CN115774997A - Substitute material determination method, system and equipment - Google Patents
Substitute material determination method, system and equipment Download PDFInfo
- Publication number
- CN115774997A CN115774997A CN202211450445.0A CN202211450445A CN115774997A CN 115774997 A CN115774997 A CN 115774997A CN 202211450445 A CN202211450445 A CN 202211450445A CN 115774997 A CN115774997 A CN 115774997A
- Authority
- CN
- China
- Prior art keywords
- materials
- substituted
- text
- stock
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present disclosure provides a substitute material determination method, system and device, the substitute material determination method includes: establishing a material data dictionary, wherein the material data dictionary comprises special words for materials; the method comprises the steps of obtaining a text of materials to be replaced and a text of stock materials, wherein the text of the materials to be replaced is a description text of the materials to be replaced, and the text of the stock materials is a description text of the stock materials; according to the material data dictionary, performing Chinese word segmentation on a material text to be replaced and an inventory material text, and establishing a word bag model; determining a weighting vector of the material to be replaced and a weighting vector of the stock material according to the bag-of-words model; and determining the substitute materials in the stock materials according to the weighting vectors of the materials to be substituted and the weighting vectors of the stock materials. The method can quickly and accurately find out appropriate substitute materials in the stock materials, and obviously improves the condition of stock extrusion waste.
Description
Technical Field
The present disclosure relates to the field of data processing, and in particular, to a method, system, and device for determining substitute materials.
Background
In the mechanical manufacturing industry, especially in discrete manufacturing enterprises, the generation mode has the characteristics of multiple varieties, small batch and customization, so that the overstocked waste of material is easy to occur.
In the related art, in order to reduce the overstock waste of the stock of the material, before the designer requires the purchase of a new material, the material manager of the warehouse compares the material to be purchased with the stock material to find out whether a substitute material exists in the stock material.
However, the above method for searching for substitute materials is very limited by the technical level of the material manager, it is difficult to quickly and accurately find suitable substitute materials in the stock materials, and the improvement on the overstock waste of the stock is not obvious.
Disclosure of Invention
The embodiment of the disclosure provides a substitute material determining method, system and device, which can quickly and accurately find out a proper substitute material from stock materials, and obviously improve the waste of stock extrusion. The technical scheme is as follows:
in one aspect, an embodiment of the present disclosure provides a substitute material determination method, including:
establishing a material data dictionary, wherein the material data dictionary comprises special words for materials;
the method comprises the steps of obtaining a text of materials to be replaced and a text of stock materials, wherein the text of the materials to be replaced is a description text of the materials to be replaced, and the text of the stock materials is a description text of the stock materials;
according to the material data dictionary, chinese word segmentation is carried out on the material text to be substituted and the stock material text, and a word bag model is established;
determining a weighting vector of the material to be substituted and a weighting vector of the stock material according to the bag-of-word model;
and comparing the weight vector of the material to be replaced with the weight vector of the stock material to determine a replacement material in the stock material.
In yet another implementation of the present disclosure, establishing a material data dictionary includes:
acquiring enterprise main data resources, wherein the main data resources comprise special words of materials in the industry field of enterprises;
and establishing the material data dictionary according to the main data resource, wherein the material data dictionary at least comprises material codes, material marks, materials, specifications, standard numbers, material performance grades, material names and classification society names.
In another implementation manner of the present disclosure, performing chinese word segmentation on the to-be-substituted material text and the stock material text according to the material data dictionary, and establishing a word bag model includes:
acquiring a stop word list, wherein the stop word list comprises irrelevant words and redundant words;
according to the material data dictionary, chinese word segmentation is carried out on the material text to be substituted and the stock material text to obtain a set of feature words;
and according to the stop word list, removing irrelevant words and redundant words from the feature word set to establish the bag-of-words model.
In yet another implementation of the present disclosure, determining the weight vector of the material to be substituted and the weight vector of the inventory material based on the bag-of-words model includes:
determining the characteristic words of the materials to be substituted, calculating to obtain the characteristic word weighting vectors of the materials to be substituted based on the word bag model, and determining the weighting vectors of the materials to be substituted according to the characteristic word weighting vectors of the materials to be substituted;
determining the characteristic words of the inventory materials, calculating to obtain the characteristic word weighting vector of the inventory materials based on the word bag model, and determining the weighting vector of the inventory materials according to the characteristic word weighting vector of the inventory materials.
