CN112446792B - Benefit demonstration generation method, device, electronic equipment and storage medium - Google Patents
Benefit demonstration generation method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112446792B CN112446792B CN202011388317.9A CN202011388317A CN112446792B CN 112446792 B CN112446792 B CN 112446792B CN 202011388317 A CN202011388317 A CN 202011388317A CN 112446792 B CN112446792 B CN 112446792B
- Authority
- CN
- China
- Prior art keywords
- insurance
- information
- benefit
- class information
- digital
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000008901 benefit Effects 0.000 title claims abstract description 142
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000000605 extraction Methods 0.000 claims abstract description 27
- 230000015654 memory Effects 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000012552 review Methods 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000012790 confirmation Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 2
- 238000004891 communication Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000001747 exhibiting effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/288—Entity relationship models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/338—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The specification provides a benefit demonstration generation method, comprising the following steps: acquiring insurance clauses expressed in a natural language form; extracting insurance entity class information and digital class information from the insurance clauses based on an entity extraction model; establishing an association relation between the digital information and the insurance entity information; writing the digital class information and the insurance entity class information into a database according to the association relation; receiving a benefit demonstration generation request; wherein the benefit presentation generation request includes user information and a benefit presentation item requested thereby; invoking corresponding data from the database according to the requested benefit presentation; and generating a benefit presentation from the invoked data. The specification also provides a benefit presentation generating device, an electronic device and a storage medium.
Description
Technical Field
One or more embodiments of the present disclosure relate to the field of natural language parsing, and in particular, to a benefit presentation generating method, apparatus, electronic device, and storage medium.
Background
In the insurance industry, in order to present the most "transparent" product content to customers, agents typically choose to present various insurance products to customers by way of benefit presentation prior to sale. The benefit presentation itself is the product of a refined assumption, exhibiting insurance responsibilities, e.g., premium over the year of the policy, and information on insurance benefits, e.g., amount of the policy, cash value of the policy, value of the account, etc. The benefit presentation may comprehensively present detailed information of benefits that an insurance product may provide to a customer.
At present, when an insurance company pushes out a new product, the insurance clauses of the text version are read manually, corresponding information in the clauses is extracted manually, and the information is input into a product system database through the front end of the product system. And the product system database provides a data query interface for the outside for the benefit demonstration display front end to call. However, the method is completed by purely manual configuration, takes manpower and time to do repeated work, and has low intelligent degree.
Disclosure of Invention
In view of this, one or more embodiments of the present disclosure provide a benefit presentation generating method, which can automatically extract service data of an insurance product from an insurance clause expressed in a natural language form, and automatically generate a benefit presentation table based on the extracted service data, thereby replacing manual operation of configuring service data related to insurance, saving manpower and time costs, and accelerating new product uploading process.
The benefit demonstration generation method of the embodiment of the specification comprises the following steps: acquiring insurance clauses expressed in a natural language form; extracting insurance entity class information and digital class information from the insurance clauses based on an entity extraction model; establishing an association relation between the digital information and the insurance entity information; writing the digital class information and the insurance entity class information into a database according to the association relation; receiving a benefit demonstration generation request; wherein the benefit presentation generation request includes user information and a requested benefit presentation item; invoking corresponding data from the database according to the requested benefit presentation; and generating a benefit presentation from the invoked data.
The entity extraction model is a named entity recognition model obtained by training according to a word library of marked insurance industry proper nouns; the insurance entity class information comprises proper nouns of insurance industry; the digital class information includes: numbers and percentages.
Wherein, the establishing the association relationship between the digital class information and the insurance entity class information includes: for the extracted digital class information, determining at least one insurance entity class information in the context of the insurance clause in which the digital class information is located; and finding out the insurance entity class information which meets the corresponding digital range rule and is nearest to the digital class information, and establishing the association relation between the insurance entity class information and the digital class information.
Wherein writing the digital class information and the insurance entity class information into a database comprises: establishing an insurance business information table in the database; and determining the field name of the data field of the insurance business information table according to the association relation and writing the corresponding digital class information as the value of the field into the insurance business information table.
Wherein said invoking corresponding data from said database in accordance with said requested benefit presentation comprises: for each benefit demonstration item, determining a calculation formula corresponding to the benefit demonstration item and a data field to be extracted, and extracting corresponding data from the database according to the data field to be extracted; and generating a benefit presentation from the invoked data includes: generating a demonstration result of the benefit demonstration item according to a calculation formula corresponding to the benefit demonstration item and the extracted data and a preset or user-selected mode; or alternatively
Said invoking corresponding data from said database in accordance with said requested benefit presentation comprises: for each benefit demonstration item, determining a data field required to be extracted from the benefit demonstration item, and extracting corresponding data from the database according to the data field required to be extracted; and generating a benefit presentation from the invoked data includes: and generating a demonstration result of the benefit demonstration item according to the extracted data and according to a preset or user-selected mode.
