CN114818706A - A text matching method, device and government service text matching method - Google Patents

Abstract

The application provides a text matching method, which comprises the following steps: obtaining a target entity type corresponding to the entity name text to be matched; according to the target entity category, obtaining a candidate standardized entity name text corresponding to the entity name text to be matched, wherein the entity category is the same as the target entity category; and obtaining a target standardized entity name text matched with the entity name text to be matched from the candidate standardized entity name text according to the text similarity between the entity name text to be matched and the candidate standardized entity name text. According to the text matching method, the target standardized entity name text matched with the entity name text to be matched can be obtained according to the text similarity between the entity name text to be matched and the candidate standardized entity name text, the entity name text to be matched and the target standardized entity name text do not need to be matched in a manual summarizing mode, and therefore the entity name document standardization efficiency is improved.

Description

A text matching method, device and government service text matching method

technical field

The present application relates to the field of computer technology, in particular to a text matching method. The present application also relates to a text matching device, an electronic device, a storage medium, and a text matching method for government services.

Background technique

With the rapid development of Internet technology, more and more Internet-based business service systems have begun to appear or have been applied in different service fields. For example, the technical system of "Internet + government services" applied to government services has begun to be constructed. However, the Internet-based business service system has to face many problems, such as the standardization of entity name documents.

Taking "Internet + government services" as an example, in the process of optimizing government services, it is necessary to analyze which materials can be digitized. At this time, the usual practice is to collect the most reliant materials for government services from various governments, and then analyze which materials can be electronic. However, when local governments describe the government materials required for government service matters, the descriptions of the names of government service materials are often non-standard, such as: "People's Republic of China resident ID card" is described as "personal ID card", "double ID card" ID card", "spouse ID card" and so on. The non-standard description of the names of government service materials not only causes a bad user experience, but also brings great challenges to the subsequent optimization of government service items. Therefore, how to standardize the non-standardized entity name document has become an urgent problem to be solved in the development of the Internet-based business service system.

In the prior art, the method for solving the standardization problem of non-standardized entity name documents is generally as follows: establishing a database containing a large number of entity name documents of the same category, and manually summarizing the non-standardized entity name documents describing the same entity name in the database and linking them to the database. on the Standardized Entity Name document describing the name of this entity. Since the existing methods to solve the problem of standardization of non-standardized entity name documents need to be based on manual aggregation, the efficiency of standardization of non-standardized entity name documents is low.

SUMMARY OF THE INVENTION

The present application provides a text matching method, apparatus, electronic device and storage medium to improve the efficiency of entity name document standardization.

The present application provides a text matching method, including:

Obtain the target entity category corresponding to the entity name text to be matched;

According to the target entity category, obtain the candidate standardized entity name text corresponding to the entity name text to be matched whose entity category is the same as the target entity category;

According to the text similarity between the entity name text to be matched and the candidate standardized entity name text, the target standardized entity name text that matches the to-be-matched entity name text is obtained from the candidate standardized entity name text.

Optionally, the method further includes: providing the target standardized entity name text to the user equipment.

Optionally, the method further includes: associating the entity name text to be matched with the target standardized entity name text.

Optionally, the associating the entity name text to be matched with the target standardized entity name text includes: establishing a correspondence between the entity name text to be matched and the target standardized entity name text.

Optionally, the obtaining the target entity category corresponding to the entity name text to be matched includes: obtaining a text matching instruction sent by the user equipment, where the text matching instruction carries the entity name text to be matched;

The providing the location recommendation information to the user equipment includes: for the text matching instruction, providing the target standardized entity name text to the user equipment.

Optionally, the method further includes: displaying the text of the target standardized entity name.

Optionally, the obtaining the target entity category corresponding to the entity name text to be matched includes:

Adopt a preset word segmentation strategy to perform word segmentation on the entity name text to be matched, and obtain the category keywords in the entity name text to be matched;

The target entity category is obtained according to the category keyword in the entity name text to be matched.

Optionally, according to the target entity category, obtain the candidate standardized entity name text corresponding to the entity name text to be matched whose entity category is the same as the target entity category, including:

According to the keywords in the entity name text to be matched, obtain the associated standardized entity name text associated with the entity name to be matched;

obtaining the entity category associated with the normalized entity name text;

The candidate normalized entity name text is obtained from the associated normalized entity name text based on the target entity class and the entity class.

Optionally, according to the text similarity between the entity name text to be matched and the candidate standardized entity name text, obtain the target standardized entity matching the to-be-matched entity name text from the candidate standardized entity name text. Name text, including:

Obtain the weight of the keyword in the entity name text to be matched and the weight of the keyword in the candidate standardized entity name text;

Obtain the first word vector corresponding to the keyword in the entity name text to be matched, and the second word vector corresponding to the keyword in the candidate standardized entity name text;

The first word vector is obtained according to the weight of the keyword in the entity name text to be matched, the weight of the keyword in the candidate standardized entity name text, the first word vector and the second word vector word vector similarity with the second word vector;

According to the word vector similarity, the text similarity is obtained.

Optionally, obtaining the text similarity according to the word vector similarity includes:

Obtain the character string matched by the name of the entity to be matched;

obtaining the character string corresponding to the candidate standardized entity name text;

According to the character string matched by the entity name text to be matched and the character string corresponding to the candidate standardized entity name text, obtain the difference between the character string matched by the to-be-matched entity name text and the character string corresponding to the candidate standardized entity name text string similarity;

The text similarity is obtained according to the word vector similarity and the character string similarity.

Optionally, obtaining the text similarity according to the word vector similarity and the character string similarity includes: according to a preset first similarity weight corresponding to the word vector similarity and the The second similarity weight corresponding to the word vector similarity is weighting the word vector similarity and the character string similarity to obtain the text similarity.

Optionally, it also includes: judging whether the text similarity reaches a text similarity threshold;

According to the text similarity between the entity name text to be matched and the candidate standardized entity name text, the target standardized entity name text that matches the to-be-matched entity name text is obtained from the candidate standardized entity name text, including : if the text similarity reaches the text similarity threshold, obtain the candidate standardized entity name text whose text similarity reaches the text similarity threshold from the candidate standardized entity name text as the target standardization Entity name text.

Optionally, obtaining the candidate standardized entity name text whose text similarity reaches the text similarity threshold from the candidate standardized entity name text as the target standardized entity name text includes: obtaining the candidate standardized entity name text from the candidate standardized entity name text. In the standardized entity name text, the candidate standardized entity name text whose text similarity reaches the text similarity threshold and has the highest similarity is obtained as the target standardized entity name text.

Optionally, it also includes: if the text similarity does not reach the text similarity threshold, determining that the target standardized entity name text does not exist in the candidate standardized entity name text.

