CN-122019785-A - Water meter matching method, device, electronic equipment, storage medium and program product

CN122019785ACN 122019785 ACN122019785 ACN 122019785ACN-122019785-A

Abstract

The invention relates to the technical field of water meter management and discloses a water meter matching method, a device, electronic equipment, a storage medium and a program product, wherein the water meter matching method comprises the steps of carrying out semantic analysis on description information of a target water meter to obtain a plurality of target keywords; the method comprises the steps of obtaining a target feature factor by corresponding each target keyword to feature factors of a plurality of pieces of water meter information in a water meter knowledge graph, determining an initial matching score according to dynamic weights, adjustable parameters, normalization factors and word frequencies of each target keyword, determining a semantic compensation score according to dynamic weights, relation path weights and distance attenuation factors, determining a target score sequence of the target water meter according to the initial matching score, the semantic compensation score and the semantic compensation score weight coefficient, and matching the target water meter according to the target score sequence.

Inventors

SUN YUNXIA
Rao Xuanjun
PENG JIANDONG
SONG HAIFENG
ZHENG YIFEI
WANG JUNSHENG
YAO LEI
CHEN ANQI
XUE FENG

Assignees

中国水务投资集团有限公司
中采物联(北京)供应链管理咨询有限公司

Dates

Publication Date: 20260512
Application Date: 20251231

Claims (10)

1. A method of matching a water meter, the method comprising: Acquiring description information of a target water meter input by a user, and carrying out semantic analysis on the description information to obtain a plurality of target keywords; Corresponding each target keyword to characteristic factors of a plurality of pieces of water meter information in a water meter knowledge graph to obtain a target characteristic factor corresponding to each target keyword; the target feature factors corresponding to the target keywords are feature factors corresponding to the target keywords in the water meter information; Acquiring dynamic weights of the target feature factors corresponding to each target keyword, and determining initial matching scores of the description information of the target water meter and each water meter information according to the dynamic weights, the adjustable parameters, the normalization factors corresponding to each water meter information and word frequencies of each target keyword, wherein the dynamic weights are used for representing importance degrees of the target feature factors adjusted according to attribute adjustment factors; determining semantic compensation scores of the description information of the target water meter and the water meter information according to the dynamic weight, the relation path weight and the distance attenuation factor of the target feature factor corresponding to each target keyword, wherein the relation path weight is a preset association strength weight of each target keyword and the corresponding target feature factor; And determining a target score sequence of the target water meter according to the initial matching score, the semantic compensation score and the semantic compensation score weight coefficient, and matching the target water meter according to the target score sequence.
2. The method of claim 1, further comprising a process of constructing the water meter knowledge graph, the process of constructing the water meter knowledge graph comprising: acquiring a plurality of pieces of water meter information, constructing a plurality of knowledge graph nodes according to a plurality of characteristic factors of each piece of water meter information, and constructing association types among the plurality of knowledge graph nodes according to association relations among the plurality of characteristic factors; Determining the dynamic weight of each characteristic factor according to the inverse product frequency of the characteristic factor and the attribute adjustment factor corresponding to each knowledge graph node; And obtaining the water meter knowledge graph according to the plurality of knowledge graph nodes, the association types among the plurality of knowledge graph nodes and the dynamic weights of the plurality of characteristic factors.
3. The method according to claim 1 or 2, wherein determining the initial matching score of the description information of the target water meter and each water meter information according to the dynamic weight, the adjustable parameter, the normalization factor corresponding to each water meter information, and the word frequency of each target keyword includes: obtaining a first summation result according to the sum of the adjustable parameters and 1, and obtaining a product result according to the product of the first summation result and the word frequency of each target keyword; obtaining a second summation result according to the sum of the normalization factor corresponding to each piece of water meter information and the word frequency of each target keyword; Obtaining a division result according to the quotient of the product result and the second summation result, and obtaining a score of each target keyword according to the product of the dynamic weight of the target feature factor corresponding to each target keyword and the division result; And summing the scores of the target keywords to obtain an initial matching score of the description information of the target water meter and each type of water meter information.
4. The method according to claim 1 or 2, wherein the determining the semantic compensation score of the description information of the target water meter and each water meter information according to the dynamic weight, the relationship path weight and the distance attenuation factor of the target feature factor corresponding to each target keyword includes: And summing products of the dynamic weights, the relation path weights and the distance attenuation factors of the target feature factors corresponding to the target keywords to obtain the semantic compensation scores of the description information of the target water meter and each piece of water meter information.
5. The method according to claim 1 or 2, wherein said determining a target score sequence for the target meter based on the initial match score, the semantic compensation score, and a semantic compensation score weight coefficient comprises: Obtaining a target semantic compensation score of the description information of the target water meter and each piece of water meter information according to the product of the semantic compensation score and the semantic compensation score weight coefficient; Obtaining the description information of the target water meter and the target score of each piece of water meter information according to the sum of the initial matching score and the target semantic compensation score; And arranging the description information of the target water meter and the target scores of the plurality of water meter information in order from big to small to obtain the target score sequence of the target water meter.
6. The method according to claim 1 or 2, wherein said matching the target water meter according to the target score sequence comprises: selecting target water meter information from the target score sequence, and matching the target water meter with the water meter corresponding to the target water meter information, wherein the target water meter information corresponds to the target score with the highest score in the target score sequence.
7. A water meter matching apparatus, said apparatus comprising: the semantic analysis module is used for acquiring the description information of the target water meter input by the user, and carrying out semantic analysis on the description information to obtain a plurality of target keywords; The characteristic corresponding module is used for corresponding each target keyword to characteristic factors of a plurality of pieces of water meter information in a water meter knowledge graph to obtain a target characteristic factor corresponding to each target keyword; The initial score determining module is used for obtaining the dynamic weight of the target characteristic factor corresponding to each target keyword, and determining the initial matching score of the description information of the target water meter and each water meter information according to the dynamic weight, the adjustable parameter, the normalization factor corresponding to each water meter information and the word frequency of each target keyword; The compensation score determining module is used for determining semantic compensation scores of the description information of the target water meter and the water meter information according to the dynamic weight, the relation path weight and the distance attenuation factor of the target feature factor corresponding to each target keyword, wherein the relation path weight is a preset association strength weight of each target keyword and the corresponding target feature factor; the water meter matching module is used for determining a target score sequence of the target water meter according to the initial matching score, the semantic compensation score and the semantic compensation score weight coefficient, and matching the target water meter according to the target score sequence.
8. An electronic device, comprising: A memory and a processor, the memory and the processor being communicatively connected to each other, the memory having stored therein computer instructions, the processor executing the computer instructions to perform the method of matching a water meter according to any one of claims 1 to 6.
9. A computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method of matching a water meter according to any one of claims 1 to 6.
10. A computer program product comprising computer instructions for causing a computer to perform the matching method of a water meter according to any one of claims 1 to 6.

