Chemical entity identification method and device, electronic equipment and storage medium

Abstract

The invention discloses a chemical entity identification method and device, electronic equipment and a storage medium. The method comprises the following steps: receiving to-be-recognized MSDS data of at least one chemical, and converting the to-be-recognized MSDS data into to-be-recognized MSDS text data in a target format; each piece of to-be-recognized MSDS text data comprises a plurality of to-be-recognized classes, and each to-be-recognized class corresponds to a classification number; in any business processing mode, identifying the classification number of the to-be-identified MSDS text data, and determining business text data corresponding to the business processing mode; the business text data corresponding to the business processing mode comprises text information of at least one to-be-recognized class; inputting the service text data into an entity recognition model corresponding to the service processing mode to obtain a target service field corresponding to the service processing mode; and executing a task corresponding to the business processing mode based on the target business field. According to the method, the chemical entities in the MSDS data can be quickly and accurately identified, and meanwhile, accidents caused by errors in manual identification are avoided.

Description

Technical Field

[0001] The natural language processing technology of the present invention relates to a field, and in particular to a chemical entity recognition method, device, electronic device and storage medium. Background Art

[0002] MSDS (Material Safety Data Sheet), also known as Material Safety Data Sheet or Chemical Safety Data Sheet, is a document used by chemical manufacturers and importers to explain the physical and chemical properties of chemicals (such as pH value, flash point, flammability, reactivity, etc.) and the possible hazards to the health of users (such as carcinogenicity, teratogenicity, etc.).

[0003] At present, in the chemical-related business field, it is necessary to quickly identify the characteristics of chemicals in order to complete chemical-related tasks as soon as possible. However, due to the huge amount of information in MSDS data, it is difficult for staff to quickly obtain key information in MSDS data, and manual identification is prone to errors, leading to accidents. Summary of the invention

[0004] The present invention provides a chemical entity recognition method, device, electronic device and storage medium to achieve rapid and accurate recognition of chemical entities in MSDS data while avoiding accidents caused by errors in manual recognition.

[0005] According to one aspect of the present invention, a method for identifying chemical entities is provided, comprising:

[0006] Receive at least one MSDS data to be identified of a chemical, and convert the MSDS data to be identified into MSDS text data to be identified in a target format; each of the MSDS text data to be identified includes multiple categories to be identified, and each category to be identified corresponds to a classification number;

[0007] Under any business processing mode, the classification number of the MSDS text data to be identified is identified to determine the business text data corresponding to the business processing mode; the business text data corresponding to the business processing mode includes text information of at least one class to be identified;

[0008] Inputting the business text data into an entity recognition model corresponding to the business processing mode to obtain a target business field corresponding to the business processing mode;

[0009] The task corresponding to the business processing mode is executed based on the target business field.

[0010] According to another aspect of the present invention, there is provided a chemical entity recognition device, comprising:

[0011] An MSDS data receiving module is used to receive at least one MSDS data to be identified of a chemical, and convert the MSDS data to be identified into MSDS text data to be identified in a target format; each of the MSDS text data to be identified includes multiple categories to be identified, and each category to be identified corresponds to a classification number;

[0012] A business text data determination module, used to identify the classification number of the MSDS text data to be identified in any business processing mode, and determine the business text data corresponding to the business processing mode; the business text data corresponding to the business processing mode includes text information of at least one class to be identified;

[0013] A target business field identification module, used for inputting the business text data into an entity recognition model corresponding to the business processing mode to obtain a target business field corresponding to the business processing mode;

[0014] A task execution module is used to execute the task corresponding to the business processing mode based on the target business field.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program executable 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 perform the chemical entity identification method described in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the chemical entity identification method described in any embodiment of the present invention when executed.