In yet another implementation of the present disclosure, determining a recommended alternative material list according to the weighting vector of the material to be substituted and the weighting vector of the inventory material includes:
sequentially calculating the weighting vector of the material to be replaced and the cosine similarity value of the weighting vector of each stock material;
and sequentially comparing each cosine similarity value with a similarity threshold, and if the cosine similarity value is greater than the similarity threshold, determining the corresponding stock material as a substitute material.
In another aspect, an embodiment of the present disclosure provides a surrogate material determining system, including:
the system comprises a dictionary module, a data processing module and a data processing module, wherein the dictionary module is used for establishing a material data dictionary which comprises special words for materials;
the text module is used for acquiring a to-be-substituted material text and an inventory material text, wherein the to-be-substituted material text is a description text of a to-be-substituted material, and the inventory material text is a description text of the inventory material;
the word bag module is used for carrying out Chinese word segmentation on the material text to be substituted and the stock material text according to the material data dictionary and establishing a word bag model;
the weighting module is used for determining a weighting vector of the material to be replaced and a weighting vector of the stock material;
and the substitute material determining module is used for determining substitute materials in the stock materials according to the weighting vector of the materials to be substituted and the weighting vector of the stock materials.
In one implementation of the present disclosure, the weighting module includes:
the to-be-substituted material weighting submodule is used for determining the characteristic words of the to-be-substituted material, calculating to obtain the characteristic word weighting vector of the to-be-substituted material based on the word bag model, and determining the weighting vector of the to-be-substituted material according to the characteristic word weighting vector of the to-be-substituted material;
and the inventory goods and materials weighting submodule is used for determining the characteristic words of the inventory goods and materials, calculating to obtain the characteristic word weighting vectors of the inventory goods and materials based on the word bag model, and determining the weighting vectors of the inventory goods and materials according to the characteristic word weighting vectors of the inventory goods and materials.
In another implementation of the disclosure, the surrogate material determination module includes:
the cosine similarity operator module is used for sequentially calculating the weighting vectors of the goods and materials to be substituted and the cosine similarity value of the weighting vector of each stock goods and materials;
and the substitute material determining submodule is used for sequentially comparing each cosine similarity value with a similarity threshold value, and if the cosine similarity value is greater than the similarity threshold value, determining the corresponding stock material as a substitute material.
In yet another aspect, embodiments of the present disclosure provide a computer device comprising a processor and a memory configured to store processor-executable instructions; the processor is configured to perform the surrogate material determination method described above.
In yet another aspect, the disclosed embodiments provide a computer storage medium having computer instructions stored thereon, wherein the computer instructions, when executed by a processor, implement the surrogate material determining method described above.
The technical scheme provided by the embodiment of the disclosure has the following beneficial effects:
by the adoption of the substitute material determining method provided by the embodiment of the disclosure, whether substitute materials exist in stock materials can be found before new material purchasing is needed. When the substitute material determining method is executed, a material data dictionary is established at first, and because the material data dictionary comprises special words for materials, the characteristic words can be accurately decomposed when the subsequent Chinese words are segmented. And then, respectively obtaining description texts of the materials to be substituted and the inventory materials, namely the texts of the materials to be substituted and the texts of the inventory materials, and carrying out Chinese word segmentation on the texts of the materials to be substituted and the texts of the inventory materials, so as to decompose characteristic words of the materials to be substituted and the inventory materials, and establishing a word bag model according to the characteristic words. Then, based on the bag-of-words model, a weighting vector for the material to be substituted and a weighting vector for the inventory material are determined. And finally, searching the materials similar to the materials to be substituted in the stock materials according to the weighting vectors of the materials to be substituted and the weighting vectors of the stock materials to determine the materials to be substituted as the substitute materials so as to replace the new materials to be purchased for use.
That is to say, through the substitute material determining method provided by the embodiment of the disclosure, a suitable substitute material can be quickly and accurately found in the stock materials, and the waste of stock extrusion is obviously improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and it is obvious for those skilled in the art to obtain other drawings based on the drawings without creative efforts.
FIG. 1 is a flow chart of a method for determining alternative materials provided by an embodiment of the present disclosure;
FIG. 2 is a flow chart of another alternative material determination method provided by the embodiments of the present disclosure;
FIG. 3 is a block diagram of a surrogate material determining system provided by an embodiment of the disclosure;
fig. 4 is a schematic structural diagram of a computer device provided in an embodiment of the present disclosure.
Detailed Description
To make the objects, technical solutions and advantages of the present disclosure more apparent, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.
In the machine manufacturing industry, especially in discrete manufacturing enterprises, the generation mode has the characteristics of multiple varieties, small batch and customization, so that the overstocked waste of materials is easy to occur.
In the related art, in order to reduce the overstock waste of the stock of the material, before the designer requires the purchase of a new material, the material manager of the warehouse compares the material to be purchased with the stock material to find out whether a substitute material exists in the stock material.
However, the above method for finding substitute materials is very limited by the technical level of the material manager, and it is difficult to find suitable substitute materials in the stock materials quickly and accurately, and the improvement of the overstock waste of the stock is not obvious.
In order to solve the above technical problem, an embodiment of the present disclosure provides a substitute material determining method, where fig. 1 is a flowchart of the substitute material determining method, and referring to fig. 1, in the embodiment, the substitute material determining method includes:
step 101: and establishing a material data dictionary, wherein the material data dictionary comprises special words for materials.
Step 102: the method comprises the steps of obtaining a to-be-substituted material text and an inventory material text, wherein the to-be-substituted material text is a description text of the to-be-substituted material, and the inventory material text is a description text of the inventory material.
Step 103: according to the goods and materials data dictionary, chinese word segmentation is carried out on the goods and materials text to be substituted and the stock goods and materials text, and a word bag model is established, wherein the word bag model comprises characteristic words of the goods and materials to be substituted and characteristic words of the stock goods and materials.
Step 104: and determining a weighting vector of the material to be replaced and a weighting vector of the stock material based on the bag-of-words model.
Step 105: and determining the substitute materials in the stock materials according to the weighting vectors of the materials to be substituted and the weighting vectors of the stock materials.
By the adoption of the substitute material determining method, whether substitute materials exist in stock materials can be found before new material purchasing is needed. When the substitute material determining method is executed, a material data dictionary is established at first, and because the material data dictionary comprises special words for materials, the characteristic words can be accurately decomposed when the subsequent Chinese words are segmented. And then, respectively obtaining description texts of the materials to be substituted and the inventory materials, namely the texts of the materials to be substituted and the texts of the inventory materials, and carrying out Chinese word segmentation on the texts of the materials to be substituted and the texts of the inventory materials, so as to decompose characteristic words of the materials to be substituted and the inventory materials, and establishing a word bag model according to the characteristic words. Then, based on the bag-of-words model, a weighting vector for the material to be substituted and a weighting vector for the inventory material are determined. And finally, searching the materials similar to the materials to be substituted in the stock materials according to the weighting vectors of the materials to be substituted and the weighting vectors of the stock materials to determine the materials to be substituted as the substitute materials so as to replace the new materials to be purchased for use.
That is to say, through the substitute material determining method provided by the embodiment of the disclosure, a suitable substitute material can be quickly and accurately found in inventory materials, and the waste of inventory extrusion is obviously improved.
Fig. 2 is a flowchart of another alternative material determining method provided in an embodiment of the present disclosure, and with reference to fig. 2, in this embodiment, the alternative material determining method is applied to a computer, and includes:
step 201: and establishing a material data dictionary, wherein the material data dictionary comprises special words for materials.
In step 201, firstly, business owner data resources are obtained, and the main data resources include special words of materials in the industry field to which the business belongs.
Then, a material data dictionary is established according to the main data resource.
In the implementation mode, for enterprises in different industry fields, the related materials are greatly different. Therefore, the material data dictionary is established based on the enterprise owner data resources, and Chinese word segmentation can be more accurately realized in the subsequent steps. The enterprise main data resources are manually compiled for enterprises according to the industry fields of the enterprises, and by combining the required purchased materials, inventory materials and other common materials. In other embodiments, the business owner data resources can also utilize historical procurement information and inventory information in combination with manual authoring.
For example, in this embodiment, the substitute material determining method is applicable to the field of ships, and the special words for materials in the material data dictionary at least include material codes, material marks, materials, specifications, standard numbers, material performance grades, material names, and classification society names.
