An information retrieval method, intelligent terminal and computer-readable storage medium

Abstract

The present invention discloses an information retrieval method, a smart terminal, and a computer-readable storage medium. The method includes: obtaining an instruction statement sent by a user; determining a replacement word corresponding to the instruction statement according to a target word in the instruction statement; and determining and outputting target information corresponding to the instruction statement according to the replacement word. The present invention can improve the accuracy of information retrieval results.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular, to an information retrieval method, an intelligent terminal, and a computer-readable storage medium. Background Art

[0002] With the development of natural language processing technology, users can issue various types of instructions through voice or text, such as controlling power on / off, opening a specific software, and so on. However, the words in such instructions are generally few and relatively fixed. For example, when a user wants to power on or off, the instructions used are generally "power on" or "power off", and when opening software A, the instruction is generally "open software A".

[0003] However, when performing information retrieval through voice or text, the instructions issued by users are often encountered. The terminal can only search for relevant information based on the target words in the user's instructions. Therefore, the obtained information is relatively crude and it is difficult to meet the user's needs. For example, when a user wants to listen to the songs of a certain band and issues the instruction "search for the songs of a certain band", the terminal may recognize it normally. However, this band may have abbreviations, transliterations, free translations, pet names, and may also have different names in different periods. When the user issues the instruction, the abbreviation of this band may be used, and at this time, the terminal may not be able to correctly recognize it. Therefore, when the instruction issued by the user is a retrieval-related instruction, that is, an instruction statement, the terminal often cannot accurately recognize it and provide an effective retrieval result. Summary of the Invention

[0004] The main purpose of the present invention is to provide an information retrieval method, an intelligent terminal, and a computer-readable storage medium, aiming to solve the problem in the prior art that an effective retrieval result cannot be provided according to the instruction statement of the user.

[0005] To achieve the above object, the present invention provides an information retrieval method, and the information retrieval method includes the following steps:

[0006] Obtain an instruction statement sent by a user;

[0007] Determine a replacement word corresponding to the instruction statement according to the target word in the instruction statement;

[0008] Determine the target information corresponding to the instruction statement according to the replacement word and output it.

[0009] Optionally, in the information retrieval method, the step of determining a replacement word corresponding to the instruction statement according to the target word in the instruction statement specifically includes:

[0010] Determine the target word corresponding to the instruction statement according to a preset target word library;

[0011] Determine the replacement word corresponding to each of the target words according to a preset replacement word library.

[0012] Optionally, in the information retrieval method, where determining the target word corresponding to the instruction statement according to a preset target word library specifically includes:

[0013] Segment the instruction statement to generate multiple text strings;

[0014] Determine the target word in the text string according to the target word similarity value between the text string and each keyword in the preset target word library.

[0015] Optionally, in the information retrieval method, where the replacement words include the hypernyms, hyponyms, synonyms, and near-synonyms corresponding to the keywords in the target word library; before determining the replacement word corresponding to each of the target words according to the preset replacement word library, it further includes:

[0016] For each of the keywords, use the hypernyms, hyponyms, synonyms, and near-synonyms corresponding to the keyword as the corresponding replacement words according to a preset established knowledge library.

[0017] Optionally, in the information retrieval method, where the replacement words include the aliases corresponding to the keywords in the target word library; before determining the replacement word corresponding to each of the target words according to the preset replacement word library, it further includes:

[0018] Obtain and collect social statements, and cluster the social statements to generate multiple social statement groups;

[0019] Determine the reference statements in each of the social statement groups according to a preset reference statement rule;

[0020] For each of the social statement groups, determine the alias corresponding to the reference string in the reference statement in each social statement in the social statement group according to the reference statement in the social statement group, where the reference string is a string corresponding to the keyword in the keyword library;

[0021] Determine the alternative name corresponding to the keyword and use it as the corresponding replacement word according to the correspondence between the reference string and the keyword.

[0022] Optionally, in the information retrieval method, where determining the reference statements in each of the social statement groups according to a preset reference statement rule specifically includes:

[0023] For each social statement group, calculate the statement similarity value between each social statement in the social statement group;

[0024] Determine a reference statement in the social statement group according to the statement similarity value.

