Item recall method and system, electronic device and readable storage medium

An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor is configured to implement an item recall method, when executing the computer program,

• wherein the item recall method comprises:
• acquiring, by the electronic device, behavior data of a user, wherein the behavior data comprises items which are clicked and/or purchased and item information of each of the items;
• inputting, by the electronic device, a retrieval category word;
• extracting, by the electronic device, target behavior data containing the retrieval category word from the behavior data;
• acquiring, by the electronic device, retrieval words of each of the items in the target behavior data and a retrieval frequency of each of the retrieval words in the target behavior data in a reverse correlation manner;
• performing, by the electronic device, word segmentation on the item information in the target behavior data to obtain a plurality of item segmented words;
• calculating, by the electronic device, a similarity between all of the retrieval words and the plurality of item segmented words;
• determining, by the electronic device, whether the similarity is greater than a first preset threshold or not, and based on a result of determination that the similarity is greater than a first preset threshold, extracting, by the electronic device, a retrieval word with a retrieval frequency greater than a preset frequency as an expansion word of the retrieval category word from the all of the retrieval words;
• and
• performing, by the electronic device, item recall according to the retrieval category word and the expansion word,
• wherein before performing, by the electronic device, the item recall according to the retrieval category word and the expansion word, the item recall method further comprises:
• constructing, by the electronic device, a corpus, wherein the corpus comprises an item recommendation article and item basic information;
• training, by the electronic device, the corpus to obtain a word vector library based on word2vec, wherein the word vector library is configured to store a plurality of item feature words and a feature vector corresponding to each of the plurality of item feature words;
• calculating, by the electronic device, a similarity between the retrieval category word and the each of the item feature words based on a similarity algorithm;
• and
• extracting, by the electronic device, an item feature word whose similarity with the retrieval category word is greater than a second preset threshold, to be added into the expansion word.

A non-transitory readable storage medium, wherein a computer program is stored on the readable storage medium, wherein the computer program is configured to implement an item recall method when executed by a processor of an electronic device,

• wherein the item recall method comprises:
• acquiring, by the electronic device, behavior data of a user, wherein the behavior data comprises items which are clicked and/or purchased and item information of each of the items;
• inputting, by the electronic device, a retrieval category word;
• extracting, by the electronic device, target behavior data containing the retrieval category word from the behavior data;
• acquiring, by the electronic device, retrieval words of each of the items in the target behavior data and a retrieval frequency of each of the retrieval words in the target behavior data in a reverse correlation manner;
• performing, by the electronic device, word segmentation on the item information in the target behavior data to obtain a plurality of item segmented words;
• calculating, by the electronic device, a similarity between all of the retrieval words and the plurality of item segmented words;
• determining, by the electronic device, whether the similarity is greater than a first preset threshold or not, and based on a result of determination that the similarity is greater than a first preset threshold, extracting, by the electronic device, a retrieval word with a retrieval frequency greater than a preset frequency as an expansion word of the retrieval category word from the all of the retrieval words;
• and
• performing, by the electronic device, item recall according to the retrieval category word and the expansion word,
• wherein before performing, by the electronic device, the item recall according to the retrieval category word and the expansion word, the item recall method further comprises:
• constructing, by the electronic device, a corpus, wherein the corpus comprises an item recommendation article and item basic information;
• training, by the electronic device, the corpus to obtain a word vector library based on word2vec, wherein the word vector library is configured to store a plurality of item feature words and a feature vector corresponding to each of the plurality of item feature words;
• calculating, by the electronic device, a similarity between the retrieval category word and the each of the item feature words based on a similarity algorithm;
• and
• extracting, by the electronic device, an item feature word whose similarity with the retrieval category word is greater than a second preset threshold, to be added into the expansion word.