In some examples, the word frequency and part-of-speech of the special words can be saved together when the materials data dictionary is established. For example, the term is "steel plate for a ship", the word frequency of the steel plate for a ship is 5, and the word property of the steel plate for a ship is noun.
Step 202: and acquiring a text of the materials to be substituted and a text of the stock materials, wherein the text of the materials to be substituted is a description text of the materials to be substituted, and the text of the stock materials is a description text of the stock materials.
In this embodiment, the stock material refers to the existing material in the warehouse. The material to be replaced refers to the material waiting for replacement by stock material, namely the material needing to be newly purchased. The text of the materials to be replaced is filled in when technical personnel purchase and apply, and the text of the stock materials is filled in when material management personnel enter a warehouse for registration.
In step 202, a material set for the material to be replaced is first determined, wherein the material set includes all the material to be replaced. Determining a material set of inventory materials, wherein the material set comprises all inventory materials.
Illustratively, the quantity of the materials to be substituted is 1, and the quantity of the materials for stock materials is more, so that the retrieval accuracy of the materials to be substituted can be improved. It should be noted that the amount of the material to be substituted and the amount of the material to be stocked are not limited in this disclosure.
And then, determining a material text to be substituted and a stock material text according to the material set of the material to be substituted and the material set of the stock material.
Step 203: a deactivation vocabulary is obtained, the deactivation vocabulary including irrelevant vocabulary and redundant vocabulary.
In the above implementation, the irrelevant word refers to a word irrelevant to the material, for example, for the special word "steel plate for ship", the word "used" is used as the irrelevant word. Redundant words refer to words with excessive frequency, such as "of", "x", etc., which appear in large numbers in specification-related specialized words.
It should be noted that the stop word list is manually written according to actual requirements.
Step 204: and performing Chinese word segmentation on the to-be-substituted material text and the stock material text according to the material data dictionary to obtain a set of characteristic words.
Step 205: and according to the stop word list, removing irrelevant words and redundant words from the feature word set to establish a word bag model, wherein the word bag model comprises feature words of the materials to be substituted and feature words of the inventory materials.
For example, the text of the material to be substituted is "010140, hot-rolled square steel pipe, GB/T3094, 140 × 140 × 8, and Q355B", and after chinese word segmentation, the decomposed characteristic words are "010140", "hot-rolled square steel pipe", "GB/T3094", "140", "8", "x", and "Q355B", and after irrelevant words and redundant words are removed, the characteristic words are "010140", "hot-rolled square steel pipe", "GB/T3094", "140", "8", "Q355B".
Step 206: based on the bag-of-words model, a weighting vector of the material to be substituted and a weighting vector of the inventory material are determined.
It should be noted that the weighting vector is obtained by using a TF-IDF weighting technique. TF-IDF (Term Frequency-Inverse Document Frequency) is a commonly used weighting technique for information retrieval and data mining, where TF is Term Frequency (Term Frequency) and IDF is Inverse text Frequency index (Inverse Document Frequency).
In step 206, firstly, the feature words of the material to be substituted are determined, the feature word weighting vector of the material to be substituted is calculated based on the word bag model, and the weighting vector of the material to be substituted is determined according to the feature word weighting vector of the material to be substituted.
Then, determining the characteristic words of the inventory materials, calculating to obtain the characteristic word weighting vector of the inventory materials based on the word bag model, and determining the weighting vector of the inventory materials according to the characteristic word weighting vector of the inventory materials.
Calculating to obtain a weighting vector of each feature word through the following relational expression:
TFIDF＝(n/N)*[log(M/m)] (1)
in the relation (1), TFIDF is the weighted value of the feature word, N is the word frequency of the feature word in the corresponding material text, N is the word frequency of the feature word in all materials, M is the number of all materials, and M is the total number of feature words in the material text corresponding to the feature word.
Step 207: and sequentially calculating the weighting vector of the material to be replaced and the cosine similarity value of the weighting vector of each stock material.
In step 207, the cosine similarity value of the weighting vector of the material to be substituted and the weighting vector of the inventory material is calculated by the following relation:
cosθ＝A*B/(||A||*||B||) (2)
in the relation (2), a and B are weight vectors of the two materials, respectively.
