Nuclear power spare part information management method, electronic equipment and computer program product

Abstract

The invention provides a nuclear power spare part information management method, electronic equipment and a computer program product. Relates to the technical field of data processing. In view of the problem of low efficiency of confirming the corresponding relation between spare part codes and function positions, the nuclear power spare part information management method provided by the invention comprises the following steps: based on an obtained design drawing file, determining equipment information corresponding to function position information of a nuclear power plant in the design drawing file; based on spare part information of a spare part list associated with the function position information, calculating the similarity between the spare part information and the equipment information; when the similarity is not smaller than a preset threshold value, establishing a first mapping relation between the parent spare parts in the spare part list and the function position information; on the basis of a spare part recognition model, spare part information of potential child spare parts in the spare part list is recognized, and target child spare parts corresponding to the parent spare parts are determined; and establishing a second mapping relationship between the parent spare part and the target child spare part. Through the embodiment of the invention, the confirmation efficiency and quality of the corresponding relation between the spare part and the function position can be improved.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and particularly to a nuclear power spare part information management method, an electronic device, and a computer program product. Background Art

[0002] The functional location information of nuclear power equipment is a prerequisite for the smooth development of equipment management and maintenance management work in nuclear power plants. The quality of the functional location information directly affects the on-site work process in nuclear power plants. In order to do a good job in the basic establishment and maintenance of functional location information in the system, each nuclear power plant has formulated functional location information management methods for each stage. After the functional location information is completed, the corresponding relationship between the spare part code and the functional location is supplemented by the maintenance users or equipment management users of the nuclear power plant.

[0003] An effective corresponding relationship between the spare part code and the functional location is a prerequisite for carrying out many spare part management tasks, such as setting spare part inventory parameters, grading the importance of spare parts, and identifying nuclear supervision spare parts. Currently, maintenance users or equipment management users confirm the corresponding relationship between the spare part code and the functional location based on manual experience, with low efficiency and it is difficult to ensure the quality of the corresponding relationship between spare parts and functional locations. Summary of the Invention

[0004] According to various embodiments of the present application, there is provided a nuclear power spare part information management method, system, and electronic device, which can improve the confirmation efficiency and quality of the corresponding relationship between spare parts and functional locations.

[0005] In a first aspect, the present application provides a nuclear power spare part information management method, which includes: determining, based on the obtained design drawing file, the equipment information corresponding to the functional location information of the nuclear power plant in the design drawing file; the design drawing file includes functional location information; calculating the similarity between the spare part information of the spare part list associated with the functional location information and the equipment information; in the case where the similarity is not less than a preset threshold, establishing a first mapping relationship between the parent spare part in the spare part list and the functional location information; identifying, based on the spare part identification model, the spare part information of potential sub-spare parts in the spare part list, and determining the target sub-spare parts corresponding to the parent spare part; the potential sub-spare parts are spare parts other than the parent spare part in the spare part list; establishing a second mapping relationship between the parent spare part and the target sub-spare parts; wherein, the spare part identification model includes a first identification model and a second identification model; the first identification model is trained based on spare part sample information and spare part category labels, and the spare part category labels include dedicated sub-spare part labels and general sub-spare part labels; the second identification model is determined based on the spare part description information of the sub-spare part list and the spare part description information of the potential sub-spare parts; the target sub-spare parts include dedicated sub-spare parts and equipment general sub-spare parts.

[0006] In the above - mentioned manner, based on the functional location information of nuclear power equipment, the equipment information in the design drawing files is quickly identified, reducing the time for manual searching and comparison, significantly improving the efficiency of equipment information extraction, and reducing the risk of human errors; based on the spare - part list corresponding to the functional location information, the similarity between the spare - part information and the equipment information is calculated, and the spare parts in the spare - part list that match the equipment information are automatically identified, thereby determining the coding information of the spare parts corresponding to the functional location information. Moreover, through the further identification of potential sub - spare parts, the corresponding relationship between the functional location and the spare - part coding of the parent spare part, as well as the corresponding relationship between the parent spare part and the sub - spare part, can be quickly improved, enhancing the efficiency and accuracy of calculating the corresponding relationship between the spare - part coding and the functional location, reducing the error rate of spare - part selection and the subsequent mis - use rate; by quickly determining the corresponding relationship between the functional location information and the spare - part coding, as well as the corresponding relationship between the parent spare part and the sub - spare part, the spare - part coding system is improved, significantly enhancing the efficiency of spare - part coding association, reducing the workload of manual association, improving the efficiency and accuracy of nuclear power equipment spare - part management, and enhancing the safety and reliability of equipment management; it has strong usability and practicality.

[0007] In a second aspect, the present application provides a nuclear power spare - part information management device, including:

[0008] An acquisition unit, configured to determine, based on the acquired design drawing files, the equipment information corresponding to the functional location information of a nuclear power plant in the design drawing files; the design drawing files include the functional location information;

[0009] A calculation unit, configured to calculate the similarity between the spare - part information and the equipment information based on the spare - part information of the spare - part list associated with the functional location information;

[0010] A first matching unit, configured to establish a first mapping relationship between the parent spare part in the spare - part list and the functional location information when the similarity is not less than a preset threshold;

[0011] An identification unit, configured to identify the spare - part information of potential sub - spare parts in the spare - part list based on a spare - part identification model, and determine the target sub - spare parts corresponding to the parent spare part; the potential sub - spare parts are the spare parts in the spare - part list other than the parent spare part;

[0012] A second matching unit, configured to establish a second mapping relationship between the parent spare part and the target sub - spare parts; wherein, the spare - part identification model includes a first identification model and a second identification model; the first identification model is trained based on spare - part sample information and spare - part category labels, and the spare - part category labels include dedicated sub - spare - part labels and general sub - spare - part labels; the second identification model is determined based on the spare - part description information of the sub - spare - part list and the spare - part description information of the potential sub - spare parts; the target sub - spare parts include dedicated sub - spare parts and equipment general sub - spare parts.

[0013] In a third aspect, the present application provides an electronic device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the method described in any one of the first aspects is implemented.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described in any one of the first aspects is implemented.

[0015] In a fifth aspect, the present application provides a computer program product. When the computer program product runs on a device, the device is enabled to execute the method described in any one of the above first aspects.

[0016] It can be understood that for the beneficial effects of the above second aspect to fifth aspect, reference can be made to the relevant descriptions in the above first aspect, and details are not elaborated herein. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 It is a schematic diagram of the architecture of each module of the system provided by the embodiment of the present application;

[0019] Figure 2 It is a schematic diagram of the relationship between the functional location BOM and the spare part parent-child BOM provided by the embodiment of the present application;

[0020] Figure 3 It is a schematic diagram of the implementation process of the nuclear power spare part information management method provided by the embodiment of the present application;

[0021] Figure 4 It is a schematic diagram of the functional location information in the design drawing file provided by the embodiment of the present application;

[0022] Figure 5 It is a schematic diagram of obtaining a spare part requisition list based on functional location information provided by the embodiment of the present application;

[0023] Figure 6 It is a schematic diagram of the internal annotation information including functional location information provided by the embodiment of the present application;

[0024] Figure 7 It is a schematic diagram of the proportion distribution of the parent spare part keywords of similar equipment types provided by the embodiment of the present application;

[0025] Figure 8 Schematic diagram of the process for calculating the parent-child BOM provided by the embodiments of the present application;

[0026] Figure 9 Schematic diagram of the classification of material categories provided by the embodiments of the present application;

[0027] Figure 10 Schematic diagram of the drawing information of the spare part code provided by the embodiments of the present application;

[0028] Figure 11 Schematic diagram of the implementation process for identifying general sub-spare parts provided by the embodiments of the present application;

[0029] Figure 12 Schematic diagram of the keyword library of equipment types provided by the embodiments of the present application;

[0030] Figure 13 Schematic diagram of the display interface of the system architecture provided by the embodiments of the present application;

[0031] Figure 14 Schematic diagram of the structure of the nuclear power spare part information management device provided by the embodiments of the present application;

[0032] Figure 15 Schematic diagram of the structure of the electronic device provided by the embodiments of the present application. Detailed implementation manners

[0033] Next, embodiments of the technical solutions of the present application will be described in detail with reference to the accompanying drawings. The following embodiments are only used to illustrate the technical solutions of the present application more clearly, so they are only examples and cannot be used to limit the protection scope of the present application.

[0034] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above accompanying drawing descriptions are intended to cover non-exclusive inclusion.

[0035] In the description of the embodiments of the present application, technical terms such as "first" and "second" are only used to distinguish different objects and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity, specific order or primary-secondary relationship of the indicated technical features. In the description of the embodiments of the present application, "a plurality" means more than two unless otherwise specifically defined.

[0036] References to "embodiments" in this specification mean that specific features, structures, or characteristics described in connection with the embodiments can be included in at least one embodiment of the present application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0037] In the description of the embodiments of the present application, the term "and / or" is merely a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this text generally represents an "or" relationship between the associated objects before and after.

[0038] Currently, after the functional location information of a nuclear power plant is established, the corresponding relationship between spare part codes and functional locations is supplemented by the maintenance users or equipment management users of the nuclear power plant. For example, maintenance personnel or equipment management personnel determine the parent spare parts corresponding to the functional location by looking up the design drawing documents of the functional location and combining the spare part model information in the spare part database; based on the spare part requisition information under the functional location and the experience of the user, determine the sub-spare parts under the parent spare parts. When there is no spare part model information corresponding to the functional location in the design drawings of the nuclear power plant, the user will determine the parent spare parts corresponding to the functional location, and the sub-spare parts corresponding to the parent spare parts, based on the historical requisition records of the functional location, or based on the model information of the on-site installed equipment and the experience of the user. However, improving item by item based on manual experience has low efficiency and it is difficult to review the quality of the improvement.