[0020] The technical solution of the embodiment of the present invention receives at least one MSDS data to be identified of a chemical, and converts the MSDS data to be identified into MSDS text data to be identified in a target format; each MSDS text data to be identified includes multiple classes to be identified, and each class to be identified corresponds to a classification number; in any business processing mode, the classification number of the MSDS text data to be identified is identified to determine the business text data corresponding to the business processing mode; the business text data corresponding to the business processing mode includes text information of at least one class to be identified; the business text data is input into the entity recognition model corresponding to the business processing mode to obtain the target business field corresponding to the business processing mode; and the task corresponding to the business processing mode is executed based on the target business field. Rapid and accurate identification of chemical entities in MSDS data can be achieved, thereby improving the speed of obtaining key information and avoiding accidents caused by errors in manual identification.

[0021] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 is a flow chart of a chemical entity identification method provided in Example 1 of the present invention;

[0024] Figure 2 is a flow chart of a chemical entity identification method provided by Embodiment 2 of the present invention;

[0025] Figure 3 is a schematic diagram of the structure of a chemical entity identification device provided in Embodiment 3 of the present invention;

[0026] Figure 4 It is a structural schematic diagram of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention 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 interchanged where appropriate, so that the embodiments of the present invention 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, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] Embodiment 1

[0030] Figure 1 This is a flow chart of a chemical entity recognition method provided in the first embodiment of the present invention. This embodiment is applicable to the case of identifying the entity characteristics of chemicals in MSDS documents. The method can be executed by a chemical entity recognition device, which can be implemented in the form of hardware and / or software, and the chemical entity recognition device can be configured in a back-end server. Figure 1 As shown, the method includes:

[0031] S110, receiving at least one MSDS data to be identified of a chemical, and converting the MSDS data to be identified into MSDS text data to be identified in a target format; each of the MSDS text data to be identified includes multiple categories to be identified, and each category to be identified corresponds to a classification number.

[0032] Among them, the MSDS data to be identified refers to the MSDS data of the chemical to be identified. Specifically, the MSDS data to be identified can be MSDS data in different formats and languages. The format of the MSDS data to be identified includes but is not limited to picture format, Word format, PDF format, etc., which is not limited here. The languages ​​of the MSDS data to be identified include Chinese and English. Correspondingly, the MSDS text data to be identified include Chinese text and English text. In this embodiment, the MSDS data to be identified of at least one chemical uploaded by the user is received, and the MSDS data to be identified is converted into the MSDS text data to be identified in the target format. Among them, the target format can be PDF format. It can be understood that the purpose of the conversion format is to unify the format of the MSDS data for easy processing. If the format of the MSDS data to be identified is PDF format, there is no need to convert the format of the MSDS data to be identified.

[0033] It should be noted that each MSDS data includes multiple categories to be identified, including but not limited to chemicals and corporate identification, hazard overview, ingredients / composition information, first aid measures, firefighting measures, emergency treatment of leaks, handling and storage, contact control and personal protection, physical and chemical properties, etc. Classification numbers include but are not limited to Arabic numerals, Roman characters, Chinese format numbers, Chinese numbers, English numbers, etc. Each category to be identified corresponds to a classification number. For example, in Chinese text, the classification number corresponding to chemicals and corporate identification is the first part, the classification number corresponding to hazard overview is the second part, and the classification number corresponding to ingredients / composition information is the third part. By analogy, each category to be identified corresponds to a classification number, and the category to be identified can be determined by identifying the classification number.

[0034] It should also be noted that the correspondence between the categories to be identified and the classification numbers is related to the template format of the MSDS. The MSDS data in the same template format have the same correspondence between the categories to be identified and the classification numbers.

[0035] On the basis of the above embodiment, optionally, when the MSDS data to be identified is in a picture format, text recognition is performed on the MSDS data to be identified to obtain the MSDS text data to be identified, and the MSDS text data to be identified is converted into a target format.

[0036] Specifically, after receiving the MSDS data to be identified of the chemical, the format of the MSDS data to be identified is determined. If the MSDS data to be identified is in a picture format, text recognition is performed on the MSDS data to be identified based on the image recognition model to obtain the MSDS text data to be identified; further, the MSDS text data to be identified is format converted to convert the MSDS text data to be identified into the target format of the MSDS text data to be identified. The image recognition model can be an optical character recognition (OCR) model, and specifically, can be an OCR model based on deep learning, such as a recurrent neural network, a convolutional neural network model, a Tesseract OCR model, an EasyOCR model, etc.

