A method and device for verifying the name of a work unit

Abstract

The present application relates to the field of financial technology (Fintech), and discloses a work unit name verification method and device, which verifies the work unit name and the standard work unit name by segmenting them to obtain each first participle and each second participle; according to the parts of speech of each first participle and each second participle, determines the first classification information of each first participle under each constituent element of the work unit name and the second classification information of each second participle under each constituent element; determines a first naming structure formula of the verified work unit name based on an identifier and the first classification information respectively corresponding to each constituent element, and determines a second naming structure formula of the standard work unit name based on the identifier and the second classification information respectively corresponding to each constituent element; determines the similarity between the verified work unit name and the standard work unit name based on at least the same constituent elements in the first naming structure formula and the second naming structure formula, thereby improving the efficiency and accuracy of determining the authenticity of the work unit name input by the user.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of financial technology (Fintech), and in particular, to a method and device for verifying the name of a work unit. Background Art

[0002] With the development of computer technology, more and more technologies (such as big data, cloud computing or blockchain) are being applied in the financial field, and the traditional financial industry is gradually transforming to financial technology. For example, banks gradually transform many offline businesses into online ones, which will improve the efficiency of business processing for users and increase the stickiness of users to banks.

[0003] At present, in the field of Internet finance, there are often cases of fraud by others impersonating others. Specifically, when a user applies for a financial product provided by the organizer, during the application stage of the financial product, the organizer generally requires the user to manually fill in the information of his or her work unit, such as the name of the work unit, and some other personal information. Obviously, this stage will give some lawless elements an opportunity to take advantage of. For example, after some gangs collect a batch of real user identity information through some improper means, although the gangs can fill in the real user identity information during the application stage of the financial product, because they do not know the information of the work units of these users, the gangs will fill in some false work unit names, or fill in some real work unit names that do not match the applicants. After the system receives the applicant's information provided by the gang, the applicant's real work unit name can be queried through formal channels. Finally, by comparing the applicant's work unit name manually entered by the gang and the applicant's real work unit name queried, the system can confirm whether the gang's application for the financial product is legal.

[0004] However, currently, because users are required to manually fill in and upload their own work unit names, the manual input of work unit names often results in abbreviations, non-standard information, missing information, or even errors. In this case, the subsequent system will find it difficult to determine the legality of the work unit name manually entered by the user based on the applicant's real work unit name queried by itself. As a result, if criminals fill in some false or forged information during the application stage of financial products, their behavior will easily deceive financial risk control rules and achieve the purpose of obtaining profits.

[0005] Specifically, for the above situation, there is currently the following method to identify the authenticity of the work unit name actively entered by the user - Elasticsearch-matchQuery (fuzzy query). Among them:

[0006] Elasticsearch is a distributed, scalable, real-time search and analysis engine, a search engine built on the full-text search engine Apache Lucene(TM), including precise query terms and fuzzy query matches.

[0007] Term stands for complete match, that is, precise query. The search term will not be segmented before searching, so the search term must be one of the document segmentation set. Match query will first segment the search term, and then match the segmentation results one by one after the segmentation is completed. Therefore, compared with the precise search of term, match is a segmentation matching search. For example: when searching for "China Merchants Bank", the search term will be pre-segmented into two terms, "China Merchants" and "Bank", so as long as the document contains any of the terms "China Merchants" and "Bank", it will be searched.

[0008] The above method has obvious disadvantages, which are as follows: when word segmentation is widely used, there will be a large number of query results. When calculating the real work unit names of users returned from formal channels, the scores of various query results are not much different, so it is easy to make it impossible to decide which query result is the best match.

[0009] In summary, there is an urgent need for a method that can quickly and accurately confirm the authenticity of the work unit name entered by the user. Summary of the invention

[0010] The present application provides a work unit name verification method and device for quickly and accurately confirming whether the work unit name manually input by a user is authentic and reliable.

[0011] In a first aspect, an embodiment of the present application provides a method for verifying a work unit name, the method comprising: performing word segmentation on a verification work unit name of a verification object to obtain first word segmentations, and performing word segmentation on a standard work unit name of the verification object to obtain second word segmentations; determining first classification information of each first word segmentation under each constituent element of the work unit name for the part of speech of each first word segmentation, and determining second classification information of each second word segmentation under each constituent element for the part of speech of each second word segmentation; wherein the parts of speech of the words contained in each constituent element are different, and each constituent element includes a first word segmentation indicating the region to which the work unit belongs. A first constituent element, a second constituent element indicating the industry to which the work unit belongs, a third constituent element indicating keywords in the work unit name, and a fourth constituent element indicating suffix information of the work unit name; determining a first naming structure corresponding to the verification work unit name based on identifiers corresponding to each of the constituent elements and the first classification information, and determining a second naming structure corresponding to the standard work unit name based on identifiers corresponding to each of the constituent elements and the second classification information; determining the similarity between the verification work unit name and the standard work unit name based on at least the same constituent elements in the first naming structure and the second naming structure.

[0012] In the above scheme, by considering the various constituent elements of the work unit name, including the constituent elements indicating the region to which the work unit belongs, the constituent elements indicating the industry to which the work unit belongs, the constituent elements indicating the keywords in the work unit name and the constituent elements indicating the suffix information of the work unit name, different constituent elements can contain different parts of speech of words. Therefore, by performing word segmentation processing on a work unit name, then according to the parts of speech of the word segments obtained after the word segmentation processing, the work unit name can be converted into a style expressed by the constituent elements of the work unit name, that is, a naming structure. Therefore, when subsequently determining the credibility of a verification work unit name of a verification object, the similarity between the two work unit names can be determined based on the same constituent elements in the naming structure corresponding to the verification work unit name and the naming structure corresponding to the standard work unit name corresponding to the verification work unit name. This similarity can be used to characterize whether the verification work unit name is a true and credible work unit name. In this method, since the work unit name can be converted into a style expressed by the constituent elements of the work unit name based on the part of speech of each participle in the work unit name, when subsequently determining whether a verified work unit name is a true value, the similarity between the two work unit names can be quickly and accurately obtained based on the same constituent elements between the verified work unit name and the standard work unit name, thereby improving the efficiency and accuracy of determining the authenticity of the work unit name input by the user.

[0013] In a possible implementation method, the similarity between the verification work unit name and the standard work unit name is determined based on at least the same element structure in the first naming structure and the second naming structure, including: determining each verification sub-name in the verification work unit name based on each fourth component in the first naming structure; determining each standard sub-name in the standard work unit name based on each fourth component in the second naming structure; determining the verification abbreviation of the verification work unit name by the first verification sub-name that is at the first position in each verification sub-name; determining the standard abbreviation of the standard work unit name by the first standard sub-name that is at the first position in each standard sub-name; determining the similarity between the verification work unit name and the standard work unit name based on at least the element similarity of the same elements in the first naming structure and the second naming structure, and the abbreviation similarity between the verification abbreviation and the standard abbreviation.

[0014] Since the user may directly write the abbreviation of the work unit name when entering the work unit name, in response to this problem, the above scheme proposes that the fourth component in the naming structure corresponding to the work unit name can be used as the basis, and the work unit name can be divided into sub-names in sequence. At the same time, taking into account the user's writing habits of abbreviations, the abbreviation of the work unit name will be determined according to the sub-name that comes first in the work unit name in this application. Finally, in this application, when determining the similarity between the verification work unit name and the standard work unit name, in addition to considering the element similarity of the same components in the naming structures corresponding to the two work unit names, the similarity between the abbreviations of the two work unit names is further considered. Obviously, this is of great significance for accurately determining whether the verification work unit name is the standard work unit name.

[0015] In a possible implementation method, determining the verification abbreviation of the verification work unit name by using the first syndrome name that is at the first position among the syndrome names includes: determining a verification naming structure corresponding to the first syndrome name that is at the first position among the syndrome names; applying the abbreviation rule of the naming structure to the verification naming structure to determine the abbreviations corresponding to the first syndrome name, and using the abbreviations corresponding to the first syndrome name as the verification abbreviations of the verification work unit name; the abbreviation rule of the naming structure is determined by a sample work unit name and a sample work unit abbreviation.

[0016] In the above scheme, by taking into account the writing habits of users for the abbreviation of the work unit name, that is, generally writing the abbreviation corresponding to the sub-name that is relatively front in the work unit name, therefore in this application, when determining the abbreviation corresponding to the work unit name, the naming structure corresponding to the sub-name at the first position can be extracted from the corresponding naming structure in the work unit name, and then by applying the abbreviation rule of the naming structure to the extracted naming structure, the abbreviation corresponding to the sub-name at the first position can be obtained, and in this application, the abbreviation corresponding to the sub-name at the first position can be used as the abbreviation of the work unit name. Among them, the abbreviation rule of the naming structure is preset, that is, it is determined by sample work unit names and sample work unit abbreviations. Therefore, in this application, after the abbreviation rule of the naming structure is preset, for a work unit name, based on the abbreviation rule of the naming structure, the abbreviation corresponding to the work unit name can be quickly determined.

