Labor guarantee loss assessment method, device and equipment and storage medium

Abstract

The invention relates to the technical field of data processing, and discloses a labor guarantee loss assessment method, device and equipment and a storage medium, and the method comprises the steps: obtaining a special text and a document image of labor guarantee loss assessment; performing special analysis on the special text to obtain a target text; performing calibration processing on the document image to obtain a calibrated document; performing optical character recognition on the calibration document to obtain a target document; and performing responsibility loss assessment according to the target text and the target document to obtain a labor guarantee loss assessment result. According to the invention, the accuracy and efficiency of labor guarantee loss assessment can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the fields of artificial intelligence technology and financial technology, and in particular to a labor insurance loss assessment method, device, electronic device and computer-readable storage medium. Background Art

[0002] Labor security refers to the sum of all measures and actions taken to protect the basic rights and interests of workers. Medical insurance is an important part of the labor security system, which provides workers with necessary medical security to ensure that they can receive timely and effective treatment when they are sick or injured. Labor security damage assessment often adopts manual assessment, but this method is labor-intensive, time-consuming, and prone to errors.

[0003] In the prior art, manual methods are often used to assess labor insurance losses. Traditionally, labor insurance loss assessment, such as medical insurance loss assessment, requires cumbersome application, verification, and review processes. Workers need to provide a series of documents and materials to support their claims, and insurance companies need to spend a lot of time and manpower to verify and process. The entire loss assessment process is cumbersome and time-consuming, and it all involves data retrieval and query. Errors are prone to occur during the loss assessment process, and the accuracy is not high enough, resulting in poor efficiency in labor insurance loss assessment. However, with the development of artificial intelligence, more and more areas in life can achieve improved processing efficiency by combining with technologies such as artificial intelligence. In terms of labor insurance loss assessment, how to combine artificial intelligence technology to improve the accuracy and efficiency of labor insurance loss assessment has become an urgent problem to be solved. Summary of the invention

[0004] The present invention provides a labor security damage assessment method, device and computer-readable storage medium, the main purpose of which is to solve the problems of insufficient accuracy and low efficiency of labor security damage assessment.

[0005] In a first aspect, in order to achieve the above-mentioned purpose, the present invention provides a labor insurance damage assessment method, comprising:

[0006] Obtain the special text and document images of labor insurance damage assessment;

[0007] Performing special parsing on the special text to obtain a target text;

[0008] Performing calibration processing on the document image to obtain a calibrated document;

[0009] Performing optical character recognition on the calibration document to obtain a target document;

[0010] Liability assessment is performed based on the target text and the target document to obtain a labor insurance assessment result.

[0011] In a second aspect, the present invention further provides a labor insurance damage assessment device, the device comprising:

[0012] The acquisition module is used to obtain the special text and document images of labor insurance damage assessment;

[0013] A special parsing module, used for performing special parsing on the special text to obtain a target text;

[0014] A calibration processing module, used for performing calibration processing on the document image to obtain a calibration document;

[0015] A recognition module, used for performing optical character recognition on the calibration document to obtain a target document;

[0016] The liability assessment module is used to conduct liability assessment based on the target text and the target document to obtain a labor insurance damage assessment result.

[0017] In a third aspect, the present invention further provides an electronic device, the electronic device comprising:

[0018] at least one processor; and,

[0019] a memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the labor insurance damage assessment method described above.

[0021] In a fourth aspect, the present invention further provides a computer-readable storage medium, in which at least one computer program is stored, and the at least one computer program is executed by a processor in an electronic device to implement the above-mentioned labor insurance damage assessment method.

[0022] In the embodiment of the present invention, a special text is obtained by querying the official website and a document image is obtained by methods such as intelligent shooting tools, thereby ensuring the authority of the obtained special text and the high quality of the obtained document image, and facilitating the subsequent recognition and processing of the document image; the target text is obtained by performing special analysis on the special text, and the document image is calibrated and optical character recognition is performed to obtain the target document, thereby improving the accuracy of recognition; the target text and the target document are subjected to liability assessment to obtain a labor security assessment result, thereby improving the accuracy of labor security assessment and the efficiency of assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0024] Figure 1 is a schematic diagram of an application environment of an intelligent question-answering processing method in one embodiment of the present invention;

[0025] Figure 2 A schematic diagram of a process flow of a labor insurance damage assessment method provided by an embodiment of the present invention;

[0026] Figure 3 A schematic diagram of a module of a labor insurance damage assessment device provided by an embodiment of the present invention;

[0027] Figure 4 A schematic diagram of the structure of an electronic device of a labor insurance damage assessment device provided by one embodiment of the present invention;

[0028] Figure 5 It is another structural schematic diagram of an electronic device of a labor security damage assessment device provided by one embodiment of the present invention.

[0029] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the technical solution of the present disclosure, and to fully understand and implement how the present disclosure applies technical means to solve technical problems and achieve the corresponding technical effects, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only embodiments of a part of the present disclosure, not all of the embodiments. The embodiments of the present disclosure and the various features in the embodiments can be combined with each other without conflict, and the technical solutions formed are all within the scope of protection of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present disclosure.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, device, product or equipment that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0032] The embodiment of the present application provides a labor security damage assessment method, and the execution subject of the labor security damage assessment method includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the device provided by the embodiment of the present application. In other words, the labor security damage assessment method can be executed by software or hardware installed on a terminal device or a server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms.

[0033] The labor insurance loss assessment method provided by the embodiment of the present invention can be applied in the following aspects: Figure 1In the application environment, the client communicates with the server through the network. The server can obtain the special text and document image of the labor security damage assessment through the client; obtain the target text by performing special analysis on the special text; obtain the calibration document by calibrating the document image; obtain the target document by performing optical character recognition according to the calibration document; perform liability assessment according to the target text and the target document to obtain the labor security damage assessment result, and feed back the labor security damage assessment result to the client. In the present invention, for the labor security damage assessment, the special text is first obtained by querying the official website and the document image is obtained by methods such as intelligent shooting tools, which ensures the authority of the obtained special text and the high quality of the obtained document image, and facilitates the subsequent recognition and processing of the document image; obtain the target text by performing special analysis on the special text, calibrate the document image and perform optical character recognition to obtain the target document, thereby improving the accuracy of recognition; perform liability assessment on the target text and the target document to obtain the labor security damage assessment result, thereby improving the accuracy of labor security damage assessment and the efficiency of damage assessment. The client may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and portable wearable devices. The server may be implemented by an independent server or a server cluster consisting of multiple servers. The present invention is described in detail below through specific embodiments.

[0034] Reference Figure 2 The figure is a flow chart of a labor insurance damage assessment method provided in one embodiment of the present invention.

[0035] In this embodiment, the labor insurance damage assessment method includes:

[0036] S1. Obtain the special text and document image of labor insurance damage assessment.

[0037] In an embodiment of the present invention, the special text of labor and social security damage assessment refers to the laws and regulations required for use in liability damage assessment, such as special agreements or clauses formulated in the field of work-related injury insurance to clarify the rights and obligations of both parties and avoid disputes, including basic information of the responsible parties, an overview of the work-related accident, compensation matters and compensation amounts; the documents of labor and social security damage assessment refer to the supporting materials required for use in liability damage assessment, such as the diagnosis certificate, discharge record, pay slip, etc. of the labor and social security party in the field of work-related injury insurance.

[0038] In an embodiment of the present invention, the labor security damage assessment refers to the process of evaluating and determining the economic losses suffered by workers due to work injuries, occupational diseases, labor disputes, etc. under the labor security legal framework. The labor security damage assessment includes the quantification of various losses such as medical expenses, disability compensation, loss of work time, and mental damages.

[0039] Furthermore, in the process of labor security damage assessment, the labor security damage assessment should be carried out in a timely manner to ensure that workers can obtain compensation in a timely manner. It should also follow the principles of fairness, equity and openness to ensure the objectivity and accuracy of the damage assessment results. All damage assessment and compensation actions must be carried out in accordance with the law and must not violate the provisions of relevant laws and regulations.

[0040] The special text of the present invention can be connected to an official website such as the website of an industrial injury determination agency through the HTTP protocol via programming languages ​​such as Python and Java, and an HTTP request is sent to obtain data, thereby obtaining the special text of the labor insurance damage assessment.