Step 208: and comparing each cosine similarity value with the similarity threshold value in sequence, and if the cosine similarity value is greater than the similarity threshold value, executing step 209. If the cosine similarity value is not greater than the similarity threshold, the cosine similarity value is considered to be irrelevant, and step 207 is executed again to calculate the cosine similarity values of the weighting vectors of the materials to be substituted and the weighting vectors of other stock materials.
Illustratively, the similarity threshold is 0.5.
Step 209: and determining the corresponding stock materials as substitute materials.
Illustratively, step 209 is performed by:
step 2091: and determining the corresponding stock material with the cosine similarity value larger than the similarity threshold value as the quasi-substitute material.
Step 2092: judging the type of the material to be substituted and the type of the material to be substituted, if the type of the material to be substituted is the same as the type of the material to be substituted, executing step 2093, otherwise, judging the two are not related.
Step 2093: and judging whether the difference between the size of the material to be substituted and the size of the material to be substituted is within the size difference range, if so, determining the material to be substituted as the substituted material, and if not, determining that the two are irrelevant.
For example, for hot-rolled square steel pipes, the range of the size difference includes a range of length difference, a range of width difference, and a range of wall thickness difference. The length difference ranges from L to L,1.2 to L, and the width difference ranges from H to H. 1.3H, wall thickness difference range is delta epsilon [ delta, 1.5 delta ].
In some examples, the supplies to be substituted and the corresponding substitute supplies are recorded together as a table for reference when subsequently purchasing new supplies.
Fig. 3 is a block diagram of a substitute material determination system according to an embodiment of the present disclosure, which is combined with fig. 3, and in this embodiment, the substitute material determination system includes a dictionary module 10, a text module 20, a word bag module 30, a weighting module 40, and a substitute material determination module 50.
The dictionary module 10 is used for establishing a material data dictionary, and the material data dictionary comprises special words for materials. The text module 20 is used for acquiring a text of the materials to be substituted and a text of the stock materials, wherein the text of the materials to be substituted is a description text of the materials to be substituted, and the text of the stock materials is a description text of the stock materials. The word bag module 30 is configured to perform chinese word segmentation on the to-be-substituted material text and the stock material text according to the material data dictionary, and establish a word bag model. The weighting module 40 is configured to determine a weighting vector for the supply to be replaced and a weighting vector for the inventory supply. The substitute material determining module 50 is configured to determine substitute materials from the inventory materials according to the weighting vectors of the materials to be substituted and the weighting vectors of the inventory materials.
In this embodiment, the weighting module 40 includes: a material to be substituted weighting submodule and an inventory material weighting submodule. The goods and materials to be substituted weighting submodule is used for determining the feature words of the goods and materials to be substituted, calculating to obtain the feature word weighting vectors of the goods and materials to be substituted based on the word bag model, and determining the weighting vectors of the goods and materials to be substituted according to the feature word weighting vectors of the goods and materials to be substituted. The inventory material weighting submodule is used for determining the characteristic words of the inventory materials, calculating to obtain the characteristic word weighting vectors of the inventory materials based on the word bag model, and determining the weighting vectors of the inventory materials according to the characteristic word weighting vectors of the inventory materials.
In this embodiment, the substitute material determination module 50 includes: a cosine similarity operator module and a substitute material determination sub-module. And the cosine similarity operator module is used for sequentially calculating the weighting vector of the material to be substituted and the cosine similarity value of the weighting vector of each stock material. And the substitute material determining submodule is used for sequentially comparing each cosine similarity value with the similarity threshold, and if the cosine similarity value is greater than the similarity threshold, determining the corresponding stock material as the substitute material.
The substitute material determining system has the same beneficial effects as the substitute material determining method, and the description is omitted.
Fig. 4 is a schematic structural diagram of a computer device provided in an embodiment of the present disclosure, and in conjunction with fig. 4, the computer device 400 may include one or more of the following components: a processor 401, a memory 402, a communication interface 403, and a bus 404.
The processor 401 includes one or more processing cores, and the processor 401 executes various functional applications and information processing by running software programs and modules. The memory 402 and the communication interface 403 are connected to the processor 401 through a bus 404. The memory 402 may be configured to store at least one instruction that is executable by the processor 401 to perform the various steps of the surrogate material determining method described above.
Further, the memory 402 may be implemented by any type or combination of volatile or non-volatile storage devices, including, but not limited to: magnetic or optical disks, electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), static Random Access Memory (SRAM), read-only memory (ROM), magnetic memory, flash memory, programmable read-only memory (PROM).
Embodiments of the present disclosure also provide a computer storage medium, and computer instructions, when executed by a processor, implement the above method for determining substitute materials.
Unless defined otherwise, technical or scientific terms used herein shall have the ordinary meaning as understood by one of ordinary skill in the art to which this disclosure belongs. The use of "first," "second," "third," and similar terms in the description and claims of the present disclosure are not intended to indicate any order, quantity, or importance, but rather are used to distinguish one element from another. Also, the use of the terms "a" or "an" and the like do not denote a limitation of quantity, but rather denote the presence of at least one. The word "comprising" or "comprises", and the like, means that the element or item appearing in front of the word "comprising" or "comprises" includes the element or item listed after the word "comprising" or "comprises" and its equivalents, and does not exclude other elements or items.
Although the present disclosure has been described with reference to specific embodiments, it will be understood by those skilled in the art that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the disclosure, and it is intended that all matter contained in the above description or shown in the accompanying drawings shall be interpreted as illustrative and not in a limiting sense.
Claims (10)
1. A method for identifying a substitute material, comprising:
establishing a material data dictionary, wherein the material data dictionary comprises special words for materials;
the method comprises the steps of obtaining a text of materials to be replaced and a text of stock materials, wherein the text of the materials to be replaced is a description text of the materials to be replaced, and the text of the stock materials is a description text of the stock materials;
according to the material data dictionary, chinese word segmentation is carried out on the material text to be substituted and the stock material text, and a word bag model is established, wherein the word bag model comprises characteristic words of the material to be substituted and characteristic words of the stock material;
determining a weighting vector of the material to be replaced and a weighting vector of the stock material based on the bag-of-words model;
and determining substitute materials in the stock materials according to the weighting vector of the materials to be substituted and the weighting vector of the stock materials.
2. A surrogate material determination method as claimed in claim 1 in which establishing a material data dictionary comprises:
acquiring main data resources of an enterprise, wherein the main data resources comprise special words of materials in the industry field of the enterprise;
and establishing the material data dictionary according to the main data resource, wherein the material data dictionary at least comprises material codes, material marks, materials, specifications, standard numbers, material performance grades, material names and classification society names.
3. The substitute material determination method according to claim 1, wherein performing chinese word segmentation on the material text to be substituted and the stock material text according to the material data dictionary, and establishing a word bag model comprises:
acquiring a stop word list, wherein the stop word list comprises irrelevant words and redundant words;
according to the material data dictionary, chinese word segmentation is carried out on the material text to be substituted and the stock material text to obtain a set of feature words;
and according to the stop word list, removing irrelevant words and redundant words from the feature word set to establish the bag-of-words model.
4. The surrogate material determination method of claim 1, wherein determining the weight vector for the material to be surrogate and the weight vector for the inventory material based on the bag-of-words model comprises:
determining the characteristic words of the materials to be substituted, calculating to obtain the characteristic word weighting vectors of the materials to be substituted based on the word bag model, and determining the weighting vectors of the materials to be substituted according to the characteristic word weighting vectors of the materials to be substituted;
determining the characteristic words of the inventory materials, calculating to obtain the characteristic word weighting vector of the inventory materials based on the word bag model, and determining the weighting vector of the inventory materials according to the characteristic word weighting vector of the inventory materials.
5. A proxy material determination method as claimed in claim 1, wherein determining a recommended list of proxy materials based on the weighted vector of materials to be substituted and the weighted vector of inventory materials comprises:
sequentially calculating the weighting vector of the material to be replaced and the cosine similarity value of the weighting vector of each stock material;
and sequentially comparing each cosine similarity value with a similarity threshold, and if the cosine similarity value is greater than the similarity threshold, determining the corresponding stock material as a substitute material.
6. A surrogate material determination system, comprising:
the system comprises a dictionary module, a data processing module and a data processing module, wherein the dictionary module is used for establishing a material data dictionary which comprises special words for materials;
the text module is used for acquiring a to-be-substituted material text and an inventory material text, wherein the to-be-substituted material text is a description text of a to-be-substituted material, and the inventory material text is a description text of the inventory material;
the word bag module is used for carrying out Chinese word segmentation on the material text to be substituted and the stock material text according to the material data dictionary and establishing a word bag model;
the weighting module is used for determining a weighting vector of the material to be replaced and a weighting vector of the stock material;
and the substitute material determining module is used for determining substitute materials in the stock materials according to the weighting vector of the materials to be substituted and the weighting vector of the stock materials.