[0037] In some embodiments, optionally, the method further comprises: cleaning invalid text information in the target format MSDS text data to be identified to obtain cleaned MSDS text data to be identified.

[0038] In this embodiment, the invalid text information in the target format MSDS text data to be identified can be cleaned to obtain the cleaned MSDS text data to be identified. The invalid text information includes but is limited to the legends, tables, directories, references, etc. that are not fixed in the MSDS text data to be identified, which are not limited here. For example, taking the target format as PDF format as an example, the invalid text information in the MSDS text data to be identified can be cleaned based on the pdfplumber library.

[0039] S120. Under any business processing mode, identify the classification number of the MSDS text data to be identified, and determine the business text data corresponding to the business processing mode; the business text data corresponding to the business processing mode includes text information of at least one category to be identified.

[0040] Among them, the business processing modes include chemical safety detection mode, warehouse management mode and transportation management mode. Business text data refers to the text data of the to-be-identified category corresponding to the business processing mode. It can be understood that each business processing mode requires different text data due to different business types. Exemplarily, taking the warehouse management mode as an example, the information required for the warehousing business includes flash point, transport packaging, class number, fire hazard and other information. Therefore, under the warehouse management mode, the business text data corresponding to the warehouse management mode is the text information corresponding to the physical and chemical properties, transportation information, and fire-fighting measures waiting for identification.

[0041] In this embodiment, under any business processing mode, the classification number of the MSDS text data to be identified is identified to determine the text data of each class to be identified; further, based on the class to be identified corresponding to the business processing mode, the business text information corresponding to the business processing mode is determined in the text data of each class to be identified.

[0042] It should be noted that a correspondence between the business processing mode and the class to be identified is pre-established.

[0043] On the basis of the above embodiment, optionally, the MSDS text data to be identified includes multiple text pages; for each of the text pages, the classification number of the text page is identified to obtain an identification result; the identification of the classification number of the MSDS text data to be identified and the determination of the business text data corresponding to the business processing mode includes: if the identification result includes multiple classification numbers, the text page is segmented to obtain a new text page; the above steps are repeated, and when the number of classification numbers of the identification result is one, the text data in the text page is determined as the text data of the class to be identified corresponding to the classification number; the business text data is determined based on the text data of at least one class to be identified corresponding to the business mode. It can be understood that the amount of information in the MSDS text data to be identified is huge, so each MSDS text data to be identified includes multiple text pages. Exemplarily, taking the identification of MSDS text data as text in PDF format as an example, each PDF page is a text page.

[0044] In this embodiment, for each text page, the classification number of the text page is identified to obtain a recognition result; wherein the recognition result is the classification number in the text page. Furthermore, if the recognition result includes multiple classification numbers, it indicates that the text page includes text data of multiple categories to be recognized, and the text page is segmented based on a preset segmentation logic to obtain a new text page; wherein the preset segmentation logic can be a specific keyword or format (such as a title or a dividing line, etc.). The above steps are repeated, and when the number of classification numbers of the recognition result is one, the text data in the text page is determined to be the text data of the category to be recognized corresponding to the classification number. wherein the new text page is formed by the partial text segmented from the original text page.

[0045] S130: Input the business text data into an entity recognition model corresponding to the business processing mode to obtain a target business field corresponding to the business processing mode.

[0046] Among them, the entity recognition model is an entity recognition model pre-trained for each class to be recognized, and is used to extract key fields in the text data corresponding to the class to be recognized. Specifically, the entity recognition model includes but is not limited to a recurrent neural network model, a convolutional neural network model, a hidden Markov model, etc., which are not limited here. In this embodiment, the business text data is input into the entity recognition model of the class to be recognized corresponding to the business processing mode to extract key fields, and obtain the target business field corresponding to the business processing mode. Among them, the target business field is the key field in the text data of the class to be recognized corresponding to the business processing mode. Exemplarily, assuming that the class to be recognized corresponding to the business processing mode includes chemicals and corporate logos, then the target business field includes the Chinese name, English name, Chinese alias, English alias, etc. of the chemical.