[0025] Optionally, in the information retrieval method, the determining the target information corresponding to the instruction statement according to the replacement word and outputting the same specifically includes:

[0026] Combine the replacement words corresponding to each of the target words to generate a plurality of replacement word sets;

[0027] Use the target words as a target word set, and determine and output the target information corresponding to the instruction statement according to the replacement word set and the target word set.

[0028] Optionally, in the information retrieval method, the determining the target information corresponding to the instruction statement according to the replacement word set and the target word set and outputting the same specifically includes:

[0029] For each of the replacement word sets, determine the corresponding data information according to the replacement words in the replacement word set; and

[0030] Determine the corresponding data information according to the target words in the target word set;

[0031] Sort the data information according to a preset sorting rule, generate the target information corresponding to the instruction statement and output the same.

[0032] In addition, to achieve the above object, the present invention further provides an intelligent terminal, where the intelligent terminal includes: a memory, a processor, and an information retrieval program stored on the memory and executable on the processor, and when the information retrieval program is executed by the processor, the steps of the information retrieval method as described above are implemented.

[0033] In addition, to achieve the above object, the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores an information retrieval program, and when the information retrieval program is executed by a processor, the steps of the information retrieval method as described above are implemented.

[0034] After obtaining the instruction statement, the present invention does not conventionally directly perform information retrieval according to the target words that play a role in understanding the meaning in the instruction statement. Instead, it first determines the possible replacement words according to the target words in the instruction statement, and then searches for the corresponding target information according to the target words and the replacement words. Since replacing the instruction statement with the replacement words will not cause ambiguity in understanding the instruction statement, but can expand the retrieval object, more accurate retrieval results can be provided. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 is a flowchart of a preferred embodiment provided by the information retrieval method of the present invention;

[0036] Figure 2 is a flowchart of step S200 in a preferred embodiment provided by the information retrieval method of the present invention;

[0037] Figure 3 is a flowchart of step S210 in a preferred embodiment provided by the information retrieval method of the present invention;

[0038] Figure 4 is a schematic diagram of the operating environment of a preferred embodiment of the intelligent terminal of the present invention. Detailed implementation manners

[0039] To make the objectives, technical solutions and advantages of the present invention clearer and more definite, the present invention will be further described in detail below with reference to the accompanying drawings and by way of examples. It should be understood that the specific examples described herein are only used to explain the present invention and are not used to limit the present invention.

[0040] The information retrieval method according to a preferred embodiment of the present invention, as Figure 1 shown, the information retrieval method includes the following steps:

[0041] Step S100, obtaining an instruction statement sent by a user.

[0042] Specifically, in this embodiment, the main body for executing the information retrieval method is an assistant software installed on an intelligent terminal. When a user uses the intelligent terminal, the user can issue an instruction through the physical keyboard, virtual keyboard or microphone of the intelligent terminal. For example, "Find the latest album of Band A". When the instruction statement is in the form of voice, after the intelligent terminal obtains the instruction statement of the user through the microphone, for the convenience of processing, voice recognition is also required to convert it into a text-form instruction statement and store it locally. Then the assistant software obtains the instruction statement locally. Among them, the assistant software can be in a real-time running state or a sleep state. If it is in the sleep state, then when the intelligent terminal obtains the instruction statement, the assistant software can be woken up to work.

[0043] Step S200, determining a replacement word corresponding to the instruction statement according to a target word in the instruction statement.

[0044] Specifically, after obtaining the instruction statement, the assistant software first determines the target word corresponding to the instruction statement. The target word refers to a word that plays a key role in understanding the instruction statement. A replacement word library is preset, and each word may corresponding replacement words are stored in the replacement word library. The replacement word refers to a word that replaces the corresponding word in the instruction statement and does not affect the meaning of the entire instruction statement. Since the replacement words and words in the replacement word library are corresponding, therefore, according to this corresponding relationship and the target word in the instruction statement, the replacement word corresponding to the instruction statement can be determined.

[0045] Further, referring to Figure 2 , step S200 includes:

[0046] Step S210, determine the target word in the instruction statement according to a preset target word library.

[0047] Specifically, a target word library is preset in which multiple keywords are stored. In the first implementation manner of this embodiment, the process of determining the target word is as follows: According to the keywords in this target word library, traverse them in sequence according to the statement order in the instruction statement. When a certain keyword in the instruction statement completely matches a keyword in the target word library, then determine that keyword as the target word in the instruction statement.

[0048] Further, since the division between Chinese words is not determined according to the statement order. For example, for the sentence "There is a battery in the office", according to the statement order, it should be divided into "office", "indoor", "there is electricity" and "pool", but this completely does not conform to the true meaning of this sentence. Therefore, there are significant deficiencies in adopting the first implementation manner. Referring to Figure 3 , in order to improve the accuracy of target word retrieval in this embodiment, the method of determining the target word is as follows:

[0049] Step S211, perform word segmentation on the instruction statement to generate multiple text strings.

[0050] Specifically, first perform word segmentation on the instruction statement to generate multiple text strings. Word segmentation refers to the form of splitting the text into the smallest speech expression units. In this embodiment, it is preferably performed using a statistical-based word segmentation method, such as a word segmentation method based on conditional random fields, a word segmentation method based on hidden Markov models, and a word segmentation method based on deep learning. Through the above word segmentation method, the instruction statement is split into multiple text strings. For example, the sentence "Find the latest album of Band A" is split into "find", "Band A", "of", "latest" and "album".

[0051] Step S212, determine the target word in the text string according to the target word similarity value between the text string and each keyword in the preset target word library.

[0052] Specifically, the obtained text string is then calculated with each keyword in the preset target word library for the target word similarity value. There are many ways to calculate the target word similarity value. For example, the common keyword similarity calculation based on word vectors. First, the text string and the keywords in the target word library are converted into vector forms through methods such as word2vec. Since vectors have numerical values and directions, the difference between the two can be calculated. The methods to describe the difference are generally word mover's distance and cosine value. The larger the word mover's distance, the farther the two are, so the similarity value is smaller; the smaller the word mover's distance, the closer the two are, so the similarity value is larger. The cosine value uses the cosine value of the angle between two vectors to describe the similarity of the two vectors. The closer the cosine value is to 1, it indicates that the angle between the two vectors is only 0 degrees, and the vectors are more similar, so the similarity value is smaller.

[0053] In this embodiment, since not every word in the instruction statement is necessarily a target word. For example, the word "de" in the example sentence, a target word similarity value threshold is preset in advance. Then, for each text string, the target word similarity value between the text string and each keyword in the target word library is calculated. Then, the text string corresponding to the target word similarity value that exceeds the target word similarity threshold and has the largest value is selected as the target word.

[0054] Step S220, according to the preset replacement word library, determine the replacement word corresponding to each said target word.

[0055] Specifically, a replacement word library is preset in advance. The replacement word library contains the replacement words corresponding to each keyword in the above-mentioned target word library. The replacement word refers to a keyword that can replace the keyword in the sentence without affecting the meaning of the sentence. For example, the replacement words for "search" above can be "look for", "retrieve" and other words, and the replacement words are corresponded with each keyword in the target word library. Since the target word is determined through the target word library and there is a corresponding keyword for the target word in the target word library, when the target word is determined, its corresponding replacement word is searched for in the replacement word library according to the target word.

[0056] Further, the replacement words include the hypernyms, hyponyms, synonyms and near-synonyms corresponding to the keywords in the target word library; before step S220, it further includes: for each said keyword, according to the preset established knowledge base, taking the hypernyms, hyponyms, synonyms and near-synonyms corresponding to the keyword as the corresponding replacement words.