7. A surrogate material determining system as claimed in claim 6, in which the weighting module comprises:
the to-be-substituted material weighting submodule is used for determining the characteristic words of the to-be-substituted material, calculating to obtain the characteristic word weighting vector of the to-be-substituted material based on the word bag model, and determining the weighting vector of the to-be-substituted material according to the characteristic word weighting vector of the to-be-substituted material;
and the inventory material weighting submodule is used for determining the characteristic words of the inventory materials, calculating to obtain the characteristic word weighting vectors of the inventory materials based on the word bag model, and determining the weighting vectors of the inventory materials according to the characteristic word weighting vectors of the inventory materials.
8. The surrogate material determination system of claim 6, wherein the surrogate material determination module comprises:
the cosine similarity degree operator module is used for calculating the weighting vector of the material to be substituted and the cosine similarity degree of the weighting vector of each stock material in turn;
and the substitute material determining submodule is used for sequentially comparing each cosine similarity value with a similarity threshold value, and if the cosine similarity value is greater than the similarity threshold value, determining the corresponding stock material as a substitute material.
9. A computer device, comprising a processor and a memory configured to store processor-executable instructions; the processor is configured to perform the surrogate material determination method of any of claims 1 to 5.
10. A computer storage medium having computer instructions stored thereon, wherein the computer instructions, when executed by a processor, implement the surrogate material determination method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211450445.0A CN115774997A (en) | 2022-11-19 | 2022-11-19 | Substitute material determination method, system and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211450445.0A CN115774997A (en) | 2022-11-19 | 2022-11-19 | Substitute material determination method, system and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115774997A true CN115774997A (en) | 2023-03-10 |
Family
ID=85389461
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211450445.0A Pending CN115774997A (en) | 2022-11-19 | 2022-11-19 | Substitute material determination method, system and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115774997A (en) |
-
2022
- 2022-11-19 CN CN202211450445.0A patent/CN115774997A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Brickley et al. | Management fads and organizational architecture | |
| CN106776695B (en) | Method for automatically identifying value of document and file | |
| US7805462B2 (en) | Portfolio management methods, systems, and computer programs | |
| CN111931021B (en) | Engineering national standard database self-adaptive construction method based on data mining | |
| US9443214B2 (en) | News mining for enterprise resource planning | |
| CN111797115A (en) | Employee information searching method and device | |
| CN115774997A (en) | Substitute material determination method, system and equipment | |
| CN110097250B (en) | Product risk prediction method, device, computer equipment and storage medium | |
| CN112699245A (en) | Construction method and device and application method and device of budget management knowledge graph | |
| CN110941952A (en) | Method and device for perfecting audit analysis model | |
| CN112380321A (en) | Primary and secondary database distribution method based on bill knowledge graph and related equipment | |
| Anton et al. | Lean warehousing model to improve the order fulfillment in a metalworking company | |
| CN116562518A (en) | Work order recommendation method, device and storage medium | |
| Borek et al. | A risk management approach to improving information quality for operational and strategic management | |
| CN110991177B (en) | Material weight removing method and device | |
| CN112256566A (en) | Test case preservation method and device | |
| CN112015916A (en) | Completion method and device of knowledge graph, server and computer storage medium | |
| CN111782736B (en) | Data classification management method and system | |
| Gaurav et al. | Software Parts Classification for Agile and Efficient Product Life Cycle Management | |
| US20230004873A1 (en) | System and method for artificial intelligence driven document analysis, including automated reuse of predictive coding rules based on management and curation of datasets or models | |
| CN118051490A (en) | Standard file management method, system, terminal and storage medium | |
| US20240220876A1 (en) | Artificial intelligence (ai) based data product provisioning | |
| Nurrohkayati | Economic analysis development and provider elective decision model on auto-ID technology investment | |
| Hosen et al. | Data-Driven Decision Making: Advanced Database Systems for Business Intelligence | |
| Rana et al. | A framework for identifying and evaluating technologies of interest for effective business strategy: Using text analytics to augment technology forecasting |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |