Component classification and identification method, device, storage medium and electronic device

Abstract

The present application discloses a component classification and identification method, device, storage medium and electronic device, including: obtaining component text, wherein the component text includes component parameters recorded in the bill of materials, obtaining component types related to the component text according to the component text, calculating the sum of scores corresponding to the component types, and determining the component type corresponding to the component text according to the numerical value of the sum of scores. By obtaining the component type related to the component text, calculating the sum of scores corresponding to the component type, and determining the component type corresponding to the component text according to the sum, the component type corresponding to the component text can be accurately determined, thereby improving the accuracy of identification.

Description

Technical Field

[0001] The present application relates to the technical field of component classification and identification, and specifically to a component classification and identification method, device, storage medium and electronic device. Background Art

[0002] At present, the bill of materials generally includes the types and quantities of materials required to assemble or produce a product. As product functions continue to expand, the types of materials included in the product's bill of materials are increasing. However, there may be some useless information or wrong codes in the bill of materials, which makes it impossible to accurately identify the types of components in the bill of materials. Summary of the invention

[0003] In order to solve the above technical problems, the present application is proposed. The embodiments of the present application provide a component classification and identification method, device, storage medium and electronic device, thereby solving the problem of low component text recognition rate.

[0004] According to one aspect of the present application, a component classification and identification method is provided, including: obtaining a component text; wherein the component text includes the component parameters recorded in a bill of materials; according to the component text, obtaining a component type related to the component text; calculating the sum of scores corresponding to the component types; and determining the component type corresponding to the component text according to the numerical value of the sum of scores.

[0005] In one embodiment, the acquiring of the component type related to the component text according to the component text includes: performing feature recognition on the component text to obtain multiple attributes; and acquiring the component types corresponding to the multiple attributes according to the multiple attributes. By performing feature recognition on the component text and then acquiring the component type corresponding to the attribute, the component type can be accurately acquired.

[0006] In one embodiment, after acquiring the component types corresponding to the multiple attributes according to the multiple attributes, the component classification and identification method further includes: retaining the attributes related to the component types.

[0007] In one embodiment, the feature recognition of the component text to obtain multiple attributes includes: semantic analysis of words in the component text to obtain attributes corresponding to the words. The semantic analysis of words in the component text can accurately determine the attributes corresponding to the words.

[0008] In one embodiment, the number of the component types includes multiple types; wherein the determining the component type corresponding to the component text according to the numerical values ​​of the multiple fraction sums includes: determining the component type with the largest fraction sum value as the component type corresponding to the component text. The component type with the largest fraction sum data is determined as the component type corresponding to the component text, so that the component type corresponding to the component text can be accurately determined.

[0009] In one embodiment, calculating the sum of scores corresponding to the component types includes: obtaining an attribute related to the component text corresponding to the component type; wherein the attribute corresponds to a score; and calculating the sum of scores corresponding to the component types according to the scores corresponding to the attributes. By calculating the sum of scores corresponding to the component types, the component type corresponding to the component text is determined.

[0010] In one embodiment, the feature recognition of the component text to obtain multiple attributes includes: performing parameter recognition on the component text to obtain multiple parameter attributes; wherein the parameter recognition includes recognition of symbols or symbol combinations of the component text; and / or performing keyword recognition on the component text to obtain multiple keyword attributes; wherein the keyword recognition includes recognition of words or characters of the text in the bill of materials. By performing parameter recognition and / or keyword recognition on the component text, accurate parameter attributes and / or keyword attributes are determined.

[0011] In one embodiment, the obtaining of component text includes: extracting a text containing the component parameters from the bill of materials; and preprocessing the text to obtain the component text. By preprocessing the text, accurate component text is obtained.

[0012] In one embodiment, the preprocessing of the text to obtain the component text includes: performing word segmentation processing on the text to obtain a word segmentation text; wherein the word segmentation text is structured data; and correcting the word segmentation text according to a preset word library to obtain the component text. The word segmentation processing is performed on the text, so that the component text of the unstructured data is converted into the component text of the structured data.