[0039] To address the above technical problems, the present application provides a method for managing nuclear power spare part information. By identifying the functional location information and equipment information on the design drawing documents, calculating the information matching degree, and automatically determining the parent spare parts corresponding to the functional location information; identifying other spare parts except the parent spare parts through a spare part identification model, classifying the spare parts, and determining the sub-spare parts corresponding to the parent spare parts; thereby efficiently establishing the corresponding relationship between the functional location information and the parent spare part codes, and the corresponding relationship between the parent spare part codes and the sub-spare part codes, improving the reliability and perfection of the association relationship between the functional location and the spare parts.

[0040] The following introduces the implementation process of the method for managing nuclear power spare part information provided by the present application through embodiments.

[0041] Please refer to Figure 1 , Figure 1 which is a schematic diagram of the architecture of each module of the system provided by the embodiments of the present application; as Figure 1As shown in the figure, the system includes a calculation module 10 for the correspondence between spare parts and functional locations and a basic business data acquisition module 20. Among them, the calculation module 10 for the correspondence between spare parts and functional locations may include a basic information and parameter acquisition unit, a functional location BOM calculation unit, a spare parts parent-child BOM calculation unit, and a calculation result display unit. The basic business data acquisition module 20 may include a group plant material master data acquisition unit, a spare parts related document drawing acquisition unit, a functional location acquisition unit, a functional location BOM acquisition unit, a spare parts parent-child BOM acquisition unit, a spare parts purchase order acquisition unit, a maintenance work order acquisition unit, and a spare parts requisition note acquisition unit.

[0042] Exemplarily, the calculation module 10 for the correspondence between spare parts and functional locations is used to calculate the correspondence between functional locations and spare parts. In the field of supply chain management, this correspondence includes a functional location BOM and a spare parts parent-child BOM. Among them, the Bill Of Material (BOM) refers to the material structure list in the database. The functional location BOM refers to the correspondence between the functional location information of nuclear power plant equipment and the parent spare parts, which can be expressed as the connection relationship (or mapping relationship) between spare part codes (parent spare part codes). The spare parts parent-child BOM refers to the correspondence between the parent spare parts and the child spare parts, which can be expressed as the connection relationship between the spare part parent code and the spare part child code. As Figure 2 shown in the figure, the functional location BOM indicates the correspondence between the functional location and the spare part codes of the parent spare parts, and the spare parts parent-child BOM indicates the correspondence between the spare part codes of the parent spare parts and the spare part codes of the child spare parts (such as child spare part A and child spare part B).

[0043] Exemplarily, each unit of the basic business data acquisition module 20 can acquire spare parts related information. For example, the group plant material master data acquisition unit can acquire information such as spare part codes, material descriptions, models, manufacturers, quality assurance levels, spare part classifications, and internal annotations. The spare parts related document drawing acquisition unit can acquire the document drawing files corresponding to the functional locations and equipment, and thus acquire information such as the corresponding equipment descriptions, equipment models, and equipment manufacturers. The functional location acquisition unit can acquire all the functional location information of the nuclear power plant. The functional location BOM acquisition unit can acquire information on all the functional locations of the nuclear power plant and the corresponding spare part codes (parent codes). The spare parts parent-child BOM acquisition unit can acquire information on all the spare part parent codes and child codes of the nuclear power plant. The spare parts purchase order acquisition unit can acquire information such as the purchase unit price of the spare parts. The maintenance unit acquisition unit and the spare parts requisition note acquisition unit can acquire information such as the spare parts requisition data of the spare parts under the corresponding work orders (functional locations).

[0044] Based on the above system architecture, the following further introduces the specific implementation process of the nuclear power spare parts information management method through an embodiment.

[0045] Please refer to Figure 3, a schematic diagram of the implementation process of the nuclear power spare part information management method provided by the embodiments of the present application; as Figure 3 shown, the nuclear power spare part information management method may include the following steps:

[0046] S301, based on the obtained design drawing file, determine the equipment information corresponding to the functional location information of the nuclear power plant in the design drawing file; the design drawing file includes the functional location information.

[0047] In some embodiments, based on Figure 1 the spare part-related document drawing acquisition unit shown in Figure 4 acquire the design drawing file of the nuclear power plant; the design drawing file includes the functional location information set in the nuclear power plant, such as

[0048] the part marked by the dashed box in the design drawing file shown in

[0049] Exemplarily, the functional location information of the nuclear power plant is set according to the functional location coding specification, and the functional location coding rule can be expressed as follows: the total length of the functional location coding is set to 12 bits; the first bit is the nuclear power plant, for example, D, Y, H respectively represent different nuclear power plants; the second bit is the unit, for example, 1, 2, 3, 4 are used to represent the 1st, 2nd, 3rd, and 4th units; the third to sixth bits are the system name, for example, RCP is the reactor coolant system, APG is the steam generator blowdown system, CTE is the circulating water treatment system. If the number of digits of the system name is less than four, a dash is filled in the last digit, that is, RCP-; the seventh to tenth bits are the equipment serial number, for example, 001, 002, 003, etc. If the equipment serial number is less than four, a dash is filled in the last digit, that is, 001-; the eleventh to twelfth bits are the equipment type, for example, PO is the pump, MP is the pressure measurement, VA is the air valve. For example, when the functional location coding is D1RCP-001-PO, it represents the 001st pump (usually called the reactor main pump) of the reactor coolant system of Unit 1 of Power Plant D. Figure 3 As shown in (a) in Figure 3 "YAPG004MD" represents the elevation measurement equipment (usually refers to the liquid level transmitter) of the 004th serial number of the APG system of Unit 3 / 4 (in some drawings, X represents Unit 1 / 2, and Y represents Unit 3 / 4); as

[0050] Exemplarily, based on the functional location information in the design drawing file, determine the device information corresponding to the functional location information; the device information may include device description information, device model information, and device manufacturer information.

[0051] In some application scenarios, due to the design drawing files of nuclear power plants corresponding to different systems or different functional location information, there are certain differences in the content of the design drawing files, that is, the design drawing files may only include partial device information. For example, Figure 3 as shown in (a) of [reference], based on the functional location information, the device manufacturer information and device model information corresponding to the functional location information can be obtained, but there is no device description information (such as including device manufacturer information "ROSE***" and device model information "3051CD2A22A1JB4M6***"); Figure 3 as shown in (b) of [reference], based on the functional location information in the design drawing file, the device description information and device model information corresponding to the functional location information can be obtained, but there is no device manufacturer information (such as including device description information "pressure gauge" and device model information "Y-100-*"); Figure 3 as shown in (c) of [reference], there is no device description information, device model information, and device manufacturer information in the design drawing file.

[0052] Among them, based on the functional location information, obtain the corresponding device information in the design drawing file, and the obtained device information can be recorded in the set R. For example, r1 is the device description information, r2 is the device model information, and r3 is the device manufacturer information; if the set R of device information = {r1, r2, r3}. If there is no corresponding device information in the design drawing file, then record this item as NA; Figure 3 in the design drawing file shown in (b) of [reference], taking the functional location information XAPD007LP as an example, the set R of the device information corresponding to the functional location information is {pressure gauge, Y-100-B, NA}.

[0053] S302. Calculate the similarity between the spare part information and the device information based on the spare part information of the spare part list associated with the functional location information.

[0054] In some embodiments, based on Figure 1The maintenance work order acquisition unit and spare part requisition form acquisition unit shown in the figure can acquire the spare part list associated with the functional location information and the spare part information of each spare part in the spare part list. The spare part list associated with the functional location information may include all spare part requisition lists corresponding to the functional location information and the spare part list whose internal annotation of the spare part code contains the functional location information. The spare part information of the spare part list includes information such as spare part code, spare part description, spare part model, and the manufacturer of the spare part. Since all spare part requisition lists corresponding to the functional location information and the spare part list whose internal annotation of the spare part code contains the functional location information are information directly related to the functional location information, the parent spare part corresponding to the functional location information can be matched with a relatively high probability.

[0055] Exemplarily, based on the spare part information of the spare part list and the equipment information (i.e., the information in set R), the similarity of each spare part in the spare part list is calculated. Among them, when calculating the similarity between the spare part information of each spare part and set R, various text similarity calculation methods can be used to calculate the similarity; for example, the cosine similarity calculation method is used for calculation. The spare part information of each spare part and the equipment information of set R are respectively converted into multi-dimensional vectors, and the direction of the two multi-dimensional vectors is calculated through the cosine similarity formula, and the similarity of the two multi-dimensional vectors is determined based on the direction.

[0056] S303, in the case where the similarity is not less than a preset threshold, establish a first mapping relationship between the parent spare part in the spare part list and the functional location information.

[0057] In some embodiments, in the case where the similarity is not less than a preset threshold, it is determined that the spare part in the spare part list whose similarity is not less than the threshold is the parent spare part corresponding to the functional location information; based on the spare part code of the parent spare part, establish a first mapping relationship between the parent spare part and the functional location information.

[0058] In some embodiments, calculating the similarity between the spare part information and the equipment information based on the spare part information of the spare part list associated with the functional location information includes:

[0059] Based on the first spare part information of the spare part list in the first database, calculate the first similarity between the first spare part information and the equipment information. In the case where the first similarity is not less than a preset first threshold, establish a first mapping relationship between the first parent spare part and the functional location information. Among them, the spare part list in the first database includes all spare part requisition lists under the functional location information and the spare part list whose internal annotation of the spare part code contains the functional location information; the spare part list in the first database includes the first parent spare part; the first spare part information includes the spare part code of the first parent spare part; the threshold includes the first threshold.