The above method may further comprise: displaying the digital information and the insurance entity information according to the association relation so as to perform manual review; and executing the step of establishing the association relation between the digital class information and the insurance entity class information after the manual review confirmation, and adding the digital class information and the insurance entity class information into the training set of the entity extraction model.
The above method may further comprise: and writing a digital conversion tool by a regular matching method, and converting the numbers in the digital information into Arabic numbers.
One or more embodiments of the present specification also provide a benefit presentation generating apparatus, including:
The input module is used for acquiring insurance clauses expressed in a natural language form;
the information extraction module is used for extracting insurance entity type information and digital type information from the insurance clauses based on an entity extraction model;
The association module is used for establishing an association relation between the digital information and the insurance entity information;
The storage module is used for writing the digital class information and the insurance entity class information into a database according to the association relation;
the benefit demonstration request module is used for receiving a benefit demonstration generation request; wherein the benefit presentation generation request includes user information and a benefit presentation item requested thereby; and
And the benefit demonstration generating module is used for calling corresponding data from the database according to the requested benefit demonstration item and generating benefit demonstration according to the called data.
One or more embodiments of the present specification also provide an electronic device, which may include: the system comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes the benefit demonstration generating method when executing the program.
One or more embodiments of the present specification also provide a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions for causing the computer to perform the benefit presentation generating method described above.
According to the benefit demonstration generation method and device and the electronic equipment, the benefit demonstration can be automatically generated according to the insurance clauses through analysis of the insurance clauses, so that labor and time cost are greatly saved, and new product online flow can be quickened.
Drawings
For a clearer description of one or more embodiments of the present description or of the solutions of the prior art, the drawings that are necessary for the description of the embodiments or of the prior art will be briefly described, it being apparent that the drawings in the description below are only one or more embodiments of the present description, from which other drawings can be obtained, without inventive effort, for a person skilled in the art.
FIG. 1 illustrates a flow of implementation of a benefit presentation generation method according to some embodiments of the present description;
FIG. 2 shows the internal structure of the BERT-BiLSTM-CRF model described in some embodiments of the present description;
FIG. 3 is a schematic diagram showing the internal structure of a benefit presentation generating apparatus according to other embodiments of the present disclosure; and
Fig. 4 is a schematic diagram illustrating an internal structure of an electronic device according to some embodiments of the present disclosure.
Detailed Description
For the purposes of promoting an understanding of the principles and advantages of the disclosure, reference will now be made to the embodiments illustrated in the drawings and specific language will be used to describe the same.
It is noted that unless otherwise defined, technical or scientific terms used in one or more embodiments of the present disclosure should be taken in a general sense as understood by one of ordinary skill in the art to which the present disclosure pertains. The use of the terms "first," "second," and the like in one or more embodiments of the present description does not denote any order, quantity, or importance, but rather the terms "first," "second," and the like are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", etc. are used merely to indicate relative positional relationships, which may also be changed when the absolute position of the object to be described is changed.
As described above, the benefit demonstration generation mode adopted by the insurance industry is completed through manual configuration, which not only consumes manpower and time to do repetitive work, but also has low intelligent degree. Therefore, the embodiment of the specification provides a benefit demonstration generating method, which can automatically extract service data of insurance products from one insurance clause expressed in a natural language form, and automatically generate a benefit demonstration table based on the extracted service data, thereby replacing purely manual configuration operation, saving manpower and time cost and improving accuracy.
FIG. 1 shows an implementation flow of the benefit presentation generating method according to the embodiments of the present specification. The method may be implemented by a benefit presentation generating device. As shown in fig. 1, the method may include:
At step 102, insurance clauses expressed in natural language are obtained.
In embodiments of the present description, the benefit presentation generating device may include a user interface. The user interface may be a graphical user interface. When it is desired to generate a benefit presentation for an insurance, a user may first enter the insurance clause of the insurance expressed in natural language through the user interface described above. For example, the user may enter or copy+paste the insurance clauses in text format in a text box provided by the user interface.
At step 104, insurance entity class information and digital class information are extracted from the insurance clauses based on the entity extraction model.
In the embodiment of the present specification, the insurance entity class information includes proper nouns of the insurance industry. Such as payment period, payment method, the age of the insured life, etc. The digital class information may include: numbers and percentages, etc.
In addition, in the embodiment of the present disclosure, the entity extraction model may be specifically a named entity recognition model that is trained according to a word library of labeled insurance industry proper nouns. The named entity recognition model can extract insurance entity class information and digital class information from texts expressed by natural language.
Named entity Recognition (NER, named Entity Recognizion), also known as "proper noun Recognition," can be used to identify entities in text that have a particular meaning. These entities may include mainly personal names, place names, institution names, proper nouns, time and numbers, etc. Simply stated, the boundaries and categories of the various entities in the natural text are identified.