[0057] Specifically, the hypernym-hyponym relationship is a linguistic concept. A word with stronger generalization ability is called the hypernym of a word with stronger specificity, and a word with stronger specificity is called the hyponym of a word with stronger generalization ability. Near-synonyms refer to keywords with relatively similar meanings, while synonyms refer to two words with exactly the same meaning. For example, the hypernyms of "video" include "audio", and the hyponyms of "audio" include "video". The near-synonyms and synonyms of "search" include "look for", "seek", etc. A predefined knowledge base is preset. The predefined knowledge base refers to a knowledge base that has been determined. In this embodiment, the predefined knowledge base includes the relationships between the hypernyms, hyponyms, synonyms, and near-synonyms that are currently known, forming a network of hypernym-hyponym keywords and near-synonyms for the keyword. Then, according to the relationships between the words in the predefined knowledge base, the hypernyms, hyponyms, synonyms, and near-synonyms corresponding to the keywords in the target word library can be determined, and these words are used as the replacement words corresponding to the keywords in the target word library and stored in the replacement word library.

[0058] Furthermore, the replacement words include the aliases corresponding to the target words; before step S220, the following steps are further included:

[0059] Step A10, acquiring the collected social statements, and clustering the social statements to generate multiple social statement groups.

[0060] Specifically, since hypernyms, hyponyms, synonyms, and near-synonyms are all obtained based on the relationships between established words, however, with the development of the network, the meanings of many words are developing rapidly, and the changes in the meanings of many words are generated based on social networks. For example, the abbreviation of "Band A" is "B", and the transliteration name is "C", but both "B" and "C" are equivalent to "Band A". Therefore, a large number of social statements are collected first.

[0061] After the social statements are collected, the social statements are clustered. In this embodiment, the preferred clustering method is to first perform supervised clustering, classify according to the fields corresponding to the social statements, obtain multiple social statement groups based on social fields, and then perform supervised or unsupervised clustering on these social statements in the social statement groups based on social fields. The purpose of distinguishing social fields is that in different fields, the meanings of the same word may be different. For example, "outline" refers to a summary or detailed rules in the literary field, while in the biological field, it refers to two levels of biological classification based on the Linnaean biological classification method. Therefore, the fields corresponding to the social statements are divided first. The realization of dividing social fields can be based on the collection platform of social statements, such as medical-related, astronomy-related, entertainment-related, etc. After the social statements are obtained, a supervised or unsupervised clustering method is used to group the social statements within the same social field to obtain multiple social statement groups.

[0062] Step A20: Determine the reference statements in each of the social statement groups according to the preset reference statement rules.

[0063] Specifically, a reference statement refers to a statement in the social statement group that contains a keyword corresponding to the keywords in the keyword library. Since the social statements in the social statement group are related to each other, if a certain social statement contains a keyword, then in the social statements similar to this social statement, that is, the reference statement, it is very likely that an alias corresponding to the keyword appears. Therefore, according to the reference statement, it is possible to determine the aliases corresponding to the keyword that may appear in other social statements in the social statement group.

[0064] Furthermore, step A20 includes:

[0065] Step A21: For each social statement group, calculate the statement similarity values between the social statements in the social statement group.

[0066] Specifically, taking each social statement group as a unit, calculate the statement similarity values between the social statements in the same social statement group. The method of calculating statement similarity is similar to the method of calculating keyword similarity mentioned above. The difference is that the vectors obtained from words are generally smaller and the calculation is faster, while the statements are longer. Therefore, the vectors generally exist in the form of matrices and the calculation is more complex. The calculation methods include Jaccard coefficient calculation, edit distance calculation, etc., which will not be elaborated here one by one.

[0067] Step A22: Determine the reference statements in the social statement group according to the statement similarity values.

[0068] Specifically, compare the magnitudes of the statement similarity values, and then select the social statements with relatively high statement similarity values in this social statement group as reference statements.

[0069] It should be noted that according to the different levels of detail of grouping, the social statement group may include multiple small social statement groups. Taking the medical field as an example, the social statement group based on medicine can be further divided into traditional Chinese medicine and Western medicine. Western medicine can be divided into clinical medicine and basic medicine, and basic medicine can be further divided into medical biochemistry, human immunology, etc. The lowest-level social statement group is included in the upper-level social statement group. Generally, the reference statements in the social statement group are determined by selecting in the lowest-level social statement group.