Another aspect of the present application provides a text matching device, comprising:

The target entity category obtaining unit is used to obtain the target entity category corresponding to the name text of the entity to be matched;

A candidate text obtaining unit is used to obtain, according to the target entity category, a candidate standardized entity name text corresponding to the entity name text to be matched whose entity category is the same as the target entity category;

A target text matching unit, configured to obtain a target standardization matching the entity name text to be matched from the candidate standardized entity name text according to the text similarity between the entity name text to be matched and the candidate standardized entity name text Entity name text.

In another aspect of the present application, an electronic device is also provided, comprising:

processor; and

The memory is used to store the program of the text matching method, and after the device is powered on and the program of the text matching method is run by the processor, the following steps are performed:

Obtain the target entity category corresponding to the entity name text to be matched;

According to the target entity category, obtain the candidate standardized entity name text corresponding to the entity name text to be matched whose entity category is the same as the target entity category;

According to the text similarity between the entity name text to be matched and the candidate standardized entity name text, the target standardized entity name text that matches the to-be-matched entity name text is obtained from the candidate standardized entity name text.

On the other hand, the present application also provides a storage medium that stores a program of the text matching method, the program is run by the processor, and the following steps are performed: obtaining the target entity category corresponding to the entity name text to be matched;

According to the target entity category, obtain the candidate standardized entity name text corresponding to the entity name text to be matched whose entity category is the same as the target entity category;

According to the text similarity between the entity name text to be matched and the candidate standardized entity name text, the target standardized entity name text that matches the to-be-matched entity name text is obtained from the candidate standardized entity name text.

On the other hand, the present application also provides a method for text matching in government services, including:

Obtain the target entity category corresponding to the name text of the entity to be matched, which is used to describe the name of the government service material;

According to the target entity category, obtain the candidate standardized entity name text corresponding to the entity name text to be matched whose entity category is the same as the target entity category;

According to the text similarity between the entity name text to be matched and the candidate standardized entity name text, obtain the target standardized entity name text that matches the to-be-matched entity name text from the candidate standardized entity name text;

Associating the entity name text to be matched with the target standardized entity name text.

In another aspect of the present application, an address text matching method is also provided, including:

Obtain the target entity category corresponding to the entity name text to be matched for describing the geographic location name;

According to the target entity category, obtain the candidate standardized entity name text corresponding to the entity name text to be matched whose entity category is the same as the target entity category;

According to the text similarity between the entity name text to be matched and the candidate standardized entity name text, obtain the target standardized entity name text that matches the to-be-matched entity name text from the candidate standardized entity name text;

Associating the entity name text to be matched with the target standardized entity name text.

Compared with the prior art, the present application has the following advantages:

The present application provides a text matching method, by obtaining the target entity category corresponding to the entity name text to be matched; according to the target entity category, obtain the candidate entity corresponding to the entity name text to be matched whose entity category is the same as the target entity category standardized entity name text; according to the text similarity between the entity name text to be matched and the candidate standardized entity name text, obtain the target standardized entity name matching the to-be-matched entity name text from the candidate standardized entity name text text. The text matching method provided by the present application can obtain the target standardized entity name text matched by the entity name text to be matched according to the text similarity between the entity name text to be matched and the candidate standardized entity name text, and does not need to rely on manual aggregation to match the to-be-matched entity name text. The entity name text is matched with the target normalized entity name text, thereby improving the efficiency of entity name document normalization.

Description of drawings

FIG. 1 is a schematic diagram of a first scenario of the text matching method provided by the first embodiment of the present application.

FIG. 2 is a flowchart of a text matching method provided in the first embodiment of the present application.

FIG. 3 is a schematic diagram of a first scenario of the text matching method provided in the first embodiment of the present application.

FIG. 4 is a schematic diagram of a text matching apparatus provided in a second embodiment of the present application.

FIG. 5 is a schematic diagram of an electronic device provided in an embodiment of the present application.

FIG. 6 is a flowchart of a text matching method provided in a fifth embodiment of the present application.

Detailed ways

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. However, the application can be implemented in many other ways different from those described here, and those skilled in the art can make similar promotions without violating the connotation of the application. Therefore, the application is not limited by the specific implementation disclosed below.

In order to more clearly demonstrate the text matching method provided in the first embodiment of the present application, an application scenario of the text matching method provided in the first embodiment of the present application is first introduced. For the text matching method provided in the first embodiment of the present application, the execution subject may be the server, or the client with the relevant text recognition application installed, or both the server and the client, that is, by performing the server and the client at the same time. The interaction between the client and the server to complete the text matching method. The so-called client is an application program or software installed on the user equipment that can implement the text matching method provided by the embodiments of the present application. The so-called user equipment is generally a mobile phone, a PC (Personal Computer, personal computer), etc., and a tablet computer in a specific implementation manner. etc., the so-called application program (APP, Application) or software capable of implementing the text matching method provided by the embodiments of the present application may be a mobile phone application program, web version online text matching software, computer software, and the like. The so-called server is a computing device used to provide services such as data processing for the above-mentioned clients, and the so-called server is generally a server or a server cluster in a specific implementation manner.

In the first embodiment of the present application, the application scenario of the text matching method is completed through the interaction between the server and the client and the server, and the client can realize the text matching provided by the embodiment of the present application if the client is installed on a computer. Taking the computer software of the method as an example, for a detailed description of the text matching method provided in the first embodiment of the present application, please refer to FIG. 1 , which is a schematic diagram of a first scenario of the text matching method provided by the first embodiment of the present application.

First, after the user equipment obtains the text matching trigger operation triggered by the client 101, the client 101 will obtain the name text of the entity to be matched based on the user equipment.

In the first embodiment of the present application, the so-called entity name text is the text used to describe the name of the entity in the target text, and the so-called target text is generally a piece of document, a paragraph or a sentence, such as: government service matters, other than government affairs services Network service matters, equipment operation procedures and chemical experiment steps introduction, and so on. When the entity name text is the text used to describe the name of the government service material, the so-called entity is generally the required government service material in the government service matters; when the entity name text is the text used to describe the name of the network service material, the so-called entity It can also be used for network service materials required in network service matters other than government services. In addition, the so-called entity can also be other types of entities, such as: equipment in the description of equipment operation procedures, chemicals in the introduction of chemical experiment steps, and chemical reaction devices. That is to say, in the first embodiment of the present application, the target text and the entity are not specifically limited.

The so-called entity name text to be matched is generally a non-standardized entity name text, and can also be a standardized entity name text. The so-called standardized entity name text and non-standardized entity name text are respectively standard description text and non-standard description text for the same entity name. Specifically, the "People's Republic of China Resident Identity Card" can be taken as an example. The standardized entity name text of the "People's Republic of China Resident Identity Card" is "People's Republic of China Resident Identity Card", and the non-standardized entity name text can be "Personal Identity Card". "Double ID Card", "Couple ID Card" and so on. The “Real Estate Registration Application Form” can also be taken as an example. The standardized entity name text of the “Real Estate Registration Application Form” is “Real Estate Registration Application Form”, and the non-standardized entity name text can be “Real Estate Registration Application Form”, etc. You can also take "Personnel File" as an example. The standardized entity name text of "Personnel File" is "Personnel File", and the text of non-standardized entity name can be "Applicant Personnel File", "Personnel File of Insured Person" and "Original Personnel File". "and many more.

In "Internet + government services", the non-standard description of the names of government service materials not only caused a bad user experience, but also brought great challenges to the subsequent optimization of government services. In other application scenarios, it will also bring inconvenience to users. Therefore, the text matching method provided in the first embodiment of the present application needs to match the entity name text to be matched with the corresponding standardized entity name text. That is, the target normalized entity name text that matches the entity name text to be matched is obtained, that is, the non-standardized entity name text is normalized. The so-called target standardized entity name text is the standard description text whose text similarity with the entity name text to be matched exceeds the text similarity threshold and describes the same entity name as the entity name text to be matched.

Then, after obtaining the text of the entity name to be matched, the client 101 will further issue a text matching instruction to the server 102 based on the user's trigger operation on the user equipment, and the text matching instruction carries the text of the entity name to be matched. In addition, after obtaining the entity name text to be matched, the client 101 may first send the entity name text to be matched to the server 102, and then send a text matching instruction for the entity name text to be matched to the server 102. In the first embodiment of the present application, the specific manner in which the client 101 sends the text of the entity name to be matched to the server 102 is not specifically limited. After the server 102 obtains the text matching instruction carrying the entity name text to be matched, the following steps are performed in order to obtain the target standardized entity name text matching the entity name text to be matched. For details, please refer to FIG. A flowchart of a text matching method provided in the embodiment.

In step S201, the target entity category corresponding to the name text of the entity to be matched is obtained.

The so-called entity category is the category of the entity described by the entity name text, and the entity category is a pre-divided category according to a preset entity category division strategy. In the specific implementation process, the process of obtaining the target entity category is as follows: first, adopt a preset word segmentation strategy to segment the text of the entity name to be matched, and obtain the category keywords in the text of the entity name to be matched; then, according to the entity name text to be matched. The category keywords in , get the target entity category. The so-called category keywords are words in the entity name text that can identify entity categories. Specifically, taking the entity as a government service material as an example, for example: when the text of the entity name to be matched is "XX application", "XX certification", "XX certificate" and "XX form", etc. For example, "application", "certificate", "certificate" and "table", "application", "certification", "certificate" and "table" are the names of the entities to be matched Category keywords in the text. In the first embodiment of the present application, the categories are pre-divided according to the preset entity category division strategy, that is, the entity categories are determined according to the category keywords in the pre-statistical entity name text. Therefore, the "application" category, "certificate" category, "certificate" category and "table" category are also pre-divided categories according to the preset entity category division strategy.

In the first embodiment of the present application, the specific implementation method of obtaining the target entity category according to the category keywords in the entity name text to be matched is: according to the category keywords in the entity name text to be matched and the corresponding relationship between the category keywords and categories , get the target entity class.

In the first embodiment of the present application, the category of the entity is determined according to the category keywords in the pre-statistical entity name text, which ensures that after the category keywords in the entity name text are obtained, the entity name can be obtained directly according to the category keywords. The entity category of the text, so that the acquisition of the entity category of the entity name text is simpler and faster.

It should be noted that when encountering a new entity name text, the reverse maximum matching method can be used to confirm the entity category of the new entity name text.

The so-called pre-set word segmentation strategy can be: using the Chinese word segmenter used for word segmentation in natural language processing to segment the text of the entity name to be matched. In the first embodiment of the present application, in order to control the granularity of word segmentation, a personalized dictionary can be further introduced, and the entity name text text is divided into consecutive word orders according to the order, and then it is determined according to the rules and whether the consecutive word order is in a given personalized dictionary. Whether the consecutive word order is the final word segmentation result.

In step S202, according to the target entity category, the candidate standardized entity name text corresponding to the entity name text to be matched whose entity category is the same as the target entity category is obtained.

The so-called candidate standardized entity name text corresponding to the entity name text to be matched is the standardized entity name text obtained based on the keywords in the entity name text to be matched and associated with the keywords in the entity name text to be matched. In the specific implementation process, for the entity name text to be matched, the bm25 (Best Match, best match) recall strategy is adopted, and ES (Elastic Search, distributed full-text retrieval) tool is used in the preset standardized entity name text data. Quickly recall the associated normalized entity name text associated with the entity name to be matched.

In the first embodiment of the present application, the specific implementation method of obtaining the candidate standardized entity name text is as follows: First, according to the keywords in the entity name text to be matched, the associated standardized entity name text associated with the entity name to be matched is obtained. Then, obtain the entity category associated with the normalized entity name text. Finally, according to the target entity category and entity category, candidate normalized entity name texts are obtained from the associated normalized entity name texts. The detailed process of associating the entity category of the standardized entity name text is similar to the process of obtaining the target entity category corresponding to the entity name text to be matched. For details, please refer to the description of the acquisition process of the target entity category in step S201, which will not be described in detail here. of elaboration.

In step S203, according to the text similarity between the entity name text to be matched and the candidate standardized entity name text, the target standardized entity name text matching the entity name text to be matched is obtained from the candidate standardized entity name text.

In the specific implementation process, the process of obtaining the text similarity is as follows: First, obtain the weight of the keywords in the entity name text to be matched and the weight of the keywords in the candidate standardized entity name text. Second, obtain the first word vector corresponding to the keyword in the entity name text to be matched, and the second word vector corresponding to the keyword in the candidate standardized entity name text. Third, according to the weight of the keyword in the entity name text to be matched, the weight of the keyword in the candidate standardized entity name text, the first word vector and the second word vector, obtain the words of the first word vector and the second word vector Vector similarity. Fourth, according to the word vector similarity, the text similarity is obtained.

In the first embodiment of the present application, the method of obtaining the first word vector corresponding to the keyword in the entity name text to be matched and the second word vector corresponding to the keyword in the candidate standardized entity name text is: based on Word2vec(WordTo Vector, The related model used to generate word vectors) model, which maps the keywords in the entity name text to be matched and the keywords in the candidate standardized entity name text to a vector, so as to obtain the first word vector and the second word vector, the so-called Word2vec The model is a network model that quickly and efficiently expresses a word into a vector form obtained by training the model according to a given corpus.

