Error correction search method and device for English search terms

Abstract

The application discloses a kind of english search term's error correction search method and device, method includes: extracting the first letter of each first word in english search term, obtain the first initial combination of english search term;According to the first initial combination, query preset error correction dictionary, obtain the corresponding english name candidate set of first initial combination;Pre-set error correction dictionary is based on the construction of second initial combination in english name base;According to the word similarity relationship between the second word of english name in english name candidate set and the first word in english search term, the score of each english name is calculated, and the english name with the highest score is used as error correction search result. More and more close english name candidate set can be obtained by initial combination searching preset error correction dictionary, compared with error correction to entire english search term, then based on word similarity relationship, the score of english name is calculated, and the english name with the highest score is used as error correction search result, closer to the search intent of user.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of computer, in particular to a search method and device for correcting search words in English. BACKGROUND

[0002] When searching English names, such as searching English song names, the search result is often not good due to spelling errors of English words, multiple words in the input search words, missing words, and the like.

[0003] The prior art can correct the search words in the manner of name correction and the like, correct spelling errors of independent words, or use a correction dictionary composed of correct English names to correct errors, and then search according to the corrected search words. However, this processing manner generally corrects spelling errors of independent words, and cannot correct missing words, multiple words, or words that are spelled correctly but are not in the correct English names. When using a correction dictionary composed of correct English names to correct errors, if the edit distance is too small, the number of correction candidates is too small, and the desired result of the user cannot be obtained. If there are many error letters in the search words, the edit distance needs to be increased accordingly, which results in a time-consuming correction that increases in a geometric progression. SUMMARY

[0004] In view of the above problems, embodiments of the present application are proposed to provide a search method and device for correcting search words in English that overcome the above problems or at least partially solve the above problems.

[0005] According to an aspect of an embodiment of the present application, a search method for correcting search words in English is provided, and the method comprises:

[0006] extracting the first letters of each first word in the search words in English to obtain a first combination of letters of the search words in English;

[0007] querying a preset correction dictionary according to the first combination of letters to obtain a set of English name candidates corresponding to the first combination of letters; the preset correction dictionary is constructed based on a second combination of letters in an English name library;

[0008] calculating scores of each English name according to a word similarity relationship between the second word of the English name in the set of English name candidates and the first word in the search words in English, and taking the English name with the highest score as a correction search result.

[0009] According to another aspect of an embodiment of the present application, a device for correcting search words in English is provided, and the device comprises:

[0010] an extraction module adapted to extract the first letters of each first word in the search words in English to obtain a first combination of letters of the search words in English;

[0011] The query module is adapted to query a preset error correction dictionary according to the first initial combination to obtain an English name candidate set corresponding to the first initial combination; the preset error correction dictionary is constructed based on a second initial combination in an English name library;

[0012] The score calculation module is adapted to calculate scores of the English names according to a word similarity relationship between the second word of the English names in the English name candidate set and the first word in the English search term, and take the English name with the highest score as the error correction search result.

[0013] According to still another aspect of the embodiments of the present application, a computing device is provided, comprising a processor, a memory, a communication interface and a communication bus, the processor, the memory and the communication interface complete communication with each other through the communication bus;

[0014] The memory is used to store at least one executable instruction, and the executable instruction causes the processor to perform operations corresponding to the error correction search method of the English search term.

[0015] According to still another aspect of the embodiments of the present application, a computer storage medium is provided, the storage medium stores at least one executable instruction, and the executable instruction causes the processor to perform operations corresponding to the error correction search method of the English search term.

[0016] According to the error correction search method and device of the English search term provided by the embodiments of the present application, the preset error correction dictionary is searched by the initial combination method, compared with the error correction of the entire English search term, more English name candidate sets closer to the user's search intention can be obtained, and the scores of the English names are calculated based on the word similarity relationship between the second word and the first word, and the English name with the highest score is taken as the error correction search result, so that the user experience is improved.