[0017] In a possible implementation method, the similarity between the verification work unit name and the standard work unit name is determined based on at least the element similarity of the same components in the first naming structure and the second naming structure, and the abbreviation similarity between the verification abbreviation and the standard abbreviation, including: determining the first element similarity between the industry information corresponding to the second component in the verification work unit name and the industry information corresponding to the second component in the standard work unit name; determining the second element similarity between the keywords corresponding to the third component in the verification work unit name and the keywords corresponding to the third component in the standard work unit name; determining the abbreviation similarity between the verification abbreviation and the standard abbreviation; determining the sub-name similarity between the verification sub-name set in each verification sub-name and the corresponding standard sub-name in each standard sub-name; and determining the similarity between the verification work unit name and the standard work unit name based on the first element similarity, the second element similarity, the abbreviation similarity and the sub-name similarity.

[0018] In the above scheme, it is specifically described how to determine the similarity between the verification work unit name and the standard work unit name based on the factor similarity and the abbreviation similarity, including determining the factor similarity between the industries to which the two work unit names belong (i.e., the first factor similarity), determining the factor similarity between the keywords of the two work unit names (i.e., the second factor similarity), determining the abbreviation similarity between the abbreviations corresponding to the two work unit names, and determining the sub-name similarity of the two work unit names under the sub-names at the same level. After determining the similarity between the verification work unit name and the standard work unit name in the above four aspects, this will be of great significance for the subsequent rapid determination of the similarity between the two.

[0019] In one possible implementation method, before segmenting the verification work unit name of the verification object to obtain each first participle and segmenting the standard work unit name of the verification object to obtain each second participle, the method also includes: determining, based on a preset regular expression, that both the verification work unit name and the standard work unit name have corresponding work unit types, and determining whether the verification work unit name and the standard work unit name belong to different work unit types in a first calculation strategy; wherein the preset regular expression is used to determine, based on the work unit name, the work unit type to which the work unit indicated by the work unit name belongs, and the first calculation strategy includes multiple work unit types, and the work unit name of each work unit under any one of the multiple work unit types contains each constituent element of the work unit name when naming.

[0020] In the above scheme, before applying the work unit name verification method proposed in this application to the verification work unit name and the standard work unit name of the verification object, if the two work unit names of the verification object are respectively matched with the preset regular expressions for the work unit types, and the matching result is that at least one of the two work unit names does not have a corresponding work unit type or the two work unit names belong to different work unit types in the first calculation strategy, then it can be directly determined that the similarity between the two work unit names of the verification object is zero, that is, it can be directly determined that the verification work unit name of the verification object is an unreliable work unit name, and there is no need to apply the work unit name verification method proposed in this application to the two work unit names of the verification object, thereby improving the rapid approval of the verification work unit name of the verification object; otherwise, that is, except for the matching of the above two work unit names, by applying the work unit name verification method proposed in this application to the two work unit names of the verification object, the reliability of the verification work unit name of the verification object can also be quickly and accurately determined.

[0021] In a possible implementation method, after segmenting the verification work unit name of the verification object to obtain each first participle, and segmenting the standard work unit name of the verification object to obtain each second participle, the method also includes: determining, according to the preset regular expression, that the verification work unit name and the standard work unit name belong to the same work unit type in the first calculation strategy; determining the similarity between the verification work unit name and the standard work unit name according to the first element similarity, the second element similarity, the abbreviation similarity and the sub-name similarity, including: determining the similarity between the verification work unit name and the standard work unit name according to the first element similarity and a first preset weight, the second element similarity and a second preset weight, the abbreviation similarity and a third preset weight, the sub-name similarity and a fourth preset weight; wherein the abbreviation similarity and the sub-name similarity are determined by means of the shortest edit distance.

[0022] In the above scheme, for the case where it is determined by a preset regular expression that the verification work unit name of the verification object and the standard work unit name belong to the same work unit type in the first calculation strategy, the abbreviation similarity and sub-name similarity between the two work unit names of the verification object are determined by using the shortest edit distance, which will make the calculation of the similarity between the two work unit names of the verification object more accurate; in addition, in this application, by considering the four factors of industry information, keyword information, abbreviation of the work unit name and sub-name of the work unit name in the work unit name, the different importance of the work unit name during verification is considered, and therefore, by assigning corresponding weights to different sub-similarity, this is of great significance for accurately determining the authenticity of the verification work unit name.

[0023] In one possible implementation method, the segmentation of the verification work unit name of the verification object to obtain each first participle includes: segmenting the verification work unit name of the verification object by means of Jieba participle to obtain each first participle and the part of speech of each first participle; the segmentation library corresponding to the Jieba participle includes each word added based on the work unit name.

[0024] In the above scheme, the verification work unit name can be segmented by the Jieba word segmentation method, so that the first word segmentations corresponding to the verification work unit name and the parts of speech of each first word segmentation can be obtained. Among them, this application takes into account that the Jieba word segmentation performance is universal but not targeted. Therefore, in combination with the fact that the research object of this application is the work unit name, the word segmentation library corresponding to the Jieba word segmentation will be expanded in this application. For example, multiple words related to the work unit name can be added to the word segmentation library corresponding to the Jieba word segmentation. In this way, when the expanded Jieba word segmentation is used to segment the work unit name, the accuracy of the word segmentation can be improved, which will be of great significance for the subsequent accurate determination of whether the verification work unit name actively entered by the user is the standard work unit name.

[0025] In a possible implementation method, after segmenting the verification work unit name of the verification object by the Jieba word segmentation method to obtain each first participle, before determining the first classification information of each first participle under each constituent element of the work unit name based on the part of speech of each first participle, the method also includes: if there are first participles of consecutive single words in each first participle after the Jieba word segmentation processing, the consecutive single words are merged into one first participle.

[0026] In the above scheme, after using the stammering word segmentation to segment the work unit name, the problem of segmentation being single characters is easy to occur. In response to this problem, the present application proposes that the first segmentations of single characters that exist continuously in each first segmentation can be merged into one segmentation. By merging the segmentations of single characters, the actual meaning of the work unit name can be expressed more accurately, that is, the meaning of the work unit name is complete, which is of great significance for the subsequent determination of the abbreviation of the work unit name and the calculation of the similarity of the work unit name.

[0027] In one possible implementation method, the parts of speech of the words contained in each of the constituent elements are different, including: the parts of speech of the words contained in the first constituent element are regional parts of speech, the parts of speech of the words contained in the second constituent element are industry parts of speech, the parts of speech of the words contained in the third constituent element are directional parts of speech, noun parts of speech, adjective parts of speech, verb and adverb parts of speech, and unknown parts of speech, and the parts of speech of the words contained in the fourth constituent element are suffix parts of speech.

[0028] In the above scheme, it is specifically described how to convert the work unit name into a style expressed by the constituent elements of the work unit name according to the part of speech of each participle obtained after the participle processing of the work unit name. This can be mainly achieved by establishing a corresponding relationship between different constituent elements and the part of speech of the participle. For example, by establishing a mapping relationship between the vocabulary of the regional part of speech and the first constituent element, when encountering a participle of the regional part of speech in the work unit name, the participle can be converted into an identifier corresponding to the first constituent element. For another example, by establishing a mapping relationship between the vocabulary of the industry part of speech and the second constituent element, when encountering a participle of the regional part of speech in the work unit name, the participle can be converted into an identifier corresponding to the first constituent element. When the industry part of speech is segmented, the participle can be converted into the identifier corresponding to the second constituent element. For example, by establishing a mapping relationship between the locative part of speech, noun part of speech, adjective part of speech, verb adverb part of speech and unknown part of speech and the third constituent element, and by establishing a mapping relationship between the suffix part of speech and the fourth constituent element, when encountering the participle of the suffix part of speech, the participle can be converted into the identifier corresponding to the fourth constituent element, thereby realizing the naming structure of a work unit name, which is of great significance for the subsequent accurate determination and verification of whether the work unit name is the standard work unit name.

[0029] In a possible implementation method, the abbreviation rule of the naming structure is determined by the sample work unit name and the sample work unit abbreviation, including: for any sample work unit name, the sample work unit name is normalized; the normalization process at least includes removing special characters, numbers and lowercase letters in the work unit name; for the sample work unit name after the normalization process, the sample work unit name is segmented to obtain each third segmentation corresponding to the sample work unit name and the part of speech of each third segmentation; based on the identifiers corresponding to each of the constituent elements, for each third segmentation, according to the part of speech of each third segmentation, the naming structure of the sample work unit name is determined; for the sample work unit name, each abbreviation of the sample work unit name and the naming structure of each abbreviation are determined; for any of the abbreviations, according to the naming structure of the abbreviation, the position information of the abbreviation in the naming structure of the sample work unit name is marked; a corresponding relationship between the sample work unit name and the position information of each abbreviation in the naming structure of the sample work unit name is established, and used as the abbreviation rule of the naming structure.

[0030] In the above scheme, a specific description is given of how to obtain the abbreviation rule of the naming structure formula, including first normalizing a sample work unit name, and then segmenting the normalized sample work unit name, so that the naming structure formula of the sample work unit name can be determined based on the part of speech of each segmented word, and on the other hand, the abbreviations corresponding to the sample work unit name and the naming structure formula corresponding to each abbreviation can be determined. Then, for any abbreviation, the position information of the abbreviation in the naming structure formula of the sample work unit name can be marked according to the naming structure formula of the abbreviation. Finally, by establishing the positions of the sample work unit name and each abbreviation in the naming structure formula of the sample work unit name, The correspondence between the information is the abbreviation rule based on the naming structure of the sample work unit name. In the subsequent process of verifying the work unit name, if the verification work unit name or the standard work unit name of the verification object is expressed as the sample work unit name, then by extracting the first sub-name in the sample work unit name and searching for the pre-established correspondence based on the naming structure corresponding to the first sub-name, after finding the abbreviation rule based on the naming structure corresponding to the first sub-name, it will be possible to know the generation method of the abbreviation of the sample work unit name where the first sub-name is located, so that the abbreviations of the sample work unit name can be quickly generated.

