CN115544336A - Industrial chain generation method, device, computer equipment and storage medium - Google Patents

Abstract

The present application relates to an industrial chain generation method, device, computer equipment and storage medium. The method includes: according to the industrial electricity data and industrial production data of each target industry, determining the data correlation degree between the various target industries; according to the distance between the name information of the various target industries, determining the The degree of name association between industries; according to the entity relationship information in the industry association information of each target industry, determine the degree of relationship association between each target industry; according to the data association between each target industry degree, the degree of name association, and the degree of relationship association to generate an industrial chain map corresponding to each target industry. Adopting this method can improve the timeliness of industrial chain construction.

Description

Industrial chain generation method, device, computer equipment and storage medium

technical field

The present application relates to the field of big data technology, and in particular to an industrial chain generation method, device, computer equipment, storage medium and computer program product.

Background technique

The upstream and downstream of the industrial chain can reflect the relationship between different industries, and provide a research basis for guiding macroeconomic production and industry development.

At present, the existing industrial chain mainly builds a visual industrial chain manually. However, this method of manually establishing an industrial chain needs to build an industrial chain based on expert experience, which often takes a lot of time. Therefore, this method is time-sensitive. Poor question.

Contents of the invention

Based on this, it is necessary to provide an industrial chain generation method, device, computer equipment, computer readable storage medium and computer program product that can improve the timeliness of industrial chain construction in view of the above technical problems.

In a first aspect, the present application provides a method for generating an industrial chain. The methods include:

According to the industrial electricity data and industrial production data of each target industry, determine the data correlation between the various target industries;

According to the distance between the name information of the various target industries, determine the degree of name association between the various target industries;

According to the entity relationship information in the industry association information of each target industry, determine the degree of relationship association between each target industry;

According to the data association degree, the name association degree and the relationship association degree among the various target industries, an industry chain map corresponding to each target industry is generated.

In one of the embodiments, according to the industrial electricity data and industrial production data of each target industry, the data correlation degree between the various target industries is determined, including:

According to the industrial electricity data of each target industry, the historical electricity growth rate of each target industry is obtained;

According to the industrial production data of each target industry, the historical production growth rate of each target industry is obtained;

According to the historical electricity growth rate and the historical production growth rate, perform clustering processing on the target industries to obtain the industry classification results of the target industries;

According to the industry classification results of the various target industries, the degree of data association between the various target industries is obtained.

In one of the embodiments, according to the distance between the name information of the various target industries, determining the degree of name association between the various target industries includes:

In a case where it is detected that the name information of the first target industry is different from the name information of the second target industry, obtaining a text update required to update the name information of the first target industry to the name information of the second target industry times; the first target industry is any target industry among the various target industries; the second target industry is any target industry among the various target industries except the first target industry;

Obtaining the distance between the name information of the first target industry and the name information of the second target industry according to the number of text updates;

According to the distance, the degree of name association between the first target industry and the second target industry is obtained as the degree of name association between the respective target industries.

In one of the embodiments, according to the entity relationship information in the industry association information of each target industry, determining the degree of relationship between the various target industries includes:

Perform entity relationship extraction processing on the industry-related information of each target industry to obtain entity relationship information in each of the industry-related information;

According to the upstream and downstream relationships between industries in the industrial relationship dictionary database, perform upstream probability judgment and downstream probability judgment on the target industry in the entity relationship information, and obtain the upstream probability and downstream probability of the target industry in the entity relationship information ;

According to the upstream probability and the downstream probability of the target industry in the entity relationship information, the degree of relationship association between the various target industries is obtained.

In one of the embodiments, according to the data association degree, the name association degree and the relationship association degree among the various target industries, the industry chain map corresponding to each target industry is generated, including:

determining the industry association probability between the various target industries according to the data association degree, the name association degree and the relationship association degree among the various target industries;

determining the upstream and downstream industries corresponding to the respective target industries according to the upstream probability, the downstream probability and the industry association probability;

Visual graphics processing is performed on the upstream and downstream industries corresponding to each target industry to obtain the industrial chain map.

In one of the embodiments, after generating the industry chain map corresponding to each target industry according to the data association degree, the name association degree, and the relationship association degree among the various target industries, it further includes :

Obtain the current power data of each target industry in the current time period in the industrial chain map;

According to the current electricity data of each target industry, the current electricity growth rate of each target industry is obtained;

conducting year-on-year and ring-to-ring assessments of the current electricity growth rate and the historical electricity growth rate of each target industry to obtain the evaluation results of each target industry;

If the evaluation result is abnormal, the target industry corresponding to the evaluation result is updated upstream and downstream in the industry chain map to obtain the industry chain map of the current time period.

In the second aspect, the present application also provides an industrial chain generation device. The devices include:

The first correlation degree determination module is used to determine the data correlation degree between the various target industries according to the industrial electricity data and industrial production data of each target industry;

The second association degree determination module is used to determine the name association degree between the various target industries according to the distance between the name information of the various target industries;

The third association degree determination module is used to determine the relationship association degree between the various target industries according to the entity relationship information in the industry association information of the various target industries;

An industry chain graph generation module, configured to generate an industry chain graph corresponding to each target industry according to the data correlation degree, the name correlation degree, and the relationship correlation degree among the various target industries.

In a third aspect, the present application also provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

According to the industrial electricity data and industrial production data of each target industry, determine the data correlation between the various target industries;

According to the distance between the name information of the various target industries, determine the degree of name association between the various target industries;

According to the entity relationship information in the industry association information of each target industry, determine the degree of relationship association between each target industry;

According to the data association degree, the name association degree and the relationship association degree among the various target industries, an industry chain map corresponding to each target industry is generated.