[0070] Step A30: For each of the social statement groups, determine the aliases corresponding to the reference strings in the reference statements in the social statement group in each social statement, where the reference string is the string corresponding to the keyword.

[0071] Specifically, after determining the reference statement in each social statement group, first adopt the method of determining the target word in the above-mentioned instruction statement, and according to the keywords in the keyword library, determine the string equal to the keyword in the reference statement and use it as the reference string. Then, for each social statement, perform word segmentation on the social statement to obtain multiple strings, and then calculate the alias similarity value between each string and the reference string. Then, use the string whose alias similarity value exceeds the preset alias similarity threshold as the alias corresponding to the reference character.

[0072] Step A40, according to the corresponding relationship between the reference string and the keyword, determine the alias corresponding to the keyword and use it as the corresponding replacement word.

[0073] Specifically, since the reference string and the keyword are in a corresponding relationship, after determining the alias corresponding to the reference string, according to the corresponding relationship between it and the keyword, the alias corresponding to the keyword can be determined, and this alias is used as the replacement word corresponding to the keyword.

[0074] Step S300, according to the replacement word and the target word, determine the target information corresponding to the instruction statement and output it.

[0075] Specifically, after determining the replacement word corresponding to the keyword, for example, the replacement words corresponding to "Band A" above are "B" and "C". Then, according to the replacement word and the target word, perform data retrieval to determine the target information corresponding to the instruction statement and output it.

[0076] Furthermore, step S300 includes:

[0077] Step S310, combine the replacement words corresponding to each target word to generate multiple replacement word sets.

[0078] Specifically, taking the target words "search", "Band A", "latest", and "album" as examples, the replacement words corresponding to "search" are "look for", "retrieve", etc., the replacement words for "Band A" are "B" and "C", etc., the replacement word for "latest" is "recent", and the replacement words for "album" are "CD", "music collection". Randomly select one from the replacement words corresponding to "search", for example, "look for", then randomly select one from the replacement words corresponding to "Band A", for example, "B", then select "recent" and "CD" as candidate words, and then combine "look for", "B", "recent", and "CD" to generate a replacement word set. Since the replacement words selected for combination are different, the replacement words in the replacement word set are also different, so multiple replacement word sets are generated.

[0079] Step S320: Use the target word as the target word set, and based on the replacement word set and the target word set, determine the target information corresponding to the instruction statement and output it.

[0080] Specifically, after obtaining multiple replacement word sets, use the target word as a group of target word sets. Based on the target word set and the replacement word set, obtain the data information corresponding to this target word set and replacement word set in the pre-connected database as the target information corresponding to this instruction statement.

[0081] Furthermore, since there is a lot of data information obtained based on the replacement word set and the target word set, in order to be able to, Step S320 includes:

[0082] Step S321: For each of the replacement word sets, determine the corresponding data information according to the replacement words in this replacement word set; and determine the corresponding data information according to the target words in the target word set.

[0083] Specifically, use the target words in the target word set as retrieval words to conduct a search in the pre-connected database, thereby determining the data information corresponding to this target word set. At the same time, for each replacement word set, use the replacement words in this replacement word set as retrieval words to conduct a search in the pre-connected database, thereby determining the data information corresponding to this replacement word set. Finally, obtain multiple relevant data information.

[0084] Step S322: Sort the data information according to a preset sorting rule to generate the target information corresponding to the instruction statement.

[0085] Specifically, the sorting rule is the rule for sorting data information. It can calculate the similarity value between the data information and the instruction statement and sort according to the size of the similarity value; it can also give different weight values to different keywords or replacement words in advance. For example, if an alias has the highest usage frequency and the widest usage range, then increase the weight of this alias. After obtaining the data information, calculate the weight value corresponding to the data information according to the weight value of the replacement word or keyword corresponding to the data information, and then sort the data information according to the weight value to generate the target information corresponding to the instruction statement.

[0086] Furthermore, after obtaining the target information, execute the corresponding instruction according to this target information. For example, if the obtained target information is the "song list in the latest album of Band A" as mentioned above, play this album according to the song list. Therefore, this solution can be combined with the execution of instructions to perform corresponding operations in sequence according to the target information.

