CN114118083A - Industrial resource information matching optimization method - Google Patents
Industrial resource information matching optimization method Download PDFInfo
- Publication number
- CN114118083A CN114118083A CN202111456694.6A CN202111456694A CN114118083A CN 114118083 A CN114118083 A CN 114118083A CN 202111456694 A CN202111456694 A CN 202111456694A CN 114118083 A CN114118083 A CN 114118083A
- Authority
- CN
- China
- Prior art keywords
- data
- enterprise
- network
- industrial
- data information
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Abstract
The invention discloses an industrial resource information matching optimization method, which comprises the steps of collecting data information of each enterprise related to a preset industrial chain, and establishing a source database based on the data information; classifying data information in a source database according to weight calculation values of enterprises of a preset industrial chain, and constructing a network topological graph; capturing matched enterprise data required by different positioning of an industrial chain input by a terminal by using a network card to capture a packet, converting data codes into Chinese data by using a decoding model, and performing Chinese word segmentation; the data information which is optimally matched in the source database is searched based on the Chinese word segmentation result and the network topological graph and is pushed to the network terminal, so that the optimal matching of industrial resource information is realized, and the problem that the information matching deviation is large because the algorithm and the comparison model related to the existing intelligent screening means cannot perform accurate service aiming at different enterprises is solved.
Description
Technical Field
The invention relates to the technical field of new generation information technology, in particular to an industrial resource information matching optimization method.
Background
With the development of the technology and the improvement of the circuitous production degree, the production process is divided into a series of related production links, and in order to improve the production potential of enterprises, the relationship among different enterprises is communicated to form an overall industrial chain so as to promote the development of all the enterprises to become a hot spot which is concerned gradually.
Because the respective development degrees of different enterprises are inconsistent, the information of the communicated industrial chain needs to be screened and matched. The traditional screening method still depends on manual screening comparison, so that not only is a large amount of cost needed, but also the efficiency is low, and the screening accuracy is low; methods related to industrial information screening, such as screening based on big data or screening based on service capability prediction, have also been proposed in the prior art, but algorithms and comparison models related to the prior intelligent screening means cannot perform accurate service aiming at different enterprises, so that the information matching deviation is large.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and the title of the invention of this application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
The present invention has been made in view of the above-mentioned problems of the conventional industrial information screening methods.
Therefore, the technical problem solved by the invention is as follows: the algorithm and the comparison model related to the existing intelligent screening means cannot perform accurate service aiming at different enterprises, and the problem of large information matching deviation is caused.
In order to solve the technical problems, the invention provides the following technical scheme: an industrial resource information matching optimization method comprises the steps of collecting data information of each enterprise related to a preset industrial chain, and establishing a source database based on the data information; classifying the data information in the source database according to the weight calculation value of each enterprise of a preset industrial chain, and constructing a network topological graph; capturing matched enterprise data required by different positioning of an industrial chain input by a terminal by using a network card to capture a packet, converting data codes into Chinese data by using a decoding model, and performing Chinese word segmentation; and searching the best matched data information in the source database based on the Chinese word segmentation result and the network topological graph, and pushing the data information to a network terminal to realize the optimized matching of industrial resource information.
As a preferred embodiment of the industrial resource information matching optimization method of the present invention, wherein: the weight calculation value is obtained by the following formula,
the loss function is defined as:
wherein the content of the first and second substances,
the number of samples of the enterprise value analysis is represented,
representing the output characteristics of the mth sample in the enterprise value analysis samples passing through the model,
representing the category center corresponding to the mth sample;
the weight calculation value is maximized when the loss function L is minimized.
As a preferred embodiment of the industrial resource information matching optimization method of the present invention, wherein: classifying the data information according to the weight calculation values and constructing a network topology graph comprises,
dividing the weight calculation value into 3 grades according to the weight, wherein the 3 grades are respectively high grade, medium grade and low grade;
the high level is the first 30% of the weight calculation value;
the middle level is the weight calculation value interval [30%,72% ];
the low is the weight calculation value interval (72%, 100%);
and constructing a distributed topology structure chart according to the classification result.