In a fourth aspect, the present application also provides a computer-readable storage medium. The computer-readable storage medium has a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented:

According to the industrial electricity data and industrial production data of each target industry, determine the data correlation between the various target industries;

According to the distance between the name information of the various target industries, determine the degree of name association between the various target industries;

According to the entity relationship information in the industry association information of each target industry, determine the degree of relationship association between each target industry;

According to the data association degree, the name association degree and the relationship association degree among the various target industries, an industry chain map corresponding to each target industry is generated.

In a fifth aspect, the present application also provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

According to the industrial electricity data and industrial production data of each target industry, determine the data correlation between the various target industries;

According to the distance between the name information of the various target industries, determine the degree of name association between the various target industries;

According to the entity relationship information in the industry association information of each target industry, determine the degree of relationship association between each target industry;

According to the data association degree, the name association degree and the relationship association degree among the various target industries, an industry chain map corresponding to each target industry is generated.

The above-mentioned industrial chain generation method, device, computer equipment, storage medium, and computer program product determine the data correlation between each target industry according to the industrial electricity data and industrial production data of each target industry; according to the name information of each target industry According to the distance between each target industry, determine the degree of name association between each target industry; according to the entity relationship information in the industry association information of each target industry, determine the relationship association degree between each target industry; according to the data association degree between each target industry , name correlation degree and relationship correlation degree, and generate an industrial chain map corresponding to each target industry. Using this method, the data correlation degree between each target industry is determined through the industrial electricity data and industrial production data of each target industry, and the relationship correlation degree between each target industry is determined through the industry correlation information of each target industry, and combined with The name correlation between each target industry is used to comprehensively generate an industrial chain map, which solves the problem of single data dimension in building an industrial chain in traditional technology, so that the generated industrial chain map can more comprehensively display the economic factors of each target industry , production factors, and textual factors, etc., and does not need to rely on manual experience to establish an industrial chain map, which effectively improves the timeliness of the generated industrial chain map.

Description of drawings

Fig. 1 is a schematic flow diagram of an industry chain generating method in an embodiment;

Fig. 2 is a schematic diagram of an industrial chain map in an embodiment;

Fig. 3 is a schematic flow chart of the steps of obtaining the industry chain map of the current time period in one embodiment;

Fig. 4 is a schematic flow chart of an industry chain generation method in another embodiment;

Fig. 5 is a structural block diagram of an industrial chain generation device in an embodiment;

Figure 6 is an internal block diagram of a computer device in one embodiment.

detailed description

In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

In one embodiment, as shown in FIG. 1 , a method for generating an industry chain is provided. In this embodiment, the method is applied to a terminal for illustration. It can be understood that this method can also be applied to a server, or It is based on a system including a terminal and a server, and is realized through the interaction between the terminal and the server. Among them, the terminal can be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices. In this embodiment, the method includes the following steps:

Step S101, according to the industrial electricity data and industrial production data of each target industry, determine the data correlation degree between each target industry.

Among them, the industrial electricity data refers to the data describing the electricity consumption of the target industry; for example, the industrial electricity data includes but not limited to the real-time electricity consumption of the target industry and the electricity consumption of the past years; the industrial electricity data is used to reflect the target industry’s electricity consumption. First-line production factors. Industrial production data refers to data describing the production economy of the target industry; for example, industrial production data includes but is not limited to the total output value of the target industry; industrial production data reflects the economic factors of the target industry.

Among them, the degree of data correlation refers to an index used to measure the degree of correlation between two target industries in terms of production factors and economic factors. The target industry refers to the industry used to construct the industrial chain map; the number of target industries is at least two.

Specifically, if the user needs to analyze the relationship between different industries, he can send an industry chain graph viewing request to the terminal, and the terminal can obtain one or more information associated with the industrial chain graph viewing request from the metering automation system of the metering grid platform. Industrial electricity consumption data of a target industry. When the acquired industrial power consumption data is in the form of a structured database table, the terminal can perform data cleaning and data verification processing on the industrial power consumption data to obtain processed industrial power consumption data. The terminal can also perform crawler processing on the statistical website that records the industrial production data, so as to obtain the industrial production data of at least two target industries from the statistical website; when the obtained industrial production data is in a semi-structured form, Convert the semi-structured industrial production data into structured industrial production data, and then perform data cleaning and data verification processing on the structured industrial production data to obtain processed industrial production data. Furthermore, the terminal clusters at least two target industries according to the processed industrial power consumption data and processed industrial production data of each target industry, and obtains the industry classification results of at least two target industries. The degree of distance between classes or within classes in the industry classification results is used to determine the degree of data correlation between each pair of target industries.

Step S102, according to the distance between the name information of each target industry, determine the degree of name association between each target industry.

Wherein, the name information refers to the industry name of the target industry. The degree of name association refers to an indicator to measure the degree of association between two target industries in terms of names.

Specifically, the terminal calculates the distance between the name information of each target industry according to the name information of each target industry. The smaller the distance between the name information of each target industry, the greater the name correlation between each target industry; on the contrary, the larger the distance between the name information of each target industry, the greater the name correlation between each target industry. Small.

Step S103, according to the entity relationship information in the industry association information of each target industry, determine the relationship degree between each target industry.

Among them, the industry-related information is text data that may include upstream and downstream relationships of industries. Entity relationship information refers to information used to describe the upstream and downstream relationship between entities (for example, between two industries). The degree of relational relation refers to the index that measures the degree of relation between two target industries in terms of the upstream and downstream relations in the industrial chain.