[0047] S140: Execute a task corresponding to the business processing mode based on the target business field.

[0048] In this embodiment, for different business processing modes, tasks corresponding to the business processing modes are executed based on the target business fields corresponding to the business processing modes, wherein the tasks corresponding to the business processing modes include chemical safety testing tasks, warehousing tasks, and transport document generation tasks.

[0049] On the basis of the above embodiment, optionally, the task corresponding to the business processing mode is executed based on the target business field, including: if the business processing mode is a chemical safety detection mode, performing a prohibition and restriction control detection on the target business field to obtain a detection result; if the business processing mode is a warehouse management mode, determining the storage area and storage conditions of the chemical based on the target business field; if the business processing mode is a transportation management mode, generating a transportation document based on a preset transportation document template and the target business field.

[0050] In this embodiment, if the business processing mode is a chemical safety detection mode, the target business field is subjected to a prohibition, restriction and control detection according to the preset regulatory database to obtain a detection result; wherein the detection result includes whether the chemical is a prohibited item, whether the chemical is a restricted item, and whether the chemical is a special controlled item. Optionally, if the business processing mode is a warehouse management mode, the target business field can be input into the warehouse recommendation model to obtain the storage area and storage conditions of the chemical to avoid safety problems caused by human misjudgment and improve the safety of warehousing. Optionally, if the business processing mode is a transportation management mode, the target business field can be imported into the corresponding position of the preset transportation document template to generate a transportation document.

[0051] In some embodiments, optionally, the method further includes: performing feature extraction on the text data corresponding to each of the classes to be identified to obtain key fields of the MSDS text data to be identified; generating display data based on the key fields of the MSDS text data to be identified, and displaying the display data on a Web display page; the Web display page includes at least one feature item and a query control, each of the feature items including the key fields of the MSDS text data to be identified; on the Web display page, in response to a selection operation on the feature item, determining a target feature item; and in response to a trigger operation on the query control, jumping to a key field display page corresponding to the target feature item.

[0052] The display data refers to the characteristic items formed by the combination of key fields in the MSDS text data to be identified, and each chemical corresponds to a characteristic item. The web display page includes at least one characteristic item and a query control.

[0053] In this embodiment, the text data corresponding to each class to be identified can be respectively input into the entity recognition model corresponding to the class to be identified for feature extraction to obtain the key fields of the MSDS text data to be identified; the display data is generated based on the key fields of the MSDS text data to be identified, and the display data is displayed on the Web display page. On the Web display page, in response to the selection operation of the feature item, the target feature item is determined; in response to the trigger operation of the query control, jump to the key field display page corresponding to the target feature item. Among them, the target feature item refers to the feature item selected by the selection operation. The key field display page is used to specifically display the key fields in the target feature item. Exemplarily, the CAS number and composition of the chemical can be specifically displayed on the key field display page. The technical solution of this embodiment receives at least one MSDS data to be identified of a chemical, and converts the MSDS data to be identified into MSDS text data to be identified in a target format; each MSDS text data to be identified includes multiple categories to be identified, and each category to be identified corresponds to a classification number; in any business processing mode, the classification number of the MSDS text data to be identified is identified to determine the business text data corresponding to the business processing mode; the business text data corresponding to the business processing mode includes text information of at least one category to be identified; the business text data is input into the entity recognition model corresponding to the business processing mode to obtain the target business field corresponding to the business processing mode; and the task corresponding to the business processing mode is executed based on the target business field. Rapid and accurate identification of chemical entities in MSDS data can be achieved, thereby improving the speed of obtaining key information and avoiding accidents caused by errors in manual identification.