In the embodiment of the present disclosure, the entity extraction model is mainly used for extracting entities related to the insurance industry, that is, proper nouns of the insurance industry, in addition to the above information. Such as the above-described payment period, payment method, the age of the insured life, etc. In order to realize the extraction of proper nouns in the insurance industry, the proper nouns in the insurance industry can be marked in advance; and then training the named entity recognition model by using proper nouns of the marked insurance industry, so that an entity extraction model capable of recognizing insurance entity type information and digital type information can be obtained. The specific training process is to compare the predicted insurance entity information with a pre-marked mark to obtain the prediction error of the entity extraction model, and adjust the coefficient of the entity extraction model according to the prediction error in a counter-propagation mode until the entity extraction model converges.
It should be noted that, in addition to the insurance entity information and the digital information, the named entity recognition model may also recognize other entities in the text, for example: name of person, place, organization, date and time, etc.
In particular, in some embodiments of the present description, the named entity recognition model may be a BERT-BiLSTM-CRF model. Where BERT is known as Pre-training of Deep Bidirectional Transformers for Language Understanding, that is BERT is a deep bi-directional Pre-trained language understanding model using Transformers as the feature extractor. In the embodiments of the present specification, the above BERT model is mainly used for word embedding. BiLSTM represents a two-way Long Short-Term Memory (LSTM) model. In the embodiments of the present specification, the BiLSTM model is mainly used for feature extraction. CRF represents a conditional random field (Conditional Random Field), which is a serialization labeling algorithm. In the embodiments of the present specification, the CRF model described above mainly serves as an output layer.
FIG. 2 shows the internal structure of the BERT-BiLSTM-CRF model described in the examples of this specification. As can be seen from fig. 2, in the embodiment of the present specification, the above BERT-BiLSTM-CRF model may include: BERT module, biLSTM module, and CRF module. The BERT module is used for obtaining corresponding word vectors through BERT preprocessing according to the input word sequences X 1、X2、X3 and X 4 … …. The BiLSTM module comprises a forward LSTM layer and a backward LSTM layer which are used for extracting features, and features C 1、C2、C3 and C 4 … … corresponding to each word vector are obtained from the word vectors output by the BERT module. The CRF module is used as an output layer for outputting labels corresponding to the features, so that entity identification is completed. As shown in FIG. 2, the word sequences X 3 and X 4 are entities representing place names through the BERT-BiLSTM-CRF model. The above BERT-BiLSTM-CRF model can identify the boundaries and categories of the respective entities from the text expressed in natural language that it inputs.
Specifically, in embodiments of the present description, the BERT-BiLSTM-CRF model described above may identify proper nouns of the insurance industry, as well as numbers and percentages, among other things, from its entered insurance clauses. For example, proper nouns of the insurance industry described above may include: payment period, payment mode, the age of the insured life, etc. In addition, the BERT-BiLSTM-CRF model described above may also be used to identify person names, place names, institution names, and dates and times, among others.
Those skilled in the art will appreciate that the BERT model already contains a large amount of general knowledge, and that fine tuning with a small amount of labeling data using a pre-trained BERT model is a fast method for obtaining a named entity recognition model with good effect.
In other embodiments of the present disclosure, the named entity recognition model may also be implemented by other machine learning models in the field of natural language processing, for example, convolutional Neural Network (CNN) +crf model or lstm+crf model, and so on.
In step 106, an association between the digital class information and the insurance entity class information is established.
In the embodiment of the present specification, the above-mentioned digital class information is generally associated with proper nouns of the insurance industry, and thus, for one digital class information, the insurance entity class information closest to the digital class information in the context of the insurance clause may be regarded as the associated insurance entity class information.
In addition, proper nouns for the insurance industry typically have certain numerical range rules for their corresponding numbers. This numerical range rule may be summarized based on historical terms, e.g., for a proper noun of "age," its corresponding numerical range rule may be empirically set to 0-150. In this case, the process of establishing the association relationship of the digital class entity and the insurance entity class information may include: for the extracted digital class information, determining at least one insurance entity class information in the context of the insurance clause; and finding out the insurance entity class information which meets the rule of the corresponding digital range and is nearest to the digital class information from the digital class information, and establishing the association relation between the insurance entity class information and the digital class information.
For example, a certain number "3" is extracted from the insurance clause, and the insurance entity class information of "age" is extracted in advance, and the number "3" satisfies the number range rule 0-150 corresponding to "age", so that the association relationship of the number "3" and "age" can be established. For another example, if the numerical range rule of a certain insurance entity class information a is 1-100 and the number extracted by the model is "200", the number "200" cannot have an association relationship with the insurance entity class information a, and other insurance entity class information matching with the number "200" needs to be found.
In addition, in other embodiments of the present disclosure, in the entered insurance clause, some of the digits are expressed in a text form such as "two, three, four, six, seven, eight, ninety", and in this case, the numeric class information in the text form may be further converted into digits before the association between the numeric class information and the insurance entity class information is established.
Specifically, in the embodiment of the present specification, a digital conversion tool may be written by a method of regular matching, and all numbers in the text are extracted and converted into an arabic number form. The regular matching refers to the steps of matching 'one, two, three, four, five, six, seven, eight, nine, ten' and the like, judging the position of the matching, and converting the matching into an Arabic number form. For example, regular matching is fifty-nine, translating to 59.
In this way, in step 106, the association relationship between the converted number and the insurance entity class information is established.
In step 108, the digital class information and the insurance entity class information are written into a database according to the association relationship.
In the embodiment of the present disclosure, an insurance service information table may be established in a database, and according to the association relationship, a field name of a data field of the insurance service information table is generated according to insurance entity class information, and the corresponding digital class information is written into the insurance service information table as a value of the field. The above process of creating the insurance business information table and writing the corresponding digital class information can be implemented by corresponding statements of the structured query language (SQL, structured Query Language).
In addition, in other embodiments of the present disclosure, before writing the digital class information and the insurance entity class information into the database, the method may further include: and displaying the digital information and the insurance entity information on a user interface according to the association relation, and writing the digital information and the insurance entity information into a database after the user confirms the correctness of the digital information and the insurance entity information. And for the digital information and the insurance entity information confirmed by the user, the insurance entity information can be added into the training set of the entity extraction model and further used for training the entity extraction model, so that the accuracy of the entity extraction model is further improved.
Specifically, the benefit demonstration generating device can display the extracted digital class information and insurance entity class information through the user interface according to the association relation so as to perform manual review. That is, the user may modify the displayed digital class information and insurance entity class information. The benefit demonstration generating device can display the confirmation key to the user through the user interface, so that the information after the user is checked manually is confirmed.
Still further, multiple items of content may be included in the generated benefit presentation, such as including both premium and premium amounts, as well as the cash value of the policy, and so forth. In the embodiment of the present specification, each item of content included in the benefit presentation is referred to as a benefit presentation item, for example, premium, and the like. The content of some benefit demonstration items is calculated by a specific formula, for example, the premium paid by a user every year is displayed, and is usually calculated according to the information of the age, the length of the application time, the amount of the premium, and the like of the user. Under these circumstances, it is necessary to agree in advance with a calculation formula corresponding to each benefit presentation item, and to enter the above database in advance so as to be invoked in the course of generating a benefit presentation later.
In step 110, a benefit presentation generation request is received, wherein the benefit presentation generation request includes user information and a benefit presentation item requested thereby.
In an embodiment of the present specification, the benefit presentation generating device may receive the benefit presentation generating request through a user interface. The user may enter user information and select the name or identification of the requested benefit presentation item through the user interface. In the embodiment of the present specification, the user information may include information such as a name, a gender, and an age of the user. The user information may also include information such as occupation of the user. The benefit demonstration item may specifically refer to specific content to be demonstrated in the benefit demonstration, for example: premium, amount, cash value of policy, value of account, etc.
At step 112, corresponding data is recalled from the database in accordance with the requested benefit presentation item and a benefit presentation is generated in accordance with the recalled data.
In the above step 112, for each benefit presentation item, a calculation formula corresponding to the benefit presentation item and a data field to be extracted may be first determined according to the requested benefit presentation item. And then, extracting corresponding data from the database according to the data fields needing to be extracted. And finally, generating a demonstration result of the benefit demonstration item according to a calculation formula corresponding to the benefit demonstration item and the extracted data and a preset or user-selected mode. If no formula calculation is required for a benefit presentation, the data fields that the benefit presentation needs to extract may be first determined from the requested benefit presentation. And then, extracting corresponding data from the database according to the data fields needing to be extracted. And finally, generating a demonstration result of the benefit demonstration item according to the data and according to a preset mode or a mode selected by a user.
For example, if a benefit presentation item is the age range of the insured life, it may be determined that the benefit presentation item is the lowest age and the highest age of the insured life, and at this time, the stored lowest age and highest age may be read from the database, and the benefit presentation item may be generated from the read data.
Specifically, in the embodiment of the present disclosure, after data is stored in the database, the database is packaged into a Webservice, and after receiving the benefit presentation request, the Webservice of the database is requested according to the content of the benefit presentation request, so as to extract the corresponding data.
According to the benefit demonstration generation method, the benefit demonstration can be automatically generated according to insurance clauses, so that labor and time cost are greatly saved, and new product online flow can be quickened.