[0031] In a second aspect, an embodiment of the present application provides a work unit name verification device, the device comprising: a word segmentation unit, used to segment the verification work unit name of the verification object to obtain each first word segmentation, and segment the standard work unit name of the verification object to obtain each second word segmentation; a classification information determination unit, used to determine the first classification information of each first word segmentation under each constituent element of the work unit name according to the part of speech of each first word segmentation, and determine the second classification information of each second word segmentation under each constituent element according to the part of speech of each second word segmentation; wherein the parts of speech of the words contained in each constituent element are different, and each constituent element includes a first constituent element indicating the region to which the work unit belongs. a first component indicating the industry to which the work unit belongs, a second component indicating the keyword in the work unit name, a third component indicating the keyword in the work unit name, and a fourth component indicating the suffix information of the work unit name; a naming structure determination unit, used to determine the first naming structure corresponding to the verification work unit name based on the identifiers corresponding to the respective components and the first classification information, and to determine the second naming structure corresponding to the standard work unit name based on the identifiers corresponding to the respective components and the second classification information; a similarity determination unit, used to determine the similarity between the verification work unit name and the standard work unit name based on at least the same components in the first naming structure and the second naming structure.

[0032] In a third aspect, an embodiment of the present application provides a computing device, including:

[0033] A memory for storing program instructions;

[0034] The processor is used to call the program instructions stored in the memory and execute any implementation method of the first aspect according to the obtained program.

[0035] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute any implementation method of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0037] Figure 1 A schematic diagram of a work unit name verification method provided in an embodiment of the present application;

[0038] Figure 2 A schematic diagram of a work unit name verification device provided in an embodiment of the present application;

[0039] Figure 3 A schematic diagram of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0041] Currently, when the product party is confirming whether the work unit name actively entered by the user is consistent with the real work unit name of the user obtained through formal channels, if the product party confirms based on fuzzy query, the query result is prone to unreliable, which in turn provides opportunities for some lawless elements, which greatly damages the interests of the product party.

[0042] In response to the above technical problems, this application can provide a method for verifying the name of a work unit. Figure 1 FIG. 1 is a schematic diagram of a method for verifying a work unit name provided in an embodiment of the present application, the method comprising the following steps:

[0043] Step 101 : segmenting the verification work unit name of the verification object to obtain first segmented words, and segmenting the standard work unit name of the verification object to obtain second segmented words.

[0044] In this step, the verification object can be a user. Taking the verification object as user 1 as an example, the verification work unit name of the verification object is the work unit name actively entered by user 1, and the standard work unit name of the verification object is the real and credible work unit name of user 1 obtained through formal channels. That is, in this application, by determining the similarity between the verification work unit name of user 1 and the standard work unit name, the authenticity of the verification work unit name actively entered by user 1 can be determined.

[0045] It should be noted that the acquisition, storage, use, and processing of the data required during the execution of the work unit name verification method in this application are in compliance with the provisions of national laws and regulations.

[0046] In this step, by segmenting the verification work unit name of the verification object, each participle and the part of speech of each participle can be obtained, that is, each first participle and the part of speech of each first participle can be obtained; by segmenting the standard work unit name of the verification object, each participle and the part of speech of each participle can be obtained, that is, each second participle and the part of speech of each second participle can be obtained.

[0047] For example, taking a work unit name of "Shenzhen Qianhai WB Bank Co., Ltd." as an example, how to obtain each participle of the work unit name and the part of speech of each participle is explained. It is explained that "Shenzhen Qianhai WB Bank Co., Ltd." can be the verification work unit name of the verification object, or it can be the standard work unit name of the verification object, and this application does not limit this.

[0048] In certain implementations of the present application, the segmentation of the verification work unit name of the verification object to obtain each first participle includes: segmenting the verification work unit name of the verification object by means of Jieba participle to obtain each first participle and the part of speech of each first participle; the segmentation library corresponding to the Jieba participle includes each word added based on the work unit name.

[0049] Specifically, when using the Jieba word segmentation tool to segment the name of a work unit, during the process of implementing the word segmentation, each segmented word may have a corresponding part of speech at the same time.

[0050] For example, for the work unit name "Shenzhen Qianhai WB Bank Co., Ltd.", by using the Jieba word segmentation tool to segment this work unit name, the following word segmentation information can be obtained:

[0051] [[Shenzhen, 0, 2, ns], [Qianhai, 2, 4, f], [WB, 4, 6, i], [Bank, 6, 8, csx], [Co., Ltd., 8, 14, csx]]

[0052] Among them, for the above word segmentation information, it means that after segmenting the work unit name "Shenzhen Qianhai WB Bank Co., Ltd." through the Jieba word segmentation tool, a total of 5 segments are obtained, and the information of these 5 segments is as follows:

[0053] For the first segment "Shenzhen", (0, 2) represents the position information of the word "Shenzhen" in the current work unit name, that is, the word "Shenzhen" is located at the 0th and 1st positions in the current work unit name, and "ns" represents the part-of-speech of the word "Shenzhen" as a geographical term;

[0054] For the second segment "Qianhai", (2, 4) represents the position information of the word "Qianhai" in the current work unit name, that is, the word "Qianhai" is located at the 2nd and 3rd positions in the current work unit name, and "f" represents the part-of-speech of the word "Qianhai" as a locative term;

[0055] For the third segment "WB", (4, 6) represents the position information of the word "WB" in the current work unit name, that is, the word "WB" is located at the 4th and 5th positions in the current work unit name, and "i" represents the part-of-speech of the word "WB" as an unknown part-of-speech;

[0056] For the fourth segment "Bank", (6, 8) represents the position information of the word "Bank" in the current work unit name, that is, the word "Bank" is located at the 6th and 7th positions in the current work unit name, and "csx" represents the part-of-speech of the word "Bank" as a suffix term;

[0057] For the fifth segment "Co., Ltd.", (8, 14) represents the position information of the phrase "Co., Ltd." in the current work unit name, that is, the phrase "Co., Ltd." is located at the 8th and 13th positions in the current work unit name, and "csx" represents the part-of-speech of the phrase "Co., Ltd." as a suffix term.

[0058] In addition, since the currently used Jieba word segmentation tool has not yet designed relevant word segmentation for specific scenarios, and this application mainly needs to segment the name of the work unit, the current Jieba word segmentation tool is not very targeted when segmenting the name of the work unit. In this case, if the current version of the Jieba word segmentation tool is continued to be used to segment the name of the work unit, the segmented words are prone to accuracy problems, that is, the current version of the Jieba word segmentation tool performs poorly in the segmentation of the name of the work unit. In this regard, before using the Jieba word segmentation tool to segment the name of the work unit in this application, the word segmentation word library corresponding to the Jieba word segmentation tool can be supplemented first, such as in this application, the word segmentation word library corresponding to the Jieba word segmentation tool can be pre-supplemented with words related to the name of the work unit, and the ending words can be specified. Among them, the ending words are, for example, banks, joint-stock companies, companies, hospitals, public security bureaus, etc., so that this application can greatly improve the accuracy of the word segmentation by using the improved Jieba word segmentation tool to segment the name of the work unit, which is of great significance for the subsequent verification of the authenticity of the name of the work unit.

[0059] Specific:

[0060] A. Aggregate multiple parts of speech into keywords.

[0061] Jieba participle has many parts of speech and they are very detailed. For example, verbs (v, vd, vn, etc.), adjectives (a, ad, ag, etc.), adverbs (d, dg, etc.), quantifiers, numerals, etc. are all aggregated into keywords in this application. For example:

[0062] Frown and smile(verb):v:4

[0063] Immediately (adjective): ad: 2

[0064] Number of vehicles (numeral): m: 2

[0065] B. Add regional nouns.

[0066] For example, you can add the following regional nouns to the word library corresponding to the Jieba word:

[0067] Guangdong Province:ns:3

[0068] Shenzhen:ns:2

[0069] Nanshan District:ns:3

[0070] Dongguan City:ns:3

[0071] Taoyuan Village:ns:3

[0072] C. Add industry terms.

[0073] For example, you can add the following industry terms to the word library corresponding to the Jieba word:

[0074] Freight:idu:4

[0075] Wood industry:idu:4

[0076] Natural gas:idu:4

[0077] Aerospace:idu:4

[0078] Aviation:idu:4

[0079] D. Add suffix nouns.

[0080] For example, you can add the following suffix nouns to the word library corresponding to the jieba word:

[0081] Sales Department:csx:4

[0082] Branch:csx:4

[0083] Branch:csx:4

[0084] Cooperative:csx:4

[0085] Co., Ltd.:csx:4

[0086] Limited Partnership:csx:4

[0087] Limited Liability Company:csx:4

[0088] Service Center:csx

[0089] Step 102, for each part of speech of each first participle, determine the first classification information of each first participle under each constituent element of the work unit name, and for each part of speech of each second participle, determine the second classification information of each second participle under each constituent element.