Specifically, the terminal can perform text extraction processing on texts such as industry annual reports, news reports, and policy guidelines associated with each target industry, to obtain industry-related information of each target industry; The extraction process obtains the entity relationship information in each industry association information; according to the upstream probability and downstream probability between each entity relationship information, the relationship association degree between each target industry is obtained.

Step S104, according to the data correlation degree, name correlation degree and relationship correlation degree between each target industry, generate an industry chain map corresponding to each target industry.

Among them, the industrial chain map refers to the graphic data used to visually display the upstream and downstream of the industrial chain.

Specifically, the degree of data association, name association, and relationship association between each target industry of the terminal determines the industry association between various industries; where, the industry association refers to the combination of data association, name association, and relationship Correlation degree is an index used to comprehensively evaluate the degree of correlation between different industries. Furthermore, the terminal determines the upstream industry and downstream industry corresponding to each target industry according to the degree of industrial correlation between each industry, and then performs visualization processing on the upstream industry and downstream industry corresponding to each target industry to obtain the industrial chain map in the above step S101 View the industrial chain map corresponding to the request. After the terminal generates the industrial chain map, it can also display the industrial chain map for users to view the industrial chain map in real time.

In the above industrial chain generation method, according to the industrial power data and industrial production data of each target industry, the data correlation degree between each target industry is determined; according to the distance between the name information of each target industry, the relationship between each target industry is determined. Name association degree; according to the entity relationship information in the industry association information of each target industry, determine the relationship association degree between each target industry; according to the data association degree, name association degree and relationship association degree between each target industry, generate each The industrial chain map corresponding to the target industry. Using this method, the data correlation degree between each target industry is determined through the industrial electricity data and industrial production data of each target industry, and the relationship correlation degree between each target industry is determined through the industry correlation information of each target industry, and combined with The name correlation between each target industry is used to comprehensively generate an industrial chain map, which solves the problem of single data dimension in building an industrial chain in traditional technology, so that the generated industrial chain map can more comprehensively show the relationship between various target industries. There is no need to rely on manual experience to establish the industrial chain map, which effectively improves the timeliness of the generated industrial chain map.

In one embodiment, the above step S101, according to the industrial power data and industrial production data of each target industry, determines the data correlation between each target industry, specifically including the following content: according to the industrial power data of each target industry, get each The historical power growth rate of the target industry; according to the industrial production data of each target industry, the historical production growth rate of each target industry is obtained; according to the historical power growth rate and historical production growth rate, each target industry is clustered to obtain each target Industry classification results of industries: According to the industry classification results of each target industry, the data correlation between each target industry is obtained.

Among them, the historical electricity growth rate refers to the data describing the growth of the electricity data of the target industry in the historical time period; the historical electricity growth rate includes but is not limited to the historical electricity chain growth rate and the historical electricity year-on-year growth rate. The historical production growth rate refers to the data describing the growth of the production data of the target industry in the historical time period; the historical production growth rate includes but is not limited to the historical production chain growth rate and the historical production year-on-year growth rate.

Specifically, the terminal obtains the historical power consumption growth rate and the historical power consumption growth rate of each target industry according to the historical industry power data of each target industry; according to the historical industrial production data of each target industry, the historical production chain growth rate of each target industry is obtained Rate and historical production year-on-year growth rate; and then the terminal clusters the historical power chain growth rate, historical power year-on-year growth rate, historical production chain growth rate and historical production year-on-year growth rate of each target industry, which can be a method for each target industry The historical power chain growth rate, historical power year-on-year growth rate, historical production chain growth rate and historical production year-on-year growth rate are clustered by K-means, and the terminal obtains the industry classification results of each target industry. According to the industry classification results of each target industry, the terminal obtains the data correlation degree between each target industry. It can first set the same initial data correlation degree for each target industry, and then set the same initial data correlation degree for each target industry, and then pair two target industries in the same industry classification Increase the initial data correlation degree between two target industries in different industry classifications, reduce the initial data correlation degree between two target industries in different industry classifications, and obtain the updated data correlation degree between two target industries; The distance between two pairs of target industries in the classification, according to the order of the distance from large to small, the updated data correlation degree between the target industries in the same industry classification is increased, and the distance between the target industries is obtained. The data correlation degree of the target industry, that is, the smaller the distance between the target industries in the same industry classification, the greater the data correlation degree between the target industries.

In this embodiment, the industry classification results of each target industry are obtained by clustering the historical electricity growth rate and historical production growth rate of each target industry; Combined with the historical power growth rate and historical production growth rate of the target industry to analyze the data correlation degree between the target industries, it can dig out the laws of the upstream and downstream industries in the industrial chain in terms of power consumption and production, so that the generated The obtained industrial chain map can more comprehensively and finely show the relationship between various target industries in terms of economic factors, production factors and other factors.

In one embodiment, the above step S102, according to the distance between the name information of each target industry, determines the degree of name association between each target industry, which specifically includes the following content: after detecting the name information of the first target industry and the second If the name information of the two target industries is different, obtain the number of text updates required to update the name information of the first target industry to the name information of the second target industry; the first target industry is any one of the target industries; The second target industry is any target industry in each target industry except the first target industry; according to the number of text updates, the distance between the name information of the first target industry and the name information of the second target industry is obtained; according to the distance, The name association degree between the first target industry and the second target industry is obtained as the name association degree between each target industry.

Wherein, the number of times of updating the text refers to updating the name information of the first target industry according to the name information of the second target industry, and the minimum number of times required for update processing.