Based on the benefit presentation generating method described above, embodiments of the present specification provide a benefit presentation generating apparatus. Fig. 3 shows the internal structure of the device. As shown in fig. 3, the apparatus includes:
and an input module 302, configured to obtain insurance clauses expressed in natural language.
In embodiments of the present description, the benefit presentation generating device may include a user interface. When it is desired to generate a benefit presentation for an insurance, a user may enter insurance terms for the insurance expressed in natural language through the user interface.
The information extraction module 304 is configured to extract insurance entity class information and digital class information from the insurance clauses based on the entity extraction model.
In the embodiment of the present disclosure, the entity extraction model may be specifically a named entity recognition model that may extract insurance entity class information and digital class information from a text expressed in natural language.
Specifically, the named entity recognition model may be a BERT-BiLSTM-CRF model, a CNN+CRF model, or a LSTM+CRF model, or the like.
And the association module 306 is configured to establish an association relationship between the digital class information and the insurance entity class information.
In the embodiment of the present disclosure, the above digital class information is generally associated with proper nouns of the insurance industry, so for one digital class information, the insurance entity class information closest to the digital class information may be used as the associated insurance entity class information. In addition, for the proper nouns of the insurance industry, the numbers corresponding to the proper nouns generally have a certain number range rule, and the association module 306 may further determine the insurance entity class information associated with the extracted number class information according to the number range rule of the numbers corresponding to the proper nouns of the insurance industry.
The storage module 308 is configured to write the digital class information and the insurance entity class information into the database according to the association relationship.
In the embodiment of the present disclosure, the storage module 308 may establish an insurance service information table in the database, and according to the association relationship, use the insurance entity class information as a field name of the insurance service information table, and write the corresponding digital class information as a value of the field into the insurance service information table.
The benefit presentation request module 310 is configured to receive a benefit presentation generation request, where the benefit presentation generation request includes user information and a benefit presentation item requested by the user information.
In an embodiment of the present specification, the benefit presentation generating device may receive the benefit presentation generating request through a user interface. The user may enter user information and select the name of the requested data field through the user interface described above. In the embodiment of the present specification, the user information may include information such as a name and an age of the user.
And a benefit presentation generating module 312, configured to call corresponding data from the database according to the requested benefit presentation item, and generate a benefit presentation according to the called data.
In other embodiments of the present disclosure, the benefit presentation generating device may further include: the conversion module is configured to convert the digital class information extracted by the information extraction module 304 into a number, and send the number to the association module 306.
In addition, in other embodiments of the present specification, the benefit presentation generating apparatus may further include: the manual review module is configured to display the digital class information and the insurance entity class information according to the association relationship output by the association module 306, and invoke the storage module 308 after the user confirms the correctness of the digital class information and the insurance entity class information, and write the digital class information and the insurance entity class information into the database.
Specifically, the manual review module may display the extracted digital class information and insurance entity class information through the user interface according to the association relationship, so as to perform manual review. That is, the user may modify the displayed digital class information and insurance entity class information. The benefit demonstration generating device can display the confirmation key to the user through the user interface, so that the information after the user is checked manually is confirmed.
According to the benefit demonstration generating device, the benefit demonstration generating method can automatically generate benefit demonstration according to insurance clauses, so that new product online flow is quickened, and labor and time cost are greatly saved.
The benefit presentation generating method described in the embodiments of the present specification will be described in detail by way of a specific example.
First, the following insurance clauses are entered in an insurance clause input box of the user interface: "insurance period is divided into five years, six years and ten years, and the applicant can select one of them as the insurance period of the present contract. "
And extracting an insurance entity class information 'insurance period' and three digital class information 'five years, six years and ten years' from the insurance clauses through a BERT-BiLSTM-CRF model, converting the digital class information into Arabic numerals, and extracting a unit 'year' of the Arabic numerals.
And establishing the association relation of the insurance entity class information 'insurance period' and the three digital class information '3, 6 and 10'.
And then, storing the insurance entity class information 'insurance period' and the digital class information into a database according to the association relation.
Specifically, the database may store a data table as shown in table 1 below, that is, three fields of the database table.
TABLE 1
The database encapsulates Webserviec the data table to provide services to the outside. When the calculation formula of a benefit presentation item is used for the fields, the data of the corresponding fields can be read through Webserviec service of the database, and benefit presentation is generated according to the read data.
It should be noted that the methods of one or more embodiments of the present description may be performed by a single device, such as a computer or server. The method of the embodiment can also be applied to a distributed scene, and is completed by mutually matching a plurality of devices. In the case of such a distributed scenario, one of the devices may perform only one or more steps of the methods of one or more embodiments of the present description, which interact with each other to accomplish the methods described above.
The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
For convenience of description, the above devices are described as being functionally divided into various modules, respectively. Of course, the functions of each module may be implemented in one or more pieces of software and/or hardware when implementing one or more embodiments of the present description.