In the first embodiment of the present application, the specific implementation manner of obtaining the weight of the keyword in the entity name text to be matched and the weight of the keyword in the candidate standardized entity name text is as follows:

First, take the entity name text to be matched and the candidate standardized entity name text as a target text set.

Then, the to-be-matched entity name text and the candidate standardized entity name text are segmented respectively to obtain different keywords in the to-be-matched entity name text and the candidate standardized entity name text.

Finally, the TF-IDF (Term Frequency-Inverse Document Frequency, a commonly used weighting technique for information retrieval data mining) technology is used to obtain the TF (Term Frequency, word frequency), the IDF (Inverse Document Frequency, inverse text frequency index) of different keywords in the target text set in the entity name text to be matched, and obtain the different keywords in the candidate standardized entity name text in the candidate standardized entity name text. Word frequency and the inverse text frequency index of different keywords in the candidate standardized entity name text in the target text set; then according to the word frequency and inverse text frequency index, obtain the TF-IDF of different keywords in the entity name text to be matched and the candidate standardized entity TF-IDF of different keywords in the name text; and determine the entity name text to be matched according to the TF-IDF of different keywords in the entity name text to be matched and the TF-IDF of different keywords in the candidate standardized entity name text Different keywords in and different keywords in the candidate standardized entity name text are used to calculate the weight of word vector similarity.

Taking the government service material name text "People's Republic of China Resident Identity Card" as an example, if the government service material name text "People's Republic of China Resident Identity Card", for the target text set composed of the corresponding candidate standardized entity name text, "China The TF-IDF of "People's Republic of China" is 2, the TF-IDF of "resident" is 1, and the TF-IDF of "ID card" is 7, then when calculating the word vector similarity, the weight of "People's Republic of China" is 0.2, " The weight of "resident" is 0.1, and the weight of "ID card" is 0.7.

In the first embodiment of the present application, the first word vector and the second word vector are obtained according to the weight of the keyword in the entity name text to be matched, the weight of the keyword in the candidate standardized entity name text, the first word vector and the second word vector. The process of the word vector similarity of the two word vectors is as follows: for the first word vector and the second word vector, the cosine similarity of the first word vector and the second word vector is obtained as the word vector similarity. Specifically, when calculating the cosine similarity of the first word vector and the second word vector for the first word vector and the second word vector, the elements in the first word vector and the second word vector are multiplied by their respective weights.

In order to improve the accuracy of the text similarity between the entity name text to be matched and the candidate standardized entity name text, in the first embodiment of the present application, when obtaining the text similarity, the string similarity is further introduced to solve the text similarity. In the specific implementation process, first, obtain the character string matched by the text of the entity name to be matched; secondly, obtain the character string corresponding to the text of the candidate standardized entity name; thirdly, according to the character string matched by the text of the entity name to be matched and the corresponding text of the candidate standardized entity name obtain the string similarity between the character string matched by the entity name text to be matched and the character string corresponding to the candidate standardized entity name text; finally, obtain the text similarity according to the word vector similarity and the string similarity. Specifically, according to the preset first similarity weight corresponding to the word vector similarity and the second similarity weight corresponding to the word vector similarity, the word vector similarity and the character string similarity are weighted to obtain the text similarity.

In the first embodiment of the present application, before obtaining the text similarity according to the word vector similarity and the character string similarity, it is necessary to judge whether the text similarity reaches the text similarity threshold. If the text similarity reaches the text similarity threshold, the candidate standardized entity name text whose text similarity reaches the text similarity threshold is obtained from the candidate standardized entity name text as the target standardized entity name text. Specifically, from the candidate standardized entity name text, the candidate standardized entity name text whose text similarity reaches the text similarity threshold and has the highest similarity is obtained as the target standardized entity name text. For example, the text similarity between "Personal ID Card" and "People's Republic of China Resident ID Card" is 0.78. When the preset text similarity threshold is 0.7, "People's Republic of China Resident ID Card" is regarded as the "Personal ID Card". Target normalized entity name text.

In addition, if the text similarity does not reach the text similarity threshold, it is determined that the target normalized entity name text does not exist in the candidate normalized entity name text.

In the first embodiment of the present application, when the server 102 determines that the target standardized entity name text does not exist in the candidate standardized entity name text, it will generate feedback information that the target standardized entity name text does not exist and feed it back to the client 101. The client 101 uses the user The interactive interface of the device displays the feedback information.

After the server 102 obtains the target standardized entity name text, it can first provide the target standardized entity name text to the client 101 for the text matching instruction, and then the client 101 associates the to-be-matched entity name text with the target standardized entity name text, That is, a corresponding relationship between the entity name text to be matched and the target standardized entity name text is established. In addition, after the server 102 obtains the target standardized entity name text, it can also first associate the to-be-matched entity name text with the target standardized entity name text, and then obtain the association result and provide it to the client 101.

The text matching method provided in the first embodiment of the present application can also be applied to an application scenario where the server is the execution body. Please refer to FIG. 3 , which is a schematic diagram of the first scenario of the text matching method provided in the first embodiment of the present application.

Step S301: Obtain the name text of the entity to be matched. Step S302: Obtain the target entity category, that is, obtain the target entity category corresponding to the name text of the entity to be matched. Step S303: Obtain the candidate standardized entity name text, that is, according to the target entity category, obtain the candidate standardized entity name text corresponding to the entity name text to be matched whose entity category is the same as the target entity category. Step S304-1: Obtain word vector similarity. Step S304-2: Obtain the string similarity. Step S305: Obtain the text similarity, that is, obtain the text similarity according to the word vector similarity and the character string similarity. Step S306: Determine whether the text similarity reaches a text similarity threshold. Step S306-1: If yes, obtain the target standardized entity name text, that is, from the candidate standardized entity name text, obtain the candidate standardized entity name text whose text similarity reaches the text similarity threshold as the target standardized entity name text. Step S306-2: If no, obtain feedback information, that is, determine that the target standardized entity name text does not exist in the candidate standardized entity name text, and obtain feedback information of the unobtained target standardized entity name text.

The text matching method provided in the first embodiment of the present application can also be applied to an application scenario where the client is the execution subject.

In the specific implementation process, after obtaining the entity name text to be matched, the client will perform the following steps in sequence. First, obtain the target entity category corresponding to the entity name text to be matched; then, according to the target entity category, obtain the entity category and the target entity category. The candidate standardized entity name text corresponding to the entity name text to be matched with the same entity category; finally, according to the text similarity between the entity name text to be matched and the candidate standardized entity name text, obtain the entity name text to be matched from the candidate standardized entity name text. The matching target normalized entity name text.