[0013] In one embodiment, the preprocessing of the text to obtain the component text includes: performing encoding conversion on the text to obtain an encoded text; converting full-width characters in the encoded text into half-width characters to obtain a character text; and retaining matching text in the character text to obtain the component text; wherein the matching text is the cleaned text of the character text. By performing encoding conversion on the component text, converting it into half-width characters, and finally cleaning the character text, an accurate component text is obtained.

[0014] According to another aspect of the present application, a component classification and identification device is provided, characterized in that it includes: an acquisition module for acquiring component text; wherein the component text includes the component parameters recorded in the bill of materials; a type acquisition module for acquiring the component type related to the component text according to the component text; a calculation module for calculating the sum of scores corresponding to the component type; and a determination module for determining the component type corresponding to the component text according to the numerical value of the sum of scores.

[0015] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and the computer program is used to execute any of the above-mentioned component classification and identification methods.

[0016] According to another aspect of the present application, an electronic device is provided, comprising: a processor; a memory for storing instructions executable by the processor; and the processor for executing any of the above-mentioned component classification and identification methods.

[0017] The component classification and identification method, device, storage medium and electronic device provided by the present application include: obtaining component text, wherein the component text includes component parameters recorded in the bill of materials, obtaining component types related to the component text according to the component text, calculating the sum of scores corresponding to the component types, and determining the component type corresponding to the component text according to the numerical value of the sum of scores. By obtaining the component type related to the component text, calculating the sum of scores corresponding to the component type, and determining the component type corresponding to the component text according to the sum, the component type corresponding to the component text can be accurately determined, thereby improving the accuracy of identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0019] Figure 1 It is a flowchart of a component classification and identification method provided by an exemplary embodiment of the present application.

[0020] Figure 2 It is a schematic diagram of a process for obtaining component types provided by an exemplary embodiment of the present application.

[0021] Figure 3 It is a flowchart of a component classification and identification method provided by another exemplary embodiment of the present application.

[0022] Figure 4 It is a flowchart of a method for calculating the sum of scores provided by an exemplary embodiment of the present application.

[0023] Figure 5 It is a flowchart of a component text acquisition method provided by an exemplary embodiment of the present application.

[0024] Figure 6 It is a flowchart of a component text acquisition method provided by another exemplary embodiment of the present application.

[0025] Figure 7 It is a flowchart of a component text acquisition method provided by another exemplary embodiment of the present application.

[0026] Figure 8 It is a structural schematic diagram of a component classification and identification device provided by an exemplary embodiment of the present application.

[0027] Fig. 9 It is a structural schematic diagram of a component classification and identification device provided by another exemplary embodiment of the present application.

[0028] Fig.10 It is a structural diagram of an electronic device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0029] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0030] Figure 1FIG. 1 is a flow chart of a component classification and identification method provided by an exemplary embodiment of the present application. Figure 1 As shown, the component classification and identification method includes:

[0031] Step 110: Obtain component text, wherein the component text includes component parameters recorded in the bill of materials.

[0032] Get the component text containing component parameters, and determine the component type corresponding to the component text by identifying the component parameters. The bill of materials is a BOM file (Bill of Material), which is a file that describes the product structure in a data format and is a data file that can be recognized by a computer). The component text is the text in the bill of materials, and the data in the component text can describe the component parameters or type. The component text can include name, unit, value, etc.

[0033] Step 120: According to the component text, obtain the component type related to the component text.

[0034] The component type related to the component text is obtained through the component text. A preset database or model can be set, in which the corresponding relationship between the component text and the component type is stored, and the component text can be input into the model to obtain the corresponding component type. The related component type can be one or more.

[0035] Step 130: Calculate the total score corresponding to the component type.

[0036] When there are multiple component types, calculate the sum of the scores corresponding to each component type for subsequent comparison. A component type corresponds to multiple attributes, each attribute corresponds to a score, and the weights of the scores corresponding to multiple attributes are calculated, which is the sum of the scores of the component type.

[0037] Step 140: Determine the component type corresponding to the component text according to the numerical value of the total score.

[0038] The sum of the scores corresponding to each component type is calculated, and the component type corresponding to the component text is determined by determining the value thereof, thereby determining which component type the component text belongs to.