[0060] Exemplarily, based on the spare part requisition data corresponding to the functional location, a spare part requisition list can be obtained. As Figure 5 shown, obtain historical maintenance work orders based on functional location information, obtain the material requisition numbers of spare parts based on the historical maintenance work orders, and obtain the spare part requisition list based on the material requisition numbers; for example, based on the historical maintenance work orders under the functional location information, determine the material requisition orders associated with the functional location information based on the material requisition numbers of the spare parts attached to the historical maintenance work orders, calculate the spare part requisition list based on the material requisition order information, and establish a requisitioned spare part list.

[0061] Exemplarily, during the main data coding or main data modification of spare parts, the installation and usage information of the spare parts will be noted in the internal annotation information of the spare parts. As Figure 6 shown, the functional location information is included in the internal annotation information of the spare parts. Thus, based on the functional location information, obtain the spare part list whose internal annotation contains the functional location information, and establish an internal annotation spare part list.

[0062] Correspondingly, establish a first database based on the spare part requisition list and the internal annotation spare part list, and calculate the first similarity with the equipment information based on the spare part information of each spare part in the first database.

[0063] In some embodiments, the first spare part information includes spare part description information, spare part model information, and spare part manufacturer information; calculating the first similarity between the first spare part information and the equipment information based on the first spare part information in the spare part list of the first database includes:

[0064] Vectorize the spare part description information, spare part model information, spare part manufacturer information, and equipment information to obtain text vectors; based on the text vectors and the cosine similarity algorithm, calculate the first cosine similarity values of the spare part description information, spare part model information, and spare part manufacturer information with the equipment information respectively; calculate the first similarity based on the first weight values and the first cosine similarity values corresponding to the spare part description information, spare part model information, and spare part manufacturer information respectively.

[0065] Exemplarily, vectorize the spare part description information, spare part model information, spare part manufacturer information, and equipment information to obtain multi-dimensional text vectors.

[0066] For example, the first database contains 3 spare parts, and their basic information is shown in Table 1. Calculate the similarity with the equipment information of the set {pressure gauge, Y-100-B, NA}. Based on the cosine similarity formula, such as formula (1), calculate the cosine similarity between the spare part information in Table 1 and the equipment information.

[0067]

[0068] Among them, A is the spare part information in the first database, and B is the equipment information in set R.

[0069] As shown in Table 1, the spare part description information with the code 1001 is "pressure gauge", the spare part model is "Y-100-B0-2.5Mpa", and the spare part manufacturer is "A"; the equipment description information in the set is "pressure gauge", the equipment model information is "Y-100-B", and the equipment manufacturer information is "NA".

[0070] Table 1

[0071] Spare part code Spare part description information Spare part model information Spare part manufacturer information 1001 Pressure gauge Y-100-B 0-2.5Mpa A 1002 Bolt M12*100 B 1003 Plug 1 / 2GB / T 3289.31-1982 C

[0072] First, vectorize the text information, and use formula (1) to calculate the cosine similarity value. Then, the cosine similarities corresponding to the spare part description information and the spare part model information of the spare part code 1001 are 1.0 and 0.579 respectively. Since the equipment manufacturer information in the set is empty, for the empty information in the set, the similarity value can be set to the configuration value k1. The similarity values corresponding to the spare part description information, the spare part model information, and the spare part manufacturer information are set to λ1, λ2, and λ3 respectively, and use formula (2) to calculate the comprehensive similarity value of the spare part, that is, the first similarity:

[0073]

[0074] Among them, ω1, ω2, and ω3 are the weight coefficients of different types of similarities. Usually, the ω value can be set to different grade values; for example, set to 0.5 or 1, a total of two grades; when the higher the validity of the equipment information and the spare part information associated with the function position information in the design drawing file, the greater the value of the corresponding weight coefficient.

[0075] For example, it can be set as follows. For the equipment description information, if it belongs to the standard equipment description information (for example, "pressure gauge" belongs to the standard equipment description information, and "pressure measuring table" belongs to the non-standard equipment description information), then ω1 is 1, and if it does not belong to the standard equipment description information, then ω1 is 0.5. For the spare part model information, if the spare part model information is complete (for each category of spare parts, the average value of the number of characters of the spare part model can be calculated. If the number of characters of the spare part model information is greater than or equal to the average value, then the spare part model information is complete), then ω2 is 1, otherwise ω2 is 0.5; for the spare part manufacturer information, if the spare part manufacturer information is complete manufacturer information, then ω3 is 1, and if the spare part manufacturer information is an abbreviation, then ω3 is 0.5.

[0076] Taking the data in Table 1 as an example, when the similarity configuration value k1 for the empty set R is set to 0.5 and the similarity weight ω1 is set to 0.5, the comprehensive similarity value p1 of the spare part code 1001 is 0.73, and the calculation method is as follows:

[0077] Based on formula (1), the cosine similarity between "pressure gauge" and "pressure gauge" is 1, and the cosine similarity between "Y-100-B 0-2.5Mpa" and "Y-100-B" is 0.579. Similarly, based on formula (2), the comprehensive similarity of spare part code 1002 can be calculated to be 0.33, and the comprehensive similarity of spare part code 1003 is 0.1.

[0078] By sorting the comprehensive similarity values of spare part codes 1001, 1002, and 1003, the comprehensive similarity value of code 1001 is the largest. Therefore, the comprehensive similarity value of spare part code 1001 is compared with the preset first threshold item. If the first threshold θ1 is set to 0.7, since the relationship p1≥θ1 is satisfied (comparing the sizes of 0.73 and 0.7, meeting the requirement that the comprehensive similarity value is greater than or equal to the threshold), then spare part code 1001 is the spare part code (parent spare part) for this functional location.

[0079] In addition, if the threshold θ1 is set to 0.75, since the relationship p1≥θ1 is not satisfied, the spare part code (parent spare part) for this functional location cannot be obtained through the above method and further calculation is required.

[0080] In some embodiments, after calculating the first similarity between the first spare part information and the equipment information, the method further includes:

[0081] In the case where the first similarity is less than the first threshold, based on the second spare part information in the spare part list of the second database, calculate the second similarity between the second spare part information and the equipment information; in the case where the second similarity is not less than the preset second threshold, establish a first mapping relationship between the second parent spare part and the functional location information; wherein, the spare part list of the second database includes all the issued spare part lists associated with the target equipment class corresponding to the functional location information and the spare part list whose internal annotation of the spare part code contains the target equipment class; the spare part list of the second database includes the second parent spare part; the second spare part information includes the spare part code of the second parent spare part; the threshold includes the second threshold, and the second threshold is greater than the first threshold.

[0082] Exemplarily, in the case where the first similarity is less than the first threshold, if it is determined that there is no parent spare part in the first database that matches the functional location information, then continue to construct the second database, and based on the spare part list of the second database, further calculate the parent spare part that matches the functional location information.

[0083] Among them, the target equipment class associated with the functional location information can be an equipment class similar to or of the same type as the functional location information; for example Figure 3The XAPD007LP functional location information shown in (b) of the figure, and the device category similar to this functional location information is "LP", that is, in-situ pressure measurement (pressure gauge); by obtaining all spare part requisition lists under this device category (such as LP), and the spare part lists whose internal annotations of spare part codes contain this device category (LP), a second database is constructed. This second database can contain spare part information of each spare part, and the spare part information includes spare part code, spare part description information, spare part model information, and spare part manufacturer information. The structure of the second database is the same as that of the first database, and the number of spare part codes in the second database is relatively larger; based on the same implementation principle as the above embodiment, the second similarity between the second spare part information and the device information is calculated.

[0084] In some embodiments, the second spare part information includes spare part description information, spare part model information, and spare part manufacturer information; calculating the second similarity between the second spare part information and the device information based on the second spare part information in the spare part list of the second database includes:

[0085] Vectorize the spare part description information, spare part model information, spare part manufacturer information, and device information to obtain text vectors; based on the text vectors and the cosine similarity algorithm, calculate the second cosine similarity values of the spare part description information, spare part model information, and spare part manufacturer information with the device information respectively; based on the second weight values and the second cosine similarity values corresponding to the spare part description information, spare part model information, and spare part manufacturer information respectively, calculate the second similarity.

[0086] Exemplarily, by calculating the comprehensive similarity (i.e., the second similarity) corresponding to each spare part code in the second database, sorting them, obtaining the maximum comprehensive similarity value (let it be p2), and comparing it with the second threshold θ2 (the second threshold θ2 is not less than the first threshold θ1); if the relationship p2≥θ2 is satisfied (the comprehensive similarity value is not less than or equal to the threshold), then the spare part code corresponding to p2 is the spare part code (parent spare part) at this functional location.

[0087] In addition, if the relationship p2≥θ2 is not satisfied, the spare part code (parent spare part) at this functional location cannot be obtained in the above manner and further calculation is required.

[0088] In some other application scenarios, there is no functional location information in the design drawing file, or there is no device information corresponding to the functional location information, such as Figure 3As shown in (c) thereof, in the case where there is no device description information, device model information, and device manufacturer information, the first similarity of all spare parts calculated through the above embodiments is the same, and the second similarity of all spare parts is also the same. For example, for the device information where the set R is empty, the similarity configuration value k is 0.5, and the similarity weight ω is set to 0.5, then the calculation results of the comprehensive similarity value p of all spare parts are all Consequently, the parent spare part corresponding to this functional location information cannot be calculated and further calculation is required.