As a preferred embodiment of the industrial resource information matching optimization method of the present invention, wherein: capturing matched enterprise data required by different positioning of an industrial chain input by a terminal by using a network card to grab a packet, wherein the network card is placed in a hybrid mode by using a network sniffer, and all data passing through the network card are received by the network sniffer; capturing all received data in real time by using a transmission layer and a network layer in the seven-layer model, and screening out TCP/IP protocol messages; and analyzing the TCP/IP protocol message by using an HTTP protocol specification, and converting Chinese codes into Chinese data based on a decoding model.
As a preferred embodiment of the industrial resource information matching optimization method of the present invention, wherein: and carrying out Chinese word segmentation by using an N-element grammar model.
As a preferred embodiment of the industrial resource information matching optimization method of the present invention, wherein: finding the data information in the source database that is the best match based on the chinese word segmentation results and the network topology map comprises,
constructing a data comparison model:
wherein the content of the first and second substances,
respectively representing nodes in Chinese word segmentation result
String of characters and nodes in source database
The character string of (a) is,
representing nodesXAnd nodeYThe character string edit distance between the two,
representing nodesXAnd nodeYThe text similarity of (2);
the weight coefficient of the data comparison model is as follows:
wherein the content of the first and second substances,
the weight coefficient is represented by a weight coefficient,
the constant weight coefficients are represented by the constant weight coefficients,
the number of the character string nodes is shown,
the function of the equalization is represented by,
the number of the symbols representing the constant number,
is shown as
An equalization function for each node.
As a preferred embodiment of the industrial resource information matching optimization method of the present invention, wherein: the criteria for determining whether the comparison result is the best match include,
when in use
，
The standard of successful comparison is met;
and selecting the enterprise with the largest enterprise scale from the data information meeting the comparison success standard as the best matched data information.
The invention has the beneficial effects that: the invention can increase the data comparison efficiency by utilizing the data to carry out level classification and utilizing the network card to capture the data in a packet capturing mode, carries out data searching and comparison based on the constructed data comparison model, improves the accuracy of information matching, and screens out the optimal matched enterprise information through intelligent automatic matching, thereby achieving the technical effects of improving the efficiency and the accuracy and saving the operation cost, and solving the problem that the algorithm and the comparison model related to the existing intelligent screening means can not carry out accurate service aiming at different enterprises, so that the information matching deviation is larger.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise. Wherein:
fig. 1 is a schematic basic flow chart of an industrial resource information matching optimization method provided by the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, specific embodiments accompanied with figures are described in detail below, and it is apparent that the described embodiments are a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present invention, shall fall within the protection scope of the present invention.
Example 1
The algorithm and the comparison model related to the existing intelligent screening means cannot perform accurate service aiming at different enterprises, and the caused information matching deviation is large.
FIG. 1 is a flow chart of one embodiment of a method for matching optimization of industrial resource information in accordance with the present invention; as shown in the figure:
s1: acquiring data information of each enterprise related to a preset industrial chain, and establishing a source database based on the data information;
specifically, each enterprise data information includes an enterprise direction and an enterprise size.
The enterprise direction can be searched on a registered business license and input into the database, the data is a definite value which can be clearly searched and sorted, corresponding classification can be carried out manually, the specific classification result does not influence the invention point, and redundant explanation is not carried out.
The scale of the enterprise: the value incorporation according to the conventional model is classified into 500 ten thousand and below as 3-step, 500- & ltSUB & gt 5000 ten thousand as 2-step, and more than 5000 ten thousand as 1-step, which are all determined values that can be referred to as input from the registration information, and will not be described in detail herein.
Of course, in order to improve the matching accuracy, enterprise data information may be correspondingly added, and it should be noted that the corresponding data information of the enterprise is all accurate values that can be determined, and is only required to be collated and incorporated by human.