[0041] The present invention can use intelligent shooting tools to shoot the documents required for liability assessment, such as using a mobile phone to shoot the diagnosis certificate, discharge record, pay slip, etc. of the labor and security party.

[0042] Furthermore, a scanner may be used to scan the document into an electronic image, and the electronic image in the scanner may be accessed through a computer platform to obtain the document image.

[0043] In the embodiment of the present invention, the special text is obtained by querying the official website, which ensures the timeliness and authority of the special text, and the document image is obtained by intelligent shooting tools, which ensures the high quality of the obtained document image, which facilitates the subsequent recognition and processing of the document image.

[0044] S2. Perform special parsing on the special text to obtain a target text.

[0045] In an embodiment of the present invention, the special agreement analysis refers to extracting special agreement content related to liability assessment. For example, in the field of work-related injury insurance, the responsible party, compensation conditions and other contents are extracted from the special agreement text to obtain the standard of lost work days and the number of lost work days without deductible.

[0046] In the embodiment of the present invention, the step of performing special parsing on the special text to obtain the target text includes:

[0047] Extracting target keywords of the special text, and generating indexes of each special text in a preset keyword list according to the target keywords;

[0048] Retrieving target keyword information from the special texts according to the special text indexes;

[0049] The target keyword information is subjected to convolution, pooling and activation processing to obtain the target text.

[0050] In detail, the keyword list includes target keywords of the special text. For example, in labor insurance damage assessment, the keyword list contains responsible parties, compensation conditions, compensation amounts, etc. The target keywords are converted into multiple search expressions through different permutations and combinations. Each special text index is generated in the preset keyword list through the search expression. Each special text index refers to a separate, physical storage structure that sorts one or more columns of keyword search expressions in a preset keyword table. Through each special text index, the required target keyword information can be quickly retrieved from the keywords in the directory and the target keyword information can be stored.

[0051] In detail, a pre-trained model such as BERT is used to convert each keyword in the keyword list into a vector of fixed length, and each keyword in the special text is embedded in the vector and arranged in the order of the special text to form a two-dimensional matrix, wherein the rows of the two-dimensional matrix correspond to the dimension of word embedding, and the columns correspond to the word order in the special text. A one-dimensional convolution kernel is applied to the two-dimensional matrix, and the convolution kernel slides along the special text (i.e., the columns of the matrix), and weighted sums are performed on the local area to extract local features; after the convolution layer, a pooling layer is added to reduce the spatial size of the text data while retaining the key features. For the special text, the maximum pooling method is often used to select the maximum value in the output of each convolution kernel; after the convolution layer or the pooling layer, a nonlinear activation function such as ReLU is usually used to increase the nonlinear ability of the two-dimensional matrix. After multiple convolution-pooling-activation layers, the extracted key features can be flattened and passed to the fully connected layer, and the output at this time is used as the vector representation of the target text, thereby obtaining the final target text.

[0052] Furthermore, the convolution processing is the core of the convolutional network. The convolution processing slides a sliding window (convolution kernel) on the input data (keyword data set) and performs a dot product operation to extract local features. In text processing, this usually means capturing the semantic or grammatical relationship between the keyword and its surrounding words. According to the convolution operation, useful features can be effectively extracted from the original data, and due to its local connection and weight sharing characteristics, the number of parameters is reduced and the computational complexity is reduced.

[0053] Furthermore, the pooling process is usually followed by the convolution process to further reduce the spatial size of the data (for text processing, it can be understood as reducing the dimension of the feature vector), thereby reducing the amount of calculation and avoiding overfitting; according to the pooling process, by retaining important features and discarding redundant information, a higher-level feature representation is obtained, which is more robust and effective for subsequent parsing tasks.

[0054] Furthermore, after convolution and pooling, the activation processing usually applies a nonlinear activation function (such as ReLU) to increase the nonlinear ability of the data and enable learning of more complex patterns; the ReLU activation function can set all negative values ​​to 0 and keep positive values ​​unchanged. The ReLU activation function not only speeds up the calculation process (because it does not involve complex exponential operations), but also alleviates the gradient vanishing problem and helps data convergence.

[0055] In the embodiment of the present invention, since the data volume of the special text is large, in order to realize quick processing of the special text, the target keywords of each special text can be extracted one by one, thereby realizing the reduction of data volume and reducing the complexity of special analysis of the special text.

[0056] In an embodiment of the present invention, the keyword data set is subjected to convolution, pooling and activation processing to capture the long-term dependencies in the special text, thereby enhancing the focus of the parsing process on keywords and improving the accuracy and efficiency of the special text parsing.

[0057] In detail, the extracting target keywords of the special text includes:

[0058] Select one of the special texts as the text to be processed one by one, and segment the text to be processed to obtain the special text segmentation;

[0059] Select one of the special text segmentations one by one as the segmentation to be processed;

[0060] Counting the local occurrence times of the to-be-processed segmentation in the to-be-processed text, and counting the global occurrence times of the to-be-processed segmentation in all the special texts;

[0061] Dividing the local number of occurrences by the global number of occurrences to obtain the criticality of the word to be processed;

[0062] The to-be-processed sub-words whose key degrees are greater than a preset threshold are set as keywords of the to-be-processed text.

[0063] In detail, the text keywords may be converted into word vectors, and the converted word vectors may be used as the special text retrieval.

[0064] In the embodiment of the present invention, the special text is optimized and stored by constructing a keyword data set, so that the special text is more structured, which can improve the efficiency of subsequent special analysis of the special text.

[0065] In the embodiment of the present invention, by performing special analysis on the special text to obtain the standard of lost work day quota and the number of lost work deductible days, efficient and accurate processing of the text related to liability assessment can be achieved, and information of great value to the subsequent liability assessment can be extracted, thereby improving the efficiency and accuracy of the special text analysis.

[0066] S3. Calibrate the document image to obtain a calibrated document.

[0067] In the embodiment of the present invention, calibration processing refers to preprocessing the document image, including classification, deduplication, block diagram, etc., to improve the subsequent recognition accuracy; classifying the document image according to its purpose or characteristics to facilitate subsequent processing and analysis; removing duplicate or redundant images from the classified document image to ensure that each document image is unique; drawing a block diagram for the features or key information in the document image to facilitate subsequent recognition and extraction.

[0068] In the embodiment of the present invention, the step of calibrating the document image to obtain a calibrated document includes:

[0069] classifying the document images according to the target features of the document images, and removing duplicates from the classified document images to obtain processed documents;

[0070] A block diagram is drawn for the processed document to obtain a calibration document.

[0071] In detail, the target features include color features, texture features, shape features, etc. of the document image. The document image is subjected to image enhancement techniques such as contrast adjustment and sharpening to make the key information in the document image clearer. At the same time, the size and resolution of the document image are normalized. The normalized document image is subjected to a convolutional neural network to automatically extract target features, such as color features, texture features, and shape features, from the document image. Each document image is annotated according to its features, and the BERT pre-trained model is used to predict the category features to which the input document image belongs, thereby achieving classification of the document image.

[0072] Furthermore, the block diagram representation refers to a graphical representation of the processed document. Using tools such as Microsoft Visio and Lucidchart to frame the document image helps to understand and optimize the document image.

[0073] In the embodiment of the present invention, the process of removing duplicates from the classified document images to obtain processed documents includes:

[0074] Perform hash processing on the classified document images to generate hash values;

[0075] Determining whether the classified document images are repeated according to the hash values;

[0076] When the classified document image is a repeated image, the repeated document image is removed to obtain a processed document image.

[0077] In detail, the hash processing refers to the process of converting the classified document image into a fixed-length output, namely a hash value, through a hash algorithm. The complex document image can be simplified into a fixed-length string that is easy to compare and store. The document image is judged to be repeated by comparing whether the hash values ​​are the same. When the hash values ​​of two document images are the same, the two document images are considered to be repeated. The repeated document images are removed, and the remaining document images are processed document images, which facilitates subsequent document processing and analysis.

[0078] In the embodiment of the present invention, by calibrating the document image, the document image can be effectively classified, deduplicated, etc., thereby improving the efficiency and accuracy of processing the document image, thereby improving the efficiency of subsequent liability assessment.

[0079] S4. Perform optical character recognition on the calibration document to obtain a target document.