[0089] In some embodiments, after calculating the second similarity between the second spare part information and the device information, the method further includes:

[0090] In the case where the second similarity is less than the second threshold, based on the third spare part information in the spare part list of the third database, calculate the comprehensive probability coefficient of the spare parts in the first database; in the case where the comprehensive probability coefficient is not less than the preset third threshold, establish a first mapping relationship between the spare part code of the third parent spare part and the functional location information.

[0091] Wherein, the spare part list of the third database includes the spare part list of the first database and the parent spare part list that has established a mapping relationship with the target device class associated with the functional location information; the spare part list of the first database includes the third parent spare part; the third spare part information includes the spare part code of the third parent spare part; the threshold includes the third threshold, and the third threshold is greater than the second threshold.

[0092] Exemplarily, the third database includes the spare part list of the first database, and this spare part list includes the spare part code and spare part description information; the target device class associated with the functional location information can be a device class similar to or the same as the functional location information. For example Figure 3 the functional location information 1CTE414MT shown in (c) thereof, that is, the 414th MT device (temperature measurement device) of the CTE system (circulating water treatment system) of a nuclear power plant, obtain the device class similar to this functional location information: MT device.

[0093] As shown in Table 2, the spare part requisition list and internal remarks under a certain functional location information in the third database include the spare part list containing this functional location information, and the spare part information of this spare part list can include the spare part code and spare part description information.

[0094] Table 2

[0095] Spare part code Spare part description information 1004 Temperature measuring element 1005 Terminal module 1006 Nylon binding strap 1007 Armored platinum thermal resistance 1008 Stainless steel double-ear lock washer 1009 Polytetrafluoroethylene tape 1010 Flame retardant heat shrinkable tube 1011 Thermal resistance casing

[0096] Exemplarily, the third database further includes a list of spare part codes (parent spare parts) attached under a device class similar to the functional location information, that is, a list of parent spare parts that have established a mapping relationship with the device class; the spare part information in the list of parent spare parts includes functional location information, spare part codes (parent spare parts), and spare part description information.

[0097] Exemplarily, based on the spare part information in the spare part list of the third database, calculate the comprehensive probability coefficient corresponding to each spare part; sort the calculated comprehensive probability coefficients. If the maximum comprehensive probability coefficient is greater than or equal to the third threshold, then use the spare part code of this spare part as the spare part code (parent spare part) associated and mapped with the corresponding functional location information; if the maximum comprehensive probability coefficient is less than the third threshold, then prompt that under the current conditions, the spare part code (parent spare part) corresponding to this functional location cannot be calculated.

[0098] In some embodiments, calculating the comprehensive probability coefficient of the spare parts in the first database based on the third spare part information in the spare part list of the third database includes:

[0099] Based on the list of parent spare parts with established mapping relationships, extract the keyword information of the spare part description information in the list of parent spare parts; based on the keyword information and the list of parent spare parts, calculate the keyword proportion of each keyword in the list of parent spare parts; perform word segmentation on the spare part description information in the first spare part information to obtain spare part description word segments; based on the keyword proportion, determine the word segment proportion value of the spare part description word segments in the keyword information of the list of parent spare parts; based on the maximum value of the word segment proportion value, the number of word segments, the keyword proportion value, and the number of times the word segment proportion value appears in the keyword information corresponding to the spare part code of each spare part in the first spare part information, calculate the comprehensive probability coefficient.

[0100] Exemplarily, based on the list of spare part codes attached (i.e., having established a mapping relationship) to a device class (such as MT device) similar to the functional location information (i.e., the spare part codes of the parent spare parts in the list of parent spare parts), extract the keyword information of the spare part description information to obtain the spare part description feature information of all the parent spare parts attached to this device class (all MT devices); this keyword information is used to calculate the spare part codes belonging to the parent spare parts in Table 2.

[0101] Exemplarily, based on the spare part description information of the attached parent spare part list, according to the term frequency-inverse document category (TF-IDF) algorithm, calculate the keyword proportion of each keyword in the parent spare part list to measure the importance of each keyword in the documents of the parent spare part list, that is, represent the keyword proportion by calculating the tf-idf value to determine the keywords ranked at the top. Among them, the term frequency (tf) is used to measure the frequency of a word appearing in a document. The more times a keyword appears in a document, the larger the TF value; the inverse document frequency (idf) is used to measure the universality of a keyword. The fewer the number of documents in which a keyword appears in all documents, the larger the IDF value; combining the tf value and the idf value (i.e., the tf-idf value), the higher the value indicates that the keyword is more important in the document; calculate the tf-idf value through the following formulas (3), (4), and (5):

[0102] tf-idf = tf × idf (3)

[0103]

[0104] Among them, tf is the frequency of a certain keyword appearing, and idf is the inverse document probability of a certain keyword. Treat all work order descriptions in the parent spare part list as a document, automatically split out the keywords of all documents, and calculate the term frequency value of a certain keyword according to formula (4), where n1 is the number of times the keyword appears, and n2 is the total number of words in the document. For each keyword, calculate the inverse document probability according to formula (5), where n3 is the number of document collections (the data of publicly available open document collections can be used), and n4 is the number of texts in the document collection that contain the keyword.

[0105] Exemplarily, taking the MT equipment of a nuclear power plant as an example, calculate the keyword proportion in the spare part description information of the parent spare part list corresponding to the MT equipment based on the above formula. As Figure 7 shown, the distribution of keywords with a proportion of more than 1% in the total sample; among them, 42% of the spare part description information contains the keyword "thermal resistance", and 18% of the spare part description information contains the keyword "thermocouple".

[0106] By calculating the keyword proportion in the spare part description information of the parent spare part list, the distribution of the main keyword proportions in this equipment category can be obtained. Let the keyword proportion be q i , the comprehensive probability coefficient p3 corresponding to each spare part code in Table 2 can be calculated. By performing a word segmentation operation on the spare part description information in the first spare part information, the spare part description word segmentation is obtained, and based on Figure 7 , calculate the probability of the spare part description word segmentation appearing in the parent spare part list, that is, the word segmentation proportion value. The calculation results are shown in Table 3.

[0107]

[0108]

[0109] Based on the calculation results shown in Table 3, calculate the comprehensive probability coefficient corresponding to the spare part code of each spare part in the first spare part information through the following formula (6):

[0110]

[0111] where q i is the keyword proportion, n5 is the number of word segments of the spare part description information after word segmentation of the spare part, max(q) is the maximum proportion among the keywords of this equipment type. Taking Figure 7 as an example, the keyword proportion of "resistor" is the largest, and this value is 45%. n6 is the number of times the word segments of the spare part description information after word segmentation of the spare part appear in Figure 7 , and n is the number of word segments of the spare part description information after word segmentation.

[0112] For example, based on the results in Table 3, apply formula (6) to calculate the comprehensive probability coefficient p3 of this spare part. Thus, the spare part code 1004 can be obtained, and the spare part description information is "temperature measuring element", and its comprehensive probability coefficient p3 is Similarly, the comprehensive probability coefficient p3 of the spare part with the spare part code 1005 can be obtained as The comprehensive probability coefficient p3 of the spare part with the spare part code 1006 is The comprehensive probability coefficient p3 of the spare part with the spare part code 1007 is The comprehensive probability coefficients p3 of the spare parts with the spare part codes 1008, 1009, and 1010 are 0, and the comprehensive probability coefficient p3 of the spare part with the spare part code 1011 is

[0113] By sorting the comprehensive probability coefficients of the spare part codes 1004 to 1011, the maximum value of the spare part comprehensive probability coefficient can be obtained as 0.99, and the comprehensive probability coefficient of the spare part using the code 1007 is compared with the third threshold. If the third threshold θ3 is set to 0.9, since the relationship p3≥θ3 is satisfied (the comprehensive probability coefficient is greater than or equal to the third threshold), then the spare part code 1007 is the spare part code (parent spare part) at this functional position; if the third threshold θ3 is set to 1, since the relationship p3≥θ3 is not satisfied, it is prompted that under the current conditions, the spare part code (parent spare part) corresponding to this functional position cannot be calculated.

[0114] S304. Based on the spare part identification model, identify the spare part information of potential sub-spare parts in the spare part list, and determine the target sub-spare parts corresponding to the parent spare part; the potential sub-spare parts are the spare parts in the spare part list other than the parent spare part.

[0115] Among them, the spare part identification model includes a first identification model and a second identification model; the first identification model is trained based on spare part sample information and spare part category labels, and the spare part category labels include dedicated sub-spare part labels and general sub-spare part labels; the second identification model is determined based on the spare part description information in the sub-spare part list and the spare part description information of potential sub-spare parts; the target sub-spare parts include dedicated sub-spare parts and equipment general sub-spare parts.

[0116] In some embodiments, for all spare part requisition lists corresponding to the functional location information and the potential sub-spare parts in the spare part list containing the functional location information in the internal annotation of the spare part code, the spare part identification model is used for spare part identification to determine the sub-spare parts corresponding to the parent spare parts. Among them, the potential sub-spare parts are other spare parts in the above spare part list except for the determined parent spare parts, and the spare part information in the list of the potential sub-spare parts is used as the fourth database.

[0117] Exemplarily, in order to achieve more effective lean management of spare parts, the spare parts in the fourth database can be classified and labeled, and divided into: dedicated sub-spare parts, equipment general sub-spare parts, and auxiliary installation general sub-spare parts. Among them, the dedicated sub-spare parts and equipment general sub-spare parts belong to Figure 2 the sub-spare parts of the spare part parent-child BOM shown in Figure 2 and the auxiliary installation general sub-spare parts do not belong to

[0118] the sub-spare parts of the spare part parent-child BOM shown in.