S2: classifying data information in a source database according to weight calculation values of enterprises of a preset industrial chain, and constructing a network topological graph;
further, a weight calculation value is obtained by the following formula:
the loss function is defined as:
wherein the content of the first and second substances,
the number of samples of the enterprise value analysis is represented,
representing the output characteristics of the mth sample in the enterprise value analysis samples passing through the model,
representing the category center corresponding to the mth sample;
the weight calculation value is maximized when the loss function L is minimized.
Further, classifying the data information according to the weight calculation value, and constructing the network topology map includes:
dividing the weight calculation value into 3 grades according to the weight, wherein the 3 grades are respectively high grade, medium grade and low grade;
high is the first 30% of the weight calculation value;
the middle level is the weight calculation numerical interval [30%,72% ];
low is the weight calculation value interval (72%, 100%);
and constructing a distributed topology structure chart according to the classification result.
S3: capturing matched enterprise data required by different positioning of an industrial chain input by a terminal by using a network card to capture a packet, converting data codes into Chinese data by using a decoding model, and performing Chinese word segmentation;
specifically, a network card is placed in a hybrid mode by using a network sniffer, and all data passing through the network card are received by the network sniffer;
capturing all received data in real time by using a transmission layer and a network layer in the seven-layer model, and screening out TCP/IP protocol messages;
and analyzing the TCP/IP protocol message by using the HTTP protocol specification, and converting the Chinese code into Chinese data based on a decoding model.
The method comprises the following steps of performing Chinese word segmentation by using an N-element grammar model:
wherein n represents the number of iterations,
representing the number of chinese characters and P representing the probability.
Further, the converted Chinese data are used for generating N optimal results serving as candidate sets on the basis of a dictionary and an N-element grammar statistical model, then part-of-speech tagging is carried out on the candidate sets, and finally the optimal segmentation result is determined by utilizing context understanding information of the text.
S4: and searching the best matched data information in the source database based on the Chinese word segmentation result and the network topological graph, and pushing the best matched data information to the network terminal to realize the optimal matching of the required data information.
Specifically, the method for searching the best matching data information in the source database based on the Chinese word segmentation result and the network topological graph, sequentially extracting the texts in the database according to high level, middle level and low level to search and compare the texts comprises the following steps:
constructing a data comparison model:
wherein the content of the first and second substances,
respectively representing nodes in Chinese word segmentation result
String of characters and nodes in source database
The character string of (a) is,
representing nodesXAnd nodeYThe character string edit distance between the two,
representing nodesXAnd nodeYThe text similarity of (2);
the weight coefficients of the data comparison model are:
wherein the content of the first and second substances,
the weight coefficient is represented by a weight coefficient,
the constant weight coefficients are represented by the constant weight coefficients,
the number of the character string nodes is shown,
the function of the equalization is represented by,
the number of the symbols representing the constant number,
is shown as
An equalization function for each node.
Further, the criteria for determining whether the comparison result is the best matching data information include,
when in use
，
The standard of successful comparison is met;
and selecting the enterprise with the largest enterprise scale from the data information meeting the comparison success standard as the best matching data information.
The invention utilizes the data to carry out grade classification and utilizes the network card to capture the data in a packet capturing mode, thereby increasing the data comparison efficiency, and carrying out data searching comparison based on the constructed data comparison model, thereby improving the accuracy of data information matching.
Example 2
The technical effects adopted in the method are verified and explained, different methods selected in the embodiment and the method are adopted for comparison and test, and the test results are compared by means of scientific demonstration to verify the real effect of the method.
The traditional technical scheme is as follows: methods related to industrial information screening, such as screening based on big data or screening based on service capability prediction, have also been proposed in the prior art, but algorithms and comparison models related to the prior intelligent screening means cannot perform accurate service aiming at different enterprises, so that the information matching deviation is large. In order to verify that the method has higher efficiency and information matching accuracy compared with the existing algorithm and matching model method, the matching efficiency and accuracy of the simulation industrial chain are measured and compared in real time by adopting the traditional screening and the method respectively.
And (3) testing environment: simulating the existing industrial chain on a simulation platform, adopting different enterprise requirements as test samples, screening enterprise information by respectively utilizing the existing algorithm and a matching model method, and obtaining test result data; by adopting the method, the automatic test equipment is started, MATLB software is used for programming to realize the simulation test of the method, and simulation data are obtained according to the experimental result. In each method, 50 groups of data are tested, the information time pushed by each group of data and the information of the recruiting trader are calculated, the calculation error is compared with the actual required data information input by the simulation, and the result is shown in the following table.
Table 1: the experimental results are shown in a comparison table.
As can be seen from the above table, compared with the conventional method, the method of the present invention has higher efficiency on the basis of higher message push accuracy.
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.
Claims (7)
1. An industrial resource information matching optimization method is characterized by comprising the following steps:
acquiring data information of each enterprise related to a preset industrial chain, and establishing a source database based on the data information;
classifying the data information in the source database according to the weight calculation value of each enterprise of a preset industrial chain, and constructing a network topological graph;
capturing matched enterprise data required by different positioning of an industrial chain input by a terminal by using a network card to capture a packet, converting data codes into Chinese data by using a decoding model, and performing Chinese word segmentation;
and searching the best matched data information in the source database based on the Chinese word segmentation result and the network topological graph, and pushing the data information to a network terminal to realize the optimized matching of industrial resource information.
2. The industrial resource information matching optimization method according to claim 1, characterized in that: the weight calculation value is obtained by the following formula,
the loss function is defined as:
wherein the content of the first and second substances,
the number of samples of the enterprise value analysis is represented,
representing the output characteristics of the mth sample in the enterprise value analysis samples passing through the model,
representing the category center corresponding to the mth sample;
the weight calculation value is maximized when the loss function L is minimized.
3. The industrial resource information matching optimization method according to claim 2, characterized in that: classifying the data information according to the weight calculation values and constructing a network topology graph comprises,
dividing the weight calculation value into 3 grades according to the weight, wherein the 3 grades are respectively high grade, medium grade and low grade;
the high level is the first 30% of the weight calculation value;
the middle level is the weight calculation value interval [30%,72% ];
the low is the weight calculation value interval (72%, 100%);
and constructing a distributed topology structure chart according to the classification result.
4. The industrial resource information matching optimization method according to claim 3, characterized in that: matching enterprise data required by different positioning of an industrial chain input by a network card packet capturing terminal comprises,
the network card is placed in a hybrid mode by using a network sniffer, and all data passing through the network card are received by the network sniffer;
capturing all received data in real time by using a transmission layer and a network layer in the seven-layer model, and screening out TCP/IP protocol messages;
and analyzing the TCP/IP protocol message by using an HTTP protocol specification, and converting Chinese codes into Chinese data based on a decoding model.
5. The industrial resource information matching optimization method according to claim 4, characterized in that: and carrying out Chinese word segmentation by using an N-element grammar model.
6. The industrial resource information matching optimization method according to claim 5, characterized in that: finding the data information in the source database that is the best match based on the chinese word segmentation results and the network topology map comprises,
constructing a data comparison model:
wherein the content of the first and second substances,
respectively representing nodes in Chinese word segmentation result
String of characters and nodes in source database
The character string of (a) is,
representing nodesXAnd nodeYThe character string edit distance between the two,
representing nodesXAnd nodeYThe text similarity of (2);
the weight coefficient of the data comparison model is as follows:
wherein the content of the first and second substances,
the weight coefficient is represented by a weight coefficient,
the constant weight coefficients are represented by the constant weight coefficients,
the number of the character string nodes is shown,
the function of the equalization is represented by,
the number of the symbols representing the constant number,
is shown as
An equalization function for each node.