[0080] In the embodiments of the present invention, optical character recognition refers to a process in which an electronic device (such as a scanner or a digital camera) examines characters printed on paper, determines their shapes by detecting dark and light patterns, and then translates the shapes into computer text using a character recognition method; for example, for printed characters, an optical method is used to convert the text in a paper document into a black and white dot matrix image file, and recognition software is used to convert the text in the image into a text format for further editing and processing by a word processing software.

[0081] In an embodiment of the present invention, optical character recognition refers to identifying the document content related to liability assessment in the calibration document. For example, in the field of work-related injury insurance, the content such as hospitalization and discharge time, number of days off, etc. in the calibration document is identified to obtain information such as lost work days and wages.

[0082] In an embodiment of the present invention, performing optical character recognition on the calibration document to obtain a target document includes:

[0083] Binarizing and denoising the calibration document to obtain a non-polluted calibration document;

[0084] Extracting character features of the uncontaminated calibration document as characters to be recognized, and matching the characters to be recognized with a preset character template library to obtain target characters;

[0085] The calibration document corresponding to the target character is used as the target document.

[0086] In detail, the calibration document image is converted into a black and white binary image, and the noise or impurities in the image are removed so as to display the text area more clearly and improve the image quality; the image processing technology is used to locate the text area in the image and reduce the interference of the non-text area; the character features such as edges and pixel distribution are extracted from the processed text area through the unique hot encoding technology of the characters, and the extracted character features are matched with the preset character template library to find the most similar character features, that is, the target character, and the calibration document corresponding to the target character is the target document, so as to achieve more accurate recognition.

[0087] Furthermore, the one-hot encoding technique of the characters is a data preprocessing method commonly used to process categorical variables, especially in the fields of machine learning and data mining; this method converts each possible value of the categorical variable into a new binary feature (also called a one-hot feature), thereby constructing a vector containing only 0 and 1 to represent the original data, and the one-hot encoding technique of the characters is mainly used to process categorical data or unordered discrete features. One-hot encoding represents each category by assigning an independent binary vector to the category, the length of the vector is equal to the total number of categories, each category corresponds to a position in the vector, the value at the position is 1, and the values ​​at the remaining positions are all 0.

[0088] In the present invention, in the extraction of character features of the uncontaminated calibration document, one-hot encoding can be used to represent the characters in the calibration document, and each character is mapped to a vector of a fixed length, eliminating the erroneous numerical relationship that may exist between the documents, especially for algorithms involving distance calculation (such as the K nearest neighbor algorithm). One-hot encoding converts classified data into binary form, allowing these algorithms to process better, thereby allowing computers to understand and process more easily, thereby quickly obtaining the target document.

[0089] Furthermore, the character template library is a collection of various character features, each character template is designed for the shape and structure of a specific character, and can be created manually or generated by scanning known character samples. In OCR (optical character recognition) technology, features are extracted from the calibration document to be recognized, and these features may include edges, contours, corner points, etc., which are used to describe the shape of the character. These features are compared and matched with the templates in the character template library, and the similarity between the character to be recognized and the template character is calculated by methods such as Euclidean distance or correlation coefficient, and the template most similar to the character to be recognized is found, thereby realizing character recognition.

[0090] In an embodiment of the present invention, optical character recognition technology is used to identify the hospitalization and discharge time and the number of days off work in the calibration document, thereby improving the accuracy and efficiency of recognition. The number of days of lost work is obtained by calculating the hospitalization and discharge time, thereby providing strong support for subsequent liability assessment.

[0091] S5. Carry out liability assessment based on the target text and the target document to obtain a labor insurance loss assessment result.

[0092] In the embodiments of the present invention, for example, in the field of work-related injury compensation, the labor security damage assessment results mostly refer to the loss of work time due to work-related injury compensation.

[0093] In the embodiment of the present invention, the liability assessment is performed according to the target text and the target document to obtain the labor insurance assessment result, including:

[0094] According to the target text, the standard of the day amount of lost work and the number of days of lost work deductible are obtained;

[0095] Obtaining the number of days of work delay and the daily wages of work delay according to the target document identification;

[0096] The loss of work fee is calculated based on the loss of work day standard, the loss of work deductible days, and the loss of work days to obtain the loss of work fee.