[0119] Exemplarily, the fourth database can have data of multiple attribute categories, such as relevant information of attribute categories such as spare part code, spare part description information, material category, quality assurance level, spare part grading, whether there is drawing information in the code, annual average requisition quantity, discrete coefficient, purchase unit price, etc. Through the spare part identification model, the fourth database is analyzed and identified to determine the target sub-spare parts corresponding to the parent spare parts.

[0120] Before identifying the data in the fourth database, it is necessary to normalize the data in the fourth database; for the spare part information of potential sub-spare parts, normalize it according to the attribute category to obtain the standardized value corresponding to each attribute category; the standardized value is used to generate the linear combination value of each attribute category.

[0121] Exemplarily, for data corresponding to discrete attributes of an attribute category, by establishing rules, the discrete data is normalized to a numerical value between 0 and 1; for data corresponding to numerical attributes of an attribute category, a linear transformation method is used to normalize the data to a numerical value between 0 and 1.

[0122] The following introduces the implementation process of normalization processing by attribute category.

[0123] In some embodiments, the potential sub-spares include current spares, the standardized values include material category coefficient, quality assurance level coefficient, spare part grading coefficient, average annual consumption coefficient, discrete coefficient correction value, and purchase unit price coefficient; the second database includes all the issued spare part lists corresponding to the target equipment class associated with the functional location information and the spare part list of the target equipment class is included in the internal remarks of the spare part code. The spare part information of the potential sub-spares is normalized by attribute category to obtain the standardized value corresponding to each attribute category, including:

[0124] A1. Based on the first quantity of the material category divided by nuclear power plant, the first digit code value of the material category of the potential sub-spares, the second quantity of the sub-categories included in the material category of the potential sub-spares, and the sub-category position corresponding to the material category of the potential sub-spares, the material category of the potential sub-spares is normalized to obtain the material category coefficient.

[0125] Exemplarily, when coding nuclear power spare parts, the material category corresponding to the spare parts will be set; taking a certain nuclear power plant as an example, as Figure 8 shown in the schematic diagram of the material category classification of the nuclear power plant, the material category of this nuclear power plant can be divided into 7 major categories of materials: rotating machinery, pumps, valves, general machinery, chemical consumables, instrumentation, and electrical; there are several small categories under each major category. Therefore, the material category coefficient value can be calculated based on the quantity of the major category of this material category, the quantity of the small categories in the major category, and the sub-category position where the spare part is located. For example, the material category coefficient value is calculated based on the following formula (7):

[0126]

[0127] Among them, m1 is the first digit code value of the major category of the spare part where it is located. For example, Figure 8 in the instrumentation, the major category code is 60000, then m1 is 6; m2 is the quantity of the major categories. For example, Figure 8 in Figure 8 there are 7 major categories in total, so m2 is 7; m3 is the sub-category position where the spare part is located. For example, Figure 8Among them, there are 15 subcategories in the large category of instruments and meters, so m3 is 15. Based on this method, if the material category of a spare part is a thermal resistor, its material category coefficient is

[0128] A2, normalize the quality assurance level corresponding to the potential sub-spare parts to obtain the quality assurance level coefficient corresponding to the quality assurance level.

[0129] Exemplarily, in order to distinguish items with different safety functions and different requirements in a nuclear power plant, and then put forward different quality assurance requirements, conduct quality assurance grading on the items, control the process quality of the purchased items, and obtain the corresponding quality documents in a timely manner, so as to achieve effective resource allocation and optimal utilization in the process of item procurement in the nuclear power plant. Currently, the quality assurance levels of spare parts in a certain nuclear power plant can be divided into three levels, namely C1, C2, and C3. After normalization, the value of C1 spare parts is 1; the value of C2 spare parts is 0.5, and the value of C3 spare parts is 0. The calculation method of the quality assurance level coefficient is shown in formula (8):

[0130]

[0131] A3, normalize the spare part grading corresponding to the potential sub-spare parts to obtain the spare part grading coefficient corresponding to the spare part grading.

[0132] Exemplarily, spare part grading refers to grading according to the importance of spare parts, also known as spare part criticality grading. Referring to the equipment importance grading, according to the nuclear safety and operation stability requirements of the nuclear power plant equipment, the spare parts are divided into three levels: H (high), M (medium), and L (low). Usually, when the failure or lack of a spare part causes the loss of the key function of the affiliated equipment, ultimately affecting nuclear safety, unit availability, the critical path of the overhaul, or other unacceptable events in the power plant, this spare part is an H-level spare part; when the failure or lack of a spare part causes the loss of the key function of the affiliated equipment, increasing the nuclear safety risk or the risk of shutdown and reactor trip, or introducing significant industrial safety, radioactive irradiation, or hazardous chemical release risks, or resulting in an increase in maintenance costs, this spare part is an M-level spare part. The remaining spare parts belong to L-level spare parts.

[0133] After normalization, the value of H-level spare parts is 1; the value of M-level spare parts is 0.5, and the value of L-level spare parts is 0. The calculation method of the spare part grading coefficient is shown in formula (9). In the case where some nuclear power plants have not completed the identification of the spare part grading of all spare parts, the information in the spare part grading field is NA (i.e., empty). If the proportion of spare parts with NA grading is relatively high, the normalization calculation method of the spare part grading can be adjusted, that is, the value of H-level spare parts is 1; the value of M-level spare parts is 0.66; the value of NA-level spare parts is 0.33; the value of L-level spare parts is 0.

[0134]

[0135] A4. Normalize whether there is drawing information corresponding to potential sub-spare parts to obtain the spare part grading coefficient corresponding to whether there is drawing information.

[0136] Exemplarily, when coding nuclear power spare parts, if the installation and use position of the spare part is relatively fixed, information on the design drawing file of the spare part may be attached during coding; if the spare part is a general part, such as cables, gaskets, etc., which are installed at multiple functional positions, the probability of attaching the drawing to this code is relatively low. The schematic diagram of the drawing attached to the spare part code is as Figure 9 shown, and the corresponding design drawing file is attached under the spare part code. It is only necessary to judge whether the spare part is attached with a drawing, without verifying the specific content of the attached drawing, reducing the calculation amount and improving the calculation efficiency; the calculation method of the drawing information coefficient is shown in formula (10).

[0137]

[0138] A5. Normalize the annual average consumption of the current spare part based on the annual average consumption of all spare parts in the second database and a preset multiple value to obtain the annual average consumption coefficient of the current spare part.

[0139] Exemplarily, by obtaining the annual average consumption of the spare part and comparing it with the specified upper limit value of the annual average consumption, the annual average consumption coefficient value is calculated, and its calculation method is shown in formula (11).

[0140]

[0141] Among them, m5 is the annual average consumption of the spare part; m6 is the list of all spare parts consumed annually in the equipment category with similar functional position information, and the spare part list in the internal annotation of the spare part code includes the spare part list of this equipment category (i.e., the spare part list in the second database), and calculate the annual average consumption value of all spare parts in this spare part list; n7 is the set multiple value. For example, for a certain thermal resistance spare part, its annual average consumption quantity m5 is 3.5, this spare part is an MT spare part, the annual average consumption quantity m6 of the spare part list in the second database is 9.8, and the set multiple value n7 is 2, then the annual average consumption coefficient of this spare part is

[0142] Exemplarily, the annual average consumption quantity of special parts is less than that of general parts. Therefore, in formula 11, the larger the annual average consumption coefficient value, the greater the probability that it is a general part; the smaller the annual average consumption coefficient value, the greater the probability that it is a special part.

[0143] A6. Normalize the coefficient of variation based on the annual average consumption, annual consumption standard deviation value of the current spare part and a preset upper limit value to obtain the corrected coefficient of variation value of the current spare part.

[0144] Exemplarily, by calculating the coefficient of variation of the spare part and normalizing it to a correction value between 0 and 1, the calculation method is as shown in formula (12):

[0145]

[0146] Among them, m5 is the average annual consumption of the spare part, m7 is the standard deviation of the annual consumption of the spare part, and n8 is the set upper limit value. For example, for a certain thermal resistance spare part, its average annual consumption quantity m5 is 3.5, the standard deviation of the annual consumption m6 is 5.7, and the set upper limit value n8 is 2. Then the correction value of the coefficient of variation of this spare part is

[0147] A7. Based on the upper limit value and lower limit value of the purchase unit price of the current spare part, the purchase unit price of the current spare part is normalized to obtain the purchase unit price coefficient of the current spare part.

[0148] Exemplarily, the unit price of the spare part is the price at the time of purchasing the spare part. Since there are multiple purchases of the same spare part and the prices of each purchase are not exactly the same, usually the moving average price of the spare part is selected as the purchase unit price of the spare part. There are a small number of spare part unit prices above the upper limit of the purchase unit price. To reduce the influence of a very small number of spare parts with too high unit prices on the unit price normalization, the upper limit value of the unit price can be limited to the upper limit of the purchase unit price. If the unit price of a certain spare part is greater than the upper limit of the purchase unit price, it is assigned the price of the upper limit of the purchase unit price; the unit prices of some spare parts in the database are 0, and this type of unit price data is incorrect. Therefore, the lower limit value of the spare part unit price can be limited to the lower limit of the purchase unit price. If the unit price of a certain spare part is less than the lower limit of the purchase unit price, it is assigned the price of the lower limit of the purchase unit price. For example, the purchase unit price coefficient is calculated by formula (13):

[0149]

[0150] Among them, m8 is the purchase unit price of the spare part, n9 is the set lower limit value of the purchase unit price, for example, set to 0.01, and n 10 is the set upper limit value of the purchase unit price, for example, 100000. For example, for a certain thermal resistance spare part, its purchase unit price is 8000 yuan, then its purchase unit price coefficient is

[0151] After the above data normalization process, the construction process of the spare part identification model is further introduced below.