The device of the foregoing embodiment is configured to implement the corresponding method in the foregoing embodiment, and has the beneficial effects of the corresponding method embodiment, which is not described herein.
Fig. 4 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present disclosure, where the device may include: processor 410, memory 420, input/output interface 430, communication interface 440, and bus 450. Wherein processor 410, memory 420, input/output interface 430 and communication interface 440 are communicatively coupled to each other within the device via bus 450.
The processor 410 may be implemented in a general-purpose CPU (Central Processing Unit ), microprocessor, application SPECIFIC INTEGRATED Circuit (ASIC), or one or more integrated circuits, etc. for executing a program to implement the benefit presentation generating method provided in the embodiments of the present disclosure.
The Memory 420 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory ), static storage, dynamic storage, etc. Memory 420 may store an operating system and other application programs, and when the benefit presentation generating method provided by the embodiments of the present description is implemented in software or firmware, the associated program code is stored in memory 420 and invoked for execution by processor 410.
The input/output interface 430 is used to connect with an input/output module to realize information input and output. The input/output module may be configured as a component in a device (not shown) or may be external to the device to provide corresponding functionality. Wherein the input devices may include a keyboard, mouse, touch screen, microphone, various types of sensors, etc., and the output devices may include a display, speaker, vibrator, indicator lights, etc.
The communication interface 440 is used to connect communication modules (not shown) to enable communication interactions of the device with other devices. The communication module may implement communication through a wired manner (such as USB, network cable, etc.), or may implement communication through a wireless manner (such as mobile network, WIFI, bluetooth, etc.).
Bus 450 includes a path to transfer information between components of the device (e.g., processor 410, memory 420, input/output interface 430, and communication interface 440).
It should be noted that although the above device only shows the processor 410, the memory 420, the input/output interface 430, the communication interface 440, and the bus 450, in the implementation, the device may further include other components necessary to achieve normal operation. Furthermore, it will be understood by those skilled in the art that the above-described apparatus may include only the components necessary to implement the embodiments of the present description, and not all the components shown in the drawings.
The computer readable media of the present embodiments, including both permanent and non-permanent, removable and non-removable media, may be used to implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device.
Those of ordinary skill in the art will appreciate that: the discussion of any of the embodiments above is merely exemplary and is not intended to suggest that the scope of the disclosure, including the claims, is limited to these examples; combinations of features of the above embodiments or in different embodiments are also possible within the spirit of the present disclosure, steps may be implemented in any order, and there are many other variations of the different aspects of one or more embodiments described above which are not provided in detail for the sake of brevity.
Additionally, well-known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown within the provided figures, in order to simplify the illustration and discussion, and so as not to obscure one or more embodiments of the present description. Furthermore, the apparatus may be shown in block diagram form in order to avoid obscuring the one or more embodiments of the present description, and also in view of the fact that specifics with respect to implementation of such block diagram apparatus are highly dependent upon the platform within which the one or more embodiments of the present description are to be implemented (i.e., such specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the disclosure, it should be apparent to one skilled in the art that one or more embodiments of the disclosure can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative in nature and not as restrictive.
While the present disclosure has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of those embodiments will be apparent to those skilled in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.
The present disclosure is intended to embrace all such alternatives, modifications and variances which fall within the broad scope of the appended claims. Any omissions, modifications, equivalents, improvements, and the like, which are within the spirit and principles of the one or more embodiments of the disclosure, are therefore intended to be included within the scope of the disclosure.
Claims (9)
1. A benefit presentation generation method comprising:
acquiring insurance clauses expressed in a natural language form, wherein the insurance clauses expressed in the natural language form are insurance clauses input or copied or pasted in a text box provided by a user;
extracting insurance entity class information and digital class information from the insurance clauses based on an entity extraction model;
Establishing an association relationship between the digital class information and the insurance entity class information, including: for the extracted digital class information, determining at least one insurance entity class information in the context of the insurance clause in which the digital class information is located; finding out insurance entity class information which meets the rule of the corresponding digital range and is nearest to the digital class information from the digital class information, and establishing an association relation between the insurance entity class information and the digital class information;
Writing the digital class information and the insurance entity class information into a database according to the association relation;
receiving a benefit demonstration generation request; wherein the benefit presentation generation request includes user information and a requested benefit presentation item;
Invoking corresponding data from the database according to the requested benefit presentation; and
And generating benefit demonstration according to the invoked data.
2. The method of claim 1, wherein the entity extraction model is a named entity recognition model trained from a word library of annotated insurance industry proper nouns;
the insurance entity class information comprises proper nouns of insurance industry; and
The digital class information includes: numbers and percentages.
3. The method of claim 1, wherein the writing the digital class information and insurance entity class information into a database comprises:
Establishing an insurance business information table in the database;
And determining the field name of the data field of the insurance business information table according to the association relation and writing the corresponding digital class information as the value of the field into the insurance business information table.