[0097] Specifically, the loss of working time is calculated by the following formula:

[0098] f=(wm)*r

[0099] Among them, w is the number of days of lost work, m is the number of days of lost work deductible, r is the daily rate of lost work, and f is the lost work fee.

[0100] In detail, the standards for daily loss of work include a fixed daily amount, the local minimum wage standard, and the employee's actual salary. If it is a fixed daily amount such as 100 yuan / day, the loss of work expenses will be calculated directly; if it is the local minimum wage standard, the minimum wage standard of the policy's insured area will be automatically obtained from the property insurance minimum wage standard database; if it is based on the employee's actual salary, the target document will be used to identify documents such as payrolls to obtain the employee's daily loss of work wages, thereby calculating the loss of work expenses.

[0101] In the embodiment of the present invention, through the preset badcase feedback mechanism, according to whether the closed labor security loss assessment result is consistent with the automatic loss assessment labor security loss assessment result, inconsistent cases are automatically fed back to the AI ​​model for training, thereby achieving more accurate liability loss assessment.

[0102] In detail, the badcase feedback mechanism refers to when users encounter unsatisfactory or unexpected results during the use of products or services, they feedback the problem to the platform through specific channels; the core idea of ​​the badcase feedback mechanism is to combine user feedback and model introspection, aiming to continuously improve the performance and quality of the product. Specifically, the badcase feedback mechanism is a combination of user feedback and model introspection. When users encounter inaccurate or unexpected answers from the model, they can feedback the problem to the platform through specific channels. The platform will optimize and improve the model based on user feedback to improve the accuracy of the model and user experience.

[0103] In an embodiment of the present invention, liability assessment is performed based on the target text and the target document, and a labor security assessment result is calculated using different lost work day standards, thereby improving the accuracy of liability assessment. Inconsistent labor security assessment results are fed back to a preset platform for correction through a badcase feedback mechanism, thereby achieving more accurate liability assessment and improving the efficiency of liability assessment.

[0104] In the embodiment of the present invention, a special text is obtained by querying the official website and a document image is obtained by methods such as intelligent shooting tools, thereby ensuring the authority of the obtained special text and the high quality of the obtained document image, and facilitating the subsequent recognition and processing of the document image; the target text is obtained by performing special analysis on the special text, and the document image is calibrated and optical character recognition is performed to obtain the target document, thereby improving the accuracy of recognition; the target text and the target document are subjected to liability assessment to obtain a labor security assessment result, thereby improving the accuracy of labor security assessment and the efficiency of assessment.

[0105] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0106] In the embodiment of the present disclosure, a labor insurance damage assessment device is provided, which corresponds one-to-one with the labor insurance damage assessment method in the above embodiment. Figure 3 As shown, the labor insurance damage assessment device 100 can be installed in an electronic device. According to the functions to be implemented, the labor insurance damage assessment device 100 includes a collection module 101, a special contract analysis module 102, a calibration processing module 103, an identification module 104, and a liability damage assessment module. The functional modules are described in detail as follows:

[0107] The acquisition module 101 is used to obtain the special text and document image of the labor insurance damage assessment;

[0108] A special parsing module 102 is used to perform special parsing on the special text to obtain a target text;

[0109] A calibration processing module 103, used to perform calibration processing on the document image to obtain a calibration document;

[0110] The recognition module 104 is used to perform optical character recognition on the calibration document to obtain a target document;

[0111] The liability assessment module 105 is used to perform liability assessment based on the target text and the target document to obtain a labor insurance damage assessment result.

[0112] In one embodiment, the special contract analysis module 102 is specifically used to:

[0113] Extracting target keywords of the special text, and generating indexes of each special text in a preset keyword list according to the target keywords;

[0114] Retrieving target keyword information from the special texts according to the special text indexes;

[0115] The target keyword information is subjected to convolution, pooling and activation processing to obtain the target text.

[0116] In one embodiment, the special contract analysis module 102 is specifically used to:

[0117] Select one of the special texts as the text to be processed one by one, and segment the text to be processed to obtain the special text segmentation;

[0118] Select one of the special text segmentations one by one as the segmentation to be processed;

[0119] Counting the local occurrence times of the to-be-processed segmentation in the to-be-processed text, and counting the global occurrence times of the to-be-processed segmentation in all the special texts;

[0120] Dividing the local number of occurrences by the global number of occurrences to obtain the criticality of the word to be processed;

[0121] The to-be-processed sub-words whose key degrees are greater than a preset threshold are set as keywords of the to-be-processed text.

[0122] In one embodiment, the calibration processing module 103 is specifically configured to:

[0123] classifying the document images according to the target features of the document images, and removing duplicates from the classified document images to obtain processed documents;

[0124] A block diagram is drawn for the processed document to obtain a calibration document.

[0125] In one embodiment, the calibration processing module 103 is specifically configured to:

[0126] Perform hash processing on the classified document images to generate hash values;

[0127] Determining whether the classified document images are repeated according to the hash values;

[0128] When the classified document image is a repeated image, the repeated document image is removed to obtain a processed document image.

[0129] In one embodiment, the identification module 104 is specifically configured to:

[0130] Binarizing and denoising the calibration document to obtain a non-polluted calibration document;

[0131] Extracting character features of the uncontaminated calibration document as characters to be recognized, and matching the characters to be recognized with a preset character template library to obtain target characters;

[0132] The calibration document corresponding to the target character is used as the target document.

[0133] In one embodiment, the liability assessment module 105 is specifically used to:

[0134] According to the target text, the standard of the day amount of lost work and the number of days of lost work deductible are obtained;

[0135] Obtaining the number of days of work delay and the daily wages of work delay according to the target document identification;

[0136] The loss of work fee is calculated based on the loss of work day standard, the loss of work deductible days, and the loss of work days to obtain the loss of work fee.

[0137] In the present invention, for labor insurance damage assessment, first, a special text is obtained by querying the official website and a document image is obtained by methods such as intelligent shooting tools, thereby ensuring the authority of the obtained special text and the high quality of the obtained document image, which is convenient for subsequent recognition and processing of the document image; the target text is obtained by performing special analysis on the special text, and the document image is calibrated and optically recognized to obtain the target document, thereby improving the accuracy of recognition; the target text and the target document are used to perform liability assessment to obtain a labor insurance damage assessment result, thereby improving the accuracy of labor insurance damage assessment and the efficiency of damage assessment.

[0138] For the specific definition of the labor security damage assessment device, please refer to the definition of the labor security damage assessment method above, which will not be repeated here. Each module in the above-mentioned labor security damage assessment device can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0139] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client via a network connection. When the computer program is executed by the processor, it implements the functions or steps on the service side of a labor security loss assessment method.

[0140] In one embodiment, a computer device is provided. The computer device may be a client, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external server via a network connection. When the computer program is executed by the processor, it implements the functions or steps of a client side of a labor security loss assessment method.

[0141] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0142] Obtain the special text and document images of labor insurance damage assessment;

[0143] Performing special parsing on the special text to obtain a target text;

[0144] Performing calibration processing on the document image to obtain a calibrated document;

[0145] Performing optical character recognition on the calibration document to obtain a target document;

[0146] Liability assessment is performed based on the target text and the target document to obtain a labor insurance assessment result.

[0147] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and apparatuses can be implemented in other ways. For example, the system embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0148] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0149] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0150] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0151] In some implementations of this embodiment, a computer-readable storage medium is provided, on which a computer program is stored, characterized in that when the computer program is executed by a processor, the steps of the method described in the above embodiment are implemented.

[0152] The readable storage medium of the present invention stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can achieve:

[0153] Obtain the special text and document images of labor insurance damage assessment;

[0154] Performing special parsing on the special text to obtain a target text;

[0155] Performing calibration processing on the document image to obtain a calibrated document;

[0156] Performing optical character recognition on the calibration document to obtain a target document;

[0157] Liability assessment is performed based on the target text and the target document to obtain a labor insurance assessment result.

[0158] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant descriptions on the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.

[0159] The computer-readable storage medium may also store at least one computer executable program / instruction, which may be, for example, a computer-readable instruction. The computer-readable storage medium includes, but is not limited to, for example, a volatile memory and / or a non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The computer-readable storage medium may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. For example, a non-transitory computer-readable storage medium may be connected to a computing device such as a computer, and then, when the computing device runs the computer-readable instructions stored on the computer-readable storage medium, the various methods described above may be performed.

[0160] In addition, the computer device may also include (but not limited to) a data bus, an input / output (I / O) bus, a display, and input / output devices (eg, keyboard, mouse, speaker, etc.), etc.

[0161] The processor may communicate with external devices via an I / O bus via a wired or wireless network.

[0162] In one embodiment, the at least one computer executable instruction may also be compiled into or constitute a software product / computer program product, wherein one or more computer executable instructions are executed by a processor to perform the various functions and / or method steps in the embodiments described in the present technology.

[0163] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0164] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0165] In the embodiments provided in the present disclosure, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0166] It should be noted that in the present disclosure, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element limited by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0167] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

[0168] It should be noted that if software tools or components other than those of our company appear in the embodiments of the present application, they are only used for illustrative purposes and do not represent actual use.

Claims

1. A labor insurance damage assessment method, characterized in that: The method comprises: Obtain the special text and document images of labor insurance damage assessment; Performing special parsing on the special text to obtain a target text; Performing calibration processing on the document image to obtain a calibrated document; Performing optical character recognition on the calibration document to obtain a target document; Liability assessment is performed based on the target text and the target document to obtain a labor insurance assessment result.

2. A labor insurance damage assessment method as claimed in claim 1, characterized in that: The step of performing special parsing on the special text to obtain the target text includes: Extracting target keywords of the special text, and generating indexes of each special text in a preset keyword list according to the target keywords; Retrieving target keyword information from the special texts according to the special text indexes; The target keyword information is subjected to convolution, pooling and activation processing to obtain the target text.

3. A labor insurance damage assessment method as claimed in claim 2, characterized in that: The step of extracting target keywords from the special text includes: Select one of the special texts as the text to be processed one by one, and segment the text to be processed to obtain the special text segmentation; Select one of the special text segmentations one by one as the segmentation to be processed; Counting the local occurrence times of the to-be-processed segmentation in the to-be-processed text, and counting the global occurrence times of the to-be-processed segmentation in all the special texts; Dividing the local number of occurrences by the global number of occurrences to obtain the criticality of the word to be processed; The to-be-processed sub-words whose key degrees are greater than a preset threshold are set as keywords of the to-be-processed text.

4. A labor insurance damage assessment method as claimed in claim 1, characterized in that: The step of calibrating the document image to obtain a calibrated document includes: classifying the document images according to the target features of the document images, and removing duplicates from the classified document images to obtain processed documents; A block diagram is drawn for the processed document to obtain a calibration document.

5. A labor insurance damage assessment method as claimed in claim 4, characterized in that: Deduplication of the classified document images to obtain processed documents includes: Perform hash processing on the classified document images to generate hash values; Determining whether the classified document images are repeated according to the hash values; When the classified document image is a repeated image, the repeated document image is removed to obtain a processed document image.

6. A labor insurance damage assessment method as claimed in claim 1, characterized in that: The step of performing optical character recognition on the calibration document to obtain a target document includes: Binarizing and denoising the calibration document to obtain a non-polluted calibration document; Extracting character features of the uncontaminated calibration document as characters to be recognized, and matching the characters to be recognized with a preset character template library to obtain target characters; The calibration document corresponding to the target character is used as the target document.

7. A labor insurance damage assessment method as claimed in claim 1, characterized in that: The liability assessment is performed according to the target text and the target document to obtain the labor insurance assessment result, including: According to the target text, the standard of the day amount of lost work and the number of days of lost work deductible are obtained; Obtaining the number of days of work delay and the daily wages of work delay according to the target document identification; The loss of work fee is calculated based on the loss of work day standard, the loss of work deductible days, and the loss of work days to obtain the loss of work fee.

8. A labor insurance damage assessment device, characterized in that: The device comprises: The acquisition module is used to obtain the special text and document images of labor insurance damage assessment; A special parsing module, used for performing special parsing on the special text to obtain a target text; A calibration processing module, used for performing calibration processing on the document image to obtain a calibration document; A recognition module, used for performing optical character recognition on the calibration document to obtain a target document; The liability assessment module is used to conduct liability assessment based on the target text and the target document to obtain a labor insurance damage assessment result.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute a labor insurance damage assessment method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, it implements a labor insurance damage assessment method as described in any one of claims 1 to 7.

Images