CN115438151A - Method, device, equipment and medium for determining standard clauses - Google Patents

Abstract

The disclosure provides a method for determining standard terms, which can be applied to the technical field of artificial intelligence. The method comprises the following steps: performing word segmentation processing on the statement information to be matched to obtain M keywords, wherein the statement information comprises text data used for describing standard terms; determining N first standard terms matched with the M keywords based on the knowledge graph, wherein the first standard terms comprise institutional terms aiming at the target user; determining at least one second standard clause corresponding to each of the N first standard clauses according to the incidence relation between the first standard clauses and the second standard clauses to obtain P second standard clauses, wherein the second standard clauses comprise universal standard clauses; and displaying the N first standard terms and the P second standard terms matched with the statement information. The present disclosure also provides a standard clause determination device, apparatus, storage medium, and program product.

Description

Determination method, device, equipment and medium of standard terms

technical field

The present disclosure relates to the field of artificial intelligence, and specifically relates to a method, device, electronic equipment, media and program product for determining standard terms.

Background technique

At present, internal auditing of enterprises still relies on the manual operation of auditors. For example, in the case of obtaining non-standard clause texts, auditors can determine one or more enterprise-related clauses corresponding to the non-standard clause texts based on their own experience. Then, audit work is carried out according to the found relevant articles of the enterprise.

In related technologies, auditors who do not understand the relevant terms of the enterprise or have insufficient experience cannot quickly and accurately determine the corresponding enterprise-related terms based on the text of non-standard terms, resulting in high training costs for auditors and low audit efficiency. In addition, due to the relatively similar text content of relevant enterprise clauses, there are errors and low credibility in the enterprise-related clauses determined based on non-standard clause texts.

Contents of the invention

In view of the above problems, the present disclosure provides a method, device, device, medium and program product for determining standard clauses.

According to the first aspect of the present disclosure, a method for determining standard clauses is provided, including: performing word segmentation processing on sentence information to be matched to obtain M keywords, wherein M is greater than or equal to 1, and the sentence information includes the text data of the terms;

Based on the knowledge map, determine N first standard terms that match the M keywords, where the first standard terms include institutional terms for target users, where N is greater than or equal to 1;

According to the relationship between the first standard clause and the second standard clause, determine at least one second standard clause corresponding to each of the N first standard clauses, and obtain P second standard clauses, where P is greater than or equal to 1, and P is greater than or equal to N, and the second standard terms include common standard terms; and

Display N first standard clauses and P second standard clauses matching the statement information.

According to an embodiment of the present disclosure, wherein, based on the knowledge map, determining N first standard terms matching M keywords includes:

Process M keywords by using the knowledge graph to obtain Q first standard clauses matching the M keywords, Q is greater than or equal to 1, and Q is greater than or equal to N;

Perform deduplication processing on the Q first standard clauses to obtain L first standard clauses and keyword data, and the keyword data includes the number of keywords hit by each first standard clause in the L first standard clauses, where L Greater than or equal to N, and less than or equal to Q;

According to the importance level of the keyword and the keyword data, N first standard terms are selected from the L first standard terms.

According to an embodiment of the present disclosure, N first standard clauses are selected from L first standard clauses according to the importance level of keywords and keyword data, including:

According to the keyword data, the L first standard clauses are sorted according to the number of keywords to obtain the sequence of the first standard clauses;

According to the importance level of keywords, the order of the first standard clauses with the same number of keywords is updated to obtain an updated sequence of first standard clauses; and

Filter out N first standard terms from the updated first standard term sequence.

According to an embodiment of the present disclosure, the association relationship includes the similarity between the first standard clause and the second standard clause; according to the association relationship between the first standard clause and the second standard clause, determine the There is at least one second standard clause corresponding to each clause, and P second standard clauses are obtained, including:

determining the similarity between the i-th first standard clause among the N first standard clauses and a plurality of second standard clauses, wherein i is greater than or equal to 1, and i is less than or equal to N; and

The second standard clause whose similarity meets the preset threshold is used as the second standard clause corresponding to the i-th first standard clause, and P second standard clauses are obtained.

According to an embodiment of the present disclosure, wherein the similarity includes Pearson correlation coefficient and Euclidean distance; determining the similarity between the i-th first standard clause and multiple second standard clauses among the N first standard clauses includes:

determining the Pearson correlation coefficient and the Euclidean distance between the i-th first standard term and the plurality of second standard terms; and

The Pearson correlation coefficient and the Euclidean distance are weighted and summed to obtain the similarity between the i-th first standard item and multiple second standard items.

According to an embodiment of the present disclosure, displaying N first standard clauses and P second standard clauses matching sentence information includes:

Display N first standard clauses in the order of the updated first standard clause sequence; and

In response to the target user's operation on the jth first standard clause among the N first standard clauses, display the second standard clause corresponding to the jth first standard clause, where j is greater than or equal to 1, and j is less than or equal to N .

The second aspect of the present disclosure provides a device for determining standard clauses, including: a first determination module, configured to perform word segmentation processing on sentence information to be matched to obtain M keywords, wherein M is greater than or equal to 1, and the sentence information includes Text data used to describe standard terms;

The second determination module is used to determine N first standard terms matching M keywords based on the knowledge graph, where the first standard terms include system terms preset by the target user, wherein N is greater than or equal to 1;

The third determination module is used to determine at least one second standard clause corresponding to each of the N first standard clauses according to the association relationship between the first standard clause and the second standard clause, and obtain P second standard clauses, wherein , P is greater than or equal to 1, and P is greater than or equal to N, and the second standard terms include common standard terms; and

A display module, configured to display N first standard clauses and P second standard clauses that match the sentence information.

A third aspect of the present disclosure provides an electronic device, including: one or more processors; a memory for storing one or more programs, wherein, when the one or more programs are executed by the one or more When the processor executes, it causes one or more processors to execute the determination method of the above standard clause.

The fourth aspect of the present disclosure also provides a computer-readable storage medium, on which executable instructions are stored, and when the instructions are executed by a processor, the processor executes the determination method of the above standard clause.

The fifth aspect of the present disclosure also provides a computer program product, including a computer program, when the computer program is executed by a processor, the method for determining the above standard clauses is implemented.

Description of drawings

Through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, the above content and other objects, features and advantages of the present disclosure will be more clear, in the accompanying drawings:

FIG. 1 schematically shows an application scenario of a method for determining standard clauses according to an embodiment of the present disclosure;

FIG. 2 schematically shows a flow chart of a method for determining standard clauses according to an embodiment of the present disclosure;

Fig. 3 schematically shows a flowchart of a method for determining a first standard clause according to an embodiment of the present disclosure;

Fig. 4 schematically shows a flowchart of a method for determining a second standard clause according to an embodiment of the present disclosure;

Fig. 5 schematically shows a flowchart of a method for determining similarity between a first standard clause and a second standard clause according to an embodiment of the present disclosure;

FIG. 6 schematically shows a flowchart of a method for displaying a first standard clause and a second standard clause according to an embodiment of the present disclosure;

Fig. 7 schematically shows a schematic diagram of a display interface according to a specific embodiment of the present disclosure;

FIG. 8 schematically shows a structural block diagram of an apparatus for determining standard clauses according to an embodiment of the present disclosure; and

Fig. 9 schematically shows a block diagram of an electronic device suitable for a method for determining standard terms according to an embodiment of the present disclosure.

detailed description

Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. It should be understood, however, that these descriptions are exemplary only, and are not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. Also, in the following description, descriptions of well-known structures and techniques are omitted to avoid unnecessarily obscuring the concepts of the present disclosure.

The terminology used herein is for the purpose of describing particular embodiments only, and is not intended to be limiting of the present disclosure. The terms "comprising", "comprising", etc. used herein indicate the presence of stated features, steps, operations and/or components, but do not exclude the presence or addition of one or more other features, steps, operations or components.

All terms (including technical and scientific terms) used herein have the meaning commonly understood by one of ordinary skill in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted to have a meaning consistent with the context of this specification, and not be interpreted in an idealized or overly rigid manner.

Where expressions such as "at least one of A, B, and C, etc." are used, they should generally be interpreted as those skilled in the art would normally understand the expression (for example, "having A, B, and C A system of at least one of "shall include, but not be limited to, systems with A alone, B alone, C alone, A and B, A and C, B and C, and/or A, B, C, etc. ).

In the technical solution of this disclosure, the collection, storage, use, processing, transmission, provision, disclosure, and application of the user's personal information involved are all in compliance with relevant laws and regulations, necessary confidentiality measures have been taken, and they do not violate the Public order and good customs.

In the technical solution of the present disclosure, before acquiring or collecting the user's personal information, the user's authorization or consent is obtained.

Embodiments of the present disclosure provide a method for determining standard clauses, including: performing word segmentation processing on sentence information to be matched to obtain M keywords, wherein M is greater than or equal to 1, and the sentence information includes text data used to describe standard clauses ;Based on the knowledge map, determine N first standard clauses that match M keywords, the first standard clauses include institutional clauses for target users, where N is greater than or equal to 1; according to the first standard clause and the second standard clause The relationship among them, determine at least one second standard clause corresponding to each of the N first standard clauses, and obtain P second standard clauses, wherein, P is greater than or equal to 1, and P is greater than or equal to N, and the second standard clause includes general and displaying N first standard clauses and P second standard clauses matching the sentence information.

Fig. 1 schematically shows an application scenario of standard clause determination according to an embodiment of the present disclosure.

As shown in FIG. 1 , an application scenario 100 according to this embodiment may include terminal devices 101 , 102 , 103 , a network 104 and a server 105 . The network 104 is used as a medium for providing communication links between the terminal devices 101 , 102 , 103 and the server 105 . Network 104 may include various connection types, such as wires, wireless communication links, or fiber optic cables, among others.

Users can use terminal devices 101 , 102 , 103 to interact with server 105 via network 104 to receive or send messages and the like. The terminal devices 101, 102, 103 may be installed with application software for determining the standard terms, or the user may log in the terminal device 101, 102, 103 to the web interface for determining the standard terms.

The terminal devices 101, 102, 103 may be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers and the like.

The server 105 may be a server that provides various services, such as a background management server that provides support for websites browsed by users using the terminal devices 101 , 102 , 103 (just an example). The background management server can analyze and process received data such as user requests, and feed back processing results (such as webpages, information, or data obtained or generated according to user requests) to the terminal device.

It should be noted that, the method for determining the standard terms provided by the embodiment of the present disclosure can generally be executed by the server 105 . Correspondingly, the device for determining standard clauses provided by the embodiments of the present disclosure may generally be set in the server 105 . The method for determining standard clauses provided by the embodiments of the present disclosure may also be performed by a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101 , 102 , 103 and/or the server 105 . Correspondingly, the apparatus for determining standard clauses provided by the embodiments of the present disclosure may also be set in a server or a server cluster that is different from the server 105 and can communicate with the terminal devices 101 , 102 , 103 and/or the server 105 .

It should be understood that the numbers of terminal devices, networks and servers in Fig. 1 are only illustrative. According to the implementation needs, there can be any number of terminal devices, networks and servers.

Based on the scene described in FIG. 1 , the method for determining standard clauses in the disclosed embodiments will be described in detail below through FIGS. 2 to 7 .

Fig. 2 schematically shows a flowchart of a method for determining standard clauses according to an embodiment of the present disclosure.

As shown in FIG. 2, the method includes operations S210-S240.

In operation S210, word segmentation is performed on the sentence information to be matched to obtain M keywords.

According to an embodiment of the present disclosure, the sentence information to be matched includes text data for describing standard terms. Specifically, the statement information may be a piece of natural language input by the user, or text data converted according to various types of data input by the user. For example, the various types of data input by the user include: picture data, video data and audio data.

According to an embodiment of the present disclosure, the input sentence information is segmented into multiple Chinese words through part-of-speech analysis. After the required target part of speech is determined, M keywords of the target part of speech are screened out from the plurality of Chinese words obtained by word segmentation. For example, set the target part of speech as a noun, and select M keywords of the noun part of speech from multiple Chinese words.

For example, the sentence information is "want to know how to strengthen security management to ensure network availability and reliability". After part-of-speech analysis, the obtained Chinese words are "wonder", "how", "strengthen", "safety management", "guarantee", "network", "availability", "and", "reliability" . After setting the target part of speech as a noun, "security management", "network", "availability" and "reliability" were screened from multiple Chinese words.

According to an embodiment of the present disclosure, a second screening may be performed on the keywords filtered by the part of speech according to the frequency of occurrence of the keywords. Specifically, the frequency of occurrence of keywords may be determined according to a general word library or a user dictionary. After part-of-speech screening, the frequency of occurrence of the obtained M keywords is determined. If it is determined that there is a keyword whose frequency of occurrence is lower than the preset threshold among the M keywords, the keyword is updated according to the general vocabulary or the user dictionary.

After word segmentation processing is performed on sentence information, the disclosure screens the obtained word segmentation data based on the frequency of part of speech and keywords, which improves the accuracy of word segmentation and helps to improve the accuracy of subsequent matching of the first standard terms.

For example, still taking the sentence information "I want to know how to strengthen security management and ensure network availability and reliability" as an example, after getting "security management", "network", "availability" and "reliability", according to the general word base or A user dictionary that determines that "Security Management" occurs less than 5 times, while "Security" occurs more frequently than "Security Management". Therefore, the keywords "security management", "network", "availability" and "reliability" after part-of-speech screening are updated to "security", "network", "availability" and "reliability".

In operation S220, N first standard terms matching the M keywords are determined based on the knowledge graph.

According to an embodiment of the present disclosure, after M keywords are determined according to sentence information, the M keywords are input into a pre-built knowledge graph, and the first standard terms matching the M keywords are determined.

The knowledge map can be constructed according to the content of the current first standard clause. Specifically, word segmentation can be performed on the clause content of all the first standard clauses, and then the data after word segmentation can be screened by part of speech to obtain keywords under different parts of speech. Associate the clause number of the first standard clause with keywords under different parts of speech to form a knowledge graph.

For example, the node of the knowledge graph is the item number, and information such as part of speech, keyword, and keyword frequency can be used as the attribute information of the node.

According to an embodiment of the present disclosure, the first standard terms include policy terms for target users. The target user can be a certain enterprise, or a department, department, etc. that implement different business tasks within the enterprise. Specifically, the first standard clause may be a quality inspection clause set for multiple departments within the enterprise, for example, "read the operation log of the equipment every three months to check for loopholes" and so on.

In operation S230, at least one second standard clause corresponding to each of the N first standard clauses is determined according to the association relationship between the first standard clause and the second standard clause, and P second standard clauses are obtained.

According to an embodiment of the present disclosure, after determining the matching N first standard clauses according to the M keywords, it can also be determined according to the association relationship between the first standard clause and the second standard clause, which is related to the N first standard clauses For each first standard clause there is a corresponding second standard clause.

According to an embodiment of the present disclosure, the second standard clauses include common standard clauses. For example, for the safety production department, the common standard clauses among multiple enterprises are "referring to equipment operation logs", "checking for loopholes", "daily Maintenance" etc.

For the same type of business, one or more second standard clauses are commonly used among multiple enterprises. For the second standard terms of the same type of business, each enterprise can set specific first standard terms. For multiple enterprises, there are multiple association relationships between the first standard clause and the second standard clause.

According to an embodiment of the present disclosure, the target user may pre-establish an association relationship between the first standard terms and the second standard terms according to the first standard terms of the enterprise to which they belong.

In operation S240, N first standard terms and P second standard terms matching the sentence information are displayed.

According to an embodiment of the present disclosure, after determining the P second standard clauses related to the N first standard clauses according to the association relationship between the first standard clauses and the second standard clauses, the input sentence information can be matched with The N first standard clauses and P second standard clauses are displayed on the preset interactive interface.

Specifically, it is possible to display only the article numbers of the N first standard clauses and P second standard clauses, and add a text link corresponding to the article content after the article number; it is also possible to display the article number and the article content at the same time, so that users Check.

This disclosure extracts M keywords in the sentence information by segmenting the sentence information, and then determines N first standard clauses that match the M keywords based on the knowledge map, thereby realizing the quick search of the first standard clauses without It takes a lot of labor and time to search and match the first standard terms, which improves the evaluation credibility of the audit process on the basis of reducing labor costs.

In addition, after the first standard clause is determined, the present disclosure also recommends the second standard clause related to the first standard clause according to the association relationship between the first standard clause and the second standard clause, which further realizes the correlation with sentence information. The recommendation of multi-type standard clauses expands the source of standard clauses matching sentence information and improves the evaluation credibility. In addition, by displaying N first standard clauses and P second standard clauses matching sentence information, the present disclosure realizes the intuitive, clear and comprehensive display of standard clauses related to sentence information, improves user experience, and effectively Helps to improve the efficiency of the evaluation of the follow-up audit process.

According to an embodiment of the present disclosure, the information to be matched input by the user may be various types of information, such as text data, picture data, video data, and the like. For image data, before word segmentation processing is performed on the sentence information to be matched, it also includes: using an optical character recognition (Optical Character Recognition, OCR) method to convert the image data into sentence information in text form.

For video data, you can convert video data to video frame data. Then use the optical characters to process the video data under each frame, convert the video data into text data, and obtain the sentence information after data type conversion.

For audio data, Automatic Speech Recognition (ASR) can be used to perform feature extraction, pattern matching, and text conversion on the input audio data to obtain sentence information after data type conversion.

Fig. 3 schematically shows a flowchart of a method for determining a first standard clause according to an embodiment of the present disclosure.

As shown in FIG. 3 , the method of this embodiment includes operation S321 to operation S323, which may be used as a specific embodiment of operation S220.

In operation S321, the knowledge graph is used to process the M keywords to obtain Q first standard terms matching the M keywords.

According to an embodiment of the present disclosure, each node in the knowledge graph may be an item number of the first standard item, or may be a unique identifier in other forms.

After the M keywords are obtained, the M keywords are sequentially input into the knowledge map. By searching the input keywords, the knowledge map outputs multiple first standard item numbers matching the keywords, and item contents corresponding to the multiple first standard item numbers.

According to an embodiment of the present disclosure, the knowledge graph includes multiple sub-graphs corresponding to multiple parts of speech. When using the knowledge graph to process M keywords, first determine the subgraph corresponding to the keywords according to the part of speech of the M keywords. Then, the keywords are input into the subgraph corresponding to the part of speech, and the Q first standard clause numbers corresponding to the M keywords and the clause contents corresponding to the Q first standard clause numbers are obtained.

Alternatively, the knowledge graph can retrieve multiple keywords in parallel through knowledge graph subgraphs corresponding to multiple parts of speech to obtain Q first standard terms.

According to an embodiment of the present disclosure, the knowledge map may also only output item numbers of N first standard items corresponding to M keywords, and specific item content may be obtained from the database according to the item numbers of the first standard items.

In operation S322, the Q first standard clauses are deduplicated to obtain L first standard clauses and keyword data, and the keyword data includes the number of keywords hit by each first standard clause in the L first standard clauses .

According to the embodiments of the present disclosure, since one keyword may correspond to multiple first standard terms, two or more keywords may repeatedly match the same first standard term. Therefore, after the Q first standard terms are determined according to the knowledge graph, the Q first standard terms are deduplicated to obtain L first standard terms and keyword data. Wherein, the keyword data includes the number of keywords hit by each first standard clause in the L first standard clauses.

Specifically, multiple first standard clauses with the same clause number can be selected from Q first standard clauses according to the clause number of the first standard clause, and then randomly selected from multiple first standard clauses with the same clause number to obtain For a first standard clause, other first standard clauses with the same clause number are filtered out to obtain the final L first standard clauses.

When a first standard clause is randomly selected from multiple first standard clauses with the same clause number and other first standard clauses with the same clause number are screened out, record the keywords corresponding to the first standard clause with the same clause number , and the number of keywords matched under the article number to obtain the keyword data under the article number. For the first standard clauses with different clause numbers, the number of recorded keywords may be 1.

For example, after word segmentation processing is performed on the sentence information, the obtained keywords are A, B, and C, respectively. For keyword A, the retrieved clause numbers of the first standard clause are 1.1.1 and 1.1.2; for keyword B, the retrieved clause numbers of the first standard clause are 1.1.1 and 2.1.2; for the key For word C, the retrieved clause numbers of the first standard clauses are 3.1 and 4.1, and a total of 6 first standard clauses are obtained. Since there are two first standard clauses with the same clause number, such as 1.1.1, after deduplication processing, five first standard clauses are obtained.

For the first standard clause with the clause number 1.1.1, the matching keywords are A and B, and the keyword data is 2; for the first standard clause with the clause number 1.1.2, the matching keyword is A, and the keyword data is 1; for the first standard clause with clause number 2.1.2, the matching keyword is B, and the keyword data is 1; for the first standard clause with clause numbers 3.1 and 4.1, the matching keyword is both C, and the keyword The data are all 1.

In operation S323, N first standard terms are selected from the L first standard terms according to the importance level of the keyword and the keyword data.

According to an embodiment of the present disclosure, after the L first standard terms are obtained through screening, for common keywords, the keyword will appear in multiple first standard terms. Correspondingly, multiple first standard clauses that are not highly related to sentence information are matched, affecting accuracy. Moreover, the number of matched first standard terms is too large, which wastes computing resources.

According to the embodiments of the present disclosure, the obtained L first standard terms are screened in combination with the importance level of keywords and keyword data, which can avoid low matching accuracy caused by commonly used keywords.

According to an embodiment of the present disclosure, the method for selecting N first standard clauses from the L first standard clauses includes: sorting the L first standard clauses according to the number of keywords to obtain a sequence of first standard clauses. Then, according to the importance level of the keywords, the sequence of the first standard clauses with the same number of keywords is updated to obtain an updated sequence of the first standard clauses. Filter out N first standard terms from the updated first standard term sequence.

Specifically, the first standard item sequence can be obtained by sorting according to the number of keywords from high to low; it can also be sorted according to the number of keywords from low to high. For the first standard clauses with the same clause keyword data, they can be sorted randomly, or they can be sorted according to the clause numbers of the first standard clauses.

After the first standard clause sequence is determined according to the number of keywords, the first standard clauses with the same number of keywords are sorted according to the importance level of keywords to obtain an updated first standard clause sequence. Specifically, for the sequence of the first standard clauses sorted from high to low in the number of keywords, multiple first standard clauses with the same number of keywords are sorted from high to low according to the importance of the keywords, and an updated first standard clause is obtained sequence. Similarly, for the first standard item sequence sorted from low to high in the number of keywords, the importance of the keywords is also sorted from low to high.

According to an embodiment of the present disclosure, the importance level of keywords is predetermined according to the item content of the first standard item. For example, when the keywords are "security", "network", "availability" and "reliability", the importance level of "security" and "network" is higher than that of "availability" and "reliability".

Fig. 4 schematically shows a flowchart of a method for determining a second standard clause according to an embodiment of the present disclosure.

As shown in FIG. 4 , the method in this embodiment includes operation S431 to operation S432 , which may be used as a specific embodiment of operation S230 .

In operation S431, a degree of similarity between an i-th first standard clause and a plurality of second standard clauses among the N first standard clauses is determined.

In operation S432, the second standard item whose similarity meets the preset threshold is used as the second standard item corresponding to the i-th first standard item, and P second standard items are obtained.

According to an embodiment of the present disclosure, after determining the N first standard clauses according to the M keywords, it is also possible to determine the N first standard clauses corresponding to P second standard terms. Each of the N first standard clauses corresponds to at least one second standard clause. The association relationship includes the degree of similarity between the first standard clause and the second standard clause.

According to an embodiment of the present disclosure, before determining the P second standard clauses corresponding to the N first standard clauses according to the association relationship between the first standard clauses and the second standard clauses, the N first standard clauses are calculated How similar each first standard clause is to the second standard clause.

After calculating the similarity between each first standard item and multiple second standard items, the second standard item whose similarity meets the preset threshold is taken as the second standard item corresponding to the i-th first standard item. Specifically, there may be multiple second standard items satisfying the preset threshold, P is greater than or equal to 1, and P is greater than or equal to N.

According to an embodiment of the present disclosure, the similarity includes Pearson correlation coefficient and Euclidean distance. The process of calculating the similarity between each first standard clause and multiple second standard clauses includes: determining the Pearson correlation coefficient and the Euclidean distance between the i-th first standard clause and multiple second standard clauses. The Pearson correlation coefficient and the Euclidean distance are weighted and summed to obtain the similarity between the i-th first standard item and multiple second standard items.

Specifically, the similarity between the first standard item and the second standard item can be calculated by establishing a feature vector similarity model.

According to an embodiment of the present disclosure, the weights of the Pearson correlation coefficient and the Euclidean distance can be adjusted according to actual needs. Specifically, when emphasizing the degree of linear correlation between the first standard clause and the second standard clause, the weight of the Pearson correlation coefficient is higher than the weight of the Euclidean distance; when emphasizing the first standard clause and the second standard clause In the case of text differences in , the Euclidean distance is given a higher weight than the Pearson correlation coefficient.

For example, feature extraction is performed on the first standard item X, and the feature vector of the first standard item X is obtained as X[1, 1, 1, 1, 1, 1, 1, 1]. Wherein, X[1, 1, 1, 1, 1, 1, 1, 1] indicates that keywords 1, 2, 3, 4, 5, 6, 7, and 8 all appear in the first standard clause. The eigenvector of the second standard item Y is Y[1, 1, 0, 0, 0, 1, 1, 1], indicating that keywords 1, 2, 6, 7, and 8 appear in the second standard item.

For an N-dimensional feature vector, the Pearson correlation coefficient between the first standard term X and the second standard term Y satisfies:

表示第一标准条款N维特征向量的平均值，

表示第二标准条款N维特征向量的平均值，X_i表示第一标准条款的第i维特征，Y_i表示第二标准条款的第i维特征，P(X,Y)表示第一标准条款和第二标准条款之间的皮尔逊相关系数。in,

Denotes the average of the N-dimensional eigenvectors of the first standard terms,

Indicates the average value of the N-dimensional feature vector of the second standard item, X _i indicates the i-th dimension feature of the first standard item, Y _i indicates the i-th dimension feature of the second standard item, and P(X,Y) indicates the first standard item and the Pearson correlation coefficient between the second standard terms.

For an N-dimensional feature vector, the Euclidean distance between the first criterion term X and the second criterion term Y satisfies:

Among them, D(X, Y) represents the Euclidean distance between the first standard clause and the second standard clause, and Xi and _Yi represent the _i -th dimension features of the first standard clause and the second standard clause, respectively.

The similarity between the first standard clause and the second standard clause satisfies:

similarity＝W ₁ *P(X,Y)+W ₂ *D(X,Y) (3)

Among them, W ₁ and W ₂ represent the weight of Pearson correlation coefficient and Euclidean distance respectively.

Fig. 5 schematically shows a flowchart of a method for determining similarity between a first standard clause and a second standard clause according to an embodiment of the present disclosure.

As shown in FIG. 5 , the first standard item 510 and the second standard item 520 whose similarity is to be calculated are obtained, and then the vector feature model 540 is used to perform text segmentation and feature extraction at 530 . Word segmentation processing and feature extraction are performed on the first standard clause 510 and the second standard clause 520 to obtain a feature vector 550 of the first standard clause and a feature vector 560 of the second standard clause. After obtaining the feature vector 550 of the first standard item and the feature vector 560 of the second standard item, calculate the Pearson correlation coefficient and the Euclidean distance between the two feature vectors to obtain the similarity 570 .

Fig. 6 schematically shows a flowchart of a method for displaying a first standard clause and a second standard clause according to an embodiment of the present disclosure.

As shown in FIG. 6 , the method of this embodiment includes operation S610 to operation S620.

In operation S610, N first standard terms are displayed in order of the updated first standard term sequence.

According to an embodiment of the present disclosure, after determining N first standard clauses and P second standard clauses, by presenting N first standard clauses in the order of the updated first standard clause sequence, the first standard clause can be realized visualization.

Specifically, when displaying the N first standard clauses, the clause numbers of the N first standard clauses may be displayed, or the clause contents of the clause numbers of the N first standard clauses may be displayed at the same time.

In operation S620, in response to the target user's operation on the j-th first standard item among the N first standard items, a second standard item corresponding to the j-th first standard item is displayed.

According to an embodiment of the present disclosure, after displaying the N first standard terms that match the sentence information, in response to the target user's operation on the j-th first standard term among the N first standard terms, the j-th One or more second standard clauses to which the first standard clause corresponds.

Specifically, after the first standard clause is determined, because there are too many first standard clauses, the second standard clause corresponding to the first standard clause may be hidden. After the target user clicks on the j-th first standard item, the second standard item corresponding to the j-th first standard item is displayed.

In the present disclosure, by displaying the N first standard clauses in the order of the updated first standard clause sequence, the matching first standard clauses can be intuitively displayed to the target user, and displayed to the target user in the order of relevance, which has Help improve user experience. In addition, in response to the operation of the target user, displaying the second standard terms corresponding to the first standard terms can simplify the display interface and improve the aesthetics of the interface; at the same time, it can also show the association between the second standard terms and the first standard terms relationship, which helps to improve user experience and subsequent evaluation efficiency.

According to an embodiment of the present disclosure, it is also possible to display P second standard terms while displaying N first standard terms; it is also possible to display P in response to a preset operation of the target user after displaying N first standard terms a second standard clause.

Fig. 7 schematically shows a schematic diagram of a presentation interface according to a specific embodiment of the present disclosure.

As shown in FIG. 7 , the display interface 700 includes operation buttons 702 - 706 , 709 , and sub-display windows 701 , 707 , 708 , 710 - 714 . Wherein, the sub-display window 701 is used to display the "LOGO" logo of the target user. The operation button 702 is used to obtain the first standard terms and store the first standard terms in response to the user's click operation, and similarly, the operation button 703 is used to obtain the second standard terms and store the second standard terms in response to the user's click operation .

The operation button 704 is used to calculate the similarity between the first standard clause and the second standard clause in response to the user's click operation, and complete the benchmarking between the first standard clause and the second standard clause. The operation button 705 is used to individually implement word segmentation processing of the first standard clause or the second standard clause in response to the user's click operation. Specifically, it can be realized through the word segmentation model or python's jieba package. The operation button 706 is used to respond to the user's click operation to implement standard item recommendation after inputting information. Specifically, in response to the target user's first preset operation, a first standard item matching the sentence information may be recommended; in response to the target user's second preset operation, a second standard item matching the sentence information may be recommended; It is also possible to recommend first standard terms and second standard terms matching the sentence information in response to a third preset operation of the target user.

The sub-display window 707 is used to display the application name. Specifically, the application name may be the name of the evaluation assistance system of the time-limited above-mentioned method. The sub-display window 708 is used to display text information or keywords input by the user. The operation button 709 is used to process the input information in the sub-display window 708 in response to the user's click operation.

The sub-display window 710 is used to display the obtained item content and/or item number of the first standard item, as well as the storage location of the first standard item. The sub-display window 711 is used to display the obtained item content and/or item number of the second standard item, as well as the storage location of the second standard item. The sub-display window 712 is used to display the word segmentation results of the word segmentation module 705 . The sub-display window 713 is used to display the benchmarking results of the standard item benchmarking module 704 . Specifically, information such as a specific similarity may be displayed. The sub-display window 714 is used to display the recommendation results of the standard item recommendation module 706 . Specifically, the determined N first standard clauses and P second standard clauses may be displayed.

Fig. 8 schematically shows a structural block diagram of an apparatus for determining standard clauses according to an embodiment of the present disclosure.

As shown in FIG. 8 , the apparatus 800 for determining standard clauses in this embodiment includes a first determining module 810 , a second determining module 820 , a third determining module 830 and a display module 840 .

The first determination module 810 is configured to perform word segmentation processing on the sentence information to be matched to obtain M keywords, wherein M is greater than or equal to 1, and the sentence information includes text data for describing standard terms. In an embodiment, the first determining module 810 may be configured to perform operation S210 described above, which will not be repeated here.

The second determination module 820 is configured to determine N first standard terms matching the M keywords based on the knowledge graph, where the first standard terms include institutional terms for target users, where N is greater than or equal to 1. In an embodiment, the second determination module 820 may be configured to perform the operation S220 described above, which will not be repeated here.

The third determination module 830 is configured to determine at least one second standard clause corresponding to each of the N first standard clauses according to the association relationship between the first standard clause and the second standard clause, and obtain P second standard clauses, Wherein, P is greater than or equal to 1, and P is greater than or equal to N, and the second standard terms include common standard terms. In an embodiment, the third determining module 830 may be configured to perform operation S230 described above, which will not be repeated here.

A display module 840, configured to display N first standard clauses and P second standard clauses that match the sentence information. In an embodiment, the presentation module 840 may be configured to perform the operation S240 described above, which will not be repeated here.

According to an embodiment of the present disclosure, the second determination module 820 includes a first determination unit, a second determination unit and a third determination unit.

The first determining unit is used to process M keywords by using the knowledge graph to obtain Q first standard terms matching the M keywords, Q is greater than or equal to 1, and Q is greater than or equal to N. In an embodiment, the first determining unit may be configured to perform operation S321 described above, which will not be repeated here.

The second determination unit is used to deduplicate the Q first standard clauses to obtain L first standard clauses and keyword data, and the keyword data includes the hit key of each first standard clause in the L first standard clauses Number of words, where L is greater than or equal to N and less than or equal to Q. In an embodiment, the second determining unit may be configured to perform operation S322 described above, which will not be repeated here.

The third determining unit is configured to select N first standard terms from the L first standard terms according to the importance level of the key word and the key word data. In an embodiment, the third determining unit may be configured to perform operation S323 described above, which will not be repeated here.

According to an embodiment of the present disclosure, the third determining module 830 includes a fourth determining unit and a fifth determining unit.

The fourth determining unit is configured to determine the similarity between the i-th first standard clause and multiple second standard clauses among the N first standard clauses, wherein i is greater than or equal to 1, and i is less than or equal to N. In an embodiment, the fourth determining unit may be configured to perform operation S431 described above, which will not be described again here.

The fifth determining unit is configured to use the second standard clause whose similarity meets the preset threshold as the second standard clause corresponding to the i-th first standard clause, to obtain P second standard clauses. In an embodiment, the fifth determining unit may be configured to perform operation S432 described above, which will not be repeated here.

According to an embodiment of the present disclosure, the display module 840 includes a first display unit and a second display unit.

The first display unit is used to display N first standard clauses in the order of the updated first standard clause sequence. In an embodiment, the first presentation unit may be configured to perform operation S641 described above, which will not be repeated here.

The second display unit is used to display the second standard clause corresponding to the jth first standard clause in response to the operation of the target user on the jth first standard clause among the N first standard clauses, wherein j is greater than or equal to 1 , and j is less than or equal to N. In an embodiment, the second presentation unit may be configured to perform operation S642 described above, which will not be repeated here.

Fig. 9 schematically shows a block diagram of an electronic device suitable for a method for determining standard terms according to an embodiment of the present disclosure.

As shown in FIG. 9, an electronic device 900 according to an embodiment of the present disclosure includes a processor 901, which can be loaded into a random access memory (RAM) 903 according to a program stored in a read-only memory (ROM) 902 or from a storage section 908. Various appropriate actions and processing are performed by the program. The processor 901 may include, for example, a general-purpose microprocessor (eg, a CPU), an instruction set processor and/or related chipsets, and/or a special-purpose microprocessor (eg, an application-specific integrated circuit (ASIC)), and the like. Processor 901 may also include on-board memory for caching purposes. The processor 901 may include a single processing unit or multiple processing units for executing different actions of the method flow according to the embodiments of the present disclosure.

In the RAM 903, various programs and data necessary for the operation of the electronic device 900 are stored. The processor 901 , ROM 902 , and RAM 903 are connected to each other via a bus 904 . The processor 901 executes various operations according to the method flow of the embodiment of the present disclosure by executing programs in the ROM 902 and/or RAM 903 . It should be noted that the program may also be stored in one or more memories other than the ROM 902 and the RAM 903 . The processor 901 may also perform various operations according to the method flow of the embodiments of the present disclosure by executing programs stored in the one or more memories.

According to an embodiment of the present disclosure, the electronic device 900 may further include an input/output (I/O) interface 905 which is also connected to the bus 904 . The electronic device 900 may also include one or more of the following components connected to the I/O interface 905: an input portion 906 including a keyboard, a mouse, etc.; including a cathode ray tube (CRT), a liquid crystal display (LCD), etc. An output section 907 of a speaker or the like; a storage section 908 including a hard disk or the like; and a communication section 909 including a network interface card such as a LAN card, a modem, or the like. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the I/O interface 905 as needed. A removable medium 911 such as a magnetic disk, optical disk, magneto-optical disk, semiconductor memory, etc. is mounted on the drive 910 as necessary so that a computer program read therefrom is installed into the storage section 908 as necessary.

The present disclosure also provides a computer-readable storage medium. The computer-readable storage medium may be included in the device/apparatus/system described in the above embodiments; it may also exist independently without being assembled into the device/system device/system. The above-mentioned computer-readable storage medium carries one or more programs, and when the above-mentioned one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, such as may include but not limited to: portable computer disk, hard disk, random access memory (RAM), read-only memory (ROM) , erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include one or more memories other than the above-described ROM 902 and/or RAM 903 and/or ROM 902 and RAM 903 .

Embodiments of the present disclosure also include a computer program product, which includes a computer program including program codes for executing the methods shown in the flowcharts. When the computer program product runs in the computer system, the program code is used to make the computer system realize the method for determining the standard terms provided by the embodiments of the present disclosure.

When the computer program is executed by the processor 901, the above-mentioned functions defined in the system/apparatus of the embodiment of the present disclosure are executed. According to the embodiments of the present disclosure, the above-described systems, devices, modules, units, etc. may be implemented by computer program modules.

In one embodiment, the computer program may rely on tangible storage media such as optical storage devices and magnetic storage devices. In another embodiment, the computer program can also be transmitted and distributed in the form of a signal on a network medium, downloaded and installed through the communication part 909, and/or installed from the removable medium 911. The program code contained in the computer program can be transmitted by any appropriate network medium, including but not limited to: wireless, wired, etc., or any appropriate combination of the above.

In such an embodiment, the computer program may be downloaded and installed from a network via communication portion 909 and/or installed from removable media 911 . When the computer program is executed by the processor 901, the above-mentioned functions defined in the system of the embodiment of the present disclosure are executed. According to the embodiments of the present disclosure, the above-described systems, devices, devices, modules, units, etc. may be implemented by computer program modules.

According to the embodiments of the present disclosure, the program codes for executing the computer programs provided by the embodiments of the present disclosure can be written in any combination of one or more programming languages, specifically, high-level procedural and/or object-oriented programming language, and/or assembly/machine language to implement these computing programs. Programming languages include, but are not limited to, programming languages such as Java, C++, python, "C" or similar programming languages. The program code can execute entirely on the user computing device, partly on the user device, partly on the remote computing device, or entirely on the remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider). business to connect via the Internet).

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, program segment, or portion of code that includes one or more logical functions for implementing specified executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. It should also be noted that each block in the block diagrams or flowchart illustrations, and combinations of blocks in the block diagrams or flowchart illustrations, can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a A combination of dedicated hardware and computer instructions.

Those skilled in the art can understand that various combinations and/or combinations of the features described in the various embodiments and/or claims of the present disclosure can be made, even if such combinations or combinations are not explicitly recorded in the present disclosure. In particular, without departing from the spirit and teaching of the present disclosure, the various embodiments of the present disclosure and/or the features described in the claims can be combined and/or combined in various ways. All such combinations and/or combinations fall within the scope of the present disclosure.

The specific embodiments described above have further described the purpose, technical solutions and beneficial effects of the present disclosure in detail. It should be understood that the above descriptions are only specific embodiments of the present disclosure, and are not intended to limit the present disclosure. Within the spirit and principles of the present disclosure, any modifications, equivalent replacements, improvements, etc., shall be included in the protection scope of the present disclosure.

Claims (10)

1. A method of determining a standard term, comprising:

performing word segmentation processing on sentence information to be matched to obtain M keywords, wherein M is greater than or equal to 1, and the sentence information comprises text data used for describing standard terms;

determining N first standard terms matched with the M keywords based on a knowledge graph, wherein the first standard terms comprise institutional terms aiming at a target user, and N is greater than or equal to 1;

determining at least one second standard clause corresponding to each of the N first standard clauses according to an incidence relation between the first standard clauses and the second standard clauses to obtain P second standard clauses, wherein P is greater than or equal to 1, and P is greater than or equal to N, and the second standard clauses comprise universal standard clauses; and

and displaying the N first standard terms and the P second standard terms matched with the statement information.

2. The method of claim 1, wherein said determining N first standard terms matching said M keywords based on a knowledge-graph comprises:

processing the M keywords by using a knowledge graph to obtain Q first standard terms matched with the M keywords, wherein Q is more than or equal to 1, and Q is more than or equal to N;

performing deduplication processing on the Q first standard terms to obtain L first standard terms and keyword data, wherein the keyword data comprises the number of keywords hit by each first standard term in the L first standard terms, and L is greater than or equal to N and less than or equal to Q;

and screening the N first standard terms from the L first standard terms according to the importance level of the keyword and the keyword data.

3. The method of claim 2, wherein said screening said N first standard terms from said L first standard terms according to the importance level of the keyword and said keyword data comprises:

sequencing the L first standard terms according to the number of keywords according to the keyword data to obtain a first standard term sequence;

updating the sequence of the first standard clauses with the same number of the keywords according to the importance levels of the keywords to obtain an updated first standard clause sequence; and

and screening N first standard clauses from the updated first standard clause sequence.

4. The method of claim 1, wherein the associative relationship includes a similarity between a first standard term and a second standard term; the determining, according to the association between the first standard clause and the second standard clause, at least one second standard clause corresponding to each of the N first standard clauses to obtain P second standard clauses includes:

determining similarity between the ith first standard clause and a plurality of second standard clauses in the N first standard clauses, wherein i is greater than or equal to 1, and i is less than or equal to N; and

and taking the second standard clause with the similarity meeting the preset threshold as the second standard clause corresponding to the ith first standard clause to obtain P second standard clauses.

5. The method of claim 4, wherein the similarity includes a Pearson correlation coefficient and a Euclidean distance; determining similarity between an ith one of the N first standard terms and a plurality of second standard terms, including:

determining a Pearson correlation coefficient and a Euclidean distance between the ith first standard term and a plurality of second standard terms; and

and weighting and summing the Pearson correlation coefficient and the Euclidean distance to obtain the similarity between the ith first standard term and a plurality of second standard terms.

6. The method of claim 3, wherein said presenting said N first standard terms and said P second standard terms matching said sentence information comprises:

displaying the N first standard clauses according to the sequence of the updated first standard clause sequence; and

and responding to the operation of the target user on the jth first standard clause in the N first standard clauses, and displaying a second standard clause corresponding to the jth first standard clause, wherein j is greater than or equal to 1, and j is less than or equal to N.

7. An apparatus for determining a standard term, comprising:

the system comprises a first determining module, a second determining module and a matching module, wherein the first determining module is used for performing word segmentation processing on sentence information to be matched to obtain M keywords, M is greater than or equal to 1, and the sentence information comprises text data used for describing standard terms;

a second determining module, configured to determine, based on a knowledge graph, N first standard terms that match the M keywords, where the first standard terms include institutional terms preset by a target user, and N is greater than or equal to 1;

a third determining module, configured to determine, according to an association relationship between a first standard term and a second standard term, at least one second standard term corresponding to each of the N first standard terms, to obtain P second standard terms, where P is greater than or equal to 1 and P is greater than or equal to N, and the second standard terms include a common standard term; and

and the display module is used for displaying the N first standard terms and the P second standard terms which are matched with the statement information.

8. An electronic device, comprising:

one or more processors;

a storage device for storing one or more programs,

wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method recited in any of claims 1-6.

9. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to perform the method according to any one of claims 1 to 6.

10. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 6.

Images