Description

Water meter matching method, device, electronic equipment, storage medium and program product Technical Field The invention relates to the technical field of water meter management, in particular to a water meter matching method, a device, electronic equipment, a storage medium and a program product. Background The water meter is used as core metering equipment in water service industry, has complex types and multidimensional technical parameters, so that the water meter needs to be managed, and the type and the attribute of each water meter need to be identified when the water meter is managed, thereby implementing a targeted management strategy according to the type and the attribute of the water meter. In the related art, the method for identifying the water meter is that the type of the water meter is judged through manual experience, so that the water meter is managed, but thousands of pieces of water meter data are faced, the manual matching speed is low, and the accuracy and the efficiency cannot meet the requirements of industrial-grade application. Disclosure of Invention The invention provides a water meter matching method, a device, electronic equipment, a storage medium and a program product, which are used for solving the problems that the matching speed is low, and the accuracy and the efficiency cannot meet the requirements of industrial-grade application caused by a water meter identification method in the related technology. The invention provides a water meter matching method, which comprises the steps of obtaining description information of a target water meter input by a user, carrying out semantic analysis on the description information to obtain a plurality of target keywords, corresponding each target keyword to characteristic factors of a plurality of water meter information in a water meter knowledge graph to obtain a target characteristic factor corresponding to each target keyword, wherein the target characteristic factor corresponding to each target keyword is a characteristic factor corresponding to each target keyword in each water meter information, obtaining dynamic weights of the target characteristic factors corresponding to each target keyword, determining an initial matching score of the description information of the target water meter and each water meter information according to dynamic weights, adjustable parameters, normalization factors corresponding to each water meter information and word frequencies of each target keyword, wherein the dynamic weights are used for representing the importance degree of the target characteristic factors adjusted according to attribute adjustment factors, determining semantic compensation scores of the description information of the target water meter and each water meter information according to dynamic weights, relation path weights and distance attenuation factors of the target characteristic factors corresponding to each target keyword, determining a semantic compensation score of the target water meter according to the preset target weight corresponding to the initial matching score of the target weight and the target compensation score, and the target matching score of the initial matching score. According to the matching method of the water meter, the description information of the target water meter input by the user is obtained, semantic analysis is carried out on the description information, so that a plurality of target keywords are obtained, the limitation of strict matching of the keywords is broken through, natural language description can be understood through semantic analysis, and the flexibility of the description information of the target water meter input by the user is improved. According to the invention, each target keyword corresponds to the characteristic factors of a plurality of pieces of water meter information in the water meter knowledge graph, so that the target characteristic factors corresponding to each target keyword are obtained, the mapping from the target keywords to the target characteristic factors corresponding to each target keyword in each piece of water meter information is realized according to the water meter knowledge graph, the misplacement matching of the target keywords and the water meter attributes is avoided, and the matching accuracy is improved. The method acquires the dynamic weight of the target feature factor corresponding to each target keyword, determines the initial matching score of the description information of the target water meter and each water meter information according to the dynamic weight, the adjustable parameter, the normalization factor corresponding to each water meter information and the word frequency of each target keyword, merges the dynamic weight of the importance degree of the target feature factor adjusted according to the attribute adjustment factor, enables the initial matching score to embody the actual value priority of the water meter, combines