[0152] In some embodiments, for each type of nuclear power equipment (such as MT equipment, PO equipment, MP equipment, etc.), a first recognition model is established to identify the spare part information in the fourth database, classify the potential sub-spare parts in the fourth database, and determine the dedicated sub-spare parts and general sub-spare parts among the potential sub-spare parts. Among them, common classification and recognition algorithms include decision tree, random forest, support vector machine, K-nearest neighbor algorithm, logistic regression model, etc.; in the embodiments of the present application, based on the logistic regression algorithm, the linear combination of input variables is mapped to the probability between 0 and 1 to predict the probability of the binary output variable, and based on the probability of the output variable, the dedicated sub-spare parts and general sub-spare parts are classified.

[0153] First, the training process of the first recognition model is introduced as follows:

[0154] B1. Each attribute category included in the spare part sample information is used as an input variable, and based on the preset attribute weight value and the preset bias value, the linear combination of the input variables is calculated.

[0155] Exemplarily, each attribute category included in the spare part sample information is normalized to obtain the standardized value corresponding to each attribute category, such as the material category coefficient, quality assurance level coefficient, spare part classification coefficient, average annual consumption coefficient, discrete coefficient correction value, and purchase unit price coefficient. The standardized values corresponding to each attribute category are used as input variables, and the linear combination of the input variables is calculated. For example, the linear combination value of each input variable is calculated based on the following formula:

[0156]

[0157] Among them, z is the linear combination value of an attribute category; b is the preset bias value; is the weight value of the i-th attribute; x i is the standardized value of the i-th attribute (i.e., the input variable); n is the total number of each attribute category. For example, there are 7 attribute categories in total above, and the input value x i of each attribute category is the material category coefficient value, quality assurance level coefficient, spare part classification coefficient, whether there is drawing information coefficient, average annual consumption coefficient value, discrete coefficient correction value, and purchase unit price coefficient

[0158] B2. The linear combination of the input variables is input into the logistic regression model to calculate the output probability corresponding to the input variables.

[0159] Exemplarily, the logistic regression model uses a parametric function to calculate the output probability of the given input variables. This function is usually the sigmoid function, and its calculation formula is shown in Equation (15):

[0160]

[0161] Among them, z is a linear combination of input variables obtained based on formula (14).

[0162] B3. Train the logistic regression model through the maximum likelihood function, loss function, special sub-spare part labels, general sub-spare part labels, and output probabilities of the logistic regression model, and determine the target attribute weight value and target bias value when the value of the loss function is minimized.

[0163] B4. Substitute the target attribute weight value and the target bias value into the logistic regression model to obtain the trained first recognition model.

[0164] Exemplarily, the training process of the logistic regression model is to estimate the weights of the model by maximizing the likelihood function. The likelihood function is a function of the model parameters, that is, it represents the probability corresponding to the sample under the given model. The expression of the likelihood function is shown in formula (16):

[0165]

[0166] Among them, z j is the linear combination value of the jth sample; y j is the corresponding class label, and its value is 1 or 0; m is the number of samples used for training, is the w i weight value of n in formula 15, and b is the bias value in formula (14).

[0167] To maximize the likelihood function, the gradient descent algorithm can be used to update the model weights. The principle of gradient descent is to repeatedly iterate to calculate the minimum loss function until the optimal solution is calculated. The loss function can use the logarithmic loss function, and the calculation formula of the loss function is shown in formula (17):

[0168]

[0169] Among them, when training the model by using the spare part sample information, if the spare part belongs to a special sub-spare part, the class label y j is marked as 1; if the spare part belongs to a general sub-spare part, the class label y j is marked as 0. Calculate the target attribute weight value and the target bias value b corresponding to the minimum of the loss function, and substitute the obtained target attribute weight value and the target bias value b into formula (15) to obtain the trained first recognition model.

[0170] In some embodiments, based on the spare part recognition model, recognizing the spare part information of potential sub-spare parts in the spare part list and determining the target sub-spare parts corresponding to the parent spare part includes:

[0171] S1001. Calculate the linear combination value of each of the attribute categories based on the standardized values corresponding to the respective attribute categories included in the spare part information of the current spare part.

[0172] S1002. Input the linear combination value into the first recognition model, and through the calculation of the first recognition model, obtain the spare part category probability corresponding to the current spare part.

[0173] S1003. Based on the spare part category probability, determine that the spare part category of the current spare part is a dedicated sub-spare part or a general sub-spare part.

[0174] Exemplarily, after the model training is completed, use the model to predict the category label of the spare parts in the fourth database, that is, based on the standardized values calculated for each attribute category, use x1 to x7 of each spare part in the fourth database as input values, and apply formula (14) to calculate the linear combination value z of the input variables. Based on the calculation result of the z value, apply formula (15) to calculate the output probability of the spare part. If the output probability is greater than 0.5, then determine that the spare part is a dedicated sub-spare part and label it as a dedicated sub-spare part; if the output probability is less than or equal to 0.5, then determine that the spare part is a general sub-spare part, and further calculate whether the general sub-spare part is a device general part or an auxiliary installation general sub-spare part.

[0175] For example, taking the spare parts in Table 3 as an example, based on the trained regression training model, it can be identified that spare parts 1004 (temperature measuring element) and 1011 (thermal resistance casing) belong to dedicated sub-spare parts; spare parts 1005 (cable explosion-proof joint), 1006 (nylon binding tape), 1008 (stainless steel double-ear stop washer), 1009 (polytetrafluoroethylene thread seal tape), and 1010 (flame-retardant heat shrinkable tube) belong to general sub-spare parts.

[0176] S1004. Based on the second recognition model, identify the spare part information of the general sub-spare parts, and determine the device general sub-spare parts and auxiliary installation general sub-spare parts among the general sub-spare parts.

[0177] Exemplarily, for each type of equipment (such as MT equipment, PO equipment, MP equipment), based on the constructed second recognition model, classify the general sub-spare parts in the fourth database to identify the device general sub-spare parts and auxiliary installation general sub-spare parts. Taking the spare parts in Table 3 as an example, spare parts 1004 (temperature measuring element) and 1011 (thermal resistance casing) belong to dedicated sub-spare parts; spare parts 1005 (cable explosion-proof joint) and 1008 (stainless steel double-ear stop washer) belong to device general parts; spare parts 1006 (nylon binding tape), 1009 (polytetrafluoroethylene thread seal tape), and 1010 (flame-retardant heat shrinkable tube) belong to auxiliary installation general sub-spare parts.

[0178] Before introducing the spare part information of the general sub-spare parts further identified based on the second recognition model, the construction method of the second recognition model will be introduced first. The construction method of this second recognition model may include the following steps:

[0179] S1101. For each equipment type, based on the spare part description information of the sub-spare part list already attached to this equipment type, construct a first keyword library.

[0180] Exemplarily, for each type of equipment, obtain all the attached spare part parent-child BOMs under this equipment type, extract all the sub-spare part lists in this parent-child BOM, and establish a first keyword library corresponding to the description information of the sub-spare part list.

[0181] S1102. Based on the spare part description information of the spare part list corresponding to this equipment type, construct a second keyword library.

[0182] Exemplarily, for this equipment type, obtain all the spare part requisition lists under this equipment type, as well as the spare part lists whose internal annotations of spare part codes contain this equipment type, extract the spare part description information in the lists, and establish a second keyword library for the relevant spare parts.

[0183] S1103. Compare the second keyword library with the first keyword library, and extract the keywords that exist in the second keyword library but do not exist in the first keyword library to obtain an auxiliary installation general sub-spare part keyword library.

[0184] Exemplarily, use the second keyword library of the relevant spare parts to reverse-match the first keyword library of the sub-spare part list, extract the keywords that only appear in the second keyword library (keywords that have not appeared in the first keyword library), and establish an auxiliary installation general sub-spare part keyword library. As long as the spare part description information in the sub-spare part list contains the keywords in the auxiliary installation general sub-spare part keyword library, then this spare part belongs to the auxiliary installation general sub-spare part; use the auxiliary installation general sub-spare part keyword library as the second recognition model, and thus establish the second recognition model corresponding to this equipment type.

[0185] Among them, when converting the spare part description information into a keyword library, the spare part description information in the sub-spare part list can be calculated based on formulas (3), (4), and (5) to obtain the first keyword library; and the spare part description information of the spare part list corresponding to this equipment type can be calculated to obtain the second keyword library.

[0186] Exemplarily, taking a certain type of equipment as an example, the results of the extracted keyword library are as Figure 11 shown. As Figure 11As shown in (a) in [reference], a first keyword library is extracted based on all the sub-spare part lists in the parent-child BOM; based on all the attached parent-child BOMs of spare parts under this equipment type, the spare part description information in all the sub-spare part lists is extracted to establish the first keyword library. For this first keyword library, the top 200 keywords with the highest frequency of occurrence are selected. In practical applications, based on the size of the sub-spare part list, the top 200 - 500 keywords with the highest frequency of occurrence can be selected.

[0187] As Figure 11 As shown in (b) in [reference], for this type of equipment, all the spare part requisition lists under this type of equipment are obtained, as well as the spare part lists in which the internal annotations of the spare part codes contain this type of equipment, and the spare part description information in the spare part lists is extracted to establish the second keyword library for the relevant spare parts.

[0188] Correspondingly, use the second keyword library of the relevant spare parts to reverse-match the first keyword library of the sub-code spare parts, and extract the keywords that only appear in the second keyword library (keywords that have not appeared in the first keyword library) to establish an auxiliary installation general sub-spare part keyword library. As Figure 11 As shown in (c) in [reference], for example, keywords such as sealant, frosting, self-adhesive, etc. only appear in the first keyword library of the sub-code spare parts and do not appear in the second keyword library of the relevant spare parts, so they are extracted as the auxiliary installation general sub-spare part keyword library.

[0189] S1104. Based on the auxiliary installation general sub-spare part keyword library, identify the types of general sub-spare parts. By establishing the auxiliary installation general keyword library, an identification model for the general sub-spare parts of the equipment and the auxiliary installation general sub-spare parts is established, and the general sub-spare parts in the fourth database can be identified and marked.

[0190] In some embodiments, based on the second identification model, identify the spare part information of the general sub-spare parts, and determine the equipment general sub-spare parts and the auxiliary installation general sub-spare parts in the general sub-spare parts, including:

[0191] Determine the general sub-spare parts whose spare part description information contains the keywords in the auxiliary installation general sub-spare part keyword library as the auxiliary installation general sub-spare parts; determine the general sub-spare parts other than the auxiliary installation general sub-spare parts in the general sub-spare parts as the equipment general sub-spare parts.

[0192] Exemplarily, taking the spare parts in Table 3 as an example, the second identification model can identify that spare parts 1005 (cable explosion-proof joint) and 1008 (stainless steel double-ear stop washer) belong to the equipment general sub-spare parts; spare parts 1006 (nylon tie strap), 1009 (polytetrafluoroethylene thread seal tape), and 1010 (flame-retardant heat shrinkable tube) belong to the auxiliary installation general sub-spare parts.

[0193] S305. Establish a second mapping relationship between the parent spare part and the target sub-spare part.

[0194] Exemplarily, after identifying the target sub-spare part, establish a second mapping relationship between the spare part code of the parent spare part and the spare part code of the target sub-spare part, such as Figure 2 the corresponding relationship between the parent spare part and the sub-spare part represented by the spare part parent-child BOM shown in

[0195] Figure 13 For the display of the system architecture provided by the application embodiment, after the system inputs the functional location information, the system can automatically apply the corresponding model to calculate the information of the parent spare part and the sub-spare part corresponding to the functional location, classify the sub-spare parts, and identify the dedicated sub-spare parts, equipment general sub-spare parts, and auxiliary installation general sub-spare parts. Thus, the user can, based on the recognition result of the system tool, maintain the information of the functional location BOM and the spare part parent-child BOM in the database of the nuclear power plant, which is convenient for subsequent work such as setting spare part inventory parameters, grading the importance of spare parts, and identifying nuclear supervision spare parts.

[0196] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The order of execution of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0197] Corresponding to the nuclear power spare part information management method provided in the above embodiments, Figure 14 FIG. shows a schematic structural diagram of a nuclear power spare part information management device provided by an embodiment of the present application. For the convenience of description, only the parts related to the embodiments of the present application are shown.

[0198] Referring to Figure 14 , the device includes:

[0199] An acquisition unit 1401, configured to determine the device information corresponding to the functional location information of the nuclear power plant in the acquired design drawing file; the design drawing file includes the functional location information;

[0200] A calculation unit 1402, configured to calculate the similarity between the spare part information and the device information based on the spare part information in the spare part list associated with the functional location information;

[0201] A first matching unit 1403, configured to establish a first mapping relationship between the parent spare part in the spare part list and the functional location information when the similarity is not less than a preset threshold;

[0202] An identification unit 1404, configured to identify spare part information of potential sub-spare parts in the spare part list based on a spare part identification model, and determine target sub-spare parts corresponding to the parent spare part; the potential sub-spare parts are spare parts in the spare part list other than the parent spare part;

[0203] A second matching unit 1405, configured to establish a second mapping relationship between the parent spare part and the target sub-spare part; wherein, the spare part identification model includes a first identification model and a second identification model; the first identification model is trained based on spare part sample information and spare part category labels, and the spare part category labels include dedicated sub-spare part labels and general sub-spare part labels; the second identification model is determined based on the spare part description information in the sub-spare part list and the spare part description information of the potential sub-spare parts; the target sub-spare parts include dedicated sub-spare parts and equipment general sub-spare parts.

[0204] Each of the above units is further configured to implement each step in the above method embodiments.

[0205] Figure 15 The hardware structure diagram of the electronic device 15 is shown.

[0206] As Figure 15 shown, the electronic device 15 in this embodiment includes: at least one processor 1501( Figure 15 only one is shown in the figure), a memory 1502, and a computer program 1503 that can run on the processor 1501 is stored in the memory 1502. When the processor 1501 executes the computer program 1503, the steps in the above method embodiments are implemented, such as Figure 3 shown in S301 to S305. Alternatively, when the processor 1501 executes the computer program 1503, the functions of each module / unit in the above device embodiments are implemented.

[0207] It can be understood that the structure schematically shown in the embodiments of the present application does not constitute a specific limitation on the electronic device 15. In other embodiments of the present application, the electronic device 15 may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or different component arrangements. The components shown in the figure can be implemented in hardware, software, or a combination of software and hardware.

[0208] The electronic device 15 may include, but is not limited to, a processor 1501 and a memory 1502. Those skilled in the art can understand that Figure 15 this is only an example of the electronic device 15 and does not constitute a limitation on the electronic device 15. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, the server may further include an input and sending device, a network access device, a bus, etc.

[0209] The above-mentioned processor 1501 may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0210] A memory may also be provided in the processor 1501 for storing instructions and data. In some embodiments, the memory in the processor 1501 is a cache memory. This memory can save the instructions or data that the processor 1501 has just used or recycled. If the processor 1501 needs to use the instruction or data again, it can be directly called from the memory. This avoids repeated accesses, reduces the waiting time of the processor 1501, and thus improves the efficiency of the system.

[0211] In some embodiments, the above-mentioned memory 1502 may be an internal storage unit of the electronic device 15, such as the hard disk or memory of the electronic device 15. The memory 1502 may also be an external storage device of the electronic device 15, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc., equipped on the electronic device 15. Further, the memory 1502 may also include both the internal storage unit and the external storage device of the electronic device 15. The memory 1502 is used to store an operating system, application programs, a BootLoader, data, and other programs, such as the program code of a computer program. The memory 1502 may also be used to temporarily store data that has been sent or will be sent.

[0212] In addition, in each embodiment of the present application, the various functional units may be integrated in one processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit.

[0213] It should be noted that the structure of the above-mentioned electronic device is only an exemplary illustration. Based on different application scenarios, it may also include other entity structures, and the entity structure of the electronic device is not limited herein.

[0214] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For parts not detailed or recorded in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0215] The embodiments of the present application further provide a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments can be implemented.

[0216] The embodiments of the present application provide a computer program product. When the computer program product runs on a server, the server can implement the steps in the above method embodiments when executed.

[0217] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above method embodiments of the present application, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps in the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0218] The electronic device, computer storage medium, and computer program product provided in the above embodiments of the present application are all used to execute the method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects corresponding to the method provided above, and will not be elaborated here.

[0219] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0220] It should be understood that the above is only to help those skilled in the art better understand the embodiments of the present application, rather than to limit the scope of the embodiments of the present application. Those skilled in the art can obviously make various equivalent modifications or changes according to the above examples. For example, in the various embodiments of the above detection method, some steps may not be necessary, or some steps may be newly added, etc. Or any combination of any two or any multiple of the above embodiments. The solutions after such modifications, changes or combinations also fall within the scope of the embodiments of the present application.

[0221] It should also be understood that the classification of the methods, situations, categories and embodiments in the embodiments of the present application is only for the convenience of description and should not constitute a special limitation. The features in various methods, categories, situations and embodiments can be combined without conflict.

[0222] It should also be understood that in the various embodiments of the present application, if there is no special description and logical conflict, the terms and / or descriptions between different embodiments are consistent and can be cited from each other. The technical features in different embodiments can be combined to form new embodiments according to their internal logical relationships.

[0223] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0224] In the embodiments provided by the present application, it should be understood that the disclosed device / network device and method can be implemented in other ways. For example, the device / network device embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical or other forms.

[0225] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0226] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

[0227] Finally, it should be noted that: the above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any changes or replacements within the technical scope disclosed in the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claimed rights.

Claims

1. A method for managing nuclear power spare part information, characterized in that, The method includes: Based on the obtained design drawing file, determining the equipment information corresponding to the functional location information of the nuclear power plant in the design drawing file; the design drawing file includes the functional location information; Calculating the similarity between the spare part information and the equipment information based on the spare part information in the spare part list associated with the functional location information; When the similarity is not less than a preset threshold, establishing a first mapping relationship between the parent spare part in the spare part list and the functional location information; Based on the spare part identification model, identifying the spare part information of potential sub-spare parts in the spare part list, and determining the target sub-spare parts corresponding to the parent spare part; the potential sub-spare parts are the spare parts in the spare part list other than the parent spare part; Establishing a second mapping relationship between the parent spare part and the target sub-spare part; Wherein, the spare part identification model includes a first identification model and a second identification model; the first identification model is trained based on spare part sample information and spare part category labels, and the spare part category labels include dedicated sub-spare part labels and general sub-spare part labels; the second identification model is determined based on the spare part description information in the sub-spare part list and the spare part description information of potential sub-spare parts; the target sub-spare parts include dedicated sub-spare parts and equipment general sub-spare parts.

