource popularity is weighted. When the input value (i.e. the recent visits to the resource) increases, the increase rate of the output value (i.e. the weight) will gradually slow down. This means that for popular resources (i.e. resources with a large number of visits), a relatively higher weight will be given, but the weight will not increase too dramatically, thus avoiding the situation where a few extremely popular resources completely dominate the ranking.

[0027] S5. Performing model integration on the weighted results of the classification model and the weighted results of the resource heat, including taking the weighted results of the classification model as the basic weights and combining the results of the weighted results of the resource heat through multiplication operations; Combine the results of resource popularity weighting with the results of classification model weighting. Classification model weighting is usually calculated based on resource categories, attributes and other information. After combining the two, the weight of each document takes into account the classification characteristics of the resource and its popularity. Such comprehensive considerations make it more likely that popular resources will be ranked at the top in the sorting, because they may not only be related to user needs in terms of classification, but also show a high degree of popularity in actual user access behavior. The preliminary weights obtained by the classification model weighting As the basic weight, the result of combining the resource heat weight by multiplication operation The final weight after integration is obtained, and the final weight is expressed as: , in, Represents the weight of the classification model after weighting, is represented as the final weight.

[0028] For example, suppose a document has a weight of 0.6 in the classification model weighting, and a weight of 0.8 calculated by resource heat weighting. After combining the two, the new weight may be 0.6 × 0.8 = 0.48. If another document has a classification model weighting weight of 0.5 and a resource heat weighting weight of 0.5, then the new weight is 0.5×0.5=0.25. When sorting, the first document will be ranked higher because of its higher comprehensive weight. Even though it does not necessarily have an advantage over the second document in the classification model weighting, it will eventually get a better ranking position due to its higher heat.

[0029] S6. Use the weights after model integration to perform precise ranking and scoring, and sort the recalled resources according to the final scoring results.

[0030] Select matching rules and determine the matching score based on the matching rules, including exact matching, fuzzy matching, synonym matching, and considering the position and part of speech of the keyword in the document. If the keyword completely matches a piece of text in the document, it is recorded as a complete match score. , using the edit distance algorithm to measure similarity, when the similarity threshold is 0.8, the score , there is a synonym match, score , keywords appear in the title, position score , appears at the beginning of the document, position score , the noun weight is 1.5, the verb weight is 1.2, and the document and keyword are converted into vectors using the word frequency-inverse document frequency, where the word frequency-inverse document frequency is expressed as: Term Frequency - Inverse Document Frequency , , in, is the frequency of word j in document i, is the inverse document frequency, N is the total number of documents, is the number of documents containing word j. In the bag-of-words model, each element of the document vector represents the frequency of the corresponding word in the document. The term frequency-inverse document frequency (TF-IDF) focuses more on the ability to distinguish words. The term frequency (TF) calculates the frequency of a word in a document, and the inverse document frequency (IDF) measures the prevalence of a word in the entire document collection. For example, a common word that appears in many documents has a low IDF value, while a word that appears in only a few documents has a high IDF value. The TF-IDF value is obtained by multiplying TF and IDF to construct a document vector. The construction of the keyword vector is the same as that of the document vector, both using term frequency-inverse document frequency. The relevance score of the keyword vector and the document vector is calculated through cosine similarity, and the score in the rough sorting result is obtained by adding the matching score and the relevance score. , set a score threshold and remove resource information that is less than the threshold. The score threshold is all The average of the scores is used to calculate the final refined ranking score using the weights integrated in S5, and the recalled resources are sorted according to the final scoring result. The formula for calculating the final refined ranking score is: , in, It is expressed as the score in the rough sorting result. Indicates the final refined ranking score. According to the final scoring result , the recalled resources are sorted, and the resources with higher scores are considered to match the user's needs more closely, and are placed at the front of the search results.

[0031] Example 2 The difference between this embodiment and Embodiment 1 is that this embodiment provides a vertical search engine ranking system based on multi-dimensional features.

[0032] The data acquisition module is configured to: acquire user resource information, including document information, resource popularity, column information and user behavior data; The feature extraction module is configured to: perform feature extraction based on the acquired resource information, including extracting document features, resource popularity features, column features, and user behavior features of the resource information; The preliminary weighting module is configured to: perform classification model weighting according to the extracted resource information features, including calculating the classification model weighting by combining chi-square feature extraction and Bayesian classification; The heat weighting module is configured to: weight the resource heat according to the extracted resource information features, including setting resource heat hyperparameters for adjusting the weight of the resource heat; The integration module is configured to: perform model integration on the weighted result of the classification model and the weighted result of the resource heat, including taking the weighted result of the classification model as a basic weight and combining the result of the weighted result of the resource heat through a multiplication operation; The refined ranking module is configured to: perform refined ranking scoring using the weights after model integration, and sort the recalled resources according to the final scoring results.

[0033] A computer-readable storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded and executed by a processor of a terminal device for a vertical search engine precise ranking method based on multi-dimensional features.

[0034] A terminal device includes a processor and a computer-readable storage medium, wherein the processor is used to implement various instructions; the computer-readable storage medium is used to store multiple instructions, wherein the instructions are suitable for being loaded by the processor and executed by the vertical search engine ranking method based on multi-dimensional features.

[0035] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A vertical search engine ranking method based on multi-dimensional features, characterized in that: include: Obtain the recalled resource information, including document information, resource popularity, column information, and user behavior data; Feature extraction is performed based on the acquired resource information, including document features, resource popularity features, column features, and user behavior features of the resource information; Weighting the classification model according to the extracted resource information features, including calculating the classification model weight by combining chi-square feature extraction and Bayesian classification; Perform resource heat weighting according to the extracted resource information features, including setting resource heat hyperparameters to adjust the weight of resource heat; The weighted results of the classification model and the weighted results of the resource heat are integrated into a model, including taking the weighted results of the classification model as the basic weight and combining the results of the resource heat weight through multiplication operation; Use the weights after model integration to perform precise ranking and scoring, and sort the recalled resources according to the final scoring results.

2. According to claim 1, a vertical search engine ranking method based on multi-dimensional features is characterized in that: The classification model is weighted according to the extracted resource information features, including calculating the occurrence frequency and chi-square statistics of each feature in different categories, screening out features with distinguishing ability, calculating the prior probability and posterior probability of each word in different categories through Bayesian classification, and selecting the category with the largest posterior probability as the classification of the document. The calculation formula of the Bayesian classification is: ， in, Represented as keywords, Represented as categories, Represented as category The prior probability of Represented as in category Next, the word appears in the document The joint probability of Represents the word that appears in the document , the posterior probability that the document belongs to the category.

3. A vertical search engine ranking method based on multi-dimensional features according to claim 2, characterized in that: The weighting of the classification model according to the extracted resource information features also includes setting a column coefficient according to the importance of the column information to the business, and obtaining a preliminary weight of each document by multiplying the Bayesian posterior probability with the column coefficient.

4. A vertical search engine ranking method based on multi-dimensional features according to claim 3, characterized in that: The resource heat weighting according to the extracted resource information features includes obtaining the search log statistics of the recent resource visits, and setting the resource heat hyperparameters to adjust the resource heat weight, and calculating the resource heat weighting based on the recent resource visits and the heat hyperparameters. The calculation formula is: ， in, Represented as a resource heat hyperparameter, Represents the number of recent resource visits. Indicates the weight after resource heat is weighted.

5. A vertical search engine ranking method based on multi-dimensional features according to claim 4, characterized in that: The weighted results of the classification model and the weighted results of resource heat are integrated into a model, including the initial weight obtained by the weighted classification model. As the basic weight, the result of combining the resource heat weight by multiplication operation The final weight after integration is obtained, and the final weight is expressed as: , in, Represents the weight of the classification model after weighting, is represented as the final weight.

6. A vertical search engine ranking method based on multi-dimensional features according to claim 5, characterized in that: The method of using the weights after model integration to perform fine ranking scoring includes calculating the scores in the rough ranking results according to the matching rules, calculating the final fine ranking scores using the weights after model integration, and sorting the recalled resources according to the final scoring results. The formula for calculating the final fine ranking scores is: , in, It is expressed as the score in the rough sorting result. Indicates the final refined score.

7. A vertical search engine ranking method based on multi-dimensional features according to claim 6, characterized in that: The method of calculating the scores in the rough sorting results according to the matching rules includes selecting the matching rules and determining the matching scores according to the matching rules, converting the documents and keywords into vectors using the word frequency-inverse document frequency, calculating the relevance scores through the cosine similarity, determining the scores in the rough sorting results according to the matching scores and the relevance scores, setting a score threshold and eliminating resource information with a score less than the threshold.

8. A vertical search engine ranking system based on multi-dimensional features, characterized in that: include: The data acquisition module is configured to: acquire user resource information, including document information, resource popularity, column information and user behavior data; The feature extraction module is configured to: perform feature extraction based on the acquired resource information, including extracting document features, resource popularity features, column features, and user behavior features of the resource information; The preliminary weighting module is configured to: perform classification model weighting according to the extracted resource information features, including calculating the classification model weighting by combining chi-square feature extraction and Bayesian classification; The heat weighting module is configured to: weight the resource heat according to the extracted resource information features, including setting resource heat hyperparameters to adjust the weight of the resource heat; The integration module is configured to: perform model integration on the weighted result of the classification model and the weighted result of the resource heat, including taking the weighted result of the classification model as a basic weight and combining the result of the weighted result of the resource heat through a multiplication operation; The fine ranking module is configured to: use the weights after model integration to perform fine ranking scoring, and sort the recalled resources according to the final scoring results.

9. A computer-readable storage medium storing a plurality of instructions, characterized in that: The instructions are suitable for being loaded by a processor of a terminal device and executing a vertical search engine ranking method based on multi-dimensional features as described in claim 1.

10. A terminal device, comprising a processor and a computer-readable storage medium, wherein the processor is used to implement each instruction; and the computer-readable storage medium is used to store multiple instructions, characterized in that: The instructions are suitable for being loaded by a processor and executing a vertical search engine ranking method based on multi-dimensional features as described in claim 1.

Images