[0039] The component classification and identification method provided by the present application includes: obtaining component text, wherein the component text includes component parameters recorded in the bill of materials, obtaining component types related to the component text according to the component text, calculating the sum of scores corresponding to the component types, and determining the component type corresponding to the component text according to the numerical value of the sum of scores. By obtaining the component type related to the component text, calculating the sum of scores corresponding to the component type, and determining the component type corresponding to the component text according to the sum, the component type corresponding to the component text can be accurately determined, thereby improving the accuracy of identification.

[0040] Figure 2 FIG. 1 is a flow chart of obtaining component types provided by an exemplary embodiment of the present application. Figure 2 As shown, step 120 may include:

[0041] Step 121: Perform feature recognition on the component text to obtain multiple attributes.

[0042] Perform feature recognition on the component text to determine the attribute corresponding to each word in the component text. For example, if the word is red, then the word red is the color attribute. Or if it is 1Ω (ohm), then the attribute of the feature 1Ω is the resistance value.

[0043] Step 122: According to the multiple attributes, obtain component types corresponding to the multiple attributes.

[0044] Determine multiple attributes, determine which component types the multiple attributes can correspond to in a preset database or model, and obtain component types related to multiple attributes. For example, if there are color attributes, capacity attributes, and resistance attributes, electrolytic capacitors and adjustable resistors can be obtained.

[0045] In one embodiment, step 122 may be specifically implemented as: retaining attributes related to the component type.

[0046] Delete attributes that are not related to the component type. For example, a chip capacitor does not have a resistance attribute, so the feature corresponding to the resistance attribute should be deleted. Each component type only contains attributes corresponding to the necessary features of the type, and all attributes corresponding to non-essential features should be deleted.

[0047] In one embodiment, step 121 may be specifically implemented as: performing semantic analysis on words in the component text to obtain attributes corresponding to the words.

[0048] There are attributes corresponding to each word in the preset dictionary library, or you can select a dictionary at random and add some proper nouns corresponding to the component type in the dictionary, so you can perform semantic analysis on the words in the component text and get the attributes corresponding to the words. For example, 1Ω is the resistance value, and the resistance value is the attribute of the resistor.

[0049] Figure 3 FIG. 1 is a flow chart of a component classification and identification method provided by another exemplary embodiment of the present application. Figure 3 As shown, the number of component types includes multiple types, and step 140 may include:

[0050] Step 141: Determine that the component type with the largest total score value is the component type corresponding to the component text.

[0051] Select the component type with the largest total score as the component type corresponding to the component text. The largest total score indicates that the total attribute of this component type is the largest. For example, there are two attributes for chip capacitors: capacitance and brown. The score corresponding to capacitance is 5, and the score corresponding to brown is 1. The score corresponding to chip capacitors is 6. There are three attributes for electrolytic capacitors: capacitance, red, and length. The score for capacitance is 4, the score for red is 3, and the score for length is 4. The score corresponding to electrolytic capacitors is 11. 11 is greater than 6, indicating that the component type corresponding to the component text is an electrolytic capacitor.

[0052] Figure 4 FIG. 1 is a flow chart of a method for calculating the sum of scores provided by an exemplary embodiment of the present application. Figure 4 As shown, step 130 may include:

[0053] Step 131: Obtain attributes related to the component text and corresponding to the component type, wherein the attribute corresponds to a score.

[0054] Get the attributes related to the component text. Each attribute corresponds to a score. The related attributes are the necessary attributes of the component text. Delete other unnecessary attributes. For example, the necessary attribute of the chip capacitor is the capacitance, and the unnecessary attribute is the resistance.

[0055] Step 132: Calculate the total score corresponding to the component type based on the score corresponding to the attribute.

[0056] The total score corresponding to the component type can be calculated based on the scores corresponding to the attributes. For example, the chip capacitor has two attributes, capacitance and brown. The score corresponding to capacitance is 5, and the score corresponding to brown is 1, so the score corresponding to the chip capacitor is 6. The adjustable resistor has two attributes, resistance and red. The score corresponding to resistance is 3, and the score corresponding to red is 2, so the score corresponding to the adjustable resistor is 5.