[0054] Embodiment 2

[0055] Figure 2This is a flow chart of a chemical entity identification method provided by Example 2 of the present invention. Based on the above embodiments, when there are multiple MSDS data to be identified, this embodiment also includes: generating target text data based on multiple MSDS text data to be identified; correspondingly, identifying the classification number of the MSDS text data to be identified and determining the text data of each class to be identified, including: identifying the classification number of the target text data and determining the text data of each class to be identified. The explanations of the terms that are the same or corresponding to the above embodiments are not repeated here.

[0056] like Figure 2 As shown, the method includes:

[0057] S210, receiving at least one MSDS data to be identified of a chemical, and converting the MSDS data to be identified into MSDS text data to be identified in a target format; each of the MSDS text data to be identified includes multiple categories to be identified, and each category to be identified corresponds to a classification number.

[0058] S220: Generate target text data based on the plurality of MSDS text data to be identified.

[0059] The target text data is a text data formed by splicing a plurality of MSDS text data to be identified, and the plurality of MSDS text data to be identified are in the same text. In this embodiment, when there are a plurality of MSDS text data to be identified, the plurality of MSDS text data to be identified can be spliced ​​to obtain the target text data.

[0060] S230. Under any business processing mode, identify the classification number of the target text data to determine the business text data corresponding to the business processing mode; the business text data corresponding to the business processing mode includes text information of at least one category to be identified.

[0061] Wherein, the target text data includes multiple text pages. In this embodiment, for each text page, the classification number of the text page is identified to obtain a recognition result; wherein, the recognition result is the classification number in the text page. Further, if the recognition result includes multiple classification numbers, it indicates that the text page includes text data of multiple categories to be recognized, and the text page is segmented based on a preset segmentation logic to obtain a new text page; wherein, the preset segmentation logic can be a specific keyword or format (such as a title or a dividing line, etc.). Repeat the above steps, and when the number of classification numbers of the recognition result is one, the text data in the text page is determined as the text data of the category to be recognized corresponding to the classification number. Wherein, the new text page is formed by a portion of the text segmented from the original text page.

[0062] S240: Input the business text data into an entity recognition model corresponding to the business processing mode to obtain a target business field corresponding to the business processing mode.

[0063] S250: Execute a task corresponding to the business processing mode based on the target business field.

[0064] The technical solution of this embodiment generates target text data based on multiple MSDS text data to be identified when there are multiple MSDS data to be identified. It can simultaneously perform entity identification of chemicals on the MSDS text data to be identified of multiple chemicals, further improving the speed of obtaining key information.

[0065] Embodiment 3

[0066] Figure 3 Schematic diagram of a chemical entity identification device provided in Embodiment 3 of the present invention. Figure 3 As shown, the device comprises:

[0067] The MSDS data receiving module 310 is used to receive the MSDS data to be identified of at least one chemical, and convert the MSDS data to be identified into MSDS text data to be identified in a target format; each of the MSDS text data to be identified includes multiple categories to be identified, and each category to be identified corresponds to a classification number;

[0068] The business text data determination module 320 is used to identify the classification number of the MSDS text data to be identified in any business processing mode, and determine the business text data corresponding to the business processing mode; the business text data corresponding to the business processing mode includes text information of at least one category to be identified;

[0069] A target business field identification module 330 is used to input the business text data into an entity recognition model corresponding to the business processing mode to obtain a target business field corresponding to the business processing mode;

[0070] The task execution module 340 is used to execute the task corresponding to the business processing mode based on the target business field.

[0071] The technical solution of this embodiment is to receive at least one MSDS data to be identified of a chemical, and convert the MSDS data to be identified into MSDS text data to be identified in a target format; each MSDS text data to be identified includes multiple categories to be identified, and each category to be identified corresponds to a classification number; in any business processing mode, the classification number of the MSDS text data to be identified is identified to determine the business text data corresponding to the business processing mode; the business text data corresponding to the business processing mode includes text information of at least one category to be identified; the business text data is input into the entity recognition model corresponding to the business processing mode to obtain the target business field corresponding to the business processing mode; and the task corresponding to the business processing mode is executed based on the target business field. Rapid and accurate identification of chemical entities in MSDS data can be achieved, thereby increasing the speed of obtaining key information and avoiding accidents caused by errors in manual identification.