[0017] The above description is only a summary of the technical solutions of the embodiments of the present application, in order to more clearly understand the technical means of the embodiments of the present application, the embodiments of the present application can be implemented according to the content of the description, and in order to make the above and other purposes, characteristics and advantages of the embodiments of the present application more obvious and easy to understand, the following specific embodiments of the embodiments of the present application are described. BRIEF DESCRIPTION OF DRAWINGS

[0018] Various other advantages and benefits will become apparent to those of ordinary skill in the art, upon reading the following detailed description of the preferred embodiments. The accompanying drawings are intended to depict only preferred embodiments of the application, and therefore should not be considered to limit the scope of the application in any way. Similarly, like reference numerals have been used in the drawings to depict like elements and features. There may be cases in which components are shown by generalized reference character designations.

[0019] Figure 1Fig. 1 shows a flow chart of a method for error correction search of an English search term according to an embodiment of the present application;

[0020] Figure 2 Fig. 2 shows a structural schematic diagram of an error correction search device for an English search term according to an embodiment of the present application;

[0021] Figure 3 Fig. 3 shows a structural schematic diagram of a computing device according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] Exemplary embodiments of the present application will be described in detail with reference to the drawings. Although exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that this application will be thorough and complete, and will fully convey the scope of the application to those skilled in the art.

[0023] Figure 1 Fig. 1 shows a flow chart of a method for error correction search of an English search term according to an embodiment of the present application, which includes the following steps: Figure 1

[0024] In step S101, the first letter of each first word in the English search term is extracted to obtain a first combination of first letters of the English search term.

[0025] The English search term in the present embodiment can be various English search terms such as English song search terms, English video search terms, English document search terms, etc., which are used to search for English song names, English video names, English document names, etc. For the convenience of understanding, the English search term is taken as an English song search term in the following description, but is not limited thereto.

[0026] The prior art generally performs error correction search on the English search term as a whole when searching based on the English search term, which results in poor fault tolerance. For example, if the English search term as a whole is subjected to error correction, and the edit distance is too small, the error correction candidate set will be too small, and the user's desired search result will be excluded. If the edit distance is too large, the error correction time will increase exponentially. Here, the edit distance is a quantitative measure of the difference between the English search term as a whole and the error correction term as a whole, e.g., if the edit distance is 2, there are two different English letters between the English search term as a whole and the error correction term as a whole.

[0027] ​In view of the above problems, in combination with the fact that the probability of the first letter being input incorrectly is low when a user inputs an English search term, the embodiment first extracts the first letter of each first word in the English search term to obtain a first combination of the first letters of the English search term, so as to subsequently perform error correction search by using the first combination of the first letters. The number of letters in the first combination of the first letters is low, and even if a small combination edit distance is used, more English names close to the user's search intent can be obtained, thereby expanding the range of alternatives. For example, if the English search term is "myhart go on", the first letters of each first word are extracted to obtain the first combination of the first letters as "mhgo".

[0028] Further, before extracting the first combination of the first letters of the English search term, it is necessary to first determine whether the total number of first words in the English search term is greater than a preset word threshold. The preset word threshold is preferably an integer greater than 1, such as "3" and the like, to facilitate error correction based on the first combination of the first letters. When the total number of first words is greater than the preset word threshold, a small combination edit distance can be used to find a larger set of English name alternatives.

[0029] In step S102, the preset error correction dictionary is queried according to the first combination of the first letters to obtain a set of English name alternatives corresponding to the first combination of the first letters.

[0030] The preset error correction dictionary is constructed based on the second initial letter combinations in the English name library. The English name library stores a plurality of English names, and the first letter of each second word of the English names in the English name library is extracted to obtain a plurality of corresponding second initial letter combinations. One English name corresponds to one second initial letter combination. For example, "my heart will go on" corresponds to the second initial letter combination "mhwgo", "my heart goes out" corresponds to the second initial letter combination "mhgo", and "my dream go on" corresponds to the second initial letter combination "mdgo". After obtaining a plurality of second initial letter combinations, each second initial letter combination can be traversed, and each second initial letter combination can be combined according to the mutual combination edit distance to generate a second initial letter combination BK tree. When traversing, a second initial letter combination can be selected as the root node of the second initial letter combination BK tree, which is not limited here. The combination edit distance is the edit distance between the second initial letter combinations. For example, the combination edit distance between the second initial letter combinations "mhwgo" and "mhgo" is 1, the combination edit distance between the second initial letter combinations "mdgo" and "mhgo" is 1, and the combination edit distance between the second initial letter combinations "mdgo" and "mhwgo" is 2. According to each combination edit distance, a second initial letter combination BK tree is generated. The BK tree (Burkhard-Keller tree) is a metric tree of a discrete metric space. The second initial letter combination BK tree is a BK tree of the second initial letter combination, and the English name is bound to the corresponding second initial letter combination as an extended attribute of the second initial letter combination BK tree when the second initial letter combination BK tree is generated, to obtain a preset error correction dictionary.