In the first embodiment of the present application, the application scenarios of the text matching method provided in the first embodiment of the present application are not specifically limited. For example, the text matching method provided in the first embodiment of the present application can also be applied to other scenarios, I won't go into details here. The above application scenarios are provided to facilitate understanding of the text matching method provided in the first embodiment of the present application, but not to limit the text matching method provided in the first embodiment of the present application.

A first embodiment of the present application provides a text matching method, by obtaining multiple location element texts in the location query text, where the multiple location element texts are texts used to describe locations in the location query text; for multiple location element texts , obtain candidate location information corresponding to multiple location element texts; according to at least one of the number of occurrences of multiple location element texts in the location query text and the clustering scores of candidate location information corresponding to multiple location element texts, for multiple location element texts The candidate position information corresponding to the position element text is sorted, and the position recommendation information for the position query text is obtained according to the sorting result. The text matching method provided in the first embodiment of the present application sorts the candidate location information corresponding to the multiple location element texts based on the multiple location element texts, which can ensure that the candidate location information in the location recommendation information for the location query text corresponds to the corresponding location information. Multiple location element texts, thereby improving the accuracy of location recommendation information when there are multiple location element texts in the location query text.

The first embodiment of the present application provides a text matching method, by obtaining the target entity category corresponding to the entity name text to be matched; according to the target entity category, obtain the candidate standardization corresponding to the entity name text to be matched whose entity category is the same as the target entity category Entity name text; according to the text similarity between the entity name text to be matched and the candidate standardized entity name text, obtain the target standardized entity name text matching the entity name text to be matched from the candidate standardized entity name text. The text matching method provided in the first embodiment of the present application can obtain the target standardized entity name text matched by the entity name text to be matched according to the text similarity between the entity name text to be matched and the candidate standardized entity name text, without relying on manual summary The method is used to match the entity name text to be matched with the target standardized entity name text, thereby improving the efficiency of entity name document standardization. Second Embodiment

Corresponding to the application scenario of the text matching method provided by the embodiment of the present application and the text matching method provided by the first embodiment, the second embodiment of the present application further provides a text matching method. Since this embodiment of the apparatus is basically similar to the application scenario of the text matching method provided by the embodiment of the present application and the text matching method provided by the first embodiment, the description is relatively simple. For relevant details, please refer to the text matching provided by the embodiment of the present application. The application scenarios of the method and the partial description of the text matching method provided by the first embodiment are sufficient. The apparatus embodiments described below are merely illustrative.

Please refer to FIG. 4 , which is a schematic diagram of a text matching apparatus provided in a second embodiment of the present application.

The text matching device includes:

The target entity category obtaining unit 401 is used to obtain the target entity category corresponding to the entity name text to be matched;

Candidate text obtaining unit 402, configured to obtain, according to the target entity category, the candidate standardized entity name text corresponding to the entity name text to be matched whose entity category is the same as the target entity category;

A target text matching unit 403, configured to obtain a target matching the entity name text to be matched from the candidate standardized entity name text according to the text similarity between the entity name text to be matched and the candidate standardized entity name text Normalized entity name text.

Optionally, the text matching apparatus provided in the second embodiment of the present application further includes: a text providing unit, configured to provide the target standardized entity name text to the user equipment.

Optionally, the text matching apparatus provided in the second embodiment of the present application further includes: a text association unit, configured to associate the to-be-matched entity name text with the target standardized entity name text.

Optionally, the text association unit is specifically configured to establish a correspondence between the entity name text to be matched and the target standardized entity name text.

Optionally, the target entity category obtaining unit 401 is specifically configured to obtain a text matching instruction issued by the user equipment, and the text matching instruction carries the entity name text to be matched;

The text providing unit is specifically configured to provide the target standardized entity name text to the user equipment for the text matching instruction.

Optionally, the text matching apparatus provided in the second embodiment of the present application further includes: a text display unit, configured to display the text of the target standardized entity name.

Optionally, the target entity category obtaining unit 401 is specifically configured to adopt a preset word segmentation strategy to perform word segmentation on the entity name text to be matched, and obtain category keywords in the entity name text to be matched; Match the category keywords in the entity name text to obtain the target entity category.

Optionally, the candidate text obtaining unit 402 is specifically configured to obtain the associated standardized entity name text associated with the entity name to be matched according to the keywords in the entity name text to be matched; obtain the associated standardized entity name The entity category of the text; according to the target entity category and the entity category, the candidate standardized entity name text is obtained from the associated standardized entity name text.

Optionally, the target text matching unit 403 is specifically configured to obtain the weight of the keyword in the entity name text to be matched and the weight of the keyword in the candidate standardized entity name text; obtain the entity name to be matched. The first word vector corresponding to the keyword in the text, and the second word vector corresponding to the keyword in the candidate standardized entity name text; according to the weight of the keyword in the entity name text to be matched, the candidate standardized The weight of the keyword in the entity name text, the first word vector and the second word vector, to obtain the word vector similarity between the first word vector and the second word vector; according to the similarity of the word vector to obtain the text similarity.

Optionally, the obtaining the text similarity according to the word vector similarity includes: obtaining the text-matched character string of the entity name to be matched;

obtaining the character string corresponding to the candidate standardized entity name text;

According to the character string matched by the entity name text to be matched and the character string corresponding to the candidate standardized entity name text, obtain the difference between the character string matched by the to-be-matched entity name text and the character string corresponding to the candidate standardized entity name text string similarity;

The text similarity is obtained according to the word vector similarity and the character string similarity.

Optionally, obtaining the text similarity according to the word vector similarity and the character string similarity includes: according to a preset first similarity weight corresponding to the word vector similarity and the The second similarity weight corresponding to the word vector similarity is weighting the word vector similarity and the character string similarity to obtain the text similarity.

Optionally, the text matching device provided in the second embodiment of the present application further includes: a similarity judging unit for judging whether the text similarity reaches a text similarity threshold;

The target text matching unit 403 is specifically configured to obtain, from the candidate standardized entity name text, the text whose similarity of the text reaches the threshold of the text similarity if the judgment result of the similarity judgment unit is yes. The candidate normalized entity name text is used as the target normalized entity name text.

Optionally, obtaining the candidate standardized entity name text whose text similarity reaches the text similarity threshold from the candidate standardized entity name text as the target standardized entity name text includes: obtaining the candidate standardized entity name text from the candidate standardized entity name text. In the standardized entity name text, the candidate standardized entity name text whose text similarity reaches the text similarity threshold and has the highest similarity is obtained as the target standardized entity name text.

Optionally, the text matching device provided in the second embodiment of the present application further includes: a result determination unit, configured to determine whether the candidate standardized entity name text is not in the text if the determination result of the similarity determination unit is no. The target normalized entity name text exists.