[0072] On the basis of the above embodiment, optionally, the device also includes a target text data generation module, which is used to generate target text data based on multiple MSDS text data to be identified when there are multiple MSDS data to be identified; correspondingly, the business text data determination module 320 is used to identify the classification number of the target text data and determine the business text data corresponding to the business processing mode.

[0073] On the basis of the above embodiment, optionally, the MSDS text data to be identified / the target text data includes multiple text pages; the business text data determination module 320 is used to identify the classification number of the text page for each of the text pages to obtain a recognition result; if the recognition result includes multiple classification numbers, the text page is segmented to obtain a new text page; the above steps are repeated, and when the number of classification numbers of the recognition result is one, the text data in the text page is determined as the text data of the class to be identified corresponding to the classification number; the business text data is determined based on at least one text data of the class to be identified corresponding to the business model.

[0074] On the basis of the above embodiment, optionally, the MSDS data receiving module 310 includes a format conversion unit for performing text recognition on the MSDS data to be identified when the MSDS data to be identified is in a picture format, obtaining the MSDS text data to be identified, and converting the MSDS text data to be identified into a target format.

[0075] On the basis of the above embodiment, optionally, the device further comprises a data cleaning module for cleaning invalid text information in the target format MSDS text data to be identified to obtain cleaned MSDS text data to be identified.

[0076] On the basis of the above embodiment, optionally, the business processing mode includes a chemical safety detection mode, a warehouse management mode and a transportation management mode; the task execution module 340 is specifically used to, if the business processing mode is a chemical safety detection mode, perform a prohibition and restriction control detection on the target business field to obtain a detection result; if the business processing mode is a warehouse management mode, determine the storage area and storage conditions of the chemical based on the target business field; if the business processing mode is a transportation management mode, generate a transportation document based on a preset transportation document template and the target business field.

[0077] On the basis of the above embodiment, optionally, the device further comprises a key field management module, which is used to extract features from the text data corresponding to each of the to-be-identified classes to obtain key fields of the to-be-identified MSDS text data;

[0078] Generate display data based on the key fields of the MSDS text data to be identified, and display the display data on a Web display page; the Web display page includes at least one feature item and a query control, each of the feature items includes the key fields of the MSDS text data to be identified; on the Web display page, in response to a selection operation on the feature item, determine a target feature item; in response to a trigger operation on the query control, jump to a key field display page corresponding to the target feature item.

[0079] The chemical entity identification device provided in the embodiment of the present invention can execute the chemical entity identification method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0080] Embodiment 4

[0081] Figure 4 1 is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0082] like Figure 4As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0083] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0084] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a chemical entity recognition method.

[0085] In some embodiments, the chemical entity identification method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the chemical entity identification method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the chemical entity identification method in any other appropriate manner (e.g., by means of firmware).

[0086] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0087] The computer program for implementing the chemical entity identification method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or completely on a remote machine or server.

[0088] Embodiment 5

[0089] Embodiment 5 of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to execute a chemical entity identification method, the method comprising:

[0090] Receive at least one MSDS data to be identified of a chemical, and convert the MSDS data to be identified into MSDS text data to be identified in a target format; each of the MSDS text data to be identified includes multiple categories to be identified, and each category to be identified corresponds to a classification number;

[0091] Under any business processing mode, the classification number of the MSDS text data to be identified is identified to determine the business text data corresponding to the business processing mode; the business text data corresponding to the business processing mode includes text information of at least one class to be identified;

[0092] Inputting the business text data into an entity recognition model corresponding to the business processing mode to obtain a target business field corresponding to the business processing mode;

[0093] The task corresponding to the business processing mode is executed based on the target business field.