[0087] Furthermore, as Figure 4As shown, based on the above information retrieval method, the present invention also correspondingly provides an intelligent terminal, which includes a processor 10, a memory 20, and a display 30. Figure 4 Only some components of the intelligent terminal are shown. However, it should be understood that it is not required to implement all the shown components, and more or fewer components can be alternatively implemented.

[0088] In some embodiments, the memory 20 may be an internal storage unit of the intelligent terminal, such as the hard disk or memory of the intelligent terminal. In other embodiments, the memory 20 may also be an external storage device of the intelligent terminal, such as a plug-in hard disk equipped on the intelligent terminal, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory 20 may also include both the internal storage unit and the external storage device of the intelligent terminal. The memory 20 is used to store application software installed on the intelligent terminal and various types of data, such as the program code installed on the intelligent terminal. The memory 20 may also be used to temporarily store data that has been output or will be output. In one embodiment, an information retrieval program 40 is stored on the memory 20, and this information retrieval program 40 can be executed by the processor 10 to implement the information retrieval method in this application.

[0089] In some embodiments, the processor 10 may be a Central Processing Unit (CPU), a microprocessor, or other data processing chips, and is used to run the program code stored in the memory 20 or process data, such as executing the information retrieval method, etc.

[0090] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch liquid crystal display, and an OLED (Organic Light-Emitting Diode) toucher, etc. The display 30 is used to display information on the intelligent terminal and to display a visual user interface. The components 10 - 30 of the intelligent terminal communicate with each other through a system bus.

[0091] In one embodiment, when the processor 10 executes the information retrieval program 40 in the memory 20, the following steps are implemented:

[0092] Obtain an instruction statement sent by the user;

[0093] Determine a replacement word corresponding to the instruction statement according to the target word in the instruction statement;

[0094] Determine the target information corresponding to the instruction statement according to the replacement word and output it.

[0095] Among them, determining the replacement word corresponding to the instruction statement according to the target word in the instruction statement specifically includes:

[0096] Determine the target word corresponding to the instruction statement according to a preset target word library;

[0097] Determine the replacement word corresponding to each target word according to a preset replacement word library.

[0098] Among them, determining the target word corresponding to the instruction statement according to a preset target word library specifically includes:

[0099] Segment the instruction statement to generate multiple text strings;

[0100] Determine the target word in the text string according to the target word similarity value between the text string and each keyword in the preset target word library.

[0101] Among them, the replacement word includes the hypernyms, hyponyms, synonyms, and near-synonyms of the keywords in the target word library; before determining the replacement word corresponding to each target word according to the preset replacement word library, it further includes:

[0102] For each keyword, use the hypernyms, hyponyms, synonyms, and near-synonyms corresponding to the keyword as the corresponding replacement words according to a preset established knowledge base.

[0103] Among them, the replacement word includes the aliases of the keywords in the target word library; before determining the replacement word corresponding to each target word according to the preset replacement word library, it further includes:

[0104] Obtain the collected social statements, cluster the social statements, and generate multiple social statement groups;

[0105] Determine the reference statements in each social statement group according to a preset reference statement rule;

[0106] For each social statement group, determine the aliases corresponding to the reference strings in the reference statements in each social statement in the social statement group, where the reference string is a string corresponding to the keyword in the keyword library;

[0107] Determine the alternative name corresponding to the keyword according to the corresponding relationship between the reference string and the keyword and use it as the corresponding replacement word.

[0108] Among them, determining the reference statements in each of the social statement groups according to the preset reference statement rules specifically includes:

[0109] For each social statement group, calculate the statement similarity values between the social statements in this social statement group;

[0110] Determine the reference statements in this social statement group according to the statement similarity values.

[0111] Among them, determining the target information corresponding to the instruction statement according to the replacement words and outputting it specifically includes:

[0112] Combine the replacement words corresponding to each target word to generate multiple replacement word sets;

[0113] Use the target words as the target word set, and determine the target information corresponding to the instruction statement according to the replacement word set and the target word set and output it.

[0114] Among them, determining the target information corresponding to the instruction statement according to the replacement word set and the target word set and outputting it specifically includes:

[0115] For each replacement word set, determine the corresponding data information according to the replacement words in this replacement word set; and

[0116] Determine the corresponding data information according to the target words in the target word set;

[0117] Sort the data information according to the preset sorting rules, generate the target information corresponding to the instruction statement and output it.

[0118] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores an information retrieval program, and when the information retrieval program is executed by a processor, the steps of the information retrieval method described above are implemented.

[0119] Of course, those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware (such as a processor, a controller, etc.) through a computer program. The program can be stored in a computer-readable computer-readable storage medium, and when the program is executed, it can include the processes of the above method embodiments. The computer-readable storage medium can be a memory, a magnetic disk, an optical disc, etc.

[0120] It should be understood that the application of the present invention is not limited to the above examples. For those of ordinary skill in the art, improvements or transformations can be made according to the above description, and all such improvements and transformations should fall within the protection scope of the appended claims of the present invention.

Claims

1. An information retrieval method, characterized in that, The information retrieval method includes: Obtaining an instruction statement sent by a user; Determining a replacement word corresponding to the instruction statement according to a target word in the instruction statement; Determining a target word corresponding to the instruction statement according to a preset target word library; Performing word segmentation on the instruction statement to generate a plurality of text strings; the word segmentation splits the text into the form of the smallest speech expression unit, and the word segmentation is performed by using a statistics-based word segmentation method; Determining a target word in the text string according to a target word similarity value between the text string and each keyword in a preset target word library; Obtaining collected social statements, classifying them according to the corresponding fields of the social statements to obtain a plurality of social statement groups based on social fields, and clustering the social statements based on the social statement groups based on social fields to generate a plurality of social statement groups; Determining a reference statement in each of the social statement groups according to a preset reference statement rule; For each social statement group, calculating a statement similarity value between each social statement in the social statement group; Determining a reference statement in the social statement group according to the statement similarity value; For each of the social statement groups, determining an alias in each social statement in the social statement group corresponding to a reference string in the reference statement according to the reference statement in the social statement group, where the reference string is a string corresponding to a keyword in the target word library; Determining an alias corresponding to the keyword as a corresponding replacement word according to the corresponding relationship between the reference string and the keyword; Determining a replacement word corresponding to each of the target words according to a preset replacement word library; the replacement word includes an alias corresponding to a keyword in the target word library; Determining and outputting target information corresponding to the instruction statement according to the replacement word.

2. The information retrieval method according to claim 1, wherein The replacement word includes a hypernym, a hyponym, a synonym, and a near-synonym corresponding to a keyword in the target word library; before determining a replacement word corresponding to each of the target words according to a preset replacement word library, it further includes: For each of the keywords, using a hypernym, a hyponym, a synonym, and a near-synonym corresponding to the keyword as a corresponding replacement word according to a preset established knowledge base.

3. The information retrieval method according to claim 1 or 2, characterized in that, The determining and outputting target information corresponding to the instruction statement according to the replacement word specifically includes: Combining replacement words corresponding to each of the target words to generate a plurality of replacement word sets; Taking the target word as a target word set, and determining and outputting target information corresponding to the instruction statement according to the replacement word set and the target word set.

4. The information retrieval method according to claim 3, characterized in that The determining and outputting target information corresponding to the instruction statement according to the replacement word set and the target word set specifically includes: For each of the replacement word sets, determining corresponding data information according to the replacement words in the replacement word set; and Determining corresponding data information according to the target words in the target word set; Sorting the data information according to a preset sorting rule, generating target information corresponding to the instruction statement, and outputting it.

5. An intelligent terminal, characterized in that, The intelligent terminal includes: a memory, a processor, and an information retrieval program stored on the memory and executable on the processor. When the information retrieval program is executed by the processor, the steps of the information retrieval method according to any one of claims 1-4 are implemented.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores an information retrieval program. When the information retrieval program is executed by a processor, the steps of the information retrieval method according to any one of claims 1-4 are implemented.

Images