[0031] After obtaining the preset error correction dictionary, the first initial letter combination is queried in the preset error correction dictionary, for example, the position of the first initial letter combination in the second initial letter combination BK tree is found, and at least one alternative initial letter combination that matches the first initial letter combination within the preset combination edit distance is found in the second initial letter combination BK tree according to the preset combination edit distance, for example, "1". For example, according to the first initial letter combination "mhgo", the second initial letter combination BK tree can be found, and the second initial letter combination "mhgo" can be found. According to the preset combination edit distance "1", the alternative initial letter combinations "mdgo" and "mhwgo" can be found. If there is no first initial letter combination in the second initial letter combination BK tree, at least one alternative initial letter combination that matches the first initial letter combination within the preset combination edit distance can also be directly found. Here, since the first initial letter combination method is used in this embodiment, the query granularity is relatively coarse, the preset combination edit distance can use a smaller value, a larger set of English name alternatives can be obtained, and the query speed is relatively fast.

[0032] After obtaining the at least one alternative initial letter combination, the expansion attribute of the at least one alternative initial letter combination in the second initial letter combination BK tree is obtained, and the obtained English name is taken as an English name alternative set. The English name alternative set includes, for example, "my heart will go on", "my heart goes out", and "my dream go on".

[0033] In step S103, the score of each English name is calculated according to the word similarity relationship between the second word of the English name in the English name alternative set and the first word in the English search term, and the English name with the highest score is taken as the error correction search result.

[0034] For any English name in the English name alternative set, the score of each second word in the English name can be calculated according to the word similarity relationship between the second word and the first word in the English search term. The word similarity relationship includes, for example, the positional relationship when the second word is the same as the first word, the word edit distance (i.e., the edit distance between the first word and the second word) when the second word is different from the first word, the total number of second words in the English name, the length of the second word, and the like.

[0035] The English name contains multiple second words, and the score of the English name is obtained by accumulating the scores of the second words. For each second word, the score is calculated according to the word similarity relationship between the second word and the first word in the English search term.

[0036] In the score calculation of the second word, it is firstly judged whether the second word is same as the first word. If the second word is same as the first word in the English search term, the position difference between the second word and the first word can be calculated. If the second word is not same as the first word in the English search term but the first letter is same, the word edit distance between the second word and the first word can be calculated. After the above data is calculated, according to the position difference or the word edit distance, combined with the total number of the second words in the English name and the length of the second word, the score of the second word is calculated. Specifically, the following formula can be used: 1-Offset / (Offset+C)-D / L. Wherein, Offset is the position difference between the second word and the first word in the English search term when they are same. For example, the English search term is "my hart go on", the English name is "my heart will go on", the position of "go" in the English search term is 3, and the position of "go" in the English name "my heart will go on" is 4, so the position difference is 4-3=1. C is the total number of the second words in the English name, and the total number of the second words in "my heart will go on" is 5. D is the word edit distance between the second word and the first word in the English search term when they are not same but the first letter is same. For "go", since there is the same first word, D is 0; for the second word "heart" in the English name, it is not same as "hart" in the English search term but the first letter is same, and the word edit distance D between the two words is 1. L is the length of the second word, and the length L of the second word "go" is 2, and the length L of the second word "heart" is 5. According to the above formula, the score of "go" can be calculated as 1-1 / (1+5)-0 / 2=0.8333. Similarly, the scores of the second words can be calculated, and the scores of the second words are added to obtain the score of the English name. The score of "my heart will go on" is shown in Table 1:

[0037]

[0038]

[0039] Table 1

[0040] The score of "my dreams go out" is shown in Table 2:

[0041]

[0042] Table 2

[0043] The score of "my heart goes out" is shown in Table 3:

[0044]

[0045] Table 3

[0046] After the score of each English name in the English name alternative set is obtained through the above calculation, the scores of the English names are sorted, and the English name with the highest score is taken as the error correction search result. For the English search term "myhart go on", three alternative English names "my heart will goon", "my dream go on" and "my heart goes out" are obtained through the first letter combination query error correction, and the scores of the English names are calculated to be 3.4666, 3 and 2.6333 respectively, and the second screening obtains "my heart will go on" as the error correction song name closest to the English search term, that is, the error correction search result.

[0047] According to the error correction search method of the English search term provided by the embodiment of the application, the preset error correction dictionary is searched through the first letter combination, and compared with the error correction of the entire English search term, more and closer English name alternative sets can be obtained by using smaller combination edit distance, and then the scores of the English names are calculated based on the word similarity relationship between the second word and the first word, and the English name with the highest score is taken as the error correction search result, which is closer to the search intention of the user and improves the user experience.

[0048] Figure 2 The structure schematic diagram of the error correction search device of the English search term provided by the embodiment of the application is shown. As shown in the figure, the device comprises: Figure 2

[0049] The extraction module 210 is adapted to extract the first letter of each first word in the English search term to obtain the first letter combination of the English search term;

[0050] The query module 220 is adapted to query the preset error correction dictionary according to the first letter combination to obtain the English name alternative set corresponding to the first letter combination; the preset error correction dictionary is constructed based on the second letter combination in the English name library;

[0051] The score calculation module 230 is adapted to calculate the score of each English name in the English name alternative set according to the word similarity relationship between the second word of the English name and the first word in the English search term, and take the English name with the highest score as the error correction search result.

[0052] ​Optionally, the apparatus further comprises an error correction dictionary establishing module 240 adapted to extract the first letter of each second word of the English name in the English name library to obtain a plurality of second first letter combinations corresponding thereto; traverse each second first letter combination to generate a second first letter combination BK tree according to the combination edit distance between each second first letter combination, and bind the English name as an extended attribute of the second first letter combination BK tree to the corresponding second first letter combination to obtain a preset error correction dictionary.

[0053] Optionally, the querying module 220 is further adapted to:

[0054] query the preset error correction dictionary according to the first first letter combination to obtain at least one alternative first letter combination in the second first letter combination BK tree matching the first first letter combination within the preset combination edit distance;

[0055] obtain the extended attribute of the at least one alternative first letter combination in the second first letter combination BK tree to obtain the English name as an English name candidate set.

[0056] Optionally, the word similarity relationship comprises a position relationship of the second word being the same as the first word, a word edit distance of the second word being different from the first word, a total number of the second words in the English name and / or a length of the second word.

[0057] Optionally, the score calculating module 230 is further adapted to:

[0058] for any second word in the English name, if the second word is the same as the first word in the English search term, calculate the position difference between the second word and the first word; if the second word is not the same as the first word in the English search term but the first letter is the same, calculate the word edit distance between the second word and the first word;

[0059] according to the position difference or the word edit distance, in combination with the total number of the second words in the English name and the length of the second word, calculate the score of the second word;

[0060] accumulate the scores of each second word to obtain the score of the English name.

[0061] Optionally, the extracting module 210 is further adapted to:

[0062] determine whether the total number of the first words in the English search term is greater than a preset word threshold;

[0063] if yes, extract the first letter of each first word in the English search term to obtain the first first letter combination of the English search term.

[0064] Optionally, the English search term is an English song search term, an English video search term and / or an English document search term.

[0065] The above description of the modules refers to the corresponding description in the method embodiments, which will not be repeated here.

[0066] The embodiments of the present application also provide a non-volatile computer storage medium, which stores at least one executable instruction, and the executable instruction can execute the error correction search method of the English search term in any method embodiment described above.

[0067] Figure 3 A structural schematic diagram of a computing device according to an embodiment of the present application is shown, and the specific embodiments of the present application do not limit the specific implementation of the computing device.

[0068] As shown in Figure 3 The computing device can include a processor 302, a communications interface 304, a memory 306, and a communications bus 308.

[0069] characterized in that:

[0070] The processor 302, the communications interface 304, and the memory 306 complete mutual communication through the communications bus 308.

[0071] The communications interface 304 is configured to communicate with network elements of other devices, such as clients or other servers.

[0072] The processor 302 is configured to execute the program 310, and specifically can execute the related steps in the error correction search method of the English search term embodiments described above.

[0073] Specifically, the program 310 can include program code, and the program code includes computer operation instructions.

[0074] The processor 302 can be a central processing unit CPU, or an application specific integrated circuit ASIC, or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the computing device can be the same type of processor, such as one or more CPUs; or can be different types of processors, such as one or more CPUs and one or more ASICs.

[0075] The memory 306 is configured to store the program 310. The memory 306 can include a high-speed RAM memory, and can also include a non-volatile memory, such as at least one disk memory.

[0076] The program 310 can be specifically configured to enable the processor 302 to perform the error correction search method of the English search term in any of the above-described method embodiments. The specific implementation of each step in the program 310 can be referred to the corresponding description in the corresponding step and unit in the above-described error correction search method of the English search term, which will not be repeated here. It can be clearly understood by those skilled in the art that, for the convenience and brevity of description, the specific working process of the above-described device and module can be referred to the corresponding process description in the above-described method embodiments, which will not be repeated here.

[0077] The algorithms and displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems can be used with programs in accordance with the teachings herein, or it can prove convenient to construct more specialized apparatus to perform the required method steps. The required structure for a variety of these systems will be apparent from the description above. In addition, the present embodiments are not described with reference to any particular programming language. It will be appreciated that a variety of programming languages can be used to implement the teachings of the embodiments as described herein, and any references below to specific languages are provided for disclosure of the best mode of practicing the embodiments.

[0078] In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the application can be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been described in detail in order not to obscure the understanding of this description.

[0079] Similarly, it is to be understood that the mechanical details of the application embodiments sometimes are grouped into single embodiments, figures, or descriptions for the purpose of brevity and clarity. However, the disclosure is not to be interpreted as reflecting an intention that the application embodiments require more features than are explicitly recited in each claim. Rather, the inventive aspects lie in less than all features of a single disclosed embodiment. Accordingly, the claims are hereby expressly incorporated into this detailed description, with each claim acting as a separate embodiment of the application.

[0080] Those skilled in the art will appreciate that the modules in the apparatuses in the embodiments can be adapted and placed in one or more apparatuses other than the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and further can be divided into multiple sub-modules or sub-units or sub-components. Except that at least some of such features and / or processes or units are mutually exclusive, all combinations of all features disclosed in this specification (including accompanying claims, abstract and drawings) and all processes or units of any methods or apparatuses so disclosed can be adopted in any combination. Unless explicitly stated otherwise, each feature disclosed in this specification (including accompanying claims, abstract and drawings) can be replaced by alternative features providing the same, equivalent or similar functionality.

[0081] Further, those skilled in the art will appreciate that a combination of features of different embodiments means that such combination is within the scope of the application and forms a different embodiment. For example, in the following claims, any of the claimed embodiments can be used in any combination.

[0082] The various component embodiments of the present application can be implemented in hardware, or as software modules running in one or more processors, or in combinations thereof. Those skilled in the art will appreciate that a microprocessor or a digital signal processor (DSP) can be used in practice to implement some or all of the functionality of some or all of the components according to the embodiments of the present application. The embodiments of the present application can also be implemented as a program of apparatuses or devices (for example, computer programs and computer program products) for performing part or all of the methods described herein. Such program implementing the embodiments of the present application can be stored on a computer readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, or provided on a carrier signal, or in any other form.

[0083] It should be noted that the above-mentioned embodiments illustrate rather than limit the application, and that one skilled in the art will be able to design many alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word 'comprising' does not exclude the presence of elements or steps other than those listed in a claim. The word 'a' or 'an' preceding an element does not exclude the presence of a plurality of such elements. The application can be implemented by means of both hardware and software, and any combination thereof. In a unitary claim, several devices, apparatuses or means can be listed, comprising means for carrying out a certain task. The use of the term'means' in a claim is intended to refer to a combination of devices, apparatuses or means for carrying out a task. The word 'first','second', 'third', etc. do not imply any order. The use of these terms is to be construed as an indication of particular embodiments. Steps in the above-described embodiments can be carried out in any order, unless otherwise specified.

Claims

1. A method for correcting errors in English search terms, characterized in that the method... The method comprises the following steps: extracting the first letter of each first word in the English search term to obtain a first combination of initial letters of the English search term; extracting the first letter of each second word in the English name in the English name library to obtain a plurality of corresponding second combinations of initial letters; traversing each second combination of initial letters, generating a second combination of initial letters BK tree according to the combination edit distance between each second combination of initial letters, and binding the English name as the extension attribute of the second combination of initial letters BK tree to the corresponding second combination of initial letters to obtain a preset error correction dictionary; the combination edit distance is the edit distance between the second combinations of initial letters; querying the preset error correction dictionary according to the first combination of initial letters to obtain an English name candidate set corresponding to the first combination of initial letters; the preset error correction dictionary is constructed based on the second combination of initial letters in the English name library; wherein the English name candidate set includes the English name of the extension attribute of at least one alternative combination of initial letters matched with the first combination of initial letters within the preset combination edit distance in the second combination of initial letters BK tree of the preset error correction dictionary; calculating the score of each English name according to the word similarity relationship between the second word of the English name in the English name candidate set and the first word in the English search term, and taking the English name with the highest score as the error correction search result.

2. The method of claim 1, wherein, The method further comprises the following steps: querying the preset error correction dictionary according to the first combination of initial letters to obtain at least one alternative combination of initial letters matched with the first combination of initial letters within the preset combination edit distance in the second combination of initial letters BK tree; obtaining the extension attribute of the at least one alternative combination of initial letters in the second combination of initial letters BK tree to obtain the English name as the English name candidate set.

3. The method of claim 1, wherein, The word similarity relationship includes the positional relationship when the second word is the same as the first word, the word edit distance when the second word is different from the first word, the total number of second words in the English name, and / or the length of the second word.

4. The method of claim 3, wherein, The method further comprises the following steps: for any second word in the English name, if the second word is the same as the first word in the English search term, calculating the positional difference between the second word and the first word; if the second word is different from the first word in the English search term but the initial letters are the same, calculating the word edit distance between the second word and the first word; calculating the score of the second word according to the positional difference or the word edit distance, in combination with the total number of second words in the English name and the length of the second word; accumulating the scores of all second words to obtain the score of the English name.

5. The method of claim 1, wherein, The method further comprises the following steps: determining whether the total number of first words in the English search term is greater than a preset word threshold; If yes, extract the first letter of each first word in the English search word to obtain a first letter combination of the English search word.

6. The method according to any one of claims 1-5, characterized in that, The English search word is an English song search word, an English video search word, and / or an English document search word.

7. An error correction search device for an English search word, characterized in that the device comprises: a first letter extraction module adapted to extract the first letter of each first word in the English search word to obtain a first letter combination of the English search word; a module for extracting the first letter of each second word in the English name in the English name library to obtain a plurality of second letter combinations corresponding thereto; traversing each second letter combination, generating a second letter combination BK tree according to the combination edit distance between each second letter combination, and binding the English name as an extension attribute of the second letter combination BK tree to the corresponding second letter combination to obtain a preset error correction dictionary; the combination edit distance is the edit distance between the second letter combinations; a query module adapted to query the preset error correction dictionary according to the first letter combination to obtain an English name candidate set corresponding to the first letter combination; the preset error correction dictionary is constructed based on the second letter combination in the English name library; wherein the English name candidate set includes the English name of the extension attribute of at least one candidate first letter combination matching the first letter combination within the preset combination edit distance in the second letter combination BK tree of the preset error correction dictionary; a score calculation module adapted to calculate the score of each English name according to the word similarity relationship between the second word of the English name in the English name candidate set and the first word in the English search word, and take the English name with the highest score as the error correction search result.

8. A computing device, comprising: comprise: a processor, a memory, a communication interface, and a communication bus, the processor, the memory, and the communication interface complete communication with each other through the communication bus; the memory is used to store at least one executable instruction, and the executable instruction causes the processor to perform the operation corresponding to the error correction search method for an English search word according to any one of claims 1-6.

9. A computer storage medium, characterized in that the storage medium stores at least one executable instruction, and the executable instruction causes the processor to perform the operation corresponding to the error correction search method for an English search word according to any one of claims 1-6.

Images