Method for constructing electronic material SKU intelligent search engine and use method of electronic material SKU intelligent search engine

Abstract

The invention relates to the technical field of information technologies, in particular to a method for constructing an electronic material SKU intelligent search engine. S1, acquiring component parameters; s2, cleaning the acquired information by using a cleaning module; s201, carrying out simplified and traditional Chinese medicine conversion; s202, performing word segmentation on the processed parameters by using a Chinese and English word segmentation device; s203, unit conversion is carried out; s204, turning to lowercase processing; s205, carrying out synonym addition; s206, removing duplicate words in the parameters; s3, completing construction of a new ES search engine; according to attributes of components, such as brands, classification and specifications, an electronic component library convenient for a user to retrieve is established, and a word segmentation algorithm and a synonym adding method are improved, so that the ability of a search engine to understand terms and curry in the electronic component industry can be improved, and the search efficiency is improved. And a user can conveniently, quickly and accurately retrieve the corresponding component.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to a method for constructing an electronic material SKU intelligent search engine and a method of using the same. Background Art

[0002] In the online mall for electronic components, the search terms entered by users may be diverse, ambiguous, and irregular, which makes it difficult for traditional search engines to accurately understand the user's search intent, often resulting in poor relevance of search results and difficulty for users to accurately find the specific components they need. In addition, due to the wide variety of parameters and specifications of electronic components, traditional search engines are inefficient in processing this professional information and are unable to provide accurate search results.

[0003] In view of this, in order to overcome the above technical problems, the present invention proposes a method for constructing an electronic material SKU intelligent search engine and a method of using the method, which solves the above technical problems. Summary of the invention

[0004] In order to make up for the deficiencies of the prior art, the present invention proposes a method for constructing an electronic material SKU intelligent search engine and a method of using the same.

[0005] The technical solution adopted by the present invention to solve its technical problem is: A method for constructing an electronic material SKU intelligent search engine, comprising: S1. Obtain component parameters; S2, using a cleaning module to clean the above-obtained information; S201, Simplified Chinese to Traditional Chinese conversion; S202, using a Chinese and English word segmenter to segment the above processed parameters; S206, removing repeated words in the parameters; S203, specification unit conversion, unified specification unit format; S204, converting to lower case; S205, adding the newly added material codes and brand names as synonyms to the synonym dictionary; S207, storing the material code, brand, and specification of the components in corresponding data tables respectively, and obtaining a coding library, a brand library, and a specification library of the components.

[0006] S3. Complete the construction of the new ES search engine.

[0007] Preferably, the component parameters include component material code, brand and specifications.

[0008] Preferably, the simplified-traditional conversion includes converting Traditional Chinese into Simplified Chinese.

[0009] A method for constructing an electronic material SKU intelligent search engine and a method for using the method thereof, comprising: S1, user inputs text; S2, perform semantic recognition on the input text and propose effective keywords; S3, cleaning the keywords; S301, segmenting keywords; S302, unit conversion; S303, convert to lowercase; S304, removing repeated words; S305, converting the keywords into synonyms to obtain standard descriptions; S306, matching the keywords in the constructed coding library, brand library, and specification library respectively, and classifying and characterizing the keywords; S307, performing a supplementary search on the unmatched keywords in the component slang library; S4. According to the classification results of keywords, construct ES query syntax respectively to perform multi-condition combination query; S5. Match with ES search engine and perform retrieval.

[0010] The beneficial effects of the present invention are as follows: The present invention establishes a library of electronic components that is easy for users to search according to the attributes of components, such as brand, classification, and specifications, and improves the word segmentation algorithm and the method of adding synonyms, which can improve the search engine's understanding of electronic component industry terms and slang, making it convenient for users to search for corresponding components faster and more accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The present invention is further described below in conjunction with the accompanying drawings and implementation modes.

[0012] Figure 1 This is the step of constructing an electronic material SKU intelligent search engine in the present invention; Figure 2 yes Figure 1 The specific steps of S2; Figure 3 These are steps for using the electronic material SKU intelligent search engine in the present invention; Figure 4 yes Figure 2 The specific steps of S3. DETAILED DESCRIPTION

[0013] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.