Specifically, the terminal takes any target industry in all target industries as the first target industry, and at the same time takes any target industry in all target industries except the first target industry as the second target industry; and then detects the obtained second target industry Whether the industry name of the first target industry is the same as the acquired industry name of the second target industry; if it is detected that the name information of the first target industry is different from the name information of the second target industry, the terminal For each character in the name information, character conversion is performed on the characters in the name information of the first target industry that are different from the name information of the second target industry, wherein the name information of the first target industry is different from the name information of the second target industry The same characters do not need to be converted, and the minimum number of character conversions required to completely update the name information of the first target industry to the name information of the second target industry is obtained, and the number of character conversions is used as the number of text updates.

Further, the terminal increments the initial distance between the name information of the first target industry and the name information of the second target industry in ascending order of the number of text updates to obtain the name information of the first target industry and the name information of the second target industry The distance between the name information of the industry, that is, the less the number of text updates between the name information of the first target industry and the name information of the second target industry, the greater the distance between the name information of the first target industry and the name information of the second target industry. The closer the distance between. According to the descending order of the distance between the name information of the first target industry and the name information of the second target industry, the terminal increases the initial name association degree between the first target industry and the second target industry, and obtains the first The name correlation degree between the first target industry and the second target industry, that is, the smaller the distance between the name information of the first target industry and the name information of the second target industry, the smaller the distance between the first target industry and the second target industry. The greater the degree of name association, the degree of name association between various target industries.

For example, assume that the name information of target industry A is ferrous metal mining and dressing industry, the name information of target industry B is ferrous metal smelting and rolling processing industry, and the name information of target industry C is heat production and supply industry; if the target industry To convert the name information of target industry B into the name information of target industry B, it is necessary to convert the "mining and dressing" of target industry A into "smelting and rolling processing". At least 7 characters need to be converted. Therefore, the target industry B's The distance between the name information and the name information of the target industry A is 7; if the name information of the target industry C is converted into the name information of the target industry B, the "heat production and supply" in the target industry C needs to be converted into " Ferrous metal smelting and rolling processing", at least 11 characters need to be converted. Therefore, the distance between the name information of target industry B and the name information of target industry C is 11, so the distance between target industry B and target industry A The name association degree of is greater than the name association degree between target industry B and target industry C.

In this embodiment, when it is detected that the name information of the first target industry is different from the name information of the second target industry, the minimum required information for updating the name information of the first target industry to the name information of the second target industry is acquired. The number of text updates; then according to the number of text updates, the distance between the name information of the first target industry and the name information of the second target industry is obtained; according to the distance, the name association between the first target industry and the second target industry is obtained As the degree of name association between various target industries, based on the characteristics that similar industries have relatively similar names, the degree of name association between various target industries is obtained, so that the degree of name association can be used to determine the relationship between each target industry. The degree of industrial correlation between them is conducive to improving the accuracy of the generated industrial chain map.

In one embodiment, the above step S103, according to the entity relationship information in the industry association information of each target industry, determines the degree of relationship association between each target industry, specifically including the following content: Entity is carried out on the industry association information of each target industry Relational extraction process to obtain the entity relationship information in the associated information of each industry; according to the upstream and downstream relationship between industries in the industrial relationship dictionary database, carry out upstream probability judgment and downstream probability judgment on the target industry in the entity relationship information, and obtain the entity relationship The upstream probability and downstream probability of the target industry in the information; according to the upstream probability and downstream probability of the target industry in the entity relationship information, the relationship degree between each target industry is obtained.

Wherein, the industrial relationship dictionary refers to a dictionary constructed according to the conventional upstream and downstream relationships between industries. Upstream probability refers to the probability that an industry is located upstream in the industry chain. Downstream probability refers to the probability that an industry is located downstream in the industry chain.

Specifically, the terminal performs entity extraction processing on the industry-related information of each target industry to obtain the entity industry information in each industry-related information; furthermore, the terminal performs entity relationship extraction processing on the entity industry information, which may be a rule-based Entity relationship extraction, the terminal obtains entity relationship information. According to the upstream and downstream relationship between industries in the industrial relationship dictionary, the terminal judges the upstream probability of the target industry in the entity relationship information, obtains the upstream probability of the target industry in the entity relationship information, and performs downstream analysis of the target industry in the entity relationship information. Probability judgment, to obtain the downstream probability of the target industry in the entity relationship information; according to the upstream probability and downstream probability of the target industry in the entity relationship information, the upstream probability and downstream probability of the two target industries in the entity relationship information can be combined to obtain The degree of correlation between the target industries.

For example, assume that the obtained industry-related information "News reports that Indonesia will export 400 million tons of coal in 2021, of which more than 180 million tons will be sold to China, accounting for more than 61% of the total export volume and 75% of China's total coal imports The incident mainly involved related coal mining and washing industries, resulting in an increase of 234MW/10,000 yuan in energy consumption indicators during the period from January to March, a year-on-year increase of 3%; If the consumption index increased by 164MW/10,000 yuan, 5% year-on-year", then the entity extraction process of the industry-related information can be carried out, and the entity industry information can be obtained as "coal mining and washing industry" and "industrial power, heat production and supply industry". Moreover, there is an entity relationship between "coal mining and washing industry" and "industry electric power, heat production and supply industry". The upstream probability judgment and downstream probability judgment of "industry electric power, heat power production and supply industry" are judged, and the downstream probability of "industry electric power, heat power production and supply industry" is higher than that of "coal mining and washing industry", while "coal mining and washing industry The upstream probability of the “selection industry” is higher than that of the “industrial electricity, heat production and supply industry”, which means that the “industrial electricity, heat production and supply industry” has a higher probability of being the downstream of the “coal mining and washing industry”.