7. The industrial resource information matching optimization method according to claim 6, characterized in that: the criteria for determining whether the comparison result is the best match include,
when in use
，
The standard of successful comparison is met;
and selecting the enterprise with the largest enterprise scale from the data information meeting the comparison success standard as the best matched data information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111456694.6A CN114118083A (en) | 2021-12-02 | 2021-12-02 | Industrial resource information matching optimization method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111456694.6A CN114118083A (en) | 2021-12-02 | 2021-12-02 | Industrial resource information matching optimization method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114118083A true CN114118083A (en) | 2022-03-01 |
Family
ID=80369503
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111456694.6A Pending CN114118083A (en) | 2021-12-02 | 2021-12-02 | Industrial resource information matching optimization method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114118083A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116245260A (en) * | 2023-05-12 | 2023-06-09 | 国网吉林省电力有限公司信息通信公司 | Optimization method for deploying 5G base station based on substation resources |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112950347A (en) * | 2021-02-01 | 2021-06-11 | 大箴(杭州)科技有限公司 | Resource data processing optimization method and device, storage medium and terminal |
| CN112988762A (en) * | 2021-05-07 | 2021-06-18 | 江苏中辰软件科技有限公司 | Real-time identification and early warning method suitable for unit of losing message |
| CN113505242A (en) * | 2021-07-16 | 2021-10-15 | 珍岛信息技术（上海）股份有限公司 | Method and system for automatically embedding knowledge graph |
-
2021
- 2021-12-02 CN CN202111456694.6A patent/CN114118083A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112950347A (en) * | 2021-02-01 | 2021-06-11 | 大箴(杭州)科技有限公司 | Resource data processing optimization method and device, storage medium and terminal |
| CN112988762A (en) * | 2021-05-07 | 2021-06-18 | 江苏中辰软件科技有限公司 | Real-time identification and early warning method suitable for unit of losing message |
| CN113505242A (en) * | 2021-07-16 | 2021-10-15 | 珍岛信息技术（上海）股份有限公司 | Method and system for automatically embedding knowledge graph |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116245260A (en) * | 2023-05-12 | 2023-06-09 | 国网吉林省电力有限公司信息通信公司 | Optimization method for deploying 5G base station based on substation resources |
| CN116245260B (en) * | 2023-05-12 | 2023-08-08 | 国网吉林省电力有限公司信息通信公司 | Optimization method for deploying 5G base station based on substation resources |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110597735B (en) | Software defect prediction method for open-source software defect feature deep learning | |
| WO2021017679A1 (en) | Address information parsing method and apparatus, system and data acquisition method | |
| CN108287858A (en) | The semantic extracting method and device of natural language | |
| CN109325040B (en) | FAQ question-answer library generalization method, device and equipment | |
| CN110309300B (en) | Method for identifying knowledge points of physical examination questions | |
| CN109711424B (en) | Behavior rule acquisition method, device and equipment based on decision tree | |
| CN113177101B (en) | User track identification method, device, equipment and storage medium | |
| CN112416778A (en) | Test case recommendation method and device and electronic equipment | |
| CN113269239B (en) | Relation network node classification method based on multichannel convolutional neural network | |
| CN111709244A (en) | Deep learning method for identifying causal relationship of contradictory dispute events | |
| CN111651566B (en) | Multi-task small sample learning-based referee document dispute focus extraction method | |
| CN114298228A (en) | Address text information correlation learning method based on data preprocessing | |
| CN114118083A (en) | Industrial resource information matching optimization method | |
| CN117112850A (en) | Address standardization method, device, equipment and storage medium | |
| CN115062854A (en) | Dynamic estimation method for enterprise innovation information matching items | |
| CN116186506A (en) | Automatic identification method for accessibility problem report based on BERT pre-training model | |
| CN113535883B (en) | Commercial venue entity linking method, system, electronic equipment and storage medium | |
| CN114547294A (en) | Rumor detection method and system based on comprehensive information of propagation process | |
| CN114066506A (en) | AI analysis algorithm for network behavior | |
| CN114387005A (en) | Arbitrage group identification method based on graph classification | |
| CN113191707A (en) | Express delivery code generation method, device, equipment and storage medium | |
| CN113378024A (en) | Deep learning-based public inspection field-oriented related event identification method | |
| CN110738305A (en) | method and system for analyzing logistics waybill address | |
| CN111159360A (en) | Method and device for obtaining query topic classification model and query topic classification | |
| CN113722567B (en) | Entity relation extraction method based on multi-target fusion |
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 |