Third Embodiment

Corresponding to the application scenario of the text matching method provided by the embodiment of the present application and the text matching method provided by the first embodiment, the third embodiment of the present application further provides an electronic device. Since the third embodiment is basically similar to the application scenario of the text matching method provided by the embodiment of the present application and the text matching method provided by the first embodiment, the description is relatively simple. For relevant details, please refer to the text matching method provided by the embodiment of the present application. The application scenario and the partial description of the text matching method provided by the first embodiment are sufficient. The third embodiment described below is merely illustrative.

Please refer to FIG. 5 , which is a schematic diagram of an electronic device provided in an embodiment of the present application.

The electronic device includes: a processor 501;

And memory 502, for storing the program of information processing method, after this equipment is powered on and runs the program of this information processing method by processor, executes the following steps:

Obtain the target entity category corresponding to the entity name text to be matched;

According to the target entity category, obtain the candidate standardized entity name text corresponding to the entity name text to be matched whose entity category is the same as the target entity category;

According to the text similarity between the entity name text to be matched and the candidate standardized entity name text, the target standardized entity name text that matches the to-be-matched entity name text is obtained from the candidate standardized entity name text.

It should be noted that, for the detailed description of the electronic device provided by the eighth embodiment of the present application, reference may be made to the application scenario of the live broadcast service system provided by the embodiment of the present application, the live broadcast service system provided by the first embodiment, and the related aspects of the above method embodiments. description, which will not be repeated here.

Fourth Embodiment

Corresponding to the application scenario of the text matching method provided by the embodiment of the present application and the text matching method provided by the first embodiment, the fourth embodiment of the present application further provides a storage medium. Since the fourth embodiment is basically similar to the application scenario of the text matching method provided by the embodiment of the present application and the text matching method provided by the first embodiment, the description is relatively simple. For relevant details, please refer to the text matching method provided by the embodiment of the present application. The application scenario and the partial description of the text matching method provided by the first embodiment are sufficient. The apparatus embodiments described below are merely illustrative.

The storage medium stores a computer program, and the computer program is executed by the processor to perform the following steps:

Obtain the target entity category corresponding to the entity name text to be matched;

According to the target entity category, obtain the candidate standardized entity name text corresponding to the entity name text to be matched whose entity category is the same as the target entity category;

According to the text similarity between the entity name text to be matched and the candidate standardized entity name text, the target standardized entity name text that matches the to-be-matched entity name text is obtained from the candidate standardized entity name text.

It should be noted that, for the detailed description of the storage medium provided by the ninth embodiment of the present application, reference may be made to the application scenarios of the text matching method provided by the embodiments of the present application and the related descriptions of the text matching method provided by the first embodiment, which are not repeated here. Repeat.

Fifth Embodiment

Corresponding to the application scenario of the text matching method provided by the embodiment of the present application and the text matching method provided by the first embodiment, the fifth embodiment of the present application further provides another text matching method. Since this embodiment of the apparatus is basically similar to the application scenario of the text matching method provided by the embodiment of the present application and the text matching method provided by the first embodiment, the description is relatively simple. For relevant details, please refer to the text matching provided by the embodiment of the present application. The application scenarios of the method and the partial description of the text matching method provided by the first embodiment are sufficient. The method embodiments described below are merely illustrative.

A text matching method provided in the fifth embodiment of the present application will be described below with reference to FIG. 6 .

FIG. 6 is a flowchart of a text matching method provided in a fifth embodiment of the present application. FIG. 6 is a flowchart of a text matching method provided in the fifth embodiment of the present application, and the method includes steps S601 to S604.

In step S601, the target entity category corresponding to the name text of the entity to be matched for describing the name of the government service material is obtained.

In the fifth embodiment of the present application, the so-called entity name text is the text used to describe the name of the entity in the target text, and the so-called target text is generally a piece of document, a paragraph or a sentence, such as: government service matters, other than government affairs services Network service matters, equipment operation procedures, and chemical experiment procedures are introduced. The so-called entity is generally the required government service materials in government service matters. In this case, the text of the entity name is the text used to describe the name of the government service material; the so-called entity can also be required in network service matters other than government services. The web service material, in this case, the entity name text is the text used to describe the name of the web service material. In addition, the so-called entity can also be other types of entities, such as: equipment in the description of equipment operation procedures, chemicals in the introduction of chemical experiment steps, and chemical reaction devices. That is to say, in the first embodiment of the present application, the target text and entities are not specifically limited.

The so-called entity name text to be matched is generally a non-standardized entity name text, and can also be a standardized entity name text. The so-called standardized entity name text and non-standardized entity name text are respectively standard description text and non-standard description text for the same entity name. Specifically, the "People's Republic of China Resident Identity Card" can be taken as an example. The standardized entity name text of the "People's Republic of China Resident Identity Card" is "People's Republic of China Resident Identity Card", and the non-standardized entity name text can be "Personal Identity Card". "Double ID Card", "Couple ID Card" and so on. The “Real Estate Registration Application Form” can also be taken as an example. The standardized entity name text of the “Real Estate Registration Application Form” is “Real Estate Registration Application Form”, and the non-standardized entity name text can be “Real Estate Registration Application Form”, etc. You can also take "Personnel File" as an example. The standardized entity name text of "Personnel File" is "Personnel File", and the text of non-standardized entity name can be "Applicant Personnel File", "Personnel File of Insured Person" and "Original Personnel File". "and many more.

The so-called entity category is the category of the entity described by the entity name text, and the entity category is a pre-divided category according to a preset entity category division strategy. In the specific implementation process, the process of obtaining the target entity category is as follows: first, adopt a preset word segmentation strategy to segment the text of the entity name to be matched, and obtain the category keywords in the text of the entity name to be matched; then, according to the entity name text to be matched. The category keywords in , get the target entity category. The so-called category keywords are words in the entity name text that can identify entity categories. Specifically, taking the entity as a government service material as an example, for example: when the text of the entity name to be matched is "XX application", "XX certification", "XX certificate" and "XX form", etc. For example, "application", "certificate", "certificate" and "table", "application", "certification", "certificate" and "table" are the names of the entities to be matched Category keywords in the text. In the fifth embodiment of the present application, the categories are pre-divided according to the preset entity category division strategy, that is, the entity categories are determined according to the category keywords in the pre-statistical entity name text. Therefore, the "application" category, "certificate" category, "certificate" category and "table" category are also pre-divided categories according to the preset entity category division strategy.

In step S602, according to the target entity category, the candidate standardized entity name text corresponding to the entity name text to be matched whose entity category is the same as the target entity category is obtained.

In the fifth embodiment of the present application, the so-called candidate standardized entity name text corresponding to the entity name text to be matched is a standardized entity obtained based on the keywords in the entity name text to be matched and associated with the keywords in the entity name text to be matched. name text. In the specific implementation process, for the entity name text to be matched, the recall strategy of bm25 is adopted, and the ES tool is used to quickly recall the associated standardized entity name text associated with the entity name to be matched in the preset standardized entity name text data.

In step S603, according to the text similarity between the entity name text to be matched and the candidate standardized entity name text, the target standardized entity name text matching the entity name text to be matched is obtained from the candidate standardized entity name text.

In the specific implementation process, before obtaining the text similarity according to the word vector similarity and the character string similarity, it is necessary to judge whether the text similarity reaches the text similarity threshold. If the text similarity reaches the text similarity threshold, the candidate standardized entity name text whose text similarity reaches the text similarity threshold is obtained from the candidate standardized entity name text as the target standardized entity name text. Specifically, from the candidate standardized entity name texts, the candidate standardized entity name text whose text similarity reaches the text similarity threshold and has the highest similarity is obtained as the target standardized entity name text.

In addition, if the text similarity does not reach the text similarity threshold, it is determined that the target normalized entity name text does not exist in the candidate normalized entity name text.

In step S604, the entity name text to be matched is associated with the target standardized entity name text.

The specific implementation of the so-called association is generally as follows: establishing a corresponding relationship between the entity name text to be matched and the target standardized entity name text.

Sixth Embodiment

Corresponding to the application scenario of the text matching method provided by the embodiment of the present application and the text matching method provided by the first embodiment, the sixth embodiment of the present application further provides another text matching method. Since this embodiment of the apparatus is basically similar to the application scenario of the text matching method provided by the embodiment of the present application and the text matching method provided by the first embodiment, the description is relatively simple. For relevant details, please refer to the text matching provided by the embodiment of the present application. The application scenarios of the method and the partial description of the text matching method provided by the first embodiment are sufficient. The method embodiments described below are merely illustrative.

First, obtain the target entity category corresponding to the entity name text to be matched, which is used to describe the geographic location name.

In the sixth embodiment of the present application, the so-called entity name text is the text used to describe the geographical location name in the target text, and the so-called target text is generally a piece of document, a paragraph or a sentence, such as: collected when creating a map for description Documents of geographic location, documents used to describe the geographic location involved in the process of social governance and urban management, etc. It should be noted that, in the first embodiment of the present application, the target text and the entity are not specifically limited.

The so-called entity name text to be matched is generally a non-standardized entity name text, and can also be a standardized entity name text. The so-called standardized entity name text and non-standardized entity name text are respectively standard description text and non-standard description text for the same entity name. Specifically, we can take "People's Republic of China" as an example. The standardized entity name text of "People's Republic of China" is "People's Republic of China", and the non-standardized entity name text can be "China", "my country", and so on. Take "Beijing Olympic Park" as an example. The standardized entity name text of "Beijing Olympic Park" is "Beijing Olympic Park", and the non-standardized entity name text can be "Olympic Park", etc.

The so-called entity category is the category of the entity described by the entity name text, and the entity category is a pre-divided category according to a preset entity category division strategy. In the specific implementation process, the process of obtaining the target entity category is as follows: first, adopt a preset word segmentation strategy to segment the text of the entity name to be matched, and obtain the category keywords in the text of the entity name to be matched; then, according to the entity name text to be matched. The category keywords in , get the target entity category. The so-called category keywords are words in the entity name text that can identify entity categories. Specifically, take the entity as a government service material as an example. For example, when the text of the entity name to be matched is "a certain country", "a certain province", "a certain city" and "a certain mountain", etc., for "a certain country", For "a certain province", "a certain city" and "a certain mountain", "country", "province", "city" and "mountain" are the category keywords in the entity name text to be matched . In the sixth embodiment of the present application, the categories are pre-divided according to the preset entity category division strategy, that is, the entity categories are determined according to the category keywords in the pre-statistic entity name text. Therefore, "country", "province", "mountain" and "district" are also pre-divided according to the preset entity classification strategy.

Secondly, according to the target entity category, obtain the candidate standardized entity name text corresponding to the entity name text to be matched whose entity category is the same as the target entity category.

In the sixth embodiment of the present application, the so-called candidate standardized entity name text corresponding to the entity name text to be matched is a standardized entity obtained based on the keywords in the entity name text to be matched and associated with the keywords in the entity name text to be matched. name text. In the specific implementation process, for the entity name text to be matched, the recall strategy of bm25 is adopted, and the ES tool is used to quickly recall the associated standardized entity name text associated with the entity name to be matched in the preset standardized entity name text data.

Thirdly, according to the text similarity between the entity name text to be matched and the candidate standardized entity name text, the target standardized entity name text matching the entity name text to be matched is obtained from the candidate standardized entity name text.

In the specific implementation process, before obtaining the text similarity according to the word vector similarity and the character string similarity, it is necessary to judge whether the text similarity reaches the text similarity threshold. If the text similarity reaches the text similarity threshold, the candidate standardized entity name text whose text similarity reaches the text similarity threshold is obtained from the candidate standardized entity name text as the target standardized entity name text. Specifically, from the candidate standardized entity name texts, the candidate standardized entity name text whose text similarity reaches the text similarity threshold and has the highest similarity is obtained as the target standardized entity name text.

In addition, if the text similarity does not reach the text similarity threshold, it is determined that the target normalized entity name text does not exist in the candidate normalized entity name text.

Finally, associate the entity name text to be matched with the target standardized entity name text.

The specific implementation of the so-called association is generally as follows: establishing a corresponding relationship between the entity name text to be matched and the target standardized entity name text.

Although the present application is disclosed above with preferred embodiments, it is not intended to limit the present application. Any person skilled in the art can make possible changes and modifications without departing from the spirit and scope of the present invention. Therefore, this application The scope of protection shall be subject to the scope defined by the claims of this application.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

Memory may include non-persistent memory in computer readable media, random access memory (RAM) and/or non-volatile memory, such as read only memory (ROM) or flash memory (Flash RAM). Memory is an example of a computer-readable medium.

1. Computer readable media including persistent and non-permanent, removable and non-removable media can be implemented by any method or technology for information storage. Information may be computer readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other physical classes of random access memory (RAM), read-only memory Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Flash Memory or other memory technology, Compact Disc Read Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage , magnetic cartridges, magnetic disk storage, or other magnetic storage media or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include non-transitory computer-readable media (Transitory Media), such as modulated data signals and carrier waves.

2. Those skilled in the art should understand that the embodiments of the present application may be provided as methods, systems or computer program products. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

Claims (19)

1. A text matching method, comprising:

obtaining a target entity type corresponding to the entity name text to be matched;

according to the target entity category, obtaining a candidate standardized entity name text corresponding to the entity name text to be matched, wherein the entity category is the same as the target entity category;

and obtaining a target standardized entity name text matched with the entity name text to be matched from the candidate standardized entity name text according to the text similarity between the entity name text to be matched and the candidate standardized entity name text.

2. The text matching method according to claim 1, further comprising: providing the target standardized entity name text to a user device.

3. The text matching method according to claim 1 or 2, further comprising: and associating the entity name text to be matched with the target standardized entity name text.

4. The text matching method of claim 3, wherein the associating the entity name text to be matched with the target standardized entity name text comprises: and establishing a corresponding relation between the entity name text to be matched and the target standardized entity name text.

5. The text matching method according to claim 2, wherein the obtaining of the target entity category corresponding to the entity name text to be matched comprises: obtaining a text matching instruction sent by the user equipment, wherein the text matching instruction carries the name text of the entity to be matched;

the providing the location recommendation information to the user equipment includes: providing the target standardized entity name text to the user equipment for the text matching instruction.

6. The text matching method according to claim 1, further comprising: and displaying the target standardized entity name text.

7. The text matching method according to claim 1, wherein the obtaining of the target entity category corresponding to the entity name text to be matched comprises:

adopting a preset word segmentation strategy to segment the entity name text to be matched to obtain category keywords in the entity name text to be matched;

and obtaining the target entity category according to the category key words in the entity name text to be matched.

8. The text matching method according to claim 1, wherein the obtaining, according to the target entity category, a candidate standardized entity name text corresponding to the entity name text to be matched having an entity category that is the same as the target entity category comprises:

obtaining an associated standardized entity name text associated with the entity name to be matched according to the key words in the entity name text to be matched;

obtaining an entity category of the associated standardized entity name text;

and obtaining the candidate standardized entity name text from the associated standardized entity name text according to the target entity category and the entity category.

9. The text matching method according to claim 1, wherein the obtaining of the target standardized entity name text matched with the entity name text to be matched from the candidate standardized entity name text according to the text similarity between the entity name text to be matched and the candidate standardized entity name text comprises:

obtaining the weight of the key words in the entity name text to be matched and the weight of the key words in the candidate standardized entity name text;

obtaining a first word vector corresponding to a keyword in the entity name text to be matched and a second word vector corresponding to the keyword in the candidate standardized entity name text;

obtaining word vector similarity of the first word vector and the second word vector according to the weight of the keyword in the entity name text to be matched, the weight of the keyword in the candidate standardized entity name text, the first word vector and the second word vector;

and obtaining the text similarity according to the word vector similarity.

10. The text matching method according to claim 9, wherein the obtaining the text similarity according to the word vector similarity comprises:

obtaining a character string matched with the name text of the entity to be matched;

obtaining a character string corresponding to the candidate standardized entity name text;

according to the character string matched with the entity name text to be matched and the character string corresponding to the candidate standardized entity name text, obtaining the character string similarity of the character string matched with the entity name text to be matched and the character string corresponding to the candidate standardized entity name text;

and obtaining the text similarity according to the word vector similarity and the character string similarity.

11. The text matching method according to claim 10, wherein the obtaining the text similarity according to the word vector similarity and the character string similarity comprises: and weighting the word vector similarity and the character string similarity according to a preset first similarity weight corresponding to the word vector similarity and a preset second similarity weight corresponding to the word vector similarity to obtain the text similarity.

12. The text matching method according to claim 1, further comprising: judging whether the text similarity reaches a text similarity threshold value;

the obtaining a target standardized entity name text matched with the entity name text to be matched from the candidate standardized entity name text according to the text similarity between the entity name text to be matched and the candidate standardized entity name text comprises: and if the text similarity reaches the text similarity threshold, obtaining the candidate standardized entity name text with the text similarity reaching the text similarity threshold from the candidate standardized entity name text as a target standardized entity name text.

13. The text matching method according to claim 12, wherein the obtaining, from the candidate standardized entity name texts, the candidate standardized entity name texts of which the text similarity reaches the text similarity threshold as target standardized entity name texts comprises: and obtaining the candidate standardized entity name text with the text similarity reaching the text similarity threshold and the highest similarity from the candidate standardized entity name texts as a target standardized entity name text.

14. The text matching method according to claim 12, further comprising: and if the text similarity does not reach the text similarity threshold, determining that the target standardized entity name text does not exist in the candidate standardized entity name text.

15. A text matching apparatus, comprising:

the target entity type obtaining unit is used for obtaining a target entity type corresponding to the entity name text to be matched;

a candidate text obtaining unit, configured to obtain, according to the target entity category, a candidate standardized entity name text corresponding to the entity name text to be matched, where the entity category is the same as the target entity category;

and the target text matching unit is used for obtaining a target standardized entity name text matched with the entity name text to be matched from the candidate standardized entity name text according to the text similarity between the entity name text to be matched and the candidate standardized entity name text.

16. An electronic device, comprising:

a processor; and

a memory for storing a program of a text matching method, the apparatus performing the following steps after being powered on and running the program of the text matching method by the processor:

obtaining a target entity type corresponding to the entity name text to be matched;

according to the target entity category, obtaining a candidate standardized entity name text corresponding to the entity name text to be matched, wherein the entity category is the same as the target entity category;

and obtaining a target standardized entity name text matched with the entity name text to be matched from the candidate standardized entity name text according to the text similarity between the entity name text to be matched and the candidate standardized entity name text.

17. A storage medium storing a program of a text matching method, the program being executed by a processor to perform the steps of: obtaining a target entity type corresponding to the entity name text to be matched;

according to the target entity category, obtaining a candidate standardized entity name text corresponding to the entity name text to be matched, wherein the entity category is the same as the target entity category;

and obtaining a target standardized entity name text matched with the entity name text to be matched from the candidate standardized entity name text according to the text similarity between the entity name text to be matched and the candidate standardized entity name text.

18. A government affairs service text matching method, comprising:

obtaining a target entity category corresponding to the entity name text to be matched and used for describing the name of the government affair service material;

according to the target entity category, obtaining a candidate standardized entity name text corresponding to the entity name text to be matched, wherein the entity category is the same as the target entity category;

according to the text similarity between the entity name text to be matched and the candidate standardized entity name text, obtaining a target standardized entity name text matched with the entity name text to be matched from the candidate standardized entity name text;

and associating the entity name text to be matched with the target standardized entity name text.

19. An address text matching method, comprising:

obtaining a target entity category which is used for describing the geographical position name and corresponds to the entity name text to be matched;

according to the target entity category, obtaining a candidate standardized entity name text corresponding to the entity name text to be matched, wherein the entity category is the same as the target entity category;

according to the text similarity between the entity name text to be matched and the candidate standardized entity name text, obtaining a target standardized entity name text matched with the entity name text to be matched from the candidate standardized entity name text;

and associating the entity name text to be matched with the target standardized entity name text.

Images