2. The method according to claim 1, wherein Calculating the similarity between the spare part information and the equipment information based on the spare part information in the spare part list associated with the functional location information includes: Calculating a first similarity between the first spare part information in the spare part list of the first database and the equipment information; Correspondingly, when the first similarity is not less than a preset first threshold, establishing a first mapping relationship between the first parent spare part and the functional location information; Wherein, the spare part list in the first database includes all spare part requisition lists under the functional location information and the spare part list whose internal annotation of the spare part code contains the functional location information; the spare part list in the first database includes the first parent spare part; the threshold includes the first threshold.

3. The method according to claim 2, wherein After calculating the first similarity between the first spare part information and the equipment information, the method further includes: When the first similarity is less than the first threshold, calculating a second similarity between the second spare part information in the spare part list of the second database and the equipment information; Correspondingly, when the second similarity is not less than a preset second threshold, establishing a first mapping relationship between the second parent spare part and the functional location information; Wherein, the spare part list in the second database includes all requisitioned spare part lists corresponding to the target equipment class associated with the functional location information and the spare part list whose internal annotation of the spare part code contains the target equipment class; the spare part list in the second database includes the second parent spare part; the threshold includes the second threshold, and the second threshold is greater than the first threshold.

4. The method according to claim 3, wherein After calculating the second similarity between the second spare part information and the equipment information, the method further includes: In the case where the second similarity is less than the second threshold, calculate the comprehensive probability coefficient of the spare parts in the first database based on the third spare part information in the spare part list of the third database; Correspondingly, in the case where the comprehensive probability coefficient is not less than the preset third threshold, establish a first mapping relationship between the third parent spare part and the functional location information; Among them, the spare part list of the third database includes the spare part list of the first database and the parent spare part list that has established a mapping relationship with the target equipment class associated with the functional location information; the spare part list of the third database includes the third parent spare part; the thresholds include the third threshold, and the third threshold is greater than the second threshold.

5. The method according to claim 2, wherein The first spare part information includes spare part description information, spare part model information, and spare part manufacturer information; calculating the first similarity between the first spare part information and the equipment information based on the first spare part information in the spare part list of the first database includes: Vectorize the spare part description information, the spare part model information, the spare part manufacturer information, and the equipment information to obtain text vectors; Based on the text vectors and the cosine similarity algorithm, calculate the first cosine similarity values of the spare part description information, the spare part model information, and the spare part manufacturer information with the equipment information respectively; Based on the first weight values corresponding to the spare part description information, the spare part model information, and the spare part manufacturer information respectively and the first cosine similarity values, calculate the first similarity.

6. The method according to claim 3, wherein The second spare part information includes spare part description information, spare part model information, and spare part manufacturer information; calculating the second similarity between the second spare part information and the equipment information based on the second spare part information in the spare part list of the second database includes: Vectorize the spare part description information, the spare part model information, the spare part manufacturer information, and the equipment information to obtain text vectors; Based on the text vectors and the cosine similarity algorithm, calculate the second cosine similarity values of the spare part description information, the spare part model information, and the spare part manufacturer information with the equipment information respectively; Based on the second weight values corresponding to the spare part description information, the spare part model information, and the spare part manufacturer information respectively and the second cosine similarity values, calculate the second similarity.

7. The method according to claim 4, characterized in that, Calculating the comprehensive probability coefficient of the spare parts in the first database based on the third spare part information in the spare part list of the third database includes: Based on the parent spare part list with the established mapping relationship, extract the keyword information of the spare part description information in the parent spare part list; Based on the keyword information and the parent spare part list, calculate the keyword proportion of each keyword in the parent spare part list; Perform word segmentation on the spare part description information in the first spare part information to obtain spare part description word segments; Based on the keyword proportion, determine the word segment proportion value of the spare part description word segments in the keyword information of the parent spare part list; Based on the word segmentation occupancy ratio, the number of word segments, the maximum value of the keyword occupancy ratio, and the number of occurrences of the word segmentation occupancy ratio in the keyword information corresponding to the spare part code of each spare part in the first spare part information, calculate the comprehensive probability coefficient.

8. The method according to claim 1, wherein The method further includes: Taking each attribute category included in the spare part sample information as an input variable, and calculating a linear combination of the input variables based on a preset attribute weight value and a preset bias value; Inputting the linear combination of the input variables into a logistic regression model, and calculating the output probability corresponding to the input variables; Training the logistic regression model through the maximum likelihood function, loss function, the dedicated sub-spare part label and the general sub-spare part label of the logistic regression model, and the output probability, and determining the target attribute weight value and the target bias value when the value of the loss function is the smallest; Substituting the target attribute weight value and the target bias value into the logistic regression model to obtain the trained first recognition model.

9. The method according to any one of claims 1 to 8, characterized in that Based on the spare part recognition model, identifying the spare part information of potential sub-spare parts in the spare part list, and determining the target sub-spare parts corresponding to the parent spare part, includes: Based on the standardized values corresponding to each attribute category included in the spare part information of the current spare part, calculate the linear combination value of each attribute category; Inputting the linear combination value into the first recognition model, and through the calculation of the first recognition model, obtaining the spare part category probability corresponding to the current spare part; Based on the spare part category probability, determining that the spare part category of the current spare part is a dedicated sub-spare part or a general sub-spare part; Based on the second recognition model, identifying the spare part information of the general sub-spare parts, and determining the equipment general sub-spare parts and the auxiliary installation general sub-spare parts in the general sub-spare parts.

10. The method according to claim 9, characterized in that, The method further includes: For each equipment category, constructing a first keyword library based on the spare part description information of the sub-spare part list already attached to the equipment category; Constructing a second keyword library based on the spare part description information of the spare part list corresponding to the equipment category; Comparing the second keyword library with the first keyword library, and extracting the keywords that exist in the second keyword library and do not exist in the first keyword library to obtain an auxiliary installation general sub-spare part keyword library; Taking the auxiliary installation general sub-spare part keyword library as the second recognition model.

11. The method according to claim 10, wherein Based on the second recognition model, identifying the spare part information of the general sub-spare parts, and determining the equipment general sub-spare parts and the auxiliary installation general sub-spare parts in the general sub-spare parts, includes: Determining the general sub-spare parts containing the keywords in the auxiliary installation general sub-spare part keyword library in the spare part description information as the auxiliary installation general sub-spare parts; Determining the general sub-spare parts other than the auxiliary installation general sub-spare parts in the general sub-spare parts as the equipment general sub-spare parts.

12. The method according to claim 9, wherein Before identifying the spare part information of potential sub-spare parts in the spare part list based on the spare part recognition model and determining the target sub-spare parts corresponding to the parent spare part, the method further includes: Normalize the spare part information of the potential sub-spare parts according to the attribute categories to obtain the standardized values corresponding to each attribute category; the standardized values are used to generate the linear combination values of each of the attribute categories.

13. The method according to claim 12, wherein The spare part information of the potential sub-spare parts includes material category, quality assurance level, spare part classification, whether there is drawing information in the code, average annual consumption, dispersion coefficient, and purchase unit price; the normalization of the spare part information of the potential sub-spare parts according to the attribute categories to obtain the standardized values corresponding to each attribute category includes: Normalize the material category of the potential sub-spare parts based on the first quantity of the material categories divided by nuclear power plants, the leading code value of the material category of the potential sub-spare parts, the second quantity of the sub-categories included in the material category of the potential sub-spare parts, and the sub-category position corresponding to the material category of the potential sub-spare parts, to obtain the material category coefficient; Normalize the quality assurance level corresponding to the potential sub-spare parts to obtain the quality assurance level coefficient corresponding to the quality assurance level; Normalize the spare part classification corresponding to the potential sub-spare parts to obtain the spare part classification coefficient corresponding to the spare part classification; Normalize whether there is drawing information corresponding to the potential sub-spare parts to obtain the spare part classification coefficient corresponding to whether there is drawing information; Based on the average annual consumption of all spare parts in the second database and a preset multiple value, normalize the average annual consumption of the current spare part to obtain the average annual consumption coefficient of the current spare part; Based on the average annual consumption of the current spare part, the annual consumption standard deviation, and a preset upper limit value, normalize the dispersion coefficient to obtain the dispersion coefficient correction value of the current spare part; Based on the upper limit value and the lower limit value of the purchase unit price of the current spare part, normalize the purchase unit price of the current spare part to obtain the purchase unit price coefficient of the current spare part; Wherein, the potential sub-spare parts include the current spare part, and the standardized values include the material category coefficient, the quality assurance level coefficient, the spare part classification coefficient, the average annual consumption coefficient, the dispersion coefficient correction value, and the purchase unit price coefficient; the second database includes all the spare part list of the target equipment class associated with the functional location information and the spare part list of the target equipment class included in the internal annotation of the spare part code.

14. The method according to claim 9, wherein Calculating the linear combination values of each of the attribute categories based on the standardized values corresponding to each of the attribute categories included in the spare part information of the current spare part includes: Calculating the linear combination value based on the following formula: Among them, z is the linear combination value of an attribute category, b is a preset bias value, and w i is the weight value of the i-th attribute, and x i is the normalized value of the i-th attribute, and n is the total number of attribute categories.

15. An electronic device, characterized in that, Including a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, it implements the method according to any one of claims 1 to 14.

16. A computer program product, characterized in that, When the computer program product runs on the device, the device is caused to execute the method according to any one of claims 1 to 14.

Images