[0057] In one embodiment, step 121 can be specifically implemented as follows: performing parameter identification on the component text to obtain multiple parameter attributes, wherein parameter identification includes identifying symbols or symbol combinations of the component text, and / or performing keyword identification on the component text to obtain multiple keyword attributes, wherein keyword identification includes recognizing words or characters in the text in the bill of materials.

[0058] Parameter recognition of component text, such as recognition of 1Ω (ohm) or 1F (farad). Or symbol recognition, such as recognition of the number 474. 474 is the symbol of the capacitance value. Or keyword recognition of component text, such as recognition of the word red for capacitor, the attribute corresponding to the feature is the color attribute. The best way is to perform parameter recognition and keyword recognition of component text.

[0059] Figure 5 FIG. 1 is a flow chart of a component text acquisition method provided by an exemplary embodiment of the present application. Figure 5 As shown, step 110 may include:

[0060] Step 111: Extract a text containing component parameters from the bill of materials.

[0061] There are many texts in the bill of materials. Extracting a text containing component parameters can identify the component type corresponding to the text. Or a text containing component parameters and models can more accurately determine the type of the text.

[0062] Step 112: Preprocess the text to obtain component text.

[0063] Preprocess the text and delete some meaningless words to obtain the processed component text. Meaningless words mean that the words are useless for identifying the component text type. For example, some space symbols, carriage return symbols or emoticons.

[0064] Figure 6 FIG. 1 is a flow chart of a component text acquisition method provided by another exemplary embodiment of the present application. Figure 6 As shown, step 112 may include:

[0065] Step 1121: perform word segmentation processing on the text to obtain word segmentation text, wherein the word segmentation text is structured data.

[0066] The extracted text is an unstructured data, which means that the data in the text is messy and cannot express any meaning. Therefore, the text is segmented to obtain a segmented text, that is, a structured data, and the separated words represent their unique meanings. Unstructured data is essentially all data outside of structured data. Among them, unstructured data has an internal structure, but it is not structured through a predefined data model or pattern. It may be text or non-text, and it may be artificial or machine-generated. Structured data is a field that stores length display data such as phone numbers, social security numbers, or zip codes. Even variable-length text strings like names are included in the record, which makes it easy to search.

[0067] Step 1122: Modify the segmented text according to the preset vocabulary to obtain the component text.

[0068] The segmented text is corrected according to the preset word library, for example, 1r can be corrected to 1Ω. Or some words after the segmentation process are typos, for example, rad needs to be corrected to red. After the words after the segmentation are corrected, the final component text is obtained.

[0069] Figure 7 FIG. 1 is a flow chart of a component text acquisition method provided by another exemplary embodiment of the present application. Figure 7 As shown, step 112 may include:

[0070] Step 1123: Convert the text to obtain encoded text.

[0071] The text can be converted into encoding, for example, the text in gb2312 (Chinese character encoding character set for information exchange, GB2312 encoding is suitable for information exchange between systems such as Chinese character processing and Chinese character communication) format can be converted into utf8 format (utf8_encode, a standard mechanism for Unicode to convert wide character values ​​into byte streams).

[0072] Step 1124: Convert the full-width characters in the encoded text into half-width characters to obtain character text.

[0073] Convert the full-width characters in the encoded text into half-width characters to avoid the text taking up too much space. Full-width characters take up two bytes, and half-width characters take up one byte.

[0074] Step 1125: retain the matching text in the character text to obtain the component text, wherein the matching text is the text after the character text is cleaned.

[0075] Retain the meaningful or semantic text in the character text, and delete the meaningless text, such as emoticons, tabs, or invisible characters, so as to obtain the cleaned text of the character text, that is, match the text, and delete the meaningless text to ensure the accuracy of determining the final component type. Among them, cleaning the text means deleting the meaningless text.

[0076] Figure 8 is a schematic diagram of the structure of a component classification and identification device provided by an exemplary embodiment of the present application. Figure 8 As shown, the component classification and identification device 20 includes: an acquisition module 201, used to acquire component text, wherein the component text includes component parameters recorded in the bill of materials, a type acquisition module 202, used to acquire the component type related to the component text according to the component text, a calculation module 203, used to calculate the sum of scores corresponding to the component types, and a determination module 204, used to determine the component type corresponding to the component text according to the numerical value of the sum of scores.

[0077] The component classification and identification device provided by the present application obtains the component text through the acquisition module 201, wherein the component text includes the component parameters recorded in the bill of materials, the type acquisition module 202 obtains the component type related to the component text according to the component text, the calculation module 203 calculates the sum of the scores corresponding to the component type, and the determination module 204 determines the component type corresponding to the component text according to the numerical value of the sum of the scores. By obtaining the component type related to the component text, calculating the sum of the scores corresponding to the component type, and determining the component type corresponding to the component text according to the sum, the component type corresponding to the component text can be accurately determined, thereby improving the accuracy of recognition.

[0078] Fig. 9 FIG. 1 is a schematic diagram of a component classification and identification device provided by another exemplary embodiment of the present application. Fig. 9 As shown, the type acquisition module 202 may include:

[0079] The attribute acquisition unit 2021 is used to perform feature recognition on the component text to obtain multiple attributes; the component type corresponding unit 2022 is used to obtain the component types corresponding to the multiple attributes based on the multiple attributes.

[0080] In one embodiment, if Fig. 9 As shown, the component classification and identification device 20 may further include: an attribute retaining unit 2023, which is used to retain attributes related to the component type.

[0081] In one embodiment, the attribute acquisition unit 2021 may be specifically configured to: perform semantic analysis on words in the component text to obtain attributes corresponding to the words.

[0082] In one embodiment, if Fig. 9 As shown, the number of component types includes multiple ones, and the determination module 204 may include: a maximum score unit 2041, which is used to determine that the component type with the largest total score value is the component type corresponding to the component text.

[0083] In one embodiment, if Fig. 9 As shown, the calculation module 203 may include:

[0084] The correlation unit 2031 is used to obtain the attributes related to the component text corresponding to the component type, wherein the attribute corresponds to a score; the score sum calculation unit 2032 is used to calculate the score sum corresponding to the component type according to the score corresponding to the attribute.

[0085] In one embodiment, the attribute acquisition unit 2021 can be specifically configured to: perform parameter identification on the component text to obtain multiple parameter attributes, wherein parameter identification includes identifying symbols or symbol combinations of the component text, and / or perform keyword identification on the component text to obtain multiple keyword attributes, wherein keyword identification includes word or character recognition of the text in the bill of materials.

[0086] In one embodiment, if Fig. 9 As shown, the acquisition module 201 may include:

[0087] The extraction unit 2011 is used to extract a text containing component parameters from the bill of materials; the processing unit 2012 is used to pre-process the text to obtain the component text.

[0088] In one embodiment, the processing unit 2012 may be specifically configured to: perform word segmentation processing on the text to obtain a word segmentation text, wherein the word segmentation text is structured data, and modify the word segmentation text according to a preset word library to obtain a component text.

[0089] In one embodiment, the processing unit 2012 can be specifically configured to: perform encoding conversion on the text to obtain encoded text, convert the full-width characters in the encoded text into half-width characters to obtain character text, retain the matching text in the character text to obtain component text, wherein the matching text is the text after the character text is cleaned.

[0090] Below, reference Fig.10 The electronic device according to the embodiment of the present application is described. The electronic device may be any one or both of the first device and the second device, or a stand-alone device independent of them, and the stand-alone device may communicate with the first device and the second device to receive the collected input signal from them.

[0091] Fig.10 A block diagram of an electronic device according to an embodiment of the present application is illustrated.

[0092] like Fig.10 As shown, the electronic device 10 includes one or more processors 11 and a memory 12 .

[0093] The processor 11 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0094] The memory 12 may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may run the program instructions to implement the component classification and identification methods of the various embodiments of the present application described above and / or other desired functions. Various contents such as input signals, signal components, noise components, etc. may also be stored in the computer-readable storage medium.

[0095] In one example, the electronic device 10 may further include: an input device 13 and an output device 14, and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0096] When the electronic device is a stand-alone device, the input device 13 may be a communication network connector, which is used to receive the collected input signals from the first device and the second device.

[0097] In addition, the input device 13 may also include, for example, a keyboard, a mouse, and the like.

[0098] The output device 14 can output various information to the outside, including the determined distance information, direction information, etc. The output device 14 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0099] Of course, to simplify, Fig.10 Only some of the components related to the present application in the electronic device 10 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device 10 may also include any other appropriate components.

[0100] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0101] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable 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 above.

[0102] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A component classification and identification method, characterized in that: include: Obtain component text; wherein the component text includes component parameters recorded in the bill of materials; According to the component text, obtaining a component type related to the component text; Calculating the sum of scores corresponding to the component type; and Determining the component type corresponding to the component text according to the numerical value of the sum of the scores; Wherein, obtaining the component type related to the component text according to the component text includes: Performing feature recognition on the component text to obtain multiple attributes; and According to the multiple attributes, obtaining component types corresponding to the multiple attributes; retaining properties associated with the component type; The component text is subjected to feature recognition to obtain multiple attributes, including: Performing semantic analysis on words in the component text to obtain attributes corresponding to the words; The number of the component types includes multiple ones; wherein determining the component type corresponding to the component text according to the numerical value of the sum of the scores includes: Determine that the component type with the largest sum of scores is the component type corresponding to the component text; Calculating the sum of scores corresponding to the component types includes: Obtaining an attribute related to the component text and corresponding to the component type; wherein the attribute corresponds to a score; and According to the scores corresponding to the attributes, a total score corresponding to the component type is calculated.

2. The component classification and identification method according to claim 1, characterized in that: The feature recognition of the component text to obtain multiple attributes includes: Performing parameter identification on the component text to obtain a plurality of parameter attributes; wherein the parameter identification includes identifying a symbol or a combination of symbols of the component text; and / or Keyword recognition is performed on the component text to obtain a plurality of keyword attributes; wherein the keyword recognition includes word or character recognition of the text in the bill of materials.

3. The component classification and identification method according to claim 1, characterized in that: The obtaining of component text includes: extracting a text containing the component parameters from the bill of materials; and The text is preprocessed to obtain the component text.

4. The component classification and identification method according to claim 3, characterized in that: The preprocessing of the text to obtain the component text includes: Performing word segmentation processing on the text to obtain a word segmentation text; wherein the word segmentation text is structured data; and The segmented text is modified according to a preset word library to obtain the component text.

5. The component classification and identification method according to claim 3, characterized in that: The preprocessing of the text to obtain the component text includes: Performing encoding conversion on the text to obtain an encoded text; Converting the full-width characters in the encoded text into half-width characters to obtain character text; The matching text in the character text is retained to obtain the component text; wherein the matching text is the text after the character text is cleaned.

6. A component classification and identification device, characterized in that: include: An acquisition module, used to acquire component text; wherein the component text includes component parameters recorded in the bill of materials; A type acquisition module, used for acquiring a component type related to the component text according to the component text; A calculation module, used to calculate the sum of scores corresponding to the component types; and A determination module, used for determining the component type corresponding to the component text according to the numerical value of the sum of the scores; Wherein, obtaining the component type related to the component text according to the component text includes: Performing feature recognition on the component text to obtain multiple attributes; and According to the multiple attributes, obtaining component types corresponding to the multiple attributes; retaining properties associated with the component type; The component text is subjected to feature recognition to obtain multiple attributes, including: Performing semantic analysis on words in the component text to obtain attributes corresponding to the words; The number of the component types includes multiple ones; wherein determining the component type corresponding to the component text according to the numerical value of the sum of the scores includes: Determine that the component type with the largest sum of scores is the component type corresponding to the component text; Calculating the sum of scores corresponding to the component types includes: Obtaining an attribute related to the component text and corresponding to the component type; wherein the attribute corresponds to a score; and According to the scores corresponding to the attributes, a total score corresponding to the component type is calculated.

7. A computer-readable storage medium storing a computer program, wherein the computer program is used to execute the component classification and identification method according to any one of claims 1 to 5.

8. An electronic device, comprising: processor; a memory for storing instructions executable by the processor; The processor is used to execute the component classification and identification method described in any one of claims 1 to 5.

Images