[0014] like Figure 1 As shown, the method for constructing an electronic material SKU intelligent search engine according to the present invention includes: S1. Obtain component parameters, such as brand, specifications and other parameters of component materials; S2, using a cleaning module to clean the above-obtained information; S201, Simplified Chinese to Traditional Chinese conversion, it is necessary to convert the Traditional Chinese characters in the parameters into Simplified Chinese characters. In this step, the plug-in elastic search stconvert is used to achieve the Simplified Chinese to Traditional Chinese conversion; S202, using the Chinese and English word segmenters to segment the above-processed parameters, if necessary, perform word segmentation on Chinese and English, select different word segmentation tools for the word segmentation of the two different languages, after selecting the word segmentation tool, start the word segmentation operation, input the parameter keywords processed in the above steps into the tool (obtain text), call the corresponding interface or function to perform the word segmentation operation, process the result after the word segmentation operation, and perform further operations, such as removing stop words, and removing some articles in English, etc.; The above-mentioned word segmentation operation tools (such as execution code and selected tools or libraries, etc.) are all prior art, so they are not described in detail in this article. The obtained word segmentation is transferred to the next step; S203, unit conversion. In this step, the unit conversion is realized based on the component specification unit by using, for example, an elasticsearch token filter. In order to facilitate user retrieval, the unit can be converted into the minimum unit value. In the processing flow, since the parameter text has been processed by the above-mentioned word segmentation, when the token filter receives a series of words (token), it can identify words related to the unit, such as 1KΩ, 1Ω, etc. The filter will identify the unit identifiers such as KΩ and Ω, and change the unit according to the unit conversion rules (which can be uniformly modified to the minimum unit according to the rules, such as the conversion from KΩ to Ω). The converted word is output as a new token and continues to participate in the subsequent search processing flow. In this way, when searching, no matter whether the unit parameter input by the user is the original unit or the converted unit, the relevant component can be matched, which greatly improves the accuracy of the retrieval. S204, convert to lowercase; in this step, you can use elastic search lowercase tokenfilter to convert characters / segments composed of English and other Latin words to lowercase. For each input word, the filter converts all the characters to lowercase. For example, the input word "Amplifier" is output as "amplifier" after passing through the filter. After being output as a new token, when building the index, the lowercase converted word is stored in the index. When the user searches, regardless of whether the input query is uppercase, lowercase, or mixed case, Elasticsearch will also convert the query to lowercase, and then match it in the index to ensure that the components containing the corresponding content can be found. For example, when the components contain "Amplifier" and "amplifier", when the user searches for "Amplifier" or "amplifier", the component can be successfully matched; S205, add synonyms; use the elastic search Synonym token filter to add synonyms. This is because after the word segmentation process, a series of words are generated. The words are used as the input of the Synonym Token Filter. The filter will check the input words one by one to see if they match the defined synonym rules. If a word is found in the synonym rule, its synonym will be added. For example, the input word is "Inductor" and, according to the previously defined synonym rule, "coil" is added as a new token. After processing, a series of tokens containing the original word and the added synonyms are output. For example, when the user searches for the parameter "coil", components containing "Inductor" can also be found; S206, remove duplicate words in the parameters; use the elastic search unique token filter to remove duplicates, and also perform deduplication after word segmentation. When the input parameters pass through the filter, the filter will traverse all input words to check whether there are duplicate words. If duplicate words are found, only one instance is retained and the other duplicate parts are removed. By removing duplicate words, the number of words stored in the index can be reduced, thereby reducing the size of the index and improving storage efficiency and search performance; S3. Complete the construction of the new ES search engine.

[0015] like Figure 2 As shown, a method for constructing an electronic material SKU intelligent search engine and a method for using the method thereof include: S1. The user inputs text, which can be material parameters, etc. S2. Perform semantic recognition on the input text and propose effective keywords; build an electronic component knowledge base based on the above construction, which contains detailed information such as the names, specifications, parameters, functional descriptions, application scenarios, etc. of various electronic components. This knowledge base can be a structured database. When a text about electronic components is input, the text is first preprocessed, including noise removal, word segmentation, part-of-speech tagging, etc. Then, the preprocessed text is analyzed using a domain identification algorithm. The algorithm extracts features from the text, such as word frequency, word vectors, grammatical structure, etc., and compares and matches them with the information in the knowledge base. Based on the results of semantic recognition, keywords are further extracted. A variety of methods can be used for keyword extraction, that is, to select keywords from the text that best represent the subject of the text; S3, cleaning the keywords; S301, segmenting keywords; S302, unit conversion; S303, convert to lowercase; S304, removing repeated words; S4. Build ES query syntax; S5. Match with ES search engine and perform retrieval.

[0016] In the description of the present invention, it should be noted that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate directions or positional relationships based on the attached Figure 1 The orientation or positional relationship shown is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation. Therefore, it cannot be understood as limiting the scope of protection of the present invention. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0017] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for constructing an electronic material SKU intelligent search engine, characterized in that: include S1. Obtain component parameters; S2, using a cleaning module to clean the above-obtained information; S201, Simplified Chinese to Traditional Chinese conversion; S202, using a Chinese and English word segmenter to segment the above processed parameters; S203, removing repeated words in the parameters; S204, unit conversion; S205, converting to lower case; S206, adding synonyms, adding the newly added material codes and brand names as synonyms into the synonym dictionary; S207, storing the material code, brand, and specification of the components in corresponding data tables, respectively, to obtain a coding library, a brand library, and a specification library of the components; S3. Complete the construction of the new ES search engine.

2. The electronic material SKU intelligent search engine according to claim 1, characterized in that: The component parameters include component material code, brand and specifications.

3. The electronic material SKU intelligent search engine according to claim 2, characterized in that: The simplified-traditional conversion includes converting Traditional Chinese into Simplified Chinese.

4. A method for using the electronic material SKU intelligent search engine according to any one of claims 1 to 3, characterized in that: include: S1, user inputs text; S2, perform semantic recognition on the input text and propose effective keywords; S3, cleaning the keywords; S301, segmenting keywords; S302, unit conversion; S303, convert to lowercase; S304, removing repeated words; S305, converting the keywords into synonyms to obtain standard descriptions; S306, matching the keywords in the constructed coding library, brand library, and specification library respectively, and classifying and characterizing the keywords; S307, performing a supplementary search on the unmatched keywords in the component slang library; S4. According to the classification results of keywords, construct ES query syntax respectively to perform multi-condition combination query; S5. Match with ES search engine and perform retrieval.

Images