In this embodiment, according to the upstream and downstream relationships between industries in the industrial relationship dictionary, the target industry in the entity relationship information extracted from the industry association information of each target industry is judged by upstream probability and downstream probability, Obtain the upstream probability and downstream probability of the target industry in the entity relationship information; then, according to the upstream probability and downstream probability of the target industry in the entity relationship information, obtain the relationship correlation between each target industry, without the need for experts and other personnel to rely on manual experience to judge The upstream and downstream relationships of each target industry can scientifically extract the degree of relationship between industries from the industry-related information, effectively improving the efficiency of generating industrial chain maps.

In one embodiment, the above step S104 generates an industry chain map corresponding to each target industry according to the data association degree, name association degree, and relationship association degree among each target industry, specifically including the following content: According to the relationship between each target industry According to the data correlation degree, name correlation degree and relationship correlation degree, determine the industry correlation probability between each target industry; determine the upstream and downstream industries corresponding to each target industry according to the upstream probability, downstream probability and industry correlation probability; The upstream and downstream industries are visualized and processed to obtain the industrial chain map.

Among them, the industry correlation probability refers to the probability of describing the correlation between two target industries.

Specifically, the terminal integrates the data association degree, name association degree and relationship association degree between each target industry, and may weight the data association degree, name association degree and relationship association degree between each target industry, or may only According to any unilateral correlation degree among data correlation degree, name correlation degree and relationship correlation degree, the industry correlation probability between each target industry of the terminal; the industry correlation probability, upstream probability and downstream probability of each target industry between the terminal Perform matrix processing to obtain a correlation matrix; determine the upstream and downstream industries corresponding to each target industry according to the correlation matrix; perform visual graphics processing on the upstream and downstream industries corresponding to each target industry, which can be used to build visual nodes for each target industry by using a graph database , and connect the visualization nodes according to the upstream and downstream industries corresponding to each target industry to obtain the industrial chain map; for example, use neo4j (a NOSQL graph database) to construct the visualization nodes of each target industry, and according to the upstream For downstream industries, connect the visualized nodes to obtain the industrial chain map. The schematic diagram of the industrial chain map is shown in Figure 2.

In this embodiment, the industry association probability between each target industry is determined through the data association degree, name association degree and relationship association degree between each target industry; and then according to the upstream probability, downstream probability and industry association probability, each The upstream and downstream industries corresponding to the target industry; Visual graphics processing is performed on the upstream and downstream industries corresponding to each target industry to obtain an industrial chain map, so that the obtained industrial chain map can reflect the data correlation degree and name correlation degree between each target industry The degree of correlation with the relationship improves the relationship surface of the obtained industrial chain map, and does not need to rely on manual experience to establish the industrial chain map, which effectively improves the generation efficiency of the industrial chain map.

In one embodiment, as shown in Figure 3, after generating the industry chain map corresponding to each target industry according to the data association degree, name association degree and relationship association degree between each target industry, it also includes:

Step S301, obtaining the current electricity data of each target industry in the industry chain map in the current time period.

Step S302, according to the current power data of each target industry, the current power growth rate of each target industry is obtained.

In step S303, year-on-year and ring-to-ring evaluations are performed on the current electricity growth rate and the historical electricity growth rate of each target industry to obtain the evaluation results of each target industry.

Step S304, if the evaluation result is abnormal, update the target industry corresponding to the evaluation result upstream and downstream in the industry chain map to obtain the industry chain map of the current time period.

Among them, the current electricity growth rate refers to the data describing the growth of the electricity data of the target industry in the historical time period. The current power growth rate includes but is not limited to the current power chain growth rate and the current power chain chain growth rate.

Specifically, after the terminal generates the industry chain map in the above step S104, the terminal obtains the current power data of each target industry in the current time period in the industry chain map, and then according to the current power data of each target industry and the industry in the historical time period Power data, calculate the current power chain growth rate and the current power chain growth rate of each target industry in the current time period. The terminal conducts a quarter-on-quarter evaluation of the current power chain growth rate and historical power chain growth rate of each target industry, and obtains the power chain evaluation results of each target industry; conducts a year-on-year evaluation of the current power year-on-year growth rate and historical power year-on-year growth rate of each target industry , to get the year-on-year evaluation results of each target industry; the terminal comprehensive power chain evaluation results and the power chain evaluation results get the evaluation results of each target industry, or determine each target according to the power chain evaluation results or any one of the power chain evaluation results The evaluation result of the industry; if the evaluation result is abnormal, update the upstream and downstream of the target industry whose evaluation result is abnormal in the industrial chain map, and obtain the updated industrial chain map of the current time period.

In this embodiment, according to the current power data of each target industry in the current time period in the industry chain map, the current power growth rate of each target industry is obtained; and then the current power growth rate and historical power growth rate of each target industry are compared Evaluation and ring-to-ring evaluation to obtain the evaluation results of each target industry; when the evaluation results are abnormal, update the target industry corresponding to the evaluation results in the industrial chain map to obtain the industrial chain map of the current time period, which can be timely It is found that there are industries with abnormal power fluctuations in the industrial chain map, which realizes real-time screening and automatic update of the industrial chain map, thereby further improving the timeliness of the industrial chain map and improving the accuracy of the industrial chain map.

In one embodiment, as shown in FIG. 4 , another industry chain generation method is provided. The method is applied to a terminal as an example for illustration, including the following steps:

Step S401, according to the industrial electricity data of each target industry, obtain the historical electricity growth rate of each target industry; according to the industrial production data of each target industry, obtain the historical production growth rate of each target industry.

Step S402, according to the historical electricity growth rate and historical production growth rate, perform clustering processing on each target industry to obtain the industry classification results of each target industry; according to the industry classification results of each target industry, obtain the data association between each target industry Spend.

Step S403, if it is detected that the name information of the first target industry is different from the name information of the second target industry, obtain the number of text updates required to update the name information of the first target industry to the name information of the second target industry .

Among them, the first target industry is any target industry in each target industry; the second target industry is any target industry in each target industry except the first target industry.

Step S404, according to the number of text updates, the distance between the name information of the first target industry and the name information of the second target industry is obtained; according to the distance, the name correlation degree between the first target industry and the second target industry is obtained as The degree of name association between each target industry.

In step S405, the entity relationship extraction process is performed on the industry-related information of each target industry, and the entity relationship information in each industry-related information is obtained.

Step S406, according to the upstream and downstream relationship between industries in the industrial relationship dictionary database, perform upstream probability judgment and downstream probability judgment on the target industry in the entity relationship information, and obtain the upstream probability and downstream probability of the target industry in the entity relationship information.

Step S407, according to the upstream probability and downstream probability of the target industry in the entity relationship information, the degree of relational correlation between each target industry is obtained.

Step S408, according to the data correlation degree, name correlation degree and relationship correlation degree between each target industry, determine the industry correlation probability between each target industry; according to the upstream probability, downstream probability and industry correlation probability, determine the corresponding upstream and downstream industries.

Step S409, performing visual graphic processing on the upstream and downstream industries corresponding to each target industry to obtain an industrial chain map.

The above industrial chain generation method can achieve the following beneficial effects: determine the data correlation between each target industry through the industrial power data and industrial production data of each target industry, and determine the relationship between each target industry through the industry related information of each target industry. The degree of relationship between them, combined with the degree of name association between each target industry to comprehensively generate an industrial chain map, which solves the problem of single data dimensions for building an industrial chain in traditional technologies, and enables the generated industrial chain map to be more comprehensive. It shows the correlation of various target industries in terms of economic factors, production factors and textual factors, and does not need to rely on manual experience to establish an industrial chain map, which effectively improves the timeliness of the generated industrial chain map.

In order to clarify the industry chain generation method provided by the embodiments of the present disclosure more clearly, a specific embodiment will be used below to describe the above industry chain generation method in detail. Another industry chain generation method is provided, which can be applied to terminals, and specifically includes the following content:

The first is the data acquisition link: obtain real-time industrial electricity data from the metering automation system, including the electricity consumption of 133 typical industries, the resumption of work and production, etc.; obtain the industrial production data of 133 typical industries through crawlers from the website of the Bureau of Statistics; Obtain the industry-related information of 133 typical industries in 133 types of typical industries from industry annual reports, news reports, policy guidelines and other texts.

The second is the data processing link: 1) The industrial electricity data obtained from the metering automation system is structured database table data, data cleaning and data verification are performed on the industrial electricity data, and the processed industrial electricity data is obtained to ensure that the industrial electricity data after processing The quality of the industrial power data; through the neo4j-import module in the neo4j graph database, the processed industrial power data is converted into entities in the industrial chain map. 2) The industrial production data obtained from the website of the Bureau of Statistics is semi-structured data, and the industrial production data is transformed into a structured form of industrial production data, and then data cleaning and data verification are performed on the industrial production data to obtain the processed industrial production data , to ensure the quality of the processed industrial production data; through the neo4j-import module in the neo4j graph database, the processed industrial production data is converted into entities in the industrial chain map. 3) Extract the industrial characteristics of the industry-related information to obtain the industry characteristic information in the industry-related information; according to the industrial relationship dictionary database, perform entity industry matching on the industry characteristic information, and obtain the entity industry information corresponding to the industry characteristic information.

The third is the calculation of the comprehensive industry correlation degree: 1) The terminal obtains the historical electricity chain growth rate and the historical electricity year-on-year growth rate of each target industry according to the historical industry electricity data of each target industry; according to the historical industry production data of each target industry, Get the historical production chain growth rate and historical production year-on-year growth rate of each target industry; perform K-means clustering on the historical power chain growth rate, historical power year-on-year growth rate, historical production chain growth rate and historical production year-on-year growth rate of each target industry , the terminal obtains the industry classification results of each target industry; the terminal obtains the data correlation degree between each target industry according to the industry classification results of each target industry. 2) According to the obtained name information of each target industry, determine the minimum number of text updates required to convert the name information of one target industry into the name information of another target industry, and calculate each The distance between the name information of the target industry. According to the distance calculation, the name association degree between the two industries is obtained. 3) Extract the entity relationship of the industry-related information of each target industry to obtain the entity relationship information in each industry-related information; according to the upstream probability and downstream probability of the target industry in the entity relationship information, obtain the relationship between each target industry Correlation.

The fourth is the industrial chain generation link: according to the data correlation degree, name correlation degree and relationship correlation degree between each target industry, determine the industry correlation probability between each target industry; Probability and downstream probability are processed in a matrix to obtain a correlation matrix as a comprehensive industry correlation; determine the upstream and downstream industries corresponding to each target industry according to the comprehensive industry correlation; use neo4j (a NOSQL graph database) to build visual nodes for each target industry , and according to the upstream and downstream industries corresponding to each target industry, connect the visualized nodes to obtain the industrial chain map.

In this embodiment, the data association degree between each target industry is determined through the industrial electricity data and industrial production data of each target industry, and the relationship association degree between each target industry is determined through the industry association information of each target industry. Combined with the name correlation between each target industry to comprehensively generate an industrial chain map, it solves the problem of single data dimension in building an industrial chain in traditional technology, so that the generated industrial chain map can more comprehensively display the status of each target industry. There is no need to rely on manual experience to establish an industrial chain map, which effectively improves the timeliness of the generated industrial chain map.

It should be understood that although the steps in the flow charts involved in the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in the flow charts involved in the above-mentioned embodiments may include multiple steps or stages, and these steps or stages are not necessarily executed at the same time, but may be performed at different times For execution, the execution order of these steps or stages is not necessarily performed sequentially, but may be executed in turn or alternately with other steps or at least a part of steps or stages in other steps.

Based on the same inventive concept, an embodiment of the present application further provides an industry chain generation device for implementing the above-mentioned method for generating an industry chain. The solution to the problem provided by the device is similar to the implementation described in the above-mentioned method, so the specific limitations in one or more embodiments of the industrial chain generating device provided below can be referred to above for the industrial chain generating method limited and will not be repeated here.

In one embodiment, as shown in FIG. 5 , an industry chain generation device 500 is provided, including: a first association degree determination module 501, a second association degree determination module 502, a third association degree determination module 503 and an industry chain Map generation module 504, wherein:

The first correlation degree determination module 501 is configured to determine the data correlation degree between each target industry according to the industrial electricity data and industrial production data of each target industry.

The second association degree determination module 502 is configured to determine the name association degree between each target industry according to the distance between the name information of each target industry.

The third association degree determination module 503 is configured to determine the relationship association degree between each target industry according to the entity relationship information in the industry association information of each target industry.

The industry chain graph generation module 504 is used to generate an industry chain graph corresponding to each target industry according to the data correlation degree, name correlation degree and relationship correlation degree between each target industry.

In one embodiment, the first correlation degree determination module 501 is also used to obtain the historical electricity growth rate of each target industry according to the industrial electricity data of each target industry; Historical production growth rate; according to the historical electricity growth rate and historical production growth rate, each target industry is clustered to obtain the industry classification results of each target industry; according to the industry classification results of each target industry, the relationship between each target industry is obtained Data relevance.

In one embodiment, the second association degree determination module 502 is further configured to acquire and update the name information of the first target industry when it is detected that the name information of the first target industry is different from the name information of the second target industry. The number of text updates required for the name information of the second target industry; the first target industry is any target industry in each target industry; the second target industry is any target industry in each target industry except the first target industry; According to the number of text updates, the distance between the name information of the first target industry and the name information of the second target industry is obtained; according to the distance, the name correlation degree between the first target industry and the second target industry is obtained as each target industry The relationship between names.

In one embodiment, the third association degree determination module 503 is also used to extract the entity relationship from the industry association information of each target industry to obtain the entity relationship information in each industry association information; The upstream and downstream relationship between the target industry in the entity relationship information is judged by the upstream probability and downstream probability, and the upstream probability and downstream probability of the target industry in the entity relationship information are obtained; according to the upstream probability of the target industry in the entity relationship information and downstream probability to obtain the degree of relationship between each target industry.

In one embodiment, the industry chain map generation module 504 is also used to determine the industry association probability among each target industry according to the data association degree, name association degree and relationship association degree among each target industry; according to the upstream probability, The downstream probability and industry association probability determine the upstream and downstream industries corresponding to each target industry; perform visual graphic processing on the upstream and downstream industries corresponding to each target industry to obtain an industrial chain map.

In one embodiment, the industrial chain generation device 500 also includes an industrial chain update module, which is used to obtain the current electricity data of each target industry in the industry chain map in the current time period; according to the current electricity data of each target industry, obtain the The current electricity growth rate of each target industry; conduct year-on-year and ring-to-chain evaluations on the current electricity growth rate and historical electricity growth rate of each target industry, and obtain the evaluation results of each target industry; The target industry corresponding to the evaluation result is updated upstream and downstream to obtain the industrial chain map of the current time period.

Each module in the above-mentioned industrial chain generating device can be fully or partially realized by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, and can also be stored in the memory of the computer device in the form of software, so that the processor can invoke and execute the corresponding operations of the above-mentioned modules.

In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure may be as shown in FIG. 6 . The computer device includes a processor, a memory, an input/output interface, a communication interface, a display unit and an input device. Wherein, the processor, the memory and the input/output interface are connected through the system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input/output interface. Wherein, the processor of the computer device is used to provide calculation and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input/output interface of the computer device is used for exchanging information between the processor and external devices. The communication interface of the computer device is used for wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, mobile cellular network, NFC (Near Field Communication) or other technologies. When the computer program is executed by the processor, an industrial chain generation method is realized. The display unit of the computer equipment is used to form a visually visible picture, which may be a display screen, a projection device or a virtual reality imaging device. The display screen may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a button, a trackball or a touch pad set on the casing of the computer device, or a External keyboard, touchpad or mouse etc.

Those skilled in the art can understand that the structure shown in FIG. 6 is only a block diagram of a part of the structure related to the solution of this application, and does not constitute a limitation on the computer equipment to which the solution of this application is applied. The specific computer equipment can be More or fewer components than shown in the figures may be included, or some components may be combined, or have a different arrangement of components.

In one embodiment, there is also provided a computer device, including a memory and a processor, where a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the foregoing method embodiments are implemented.

In one embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the foregoing method embodiments are implemented.

It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all It is information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented through computer programs to instruct related hardware, and the computer programs can be stored in a non-volatile computer-readable memory In the medium, when the computer program is executed, it may include the processes of the embodiments of the above-mentioned methods. Wherein, any reference to storage, database or other media used in the various embodiments provided in the present application may include at least one of non-volatile and volatile storage. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive variable memory (ReRAM), magnetic variable memory (Magnetoresistive Random Access Memory, MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (Phase Change Memory, PCM), graphene memory, etc. The volatile memory may include a random access memory (Random Access Memory, RAM) or an external cache memory and the like. As an illustration but not a limitation, the RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM). The databases involved in the various embodiments provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a blockchain-based distributed database, etc., but is not limited thereto. The processors involved in the various embodiments provided by this application can be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, data processing logic devices based on quantum computing, etc., and are not limited to this.

The technical features of the above embodiments can be combined arbitrarily. To make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be It is considered to be within the range described in this specification.

The above-mentioned embodiments only express several implementation modes of the present application, and the description thereof is relatively specific and detailed, but should not be construed as limiting the patent scope of the present application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be determined by the appended claims.

Claims (10)

1. An industrial chain generation method, comprising:

determining data association degree between each target industry according to industrial electric quantity data and industrial production data of each target industry;

determining the name association degree among the target industries according to the distance among the name information of the target industries;

determining the relationship association degree among the target industries according to the entity relationship information in the industry association information of the target industries;

and generating an industry chain map corresponding to each target industry according to the data association degree, the name association degree and the relation association degree among the target industries.

2. The method of claim 1, wherein the determining the data association degree between the target industries according to the industry power data and the industry production data of the target industries comprises:

obtaining historical electric quantity growth rate of each target industry according to the industrial electric quantity data of each target industry;

obtaining historical production growth rate of each target industry according to the industrial production data of each target industry;

clustering each target industry according to the historical electric quantity growth rate and the historical production growth rate to obtain an industry classification result of each target industry;

and obtaining the data association degree among the target industries according to the industry classification result of each target industry.

3. The method according to claim 1, wherein the determining the name association degree between the target industries according to the distance between the name information of the target industries comprises:

under the condition that the name information of a first target industry is detected to be different from the name information of a second target industry, acquiring the number of times of text updating required for updating the name information of the first target industry into the name information of the second target industry; the first target industry is any one of the target industries; the second target industry is any one of the target industries except the first target industry;

obtaining the distance between the name information of the first target industry and the name information of the second target industry according to the text updating times;

and obtaining the name association degree between the first target industry and the second target industry according to the distance, wherein the name association degree is used as the name association degree between the target industries.

4. The method according to claim 1, wherein the determining the relationship association degree between the target industries according to entity relationship information in the industry association information of the target industries comprises:

performing entity relationship extraction processing on the industry associated information of each target industry to obtain entity relationship information in the industry associated information;

according to the upstream and downstream relation among industries in an industry relation dictionary library, performing upstream probability judgment and downstream probability judgment on the target industry in the entity relation information to obtain the upstream probability and the downstream probability of the target industry in the entity relation information;

and obtaining the relationship association degree between the target industries according to the upstream probability and the downstream probability of the target industries in the entity relationship information.

5. The method according to claim 4, wherein the generating an industry chain graph corresponding to each target industry according to the data association degree, the name association degree and the relationship association degree among the target industries comprises:

determining an industry association probability among the target industries according to the data association degree, the name association degree and the relationship association degree among the target industries;

determining an upstream industry and a downstream industry corresponding to each target industry according to the upstream probability, the downstream probability and the industry association probability;

and carrying out visual graphic processing on the upstream industry and the downstream industry corresponding to each target industry to obtain the industry chain map.

6. The method according to any one of claims 1 to 5, further comprising, after generating an industry chain map corresponding to each target industry according to the data association degree, the name association degree, and the relationship association degree between the target industries:

acquiring current electric quantity data of each target industry in the industry chain map in the current time period;

obtaining the current electric quantity growth rate of each target industry according to the current electric quantity data of each target industry;

performing a same-ratio evaluation and a ring-ratio evaluation on the current electric quantity growth rate and the historical electric quantity growth rate of each target industry to obtain an evaluation result of each target industry;

and under the condition that the evaluation result is abnormal, performing upstream and downstream updating on the target industry corresponding to the evaluation result in the industry chain map to obtain the industry chain map of the current time period.

7. An industrial chain generation apparatus, characterized in that the apparatus comprises:

the first association degree determining module is used for determining the data association degree between each target industry according to the industry electric quantity data and the industry production data of each target industry;

the second association degree determining module is used for determining the name association degree between the target industries according to the distance between the name information of the target industries;

a third association degree determining module, configured to determine, according to entity relationship information in the industry association information of each target industry, a relationship association degree between the target industries;

and the industry chain map generation module is used for generating an industry chain map corresponding to each target industry according to the data association degree, the name association degree and the relationship association degree among all target industries.

8. The apparatus according to claim 7, wherein the first association degree determining module is further configured to obtain a historical electricity quantity growth rate of each target industry according to the industry electricity quantity data of each target industry; obtaining the historical production growth rate of each target industry according to the industrial production data of each target industry; clustering each target industry according to the historical electric quantity growth rate and the historical production growth rate to obtain an industry classification result of each target industry; and obtaining the data association degree among the target industries according to the industry classification result of each target industry.

9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 6.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.

Images