[0090] Among them, the words contained in each of the constituent elements have different parts of speech, and the constituent elements include a first constituent element indicating the region to which the work unit belongs, a second constituent element indicating the industry to which the work unit belongs, a third constituent element indicating keywords in the name of the work unit, and a fourth constituent element indicating suffix information of the name of the work unit.

[0091] In certain implementations of the present application, the parts of speech of the vocabulary contained in each of the constituent elements are different, including: the parts of speech of the vocabulary contained in the first constituent element are regional parts of speech, the parts of speech of the vocabulary contained in the second constituent element are industry parts of speech, the parts of speech of the vocabulary contained in the third constituent element are directional parts of speech, noun parts of speech, adjective parts of speech, verb and adverb parts of speech, and unknown parts of speech, and the parts of speech of the vocabulary contained in the fourth constituent element are suffix parts of speech.

[0092] For example, according to the analysis of the characteristics of work units, when naming work units, except for some self-employed work units and a few other work units that do not have inductive characteristics in their names, generally speaking, enterprises, government agencies, and public institutions will have certain characteristics when naming, that is, when naming work units, the following four components will be included:

[0093] A component indicating the region to which the work unit belongs, a component indicating the industry to which the work unit belongs, a component indicating a keyword in the name of the work unit, and a component indicating suffix information of the name of the work unit.

[0094] For example, words with regional parts of speech such as "China", "Anhui", and "Hefei" are specific examples of the constituent element of the region to which the work unit belongs. Therefore, when encountering words with regional parts of speech, the words with regional parts of speech can be classified into the category of the constituent element of the region to which the work unit belongs; words with industry parts of speech such as "computer", "new material", and "catering" are specific examples of the constituent element of the industry to which the work unit belongs. Therefore, when encountering words with industry parts of speech, the words with industry parts of speech can be classified into the category of the constituent element of the industry to which the work unit belongs; words with suffix parts of speech such as "bank", "joint-stock company", and "hospital" are specific examples of the constituent element of the suffix information of the work unit name. Therefore, when encountering words with suffix parts of speech, the words with suffix parts of speech can be classified into the category of the suffix in the work unit name. In the classification of the constituent element of information; and for the segmented words obtained by segmenting a work unit name, if one of the segmented words is not one of the constituent element of the region to which the work unit belongs, the constituent element of the industry to which the work unit belongs, and the constituent element of the suffix information of the work unit, such as "Qianhai" (directional part of speech), "WB" (unknown part of speech), "electronic equipment" (noun part of speech), "public welfare" (adjective part of speech) and other words will be included in the classification of words of keyword part of speech, that is, the above-mentioned words such as "Qianhai", "Weizhong", "electronic equipment", "public welfare" are specific examples of the constituent element of keywords in the work unit name. Therefore, when encountering words of the keyword part of speech, the words of the keyword part of speech can be classified into the classification of the constituent element of keywords in the work unit name.

[0095] Step 103, determining a first naming structure corresponding to the verification work unit name based on the identifiers corresponding to the respective constituent elements and the first classification information, and determining a second naming structure corresponding to the standard work unit name based on the identifiers corresponding to the respective constituent elements and the second classification information.

[0096] Based on the above step 102, for each first participle after the verification work unit name is segmented, according to the part of speech of each first participle, the classification information of each first participle under each constituent element of the work unit name, that is, the first classification information, can be obtained. Similarly, for each second participle after the standard work unit name is segmented, according to the part of speech of each second participle, the classification information of each second participle under each constituent element of the work unit name, that is, the second classification information, can be obtained. In addition, for each constituent element of the work unit name, different identifiers can be used to represent different constituent elements, such as using the character "R" to represent the constituent element of the region to which the work unit belongs, and using the character "I" to represent the constituent element of the work unit. The constituent element of the industry to which the work unit belongs is identified, the character "X" is used to identify the constituent element of the keyword in the work unit name, and the character "O" is used to identify the constituent element of the suffix information in the work unit name. In this way, the verification work unit name can be converted from text form to a style represented by only the four characters "R", "I", "X" and "O", and the naming structure formula corresponding to the verification work unit name is obtained, that is, the first naming structure formula. Similarly, the standard work unit name can be converted from text form to a style represented by only the four characters "R", "I", "X" and "O", and the naming structure formula corresponding to the standard work unit name is obtained, that is, the second naming structure formula.

[0097] As shown in Table 1, a relationship mapping table between a vocabulary part of speech and identifiers corresponding to constituent elements provided in an embodiment of the present application is as follows:

[0098]

[0099] Table 1

[0100] For example, for the work unit name "Shenzhen Qianhai WB Bank Co., Ltd." in the aforementioned example, since the part of speech of the word "Shenzhen" is ns, that is, the word "Shenzhen" belongs to the constituent element of the region to which the work unit belongs, the "R" character among the four characters "R", "I", "X" and "O" can be used to represent the participle "Shenzhen"; according to the same logic, "Qianhai", "WB", "Bank", and "Co., Ltd." can be represented by "X", "X", "O", and "O" respectively, so the work unit name "Shenzhen Qianhai WB Bank Co., Ltd." can be converted to "RXXOO" for representation.

[0101] In addition, in order to facilitate understanding of the process of converting a work unit name from a text expression to a character expression, as shown in Table 2 below, a conversion relationship list of work unit names is provided in an embodiment of the present application, wherein Table 2 lists examples of converting four work unit names.

[0102] According to the reading order from top to bottom, taking the first record in Table 2 as an example, for the work unit name "Tenpay Payment Technology Co., Ltd.", after word segmentation processing, it can be obtained in sequence "Tenpay (i)", "Payment (vd)", "Technology (idu)", "Co., Ltd. (csx)" a total of 4 participles, so according to the classification of the part of speech of each participle under the constituent elements of the work unit name, the work unit name "Tenpay Payment Technology Co., Ltd." can be converted into the naming structure "XXIO" for representation.

[0103] It should be noted that this application will not repeat the conversion process of other work unit names in Table 2.

[0104]

[0105] Table 2

[0106] Step 104 : determining the similarity between the verification work unit name and the standard work unit name based on at least the same constituent elements in the first naming structure formula and the second naming structure formula.

[0107] Based on the above steps, by determining the first naming structure corresponding to the verification work unit name and the second naming structure corresponding to the standard work unit name, in this step, the similarity between the verification work unit name and the standard work unit name can be determined based on the same constituent elements in the two naming structures. For example, for the first naming structure and the second naming structure, the overlap of the two naming structures under the constituent element of the region to which the work unit belongs can be determined. For example, if there are two Rs in the first naming structure and only one R in the second naming structure, then the overlap of the first naming structure and the second naming structure under the constituent element of the region to which the work unit name belongs is determined to be 1. Similarly, the overlap of the first naming structure and the second naming structure under the other three constituent elements can be calculated, and finally based on the four overlaps, the similarity between the verification work unit name and the standard work unit name is determined.

[0108] In the above scheme, by considering the various constituent elements of the work unit name, including the constituent elements indicating the region to which the work unit belongs, the constituent elements indicating the industry to which the work unit belongs, the constituent elements indicating the keywords in the work unit name and the constituent elements indicating the suffix information of the work unit name, different constituent elements can contain different parts of speech of words. Therefore, by performing word segmentation processing on a work unit name, then according to the parts of speech of the word segments obtained after the word segmentation processing, the work unit name can be converted into a style expressed by the constituent elements of the work unit name, that is, a naming structure. Therefore, when subsequently determining the credibility of a verification work unit name of a verification object, the similarity between the two work unit names can be determined based on the same constituent elements in the naming structure corresponding to the verification work unit name and the naming structure corresponding to the standard work unit name corresponding to the verification work unit name. This similarity can be used to characterize whether the verification work unit name is a true and credible work unit name. In this method, since the work unit name can be converted into a style expressed by the constituent elements of the work unit name based on the part of speech of each participle in the work unit name, when subsequently determining whether a verified work unit name is a true value, the similarity between the two work unit names can be quickly and accurately obtained based on the same constituent elements between the verified work unit name and the standard work unit name, thereby improving the efficiency and accuracy of determining the authenticity of the work unit name input by the user.

[0109] The following will explain the above steps in detail with examples.

[0110] In one implementation of the above-mentioned step 104, the similarity between the verification work unit name and the standard work unit name is determined based on at least the same element structure in the first naming structure and the second naming structure, including: determining each verification sub-name in the verification work unit name based on each fourth component in the first naming structure; determining each standard sub-name in the standard work unit name based on each fourth component in the second naming structure; determining the verification abbreviation of the verification work unit name by the first verification sub-name that is at the first position in each verification sub-name; determining the standard abbreviation of the standard work unit name by the first standard sub-name that is at the first position in each standard sub-name; determining the similarity between the verification work unit name and the standard work unit name based on at least the element similarity of the same elements in the first naming structure and the second naming structure, and the abbreviation similarity between the verification abbreviation and the standard abbreviation.

[0111] For example, since the user may directly write the abbreviation of his or her work unit name when entering his or her own work unit name, in order to further improve the accuracy of identifying the authenticity of the verification work unit name entered by the user, in this application, in addition to considering the similarity of the elements of the same constituent elements in the naming structure corresponding to the verification work unit name and the standard work unit name of the same verification object, the similarity between the abbreviations of the two work unit names is further considered. Obviously, this is of great significance for accurately determining whether the verification work unit name is the standard work unit name.

[0112] Specifically, taking the third record in the aforementioned Table 2 as an example, for the work unit name "China Merchants Bank Wuhan Branch", the naming structure formed based on the various components of the work unit name is "XORO", wherein, with "O" as the dividing node, two sub-names corresponding to the work unit name "China Merchants Bank Wuhan Branch" can be obtained, specifically, the sub-name "China Merchants Bank" and the sub-name "Wuhan Branch"; and considering that when users write the abbreviation of their work unit, they will be accustomed to writing a larger abbreviation, which can reflect their unit and save writing time. For example, for the work unit name "China Merchants Bank Wuhan Sub-branch", users will be more inclined to write its abbreviation as "China Merchants Bank", and rarely or even will not write it based on "Wuhan Branch". Write its abbreviation. Based on this, in this application, the abbreviations corresponding to the work unit name can be determined based on the sub-name located in the first place among the sub-names corresponding to the work unit name. For the two sub-names of "China Merchants Bank Wuhan Branch" having the work unit name "China Merchants Bank (XO)" and "Wuhan Branch (RO)", in this application, the abbreviations corresponding to the work unit name "China Merchants Bank Wuhan Branch" can be determined based on the sub-name "China Merchants Bank (XO)". Finally, in addition to considering the similarity of elements, further consider the similarity of the abbreviations between the verification work unit name and the standard work unit name from the perspective of abbreviations. The final similarity obtained by integrating the similarities of these two aspects can be used to judge whether the verified work unit name is the standard work unit name very well and accurately.

[0113] In certain implementations of the present application, determining the verification abbreviation of the verification work unit name by using the first verification sub-name that is at the first position among the verification sub-names includes: determining a verification naming structure corresponding to the first verification sub-name that is at the first position among the verification sub-names; applying the abbreviation rule of the naming structure to the verification naming structure, thereby determining the abbreviations corresponding to the first verification sub-name, and using the abbreviations corresponding to the first verification sub-name as the verification abbreviation of the verification work unit name; the abbreviation rule of the naming structure is determined by a sample work unit name and a sample work unit abbreviation.

[0114] Before describing how to determine the verification abbreviation of the verification work unit name by the first verification sub-name in each verification sub-name, the present application will first describe the abbreviation rule of the naming structure; and then describe the process of determining the verification abbreviation of the verification work unit name after illustrating the abbreviation rule of the naming structure with examples.

[0115] In certain implementations of the present application, the abbreviation rule of the naming structure is determined by the sample work unit name and the sample work unit abbreviation, including: for any sample work unit name, the sample work unit name is normalized; the normalization process at least includes removing special characters, numbers and lowercase letters in the work unit name; for the sample work unit name after the normalization process, the sample work unit name is segmented to obtain each third segmentation corresponding to the sample work unit name and the part of speech of each third segmentation; based on the identifiers corresponding to each of the constituent elements, for each third segmentation, according to the part of speech of each third segmentation, the naming structure of the sample work unit name is determined; for the sample work unit name, each abbreviation of the sample work unit name and the naming structure of each abbreviation are determined; for any of the abbreviations, according to the naming structure of the abbreviation, the position information of the abbreviation in the naming structure of the sample work unit name is marked; a correspondence between the sample work unit name and the position information of each abbreviation in the naming structure of the sample work unit name is established, and used as the abbreviation rule of the naming structure.

[0116] For example, as shown in Table 3, a list of abbreviation rules for a naming structure provided in an embodiment of the present application is provided, wherein only the first record in Table 3 is used for illustration in the present application, and other records in Table 3 are not listed for illustration:

[0117]

[0118] Table 3

[0119] First aspect:

[0120] First, for the work unit name "China Mobile Limited Liability Company", the work unit name can be standardized, wherein the standardized processing at least includes removing special characters, numbers and lowercase letters in the work unit name. It should be noted that since there are no special characters, numbers and lowercase letters in the work unit name "China Mobile Limited Liability Company", the step of standardizing the work unit name can be skipped.

[0121] Next, perform word segmentation on the standardized work unit name. For example, for the work unit name "China Mobile Communications Corporation Limited", after word segmentation, the words "China (ns)", "Mobile (vd)", and "Communications Corporation Limited (csx)" can be obtained in sequence.

[0122] Then, according to the part-of-speech of each word obtained after word segmentation of "China Mobile Communications Corporation Limited", it can be determined that the naming structure formula formed by the work unit name "China Mobile Communications Corporation Limited" based on the constituent elements of the work unit name is "RXO".

[0123] Second aspect:

[0124] Those skilled in the art can enumerate all possible abbreviations of "China Mobile Communications Corporation Limited". For example, its abbreviations can be "CMCC" and "China Mobile".

[0125] Third aspect:

[0126] Based on the first aspect above, for "China Mobile Communications Corporation Limited", its naming structure formula will be "RXO". Based on the second aspect above, for "China Mobile Communications Corporation Limited", its abbreviations can be "CMCC" and "China Mobile". Then:

[0127] 1. For the abbreviation "CMCC", the character "中 (zhōng)" is in the 1st position of the word "中国 (zhōng guó)", and the word "移动 (yí dòng)" in the abbreviation is the same as the word "移动 (yí dòng)" after word segmentation. Therefore, for the abbreviation "CMCC", it can be determined that the abbreviation rule of its naming structure formula is R[1]X. Specifically, for the number "1" in the square brackets in the abbreviation rule R[1]X, it represents taking only the character "中 (zhōng)" in the 1st position of the word "中国 (zhōng guó)" indicated by the constituent element "R". Since there is no form of square brackets plus a number after "X", it means taking the complete word "移动 (yí dòng)" indicated by the constituent element "X".

[0128] 2. For the abbreviation "China Mobile", the word "中国 (zhōng guó)" in it is the same as the word "中国 (zhōng guó)" after word segmentation, and the word "移动 (yí dòng)" in the abbreviation is the same as the word "移动 (yí dòng)" after word segmentation. Therefore, for the abbreviation "China Mobile", it can be determined that the abbreviation rule of its naming structure formula is RX.

[0129] According to the above description of the abbreviation rule for determining the naming structure of the work unit name "China Mobile Co., Ltd.", it can be known that: if the first sub-name in the verification work unit name or standard work unit name of a verification object is "China Mobile Co., Ltd.", such as the verification work unit name of a verification object is "China Mobile Co., Ltd. Shanghai Branch", then it can be determined that its first sub-name is "China Mobile Co., Ltd." and the naming structure of the first sub-name is "RXO". Then, by looking up the mapping relationship from "structure" to "abbreviation" shown in Table 3, it can be determined that when the naming structure is "RXO", its abbreviation construction rule is "R[1]X" and "RX". In this way, it can be determined that the corresponding abbreviations of "China Mobile Co., Ltd." are "China Mobile" and "China Mobile".

[0130] In certain embodiments of the present application, after segmenting the verification work unit name of the verification object by the Jieba word segmentation method to obtain each first participle, before determining the first classification information of each first participle under each constituent element of the work unit name based on the part of speech of each first participle, the method also includes: if there are first participles of consecutive single words in each first participle after the Jieba word segmentation processing, the consecutive single words are merged into one first participle.

[0131] It should be noted that the above example describes a method of determining the sub-names of a work unit name from a macro perspective by dividing the sub-names corresponding to the work unit name based on the "O" in the naming structure. With regard to this issue, the present application can also determine the various information that can be revealed in a work unit name from a micro perspective (i.e., from a computer execution perspective) through the method described below, such as determining the region to which the work unit belongs, the industry to which the work unit belongs, the keywords of the work unit name, and the sub-names corresponding to the work unit name.

[0132] For example, for a naming structure corresponding to a work unit name, the first segment ending with O is intercepted and concatenated into firstName (i.e., the first name), and the second segment ending with O is concatenated to the first O position segment to form secondName (the second name), and then the abbreviation rule of the naming structure is applied to firstName to determine the abbreviations corresponding to the work unit name and form an abbreviation list; and according to the part of speech of each segment, the industry vocabulary list industryList and the keyword vocabulary list keywordList are obtained. The specific implementation is as follows:

[0133] For the convenience of description, six variables can be preset as follows:

[0134] (1) First name: firstName

[0135] (2) Second name: secondName

[0136] (3) Keyword list: keywordList

[0137] (4) Variable singleWord used for a single word = ""

[0138] It is noted that the reason why variable (4) is used in this application is that even if the word segmentation vocabulary corresponding to the Jieba word segmentation is enriched, it cannot be guaranteed to completely cover all words, or some colloquial words are not included in the Chinese dictionary. Therefore, in order to avoid the situation where words that should be combined into one word are actually divided into isolated Chinese characters, the variable singleWord = "" is set in this application to avoid the occurrence of the above unfavorable situation.

[0139] (5) Variable nameStruct = "" that stores the named structure

[0140] (6) Industry List

[0141] Based on the above-preset 6 variables, by executing the following steps e.1 to e.5 on a work unit name (specifically, the participles corresponding to the work unit name), it is possible to obtain information about the industry to which the work unit indicated by the work unit name belongs, the keyword information of the work unit name, the corresponding sub-names of the work unit name, and the corresponding abbreviations of the work unit name. Among them:

[0142] Step e.1: For the Jieba token list tokenList after the word segmentation of the work unit name, traverse the tokenList and assume that the currently traversed token is token[i], where 0<=i <length(tokenList)。

[0143] Step e.2: If the length of token[i] is equal to 1, then singleWord=singleWord+token[i], the variable singleWord=”” is used to concatenate multiple consecutive single words into a word, continue traversing and go to step e.1, otherwise go to step e.3.

[0144] Step e.3: If the length of singleWord is greater than or equal to 1, it means that a concatenated word already exists and the word can be used as a keyword nameStruct = nameStruct + "X". Add singleWord to keywordList, clear singleWord, and then go to step e.4. Otherwise, go directly to step e.4.

[0145] Step e.4: Determine the part of speech of the currently traversed token[i], where:

[0146] If it is ns (region), then nameStruct = nameStruct + "R";

[0147] If it is idu(industry), then nameStruct = nameStruct + "I", add to the industry list industryList;

[0148] If it is a company suffix (csx), then nameStruct = nameStruct + "O", recording the position index of O in the name, which can be used for names such as branches and sub-branches;

[0149] If it is x (keyword), then nameStruct = nameStruct + "X", and add it to the keyword list keywordList.

[0150] Step e.5: If index>0, it means that the suffix appears in the middle of the name, so it is necessary to separate the first name and the second name; take the string from 0 to index as firstName, and the string from index to end as secondName, intercept the string from 0 to index, and finally assign it to nameStruct as the name structure.

[0151] For example, suppose that before step e.5, nameStruct = RXIOXO, then after the update operation in step e.5, nameStruct = RXIO.

[0152] For the above-described process of determining the first name, the second name, the keyword list, and the industry word list corresponding to a work unit name, assume that according to this method, after processing the work unit name "の(⊙o⊙)…4 China Merchants Bank Co., Ltd. Shenzhen Weisheng Building Branch www", the following content is obtained:

[0153]

[0154] in:

[0155] Job refers to the general term for all the content obtained after processing the work unit name "の(⊙o⊙)…4 China Merchants Bank Co., Ltd., Shenzhen VIA Tower Sub-branch, www";

[0156] The abbreList in Job represents the abbreviation list, where abbreList = ["China Merchants Bank", "CMB"], which is obtained by taking the first sub-name "China Merchants Bank Co., Ltd." according to the nameStruct = XO of the last item in Job, and applying the abbreviation rules corresponding to the naming structure XO. For example, the abbreviation rules are X[1]O[2] and X. Thus, the abbreviations corresponding to the sub-name "China Merchants Bank Co., Ltd." are "China Merchants Bank" and "CMB". Further, the abbreviations "China Merchants Bank" and "CMB" corresponding to the sub-name "China Merchants Bank Co., Ltd." are also the abbreviations corresponding to the work unit name "の(⊙o⊙)…4 China Merchants Bank Co., Ltd., Shenzhen VIA Tower Sub-branch, www";

[0157] The jobType in Job represents the type of the work unit, which can be mainly determined by performing a regular expression match on the work unit name "の(⊙o⊙)…4 China Merchants Bank Co., Ltd., Shenzhen VIA Tower Sub-branch, www", and thus determining that the type of the work unit is COMPANY;

[0158] The oriName in Job represents the work unit name actively input by the user. For example, when oriName = 'の(⊙o⊙)…4 China Merchants Bank Co., Ltd., Shenzhen VIA Tower Sub-branch, www', then for the special character "の(⊙o⊙)…", the number "4", and the lowercase letters "www" in this work unit name, they will all be deleted. Thus, in this application, word segmentation will be performed based on "China Merchants Bank Co., Ltd., Shenzhen VIA Tower Sub-branch";

[0159] The firstName in Job represents the first sub-name in the work unit name. For example, when the work unit name is "の(⊙o⊙)…4 China Merchants Bank Co., Ltd., Shenzhen VIA Tower Sub-branch, www", its firstName = 'China Merchants Bank Co., Ltd.';

[0160] The secondName in Job represents the second sub-name in the work unit name. For example, when the work unit name is "の(⊙o⊙)…4 China Merchants Bank Co., Ltd., Shenzhen VIA Tower Sub-branch, www", its secondName = 'Shenzhen VIA Tower Sub-branch';

[0161] The region in Job indicates the region to which the work unit indicated by the work unit name belongs. For example, when the work unit name is "の(⊙o⊙)…4China Merchants Bank Co., Ltd. Shenzhen Weisheng Building Branch www", its region = 'Shenzhen City, Guangdong Province';

[0162] The regionId in Job indicates the coding method of the region to which the work unit belongs. For example, when the name of the work unit is "の(⊙o⊙)…4China Merchants Bank Co., Ltd. Shenzhen Weisheng Building Branch www", its regionId = '440300000000';

[0163] The industryList in Job indicates the industry word list of the industry to which the work unit belongs, and is used to store various industry words. For example, when the name of the work unit is "の(⊙o⊙)…4 China Merchants Bank Co., Ltd. Shenzhen Weisheng Building Branch www", its industryList = [Branch];

[0164] The keywordList in Job represents the keyword list of the work unit name, which is used to store the keywords in the work unit name. For example, when the work unit name is "の(⊙o⊙)…4China Merchants Bank Co., Ltd. Shenzhen VIA Building Branch www", its keywordList = [China Merchants, VIA, Building].

[0165] As shown in Table 4, a list of work types belonging to a work unit is provided in an embodiment of the present application, wherein the first column indicates the work type belonging to the work unit, such as 14 work types from top to bottom, including EDUCATION, MEDICAL, SCIENTIFIC, ADMINISTRATION, ARMY, COMPANY, COURT, POLICE, BANK, FACTORY, HOTEL_FOOD, EXPRESS, INDIVIDUAL and OTHER, wherein the second column is the Chinese explanation of each work type in the first column, from top to bottom, including education, medical and health, scientific research, administrative agencies, military, companies, legal work, public security bureaus, banks, factories, hotels and restaurants, express delivery, individual businesses and others, wherein the first 12 work types from top to bottom in the list shown in Table 4 defined in the present application comply with the rxo strategy, i.e., the first calculation strategy, and the last 2 work types in the list comply with the str strategy, i.e., the second calculation strategy.

[0166]

[0167]

[0168] Table 4

[0169] Based on the work types to which a work unit can belong as shown in Table 4, for a work unit name, by matching the work unit name with a regular expression, the type of work unit to which the work unit name points can be determined.

[0170] Therefore, after matching the regular expressions of the verification work unit name and the standard work unit name of the verification object respectively, the type of the work unit indicated by the verification work unit name and the type of the work unit indicated by the standard work unit name can be determined respectively, wherein the determined type of the work unit can be fed back to the jobType field in the Job, thereby, by analyzing the type of the work unit indicated by the verification work unit name and the type of the work unit indicated by the standard work unit name, the method of calculating the similarity between the verification work unit name and the standard work unit name can be determined, including the following situations:

[0171] Case 1: When using regular expressions to determine the work types of the work units indicated by the verification work unit names and the standard work unit names of the verification object respectively, it is determined that there is at least one work unit name that cannot be mapped to any work type in the rxo strategy, or it is determined that there is at least one work unit name that cannot be mapped to any work type in the str strategy, then it can be determined that the similarity between the verification work unit name and the standard work unit name is 0.

[0172] Case 2: If the type of the work unit indicated by the verification work unit name and the type of the work unit indicated by the standard work unit name are different work types under the RXO strategy, it can be determined that the similarity between the verification work unit name and the standard work unit name is 0.

[0173] Case 3: If the type of work unit indicated by the verification work unit name and the type of work unit indicated by the standard work unit name are the same work type under the RXO policy, the similarity between the verification work unit name and the standard work unit name can be calculated in the following ways, including:

[0174] In certain embodiments of the present application, the similarity between the verification work unit name and the standard work unit name is determined based on at least the element similarity of the same components in the first naming structure and the second naming structure, and the abbreviation similarity between the verification abbreviation and the standard abbreviation, including: determining the first element similarity between the industry information corresponding to the second component in the verification work unit name and the industry information corresponding to the second component in the standard work unit name; determining the second element similarity between the keywords corresponding to the third component in the verification work unit name and the keywords corresponding to the third component in the standard work unit name; determining the abbreviation similarity between the verification abbreviation and the standard abbreviation; determining the sub-name similarity between the verification sub-name set in each verification sub-name and the corresponding standard sub-name in each standard sub-name; and determining the similarity between the verification work unit name and the standard work unit name based on the first element similarity, the second element similarity, the abbreviation similarity and the sub-name similarity.

[0175] In certain embodiments of the present application, the similarity between the verification work unit name and the standard work unit name is determined based on the first factor similarity, the second factor similarity, the abbreviation similarity and the sub-name similarity, including: determining the similarity between the verification work unit name and the standard work unit name based on the first factor similarity and a first preset weight, the second factor similarity and a second preset weight, the abbreviation similarity and a third preset weight, the sub-name similarity and a fourth preset weight; wherein the abbreviation similarity and the sub-name similarity are determined by means of the shortest edit distance.

[0176] For the verification work unit name and the standard work unit name of a verification object, after word segmentation processing and job information generation operations, assuming that the job information corresponding to the verification work unit name is job1, and the job information corresponding to the standard work unit name is job2, then the similarity between the verification work unit name and the standard work unit name is obtained by multiplying the similarity of firstName, secondName, abbreList, industryList, and keywordList of job1 and job2 by the corresponding preset weight. The specific calculation method is as follows:

[0177] similar=sum(score firstName *rate firstName +score secondName *rate secondName

[0178] +score abbrName*rate abbrName +score iduName *rate iduName

[0179] +score keyword *rate keyword )

[0180] Among them, similar represents the similarity between the verification work unit name and the standard work unit name of the verification object, sum represents the sum, and score firstName Indicates the similarity of the names of two work units under the first name, rate firstName Indicates the fourth preset weight, score secondName Indicates the similarity of the names of two work units under the second name, rate secondName Indicates the fourth preset weight, score abbrName Indicates the similarity of the names of two work units under the abbreviation, rate abbrName Indicates the third preset weight, score iduName Indicates the similarity between the names of two work units in the industry to which they belong, rate iduName Indicates the first preset weight, score keyword Indicates the similarity between the names of two work units under the keywords in the names of the work units, rate keyword represents a second preset weight;

[0181] in:

[0182] score firstName =minEdit(firstName job1 ,firstName job2 )

[0183] score secondName =minEdit(secondName job1 ,secondName job2 )

[0184] i←0,len(abbrList job1 )

[0185] j←0,len(abbrList job2 )

[0186] score abbrName =max[minEdit(abbrList job1 [i],abbrList job2 [j])], minEdit is the shortest edit distance;

[0187] score idu forindustryList job1 and industryList job2 The same number of words in .

[0188] score keyword keywordList job1 and keywordList job2 The same number of words in .

[0189] By setting a threshold, if similarity reaches the preset threshold, the two work order names are considered similar, otherwise not.

[0190] Case 4: If the type of the work unit indicated by the verification work unit name and the type of the work unit indicated by the standard work unit name are the same work type or different work types under the str strategy, the similarity between the verification work unit name and the standard work unit name can be determined by string matching, where the string matching method can be the KMP algorithm.

[0191] Case 5: If the type of the work unit indicated by the verification work unit name is a work type in the rxo policy and the type of the work unit name indicated by the standard work unit name is a work type under the str policy, it is necessary to determine whether the Job corresponding to the standard work unit name has the first name, the second name, the industry vocabulary, the keyword vocabulary and the abbreviation. If it is determined that there is, the similarity between the verification work unit name and the standard work unit name can be determined based on the same algorithm as Case 3; otherwise, the similarity between the verification work unit name and the standard work unit name will be determined to be 0.

[0192] Based on the same concept, the present application embodiment provides a work unit name verification device, such as Figure 2 , which is a schematic diagram of a work unit name verification device provided in an embodiment of the present application, the device includes a word segmentation unit 201, a classification information determination unit 202, a naming structure determination unit 203 and a similarity determination unit 204;

[0193] A word segmentation unit 201 is used to segment the name of the verification work unit of the verification object to obtain each first word segmentation, and segment the name of the standard work unit of the verification object to obtain each second word segmentation;

[0194] The classification information determination unit 202 is used to determine the first classification information of each first participle under each component of the work unit name according to the part of speech of each first participle, and determine the second classification information of each second participle under each component according to the part of speech of each second participle; wherein the parts of speech of the words contained in each component are different, and each component includes a first component indicating the region to which the work unit belongs, a second component indicating the industry to which the work unit belongs, a third component indicating a keyword in the work unit name, and a fourth component indicating suffix information of the work unit name;

[0195] A naming structure determining unit 203, configured to determine a first naming structure corresponding to the verification work unit name based on the identifiers corresponding to the constituent elements and the first classification information, and to determine a second naming structure corresponding to the standard work unit name based on the identifiers corresponding to the constituent elements and the second classification information;

[0196] The similarity determination unit 204 is configured to determine the similarity between the verification work unit name and the standard work unit name based on at least the same constituent elements in the first naming structure and the second naming structure.

[0197] Further, for the device, the similarity determination unit 204 is specifically used to: determine each verification sub-name in the verification work unit name based on each fourth constituent element in the first naming structure; determine each standard sub-name in the standard work unit name based on each fourth constituent element in the second naming structure; determine the verification abbreviation of the verification work unit name through the first verification sub-name that is at the first position in each verification sub-name; determine the standard abbreviation of the standard work unit name through the first standard sub-name that is at the first position in each standard sub-name; determine the similarity between the verification work unit name and the standard work unit name based on at least the element similarity of the same constituent elements in the first naming structure and the second naming structure, and the abbreviation similarity between the verification abbreviation and the standard abbreviation.

[0198] Further, for the device, the similarity determination unit 204 is specifically used to: determine the verification naming structure corresponding to the first verification sub-name located at the first position among the verification sub-names; apply the abbreviation rule of the naming structure to the verification naming structure, so as to determine the abbreviations corresponding to the first verification sub-name, and use the abbreviations corresponding to the first verification sub-name as the verification abbreviations of the verification work unit name; the abbreviation rule of the naming structure is determined by the sample work unit name and the sample work unit abbreviation.

[0199] Further, for the device, the similarity determination unit 204 is specifically used to: determine the first element similarity between the industry information corresponding to the second component in the verification work unit name and the industry information corresponding to the second component in the standard work unit name; determine the second element similarity between the keywords corresponding to the third component in the verification work unit name and the keywords corresponding to the third component in the standard work unit name; determine the abbreviation similarity between the verification abbreviation and the standard abbreviation; determine the sub-name similarity between the verification sub-name set in each verification sub-name and the corresponding standard sub-name in each standard sub-name; determine the similarity between the verification work unit name and the standard work unit name based on the first element similarity, the second element similarity, the abbreviation similarity and the sub-name similarity.

[0200] Furthermore, for the device, the word segmentation unit 201 is also used to: determine, based on a preset regular expression, whether the verification work unit name and the standard work unit name have corresponding work unit types, and determine whether the verification work unit name and the standard work unit name belong to different work unit types in the first calculation strategy; wherein the preset regular expression is used to determine, based on the work unit name, the work unit type to which the work unit indicated by the work unit name belongs, and the first calculation strategy includes multiple work unit types, and the work unit name of each work unit under any one of the multiple work unit types contains the various constituent elements of the work unit name when naming.

[0201] Furthermore, for the device, the word segmentation unit 201 is also used to: determine, based on the preset regular expression, that the verification work unit name and the standard work unit name belong to the same work unit type in the first calculation strategy; the similarity determination unit 204 is specifically used to: determine the similarity between the verification work unit name and the standard work unit name based on the first element similarity and the first preset weight, the second element similarity and the second preset weight, the abbreviation similarity and the third preset weight, the sub-name similarity and the fourth preset weight; wherein the abbreviation similarity and the sub-name similarity are determined by means of the shortest edit distance.

[0202] Further, for the device, the word segmentation unit 201 is specifically used to: segment the name of the verification work unit of the verification object by the Jieba word segmentation method to obtain each first word and the part of speech of each first word; the word segmentation library corresponding to the Jieba word segmentation includes each word added based on the work unit name.

[0203] Furthermore, for the device, the word segmentation unit 201 is also used for: if there are first participles of consecutive single words in each first participle after the Jieba word segmentation processing, then the consecutive single words are merged into one first participle.

[0204] Furthermore, for the device, the parts of speech of the vocabulary contained in each of the constituent elements are different, including: the parts of speech of the vocabulary contained in the first constituent element are regional parts of speech, the parts of speech of the vocabulary contained in the second constituent element are industry parts of speech, the parts of speech of the vocabulary contained in the third constituent element are directional parts of speech, noun parts of speech, adjective parts of speech, verb and adverb parts of speech, and unknown parts of speech, and the parts of speech of the vocabulary contained in the fourth constituent element are suffix parts of speech.

[0205] Furthermore, the device further includes a naming structure abbreviation rule generating unit 205, which is used to: for any sample work unit name, perform normalization processing on the sample work unit name; the normalization processing at least includes removing special characters, numbers and lowercase letters in the work unit name; for the sample work unit name after normalization processing, perform word segmentation on the sample work unit name to obtain each third word corresponding to the sample work unit name and the part of speech of each third word; based on the identifiers corresponding to each of the constituent elements, for each third word, according to the part of speech of each third word, determine the naming structure of the sample work unit name; for the sample work unit name, determine each abbreviation of the sample work unit name and the naming structure of each abbreviation; for any of the abbreviations, according to the naming structure of the abbreviation, mark the position information of the abbreviation in the naming structure of the sample work unit name; establish a correspondence between the sample work unit name and the position information of each abbreviation in the naming structure of the sample work unit name, and use it as the abbreviation rule of the naming structure.

[0206] The embodiment of the present application also provides a computing device, which may be a desktop computer, a portable computer, a smart phone, a tablet computer, a personal digital assistant (PDA), etc. The computing device may include a central processing unit (CPU), a memory, an input / output device, etc. The input device may include a keyboard, a mouse, a touch screen, etc. The output device may include a display device, such as a liquid crystal display (LCD), a cathode ray tube (CRT), etc.

[0207] The memory may include a read-only memory (ROM) and a random access memory (RAM), and provides the processor with program instructions and data stored in the memory. In an embodiment of the present application, the memory may be used to store program instructions of a work unit name verification method;

[0208] The processor is used to call the program instructions stored in the memory and execute the work unit name verification method according to the obtained program.

[0209] like Figure 3 FIG. 1 is a schematic diagram of a computing device provided in an embodiment of the present application, wherein the computing device includes:

[0210] Processor 301, memory 302, transceiver 303, bus interface 304; wherein the processor 301, memory 302 and transceiver 303 are connected via bus 305;

[0211] The processor 301 is used to read the program in the memory 302 and execute the above work unit name verification method;

[0212] The processor 301 may be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and a NP. It may also be a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0213] The memory 302 is used to store one or more executable programs and can store data used by the processor 301 when performing operations.

[0214] Specifically, the program may include program code, and the program code includes computer operation instructions. The memory 302 may include volatile memory, such as random-access memory (RAM); the memory 302 may also include non-volatile memory, such as flash memory, hard disk drive (HDD) or solid-state drive (SSD); the memory 302 may also include a combination of the above-mentioned types of memory.

[0215] The memory 302 stores the following elements, executable modules or data structures, or a subset thereof, or an extended set thereof:

[0216] Operation instructions: include various operation instructions, used to implement various operations.

[0217] Operating system: includes various system programs used to implement various basic businesses and handle hardware-based tasks.

[0218] The bus 305 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0219] The bus interface 304 may be a wired communication access port, a wireless bus interface or a combination thereof, wherein the wired bus interface may be, for example, an Ethernet interface. The Ethernet interface may be an optical interface, an electrical interface or a combination thereof. The wireless bus interface may be a WLAN interface.

[0220] An embodiment of the present application also provides a computer-readable storage medium, which stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute a work unit name verification method.

[0221] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0222] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0223] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0224] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0225] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0226] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for verifying the name of a work unit, characterized in that: include: Segmenting the name of the verification work unit of the verification object to obtain first segmented words, and segmenting the name of the standard work unit of the verification object to obtain second segmented words; For the parts of speech of each of the first participles, first classification information of each of the first participles under each component of the work unit name is determined, and for the parts of speech of each of the second participles, second classification information of each of the second participles under each component is determined; wherein the parts of speech of the words contained in each of the components are different, and the components include a first component indicating the region to which the work unit belongs, a second component indicating the industry to which the work unit belongs, a third component indicating a keyword in the work unit name, and a fourth component indicating suffix information of the work unit name; Determine a first naming structure corresponding to the verification work unit name based on the identifiers corresponding to the respective components and the first classification information, and determine a second naming structure corresponding to the standard work unit name based on the identifiers corresponding to the respective components and the second classification information; The similarity between the verification work unit name and the standard work unit name is determined based on at least the same constituent elements in the first naming structure and the second naming structure.

2. The method according to claim 1, characterized in that The determining the similarity between the verification work unit name and the standard work unit name based on at least the same element structure in the first naming structure formula and the second naming structure formula includes: Determining each check sub-name in the check work unit name based on each fourth component in the first naming structure; Determining each standard sub-name in the standard working unit name based on each fourth component in the second naming structure; Determine the verification abbreviation of the verification work unit name by using the first verification sub-name in the first place among the verification sub-names; Determine the standard abbreviation of the standard work unit name by the first standard sub-name in the first place among the standard sub-names; The similarity between the verification work unit name and the standard work unit name is determined based at least on the element similarity of the same constituent elements in the first naming structure and the second naming structure, and the abbreviation similarity between the verification abbreviation and the standard abbreviation.

3. The method according to claim 2, characterized in that The step of determining the verification abbreviation of the verification work unit name by using the first verification sub-name located at the first position among the verification sub-names includes: Determine a checksum naming structure corresponding to a first checksum name in the first place among the checksum names; The abbreviation rule of the naming structure is applied to the verification naming structure to determine the abbreviations corresponding to the first verification sub-name, and the abbreviations corresponding to the first verification sub-name are used as the verification abbreviations of the verification work unit name; the abbreviation rule of the naming structure is determined by the sample work unit name and the sample work unit abbreviation.

4. The method according to claim 2, characterized in that The determining the similarity between the verification work unit name and the standard work unit name based on at least the element similarity of the same constituent elements in the first naming structure and the second naming structure, and the abbreviation similarity between the verification abbreviation and the standard abbreviation, comprises: Determine the first element similarity between the industry information corresponding to the second component of the verification work unit name and the industry information corresponding to the second component of the standard work unit name; Determine the second element similarity between each keyword corresponding to the third component in the verification work unit name and each keyword corresponding to the third component in the standard work unit name; Determining the similarity between the verification abbreviation and the standard abbreviation; Determining a subname similarity between a syndrome subname set in each syndrome subname and a corresponding standard subname in each standard subname; The similarity between the verification work unit name and the standard work unit name is determined according to the first element similarity, the second element similarity, the abbreviation similarity and the sub-name similarity.

5. The method according to claim 4, characterized in that Before segmenting the verification work unit name of the verification object to obtain each first segmentation, and segmenting the standard work unit name of the verification object to obtain each second segmentation, the method further includes: According to a preset regular expression, it is determined that there are corresponding work unit types for the verification work unit name and the standard work unit name, and it is determined whether the verification work unit name and the standard work unit name belong to different work unit types in the first calculation strategy; wherein the preset regular expression is used to determine the work unit type to which the work unit indicated by the work unit name belongs based on the work unit name, and the first calculation strategy includes multiple work unit types, and the work unit name of each work unit under any one of the multiple work unit types contains the various constituent elements of the work unit name when naming.

6. The method according to claim 5, characterized in that After segmenting the verification work unit name of the verification object to obtain each first segmentation, and segmenting the standard work unit name of the verification object to obtain each second segmentation, the method further includes: According to the preset regular expression, determining that the verification work unit name and the standard work unit name belong to the same work unit type in the first calculation strategy; Determining the similarity between the verification work unit name and the standard work unit name according to the first element similarity, the second element similarity, the abbreviation similarity and the sub-name similarity includes: The similarity between the verification work unit name and the standard work unit name is determined based on the first factor similarity and the first preset weight, the second factor similarity and the second preset weight, the abbreviation similarity and the third preset weight, and the sub-name similarity and the fourth preset weight; wherein the abbreviation similarity and the sub-name similarity are determined by means of the shortest edit distance.

7. The method according to any one of claims 1 to 6, characterized in that: The segmenting of the verification work unit name of the verification object to obtain each first segmentation includes: By means of Jieba word segmentation, the name of the verification work unit of the verification object is segmented to obtain each first word and the part of speech of each first word; the word segmentation library corresponding to the Jieba word segmentation includes each word added based on the work unit name.

8. The method according to claim 7, characterized in that After segmenting the verification work unit name of the verification object by the Jieba segmentation method to obtain each first segmentation, and before determining the first classification information of each first segmentation under each component of the work unit name according to the part of speech of each first segmentation, the method further includes: If there are consecutive first participles of single words in the first participles after the Jieba word segmentation process, the consecutive first participles of single words are merged into one first participle.

9. The method according to any one of claims 1 to 6, characterized in that: The words contained in each of the constituent elements have different parts of speech, including: The parts of speech of the vocabulary included in the first component are regional parts of speech, the parts of speech of the vocabulary included in the second component are industry parts of speech, the parts of speech of the vocabulary included in the third component are directional parts of speech, noun parts of speech, adjective parts of speech, verb and adverb parts of speech, and unknown parts of speech, and the parts of speech of the vocabulary included in the fourth component are suffix parts of speech.

10. The method according to claim 3, characterized in that The abbreviation rule of the naming structure is determined by the sample work unit name and the sample work unit abbreviation, including: For any sample work unit name, the sample work unit name is normalized; the normalization process at least includes removing special characters, numbers and lowercase letters in the work unit name; For the sample work unit name after the normalization process, the sample work unit name is segmented to obtain each third segmentation corresponding to the sample work unit name and the part of speech of each third segmentation; Based on the identifiers corresponding to the constituent elements, for each of the third participles, and according to the parts of speech of each of the third participles, determining the naming structure of the sample work unit name; For the sample work unit names, determine the abbreviations of the sample work unit names and the naming structure of the abbreviations; For any one of the abbreviations, according to the naming structure of the abbreviation, marking the position information of the abbreviation in the naming structure of the sample work unit name; A corresponding relationship between the sample work unit name and the position information of each abbreviation in the naming structure of the sample work unit name is established and used as the abbreviation rule of the naming structure.

11. A device for verifying the name of a work unit, characterized in that: include: A word segmentation unit, used for segmenting the name of the verification work unit of the verification object to obtain each first word segmentation, and segmenting the name of the standard work unit of the verification object to obtain each second word segmentation; a classification information determination unit, configured to determine first classification information of each first participle under each constituent element of the work unit name according to the part of speech of each first participle, and to determine second classification information of each second participle under each constituent element according to the part of speech of each second participle; wherein the parts of speech of the words contained in each constituent element are different, and each constituent element includes a first constituent element indicating a region to which the work unit belongs, a second constituent element indicating an industry to which the work unit belongs, a third constituent element indicating a keyword in the work unit name, and a fourth constituent element indicating suffix information of the work unit name; a naming structure determining unit, configured to determine a first naming structure corresponding to the verification work unit name based on the identifiers corresponding to the constituent elements and the first classification information, and to determine a second naming structure corresponding to the standard work unit name based on the identifiers corresponding to the constituent elements and the second classification information; A similarity determination unit is used to determine the similarity between the verification work unit name and the standard work unit name based on at least the same constituent elements in the first naming structure formula and the second naming structure formula.

12. A computer device, characterized in that: include: Memory for storing computer programs; A processor, configured to call a computer program stored in the memory, and execute the method according to any one of claims 1 to 10 according to the obtained program.

13. A computer-readable storage medium, characterized in that: The storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the method according to any one of claims 1 to 10.

Images