[0094] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0095] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0096] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0097] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0098] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0099] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A chemical entity recognition method, It is characterized in that include: Receive at least one MSDS data to be identified of a chemical, and convert the MSDS data to be identified into MSDS text data to be identified in a target format; each of the MSDS text data to be identified includes multiple categories to be identified, and each category to be identified corresponds to a classification number; Under any business processing mode, the classification number of the MSDS text data to be identified is identified to determine the business text data corresponding to the business processing mode; the business text data corresponding to the business processing mode includes text information of at least one class to be identified; Inputting the business text data into an entity recognition model corresponding to the business processing mode to obtain a target business field corresponding to the business processing mode; The task corresponding to the business processing mode is executed based on the target business field.

2. The method according to claim 1, It is characterized in that In the case where there are multiple MSDS data to be identified, the method further includes: Generate target text data based on the plurality of MSDS text data to be identified; Correspondingly, the identifying the classification number of the MSDS text data to be identified and determining the business text data corresponding to the business processing mode includes: The classification number of the target text data is identified to determine the business text data corresponding to the business processing mode.

3. The method according to claim 2, It is characterized in that The MSDS text data to be identified / the target text data includes a plurality of text pages; The step of identifying the classification number of the MSDS text data to be identified and determining the business text data corresponding to the business processing mode includes: For each of the text pages, identifying the classification number of the text page to obtain an identification result; If the recognition result includes multiple classification numbers, segmenting the text page to obtain new text pages; Repeat the above steps, and when the number of the classification number of the recognition result is one, determine the text data in the text page as the text data of the category to be recognized corresponding to the classification number; The business text data is determined based on the text data of at least one of the to-be-identified categories corresponding to the business model.

4. The method according to claim 1, It is characterized in that The step of converting the MSDS data to be identified into MSDS text data to be identified in a target format comprises: In the case that the MSDS data to be identified is in a picture format, text recognition is performed on the MSDS data to be identified to obtain the MSDS text data to be identified, and the MSDS text data to be identified is converted into a target format.

5. The method according to claim 4, It is characterized in that The method further comprises: Invalid text information in the target format MSDS text data to be identified is cleaned to obtain cleaned MSDS text data to be identified.

6. The method according to claim 1, It is characterized in that The business processing modes include chemical safety testing mode, storage management mode and transportation management mode; The executing the service corresponding to the service processing mode based on the target service field includes: If the business processing mode is a chemical safety detection mode, a prohibition and restriction control detection is performed on the target business field to obtain a detection result; If the business processing mode is a warehouse management mode, determining the storage area and storage conditions of the chemical based on the target business field; If the business processing mode is the transport management mode, a transport document is generated based on a preset transport document template and the target business fields.

7. The method according to claim 3, It is characterized in that The method further comprises: Perform feature extraction on the text data corresponding to each of the to-be-identified classes to obtain key fields of the to-be-identified MSDS text data; Generate display data based on the key fields of the MSDS text data to be identified, and display the display data on a Web display page; the Web display page includes at least one feature item and a query control, and each of the feature items includes the key fields of the MSDS text data to be identified; On the Web display page, in response to a selection operation on the feature item, determining a target feature item; In response to the triggering operation on the query control, jump to the key field display page corresponding to the target feature item.

8. A chemical entity recognition device, It is characterized in that include: An MSDS data receiving module is used to receive at least one MSDS data to be identified of a chemical, and convert the MSDS data to be identified into MSDS text data to be identified in a target format; each of the MSDS text data to be identified includes multiple categories to be identified, and each category to be identified corresponds to a classification number; A business text data determination module, used to identify the classification number of the MSDS text data to be identified in any business processing mode, and determine the business text data corresponding to the business processing mode; the business text data corresponding to the business processing mode includes text information of at least one class to be identified; A target business field identification module, used for inputting the business text data into an entity recognition model corresponding to the business processing mode to obtain a target business field corresponding to the business processing mode; A task execution module is used to execute the task corresponding to the business processing mode based on the target business field.

9. An electronic device, It is 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 executable 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 perform the chemical entity identification method according to any one of claims 1 to 7.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the chemical entity identification method according to any one of claims 1 to 7 when executed.

Images