4. The method of claim 1, wherein the invoking the corresponding data from the database in accordance with the requested benefit presentation comprises: for each benefit demonstration item, determining a calculation formula corresponding to the benefit demonstration item and a data field to be extracted, and extracting corresponding data from the database according to the data field to be extracted; and generating a benefit presentation from the invoked data includes: generating a demonstration result of the benefit demonstration item according to a calculation formula corresponding to the benefit demonstration item and the extracted data and a preset or user-selected mode; or alternatively
Said invoking corresponding data from said database in accordance with said requested benefit presentation comprises: for each benefit demonstration item, determining a data field required to be extracted from the benefit demonstration item, and extracting corresponding data from the database according to the data field required to be extracted; and generating a benefit presentation from the invoked data includes: and generating a demonstration result of the benefit demonstration item according to the extracted data and according to a preset or user-selected mode.
5. The method of claim 1, wherein the method further comprises:
displaying the digital information and the insurance entity information according to the association relation so as to perform manual review; and
And after the manual review confirmation, the step of establishing the association relation between the digital information and the insurance entity information is executed, and the digital information and the insurance entity information are added into the training set of the entity extraction model.
6. The method of claim 1, wherein the method further comprises:
and writing a digital conversion tool by a regular matching method, and converting the numbers in the digital information into Arabic numbers.
7. A benefit presentation generating device comprising:
The input module is used for acquiring insurance clauses expressed in a natural language form;
the information extraction module is used for extracting insurance entity type information and digital type information from the insurance clauses based on an entity extraction model;
The association module is used for establishing association relation between the digital information and the insurance entity information, and determining at least one insurance entity information in the context of the insurance clause of the extracted digital information; finding out insurance entity class information which meets the rule of the corresponding digital range and is nearest to the digital class information from the digital class information, and establishing an association relation between the insurance entity class information and the digital class information;
The storage module is used for writing the digital class information and the insurance entity class information into a database according to the association relation;
the benefit demonstration request module is used for receiving a benefit demonstration generation request; wherein the benefit presentation generation request includes user information and a benefit presentation item requested thereby; and
And the benefit demonstration generating module is used for calling corresponding data from the database according to the requested benefit demonstration item and generating benefit demonstration according to the called data.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the benefit presentation generating method of any of claims 1 to 6 when the program is executed.
9. A non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the benefit presentation generating method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011388317.9A CN112446792B (en) | 2020-12-01 | 2020-12-01 | Benefit demonstration generation method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011388317.9A CN112446792B (en) | 2020-12-01 | 2020-12-01 | Benefit demonstration generation method, device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112446792A CN112446792A (en) | 2021-03-05 |
| CN112446792B true CN112446792B (en) | 2024-06-25 |
Family
ID=74740503
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011388317.9A Active CN112446792B (en) | 2020-12-01 | 2020-12-01 | Benefit demonstration generation method, device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112446792B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110060169A (en) * | 2019-04-26 | 2019-07-26 | 成都众人安科技有限责任公司 | Insurance interest information fast finishing method and system |
| CN111858942A (en) * | 2020-07-29 | 2020-10-30 | 阳光保险集团股份有限公司 | Text extraction method and device, storage medium and electronic equipment |
Family Cites Families (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100257109A1 (en) * | 2009-04-01 | 2010-10-07 | Compliance Systems, Inc. | System and Method for Associating Documents in a Transaction with Transaction Data |
| US20130332450A1 (en) * | 2012-06-11 | 2013-12-12 | International Business Machines Corporation | System and Method for Automatically Detecting and Interactively Displaying Information About Entities, Activities, and Events from Multiple-Modality Natural Language Sources |
| US9026551B2 (en) * | 2013-06-25 | 2015-05-05 | Hartford Fire Insurance Company | System and method for evaluating text to support multiple insurance applications |
| US20160283876A1 (en) * | 2015-03-24 | 2016-09-29 | Tata Consultancy Services Limited | System and method for providing automomous contextual information life cycle management |
| US10127289B2 (en) * | 2015-08-19 | 2018-11-13 | Palantir Technologies Inc. | Systems and methods for automatic clustering and canonical designation of related data in various data structures |
| US20170124161A1 (en) * | 2015-11-02 | 2017-05-04 | Ebay Inc. | Presentation of digital data |
| US10776434B1 (en) * | 2016-11-16 | 2020-09-15 | First American Financial Corporation | System and method for document data extraction, data indexing, data searching and data filtering |
| US10402163B2 (en) * | 2017-02-14 | 2019-09-03 | Accenture Global Solutions Limited | Intelligent data extraction |
| CN106933802B (en) * | 2017-02-24 | 2020-02-21 | 黑龙江特士信息技术有限公司 | Multi-data-source-oriented social security entity identification method and device |
| CN110019858A (en) * | 2017-12-22 | 2019-07-16 | 深圳Tcl新技术有限公司 | A kind of method, storage medium and the presentation terminal of automation demonstration |
| CN108108493B (en) * | 2018-01-17 | 2020-04-28 | 中国平安人寿保险股份有限公司 | Algorithm processing method based on MIT benefit demonstration, server and storage medium |
| US10922359B2 (en) * | 2018-10-31 | 2021-02-16 | Verizon Media Inc. | Computerized system and method for extracting entity information from text communications and displaying content based therefrom |
| US11681710B2 (en) * | 2018-12-23 | 2023-06-20 | Microsoft Technology Licensing, Llc | Entity extraction rules harvesting and performance |
| CN109961370A (en) * | 2019-01-29 | 2019-07-02 | 宜信博诚保险销售服务(北京)股份有限公司 | A kind of the interests methods of exhibiting and device of insurance products |
| CN110175318B (en) * | 2019-04-16 | 2023-08-11 | 中国平安财产保险股份有限公司 | Insurance claim accessory generation method and apparatus |
| CN110222045B (en) * | 2019-04-23 | 2024-05-28 | 平安科技（深圳）有限公司 | Data report acquisition method and device, computer equipment and storage medium |
| CN111190882B (en) * | 2019-12-03 | 2023-07-11 | 泰康保险集团股份有限公司 | Target template creation method and device, electronic equipment and storage medium |
| CN111401065A (en) * | 2020-03-10 | 2020-07-10 | 中国平安人寿保险股份有限公司 | Entity identification method, device, equipment and storage medium |
| CN111444718A (en) * | 2020-03-12 | 2020-07-24 | 泰康保险集团股份有限公司 | Insurance product demand document processing method and device and electronic equipment |
| CN111489262A (en) * | 2020-06-15 | 2020-08-04 | 太平金融科技服务（上海）有限公司 | Policy information detection method and device, computer equipment and storage medium |
| CN111833198A (en) * | 2020-07-20 | 2020-10-27 | 民生科技有限责任公司 | Method for intelligently processing insurance clauses |
| CN118171910A (en) * | 2020-08-13 | 2024-06-11 | 支付宝(杭州)信息技术有限公司 | Business risk identification method and device and electronic equipment |
-
2020
- 2020-12-01 CN CN202011388317.9A patent/CN112446792B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110060169A (en) * | 2019-04-26 | 2019-07-26 | 成都众人安科技有限责任公司 | Insurance interest information fast finishing method and system |
| CN111858942A (en) * | 2020-07-29 | 2020-10-30 | 阳光保险集团股份有限公司 | Text extraction method and device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112446792A (en) | 2021-03-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106250385B (en) | System and method for automated information abstraction processing of documents | |
| CN112633419B (en) | Small sample learning method and device, electronic equipment and storage medium | |
| CN108959246A (en) | Answer selection method, device and electronic equipment based on improved attention mechanism | |
| US11580463B2 (en) | Systems and methods for report generation | |
| CN112328761B (en) | Method and device for setting intention label, computer equipment and storage medium | |
| CN111414561B (en) | Method and device for presenting information | |
| CN113449187A (en) | Product recommendation method, device and equipment based on double portraits and storage medium | |
| WO2021248492A1 (en) | Semantic representation of text in document | |
| US20200012650A1 (en) | Method and apparatus for determining response for user input data, and medium | |
| CN111079944B (en) | Transfer learning model interpretation realization method and device, electronic equipment and storage medium | |
| CN110033382B (en) | Insurance service processing method, device and equipment | |
| CN111950279A (en) | Entity relationship processing method, device, equipment and computer readable storage medium | |
| CN111191445A (en) | Advertisement text classification method and device | |
| CN111078842A (en) | Method, device, server and storage medium for determining query result | |
| CN110837545A (en) | Interactive data analysis method, device, medium and electronic equipment | |
| CN112560504A (en) | Method, electronic equipment and computer readable medium for extracting information in form document | |
| CN113190702A (en) | Method and apparatus for generating information | |
| CN114444465A (en) | Information extraction method, device, equipment and storage medium | |
| CN112446792B (en) | Benefit demonstration generation method, device, electronic equipment and storage medium | |
| CN112463931A (en) | Intelligent analysis method for insurance product clauses and related equipment | |
| CN112487773A (en) | Report generation method, device, equipment and storage medium | |
| CN115168607A (en) | Entity relationship extraction method and related equipment | |
| CN116702712B (en) | Word task book conversion method and device, electronic equipment and medium | |
| CN115906820A (en) | Text data aggregation analysis method and device and electronic equipment | |
| CN117131426B (en) | Brand identification method and device based on pre-training and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |