Construction method of public opinion factor for chemical raw materials based on adaptive threshold and related components

Abstract

The present invention discloses a method for constructing a public opinion factor of chemical raw materials based on an adaptive threshold and related components. The method includes: collecting a set of public opinion texts related to a specified chemical raw material according to different search keywords; inputting each public opinion text in the public opinion text set into an inference model, and outputting the price impact results of the specified chemical raw material respectively; constructing a public opinion factor of the public opinion texts collected by different search keywords; and using the public opinion factor to determine the public opinion importance of the price impact results of the specified chemical raw material. The method provided by the present invention can mine the influence of public opinion information in the chemical industry on a daily basis, and give a public opinion importance coefficient after quantitative analysis, which has the advantage of accurately evaluating the price impact results of public opinion on the specified chemical raw materials.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method for constructing a public opinion factor of chemical raw materials based on an adaptive threshold and related components. Background Art

[0002] At present, in the development of the petrochemical industry, "digital transformation" is an important goal in recent years. It is necessary to build industrial chain detection and accelerate the integration of new generation information technologies such as big data and artificial intelligence with the petrochemical industry. Public opinion in the chemical industry refers to the attitudes, opinions and views of the public and media on the public information of upstream and downstream companies in the chemical industry (including major news hot information about the company, supply and demand information, upstream and downstream company information, and macro information) through the Internet. This information is helpful for corporate managers, industry analysts, and government managers to understand the situation of the company and the industry, so as to take effective measures to deal with abnormal public opinion and better analyze and manage the company and the industry.

[0003] The current public opinion monitoring systems in the market mainly collect hot information in the industry, select the top n pieces of information with the greatest impact on public opinion, and analyze the impact of public opinion through dimensions such as channels, emotional attributes, and publishing areas. These public opinion monitoring systems target a single piece of public opinion information and cannot summarize all the important public opinion information related to the chemical company (industry) on that day; and the analysis methods used by these public opinion monitoring systems are all qualitative data analysis methods, which cannot give a quantitative influence coefficient. Summary of the invention

[0004] The purpose of the present invention is to provide a method for constructing a public opinion factor of chemical raw materials based on an adaptive threshold and related components, aiming to solve the problem that the existing public opinion monitoring system is unable to perform quantitative analysis on the chemical industry, resulting in inaccurate assessment of the impact of public opinion.

[0005] In a first aspect, an embodiment of the present invention provides a method for constructing a public opinion factor of a chemical raw material based on an adaptive threshold, comprising:

[0006] Collect public opinion text sets related to designated chemical raw materials based on different search keywords;

[0007] Input each public opinion text in the public opinion text set into the inference model, and output the price impact results of the designated chemical raw materials respectively;

[0008] Constructing public opinion factors of the public opinion texts collected by different search keywords;

[0009] The public opinion factor is used to determine the public opinion importance of the price impact result of the designated chemical raw material.

[0010] In a second aspect, an embodiment of the present invention provides a device for constructing a public opinion factor of a chemical raw material based on an adaptive threshold, comprising:

[0011] A collection unit, used to collect public opinion text sets related to designated chemical raw materials according to different search keywords;

[0012] An inference unit, used for inputting each public opinion text in the public opinion text set into an inference model, and outputting the price impact results on the designated chemical raw materials respectively;

[0013] A construction unit, used to construct public opinion factors of the public opinion text collected by different search keywords;

[0014] A determination unit is used to determine the public opinion importance of the price impact result of the designated chemical raw material by using the public opinion factor.

[0015] In a third aspect, an embodiment of the present invention provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for constructing a chemical raw material public opinion factor based on an adaptive threshold as described in the first aspect above is implemented.

[0016] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the method for constructing a chemical raw material public opinion factor based on an adaptive threshold as described in the first aspect above.

[0017] The embodiment of the present invention discloses a method for constructing a public opinion factor of chemical raw materials based on an adaptive threshold and related components. The method includes: collecting a set of public opinion texts related to a specified chemical raw material according to different search keywords; inputting each public opinion text in the public opinion text set into an inference model, and outputting the price impact results of the specified chemical raw material respectively; constructing a public opinion factor of the public opinion texts collected by different search keywords; and using the public opinion factor to determine the public opinion importance of the price impact results of the specified chemical raw material. The method provided by the embodiment of the present invention can mine the influence of public opinion information in the chemical industry on a daily basis, and give a public opinion importance coefficient after quantitative analysis, which has the advantage of accurately evaluating the price impact results of public opinion on specified chemical raw materials. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0019] Figure 1 A schematic flow chart of a method for constructing a public opinion factor for chemical raw materials based on an adaptive threshold provided in an embodiment of the present invention;

[0020] Figure 2 A schematic diagram of a sub-flow chart of step S101 provided in an embodiment of the present invention;

[0021] Figure 3 A schematic diagram of a sub-flow chart of step S103 provided in an embodiment of the present invention;

[0022] Figure 4 A schematic block diagram of a device for constructing a public opinion factor for chemical raw materials based on an adaptive threshold provided in an embodiment of the present invention;

[0023] Figure 5 A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0026] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0027] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0028] See also Figure 1 , Figure 1 A schematic flow chart of a method for constructing a public opinion factor for chemical raw materials based on an adaptive threshold provided in an embodiment of the present invention;

[0029] like Figure 1As shown, the method includes steps S101 to S104.

[0030] S101. Collecting a set of public opinion texts related to designated chemical raw materials according to different search keywords;

[0031] In this step, the public opinion text set collected through different search keywords is more comprehensive, so that subsequent evaluation can be more accurate;

[0032] S102, input each public opinion text in the public opinion text set into the inference model, and output the price impact results of the designated chemical raw materials respectively;

[0033] S103, constructing public opinion factors of public opinion texts collected by different search keywords;

[0034] In this step, the public opinion factor may include a public opinion influence factor and a public opinion evolution factor. The size of the public opinion influence factor represents the size of the impact of the public opinion text on the price of chemical raw materials. The larger the public opinion influence factor, the greater the driving effect of the public opinion on the price on that day; the public opinion evolution factor reflects the impact of public opinion on prices over time.

[0035] S104. Use public opinion factors to determine the public opinion importance of the price impact results of designated chemical raw materials.

[0036] In this step, the importance of public opinion on the price impact of the specified chemical raw material is determined based on the public opinion factor constructed in step S103, that is, the larger the public opinion factor, the more important the price impact of the specified chemical raw material is.

[0037] This embodiment can mine the influence of public opinion information in the chemical industry on a daily basis, and provide a public opinion importance coefficient after quantitative analysis, which has the advantage of accurately evaluating the impact of public opinion on the price of specified chemical raw materials.

[0038] In one embodiment, if Figure 2 As shown, step S101 includes:

[0039] S201. Collect relevant public opinion text sets based on the original name of the specified chemical raw materials {X ip} p＝1…P , where X ip It means that the pth public opinion text on the i-th day is found by using the original name of the specified chemical raw material as the keyword, and there are a total of P public opinion texts on that day;

[0040] S202, collect relevant public opinion text sets {Y iq} q＝1…Q , where Y iqIt means that the qth public opinion text on the i-th day is queried using the upstream raw material name of the specified chemical raw material as the keyword, and there are a total of Q public opinion texts on that day;

[0041] S203, collect relevant public opinion text sets according to the names of downstream products of designated chemical raw materials {Z iz} z＝1…Z , where Z iz It means that the zth public opinion text on the i-th day is queried using the name of the downstream product of the specified chemical raw material as the keyword, and there are a total of Z public opinion texts on that day.

[0042] This embodiment collects public opinion texts related to the specified chemical raw material through the information collection module. From the perspective of the industry chain, the supply situation of upstream raw materials and the demand situation of downstream products have an important impact on the raw material market environment. Based on the relevance of the industry chain, the search keyword list for information collection includes the original name of the specified chemical raw material, the name of the upstream chemical raw material (multiple names can form a list) and the name of the downstream chemical product (multiple names can form a list), thereby obtaining a set of public opinion texts related to the specified chemical raw material.

[0043] In one embodiment, step S102 includes:

[0044] Each public opinion text is normalized and encoded and input into the inference model, and the positive impact, neutral impact and negative impact are output according to the impact on the price of designated chemical raw materials.

[0045] In this embodiment, the public opinion text set can be divided into a training set and a test set in a ratio of 4:1. Each public opinion text in the training set is normalized and encoded and then input into the reasoning model. According to the impact on the price of the specified chemical raw material, the output is expressed as a positive impact of Sign(X)=1, which means that the meaning of the public opinion text is positive; the output is expressed as a neutral impact of Sign(X)=0, which means that the meaning of the public opinion text is neutral; the output is expressed as a negative impact of Sign(X)=-1, which means that the meaning of the public opinion text is negative.

[0046] The inference model obtained by learning and training based on the training set is verified through the test set for model optimization.

[0047] In one embodiment, if Figure 3 As shown, step S103 includes:

[0048] S301. Construct the public opinion factor NX of the public opinion text with the original name of the specified chemical raw material as a keyword according to the following formula:

[0049]

[0050] S302. Construct the public opinion factor NY of the public opinion text with the upstream chemical raw material name as the keyword according to the following formula:

[0051]

[0052] S303, construct the public opinion factor NZ of the public opinion text with the downstream product name as the keyword according to the following formula:

[0053]

[0054] Among them, NX i represents the public opinion importance of the original name of the specified chemical raw material as a keyword on the i-th day, NY i represents the importance of public opinion with the upstream chemical raw material name as the keyword on the i-th day, NZ i represents the importance of public opinion with the downstream product name as the keyword on the i-th day; Rd represents the reading volume, sign(X ip ) represents the impact of the p-th public opinion text on the price of a specified chemical raw material on the i-th day, Lk represents the number of likes, Ct represents the number of collections, Fd represents the number of reposts, and ε represents the reader feedback in the past year The upper quartile of the sequence of values, If If yes, the value is 1, otherwise it is 0.

[0055] It should be noted that as time goes by, the impact of historical news on raw material prices becomes smaller and smaller. After experimental verification, only the public opinion texts of the past 10 days are considered. The public opinion text of the day i = 1, T i =1, yesterday's public opinion text is represented by i=2, T i =2 and so on; upstream chemical raw materials and downstream products have an indirect impact on raw material prices. a and b both represent the impact factors of the corresponding channels, and e represents a constant.

[0056] In this embodiment, various parameters are substituted into the above public opinion factor formula to calculate and obtain the public opinion factor NX, the public opinion factor NY and the public opinion factor NZ.

[0057] In one embodiment, step S104 includes:

[0058] Based on the sum of the public opinion factors of the public opinion texts with the original name of the specified chemical raw material as keywords, the public opinion factors of the public opinion texts with the names of upstream chemical raw materials as keywords, and the public opinion factors of the public opinion texts with the names of downstream products as keywords, the public opinion importance of the public opinion text set on the price impact of the specified chemical raw material is obtained.

[0059] In this embodiment, the public opinion importance coefficient NI of the day is calculated according to the formula NI=NX+NY+NZ; based on the public opinion importance coefficient NI, the importance of the price impact result on the specified chemical raw material can be known, so that managers can analyze and manage the company and industry more accurately.

[0060] The embodiment of the present invention also provides a device for constructing a public opinion factor of chemical raw materials based on an adaptive threshold, and the device for constructing a public opinion factor of chemical raw materials based on an adaptive threshold is used to execute any embodiment of the method for constructing a public opinion factor of chemical raw materials based on an adaptive threshold. Figure 4 , Figure 4 It is a schematic block diagram of a device for constructing a public opinion factor for chemical raw materials based on an adaptive threshold provided in an embodiment of the present invention.

[0061] like Figure 4 As shown, a chemical raw material public opinion factor construction device 400 based on an adaptive threshold includes: a collection unit 401, an inference unit 402, a construction unit 403 and a determination unit 404.

[0062] A collection unit 401 is used to collect a set of public opinion texts related to a specified chemical raw material according to different search keywords;

[0063] The reasoning unit 402 is used to input each public opinion text in the public opinion text set into the reasoning model, and output the price impact results of the designated chemical raw materials respectively;

[0064] A construction unit 403 is used to construct public opinion factors of public opinion texts collected by different search keywords;

[0065] The determination unit 404 is used to determine the public opinion importance of the price impact result of the specified chemical raw material by using the public opinion factor

[0066] The device can mine the influence of public opinion information in the chemical industry on a daily basis, and give the public opinion importance coefficient after quantitative analysis. It has the advantage of accurately evaluating the impact of public opinion on the price of specified chemical raw materials.

[0067] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0068] The above-mentioned chemical raw material public opinion factor construction device based on adaptive threshold can be implemented in the form of a computer program. The computer program can be used in Figure 5 Runs on the computer device shown.

[0069] See also Figure 5 , Figure 55 is a schematic block diagram of a computer device provided by an embodiment of the present invention. The computer device 500 is a server, which can be an independent server or a server cluster composed of multiple servers.

[0070] See also Figure 5 The computer device 500 includes a processor 502 , a memory and a network interface 505 connected via a system bus 501 , wherein the memory may include a non-volatile storage medium 503 and an internal memory 504 .

[0071] The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, the processor 502 can execute a method for constructing a public opinion factor of chemical raw materials based on an adaptive threshold.

[0072] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500 .

[0073] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute a method for constructing a public opinion factor for chemical raw materials based on an adaptive threshold.

[0074] The network interface 505 is used for network communication, such as providing data information transmission, etc. Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device 500 to which the solution of the present invention is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0075] Those skilled in the art will understand that Figure 5 The embodiments of the computer device shown in the figure do not constitute a limitation on the specific composition of the computer device. In other embodiments, the computer device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. For example, in some embodiments, the computer device may only include a memory and a processor. In such embodiments, the structure and function of the memory and the processor are the same as those of the embodiment of the present invention. Figure 5 The embodiments shown are consistent and will not be described again here.

[0076] It should be understood that in the embodiment of the present invention, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0077] In another embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium may be a non-volatile computer-readable storage medium. The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, a method for constructing a public opinion factor of a chemical raw material based on an adaptive threshold according to an embodiment of the present invention is implemented.

[0078] The storage medium is a physical, non-transient storage medium, for example, it can be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk or an optical disk, etc., which can store program codes.

[0079] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0080] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for constructing a public opinion factor of chemical raw materials based on an adaptive threshold, characterized in that: include: Collect public opinion text sets related to designated chemical raw materials based on different search keywords; Input each public opinion text in the public opinion text set into the inference model, and output the price impact results of the designated chemical raw materials respectively; Constructing public opinion factors of the public opinion texts collected by different search keywords; Using the public opinion factor to determine the public opinion importance of the price impact result of the designated chemical raw material; The public opinion text set related to the designated chemical raw materials collected according to different search keywords includes: Collect relevant public opinion text collection based on the original name of the specified chemical raw materials ,in It means that the pth public opinion text on the i-th day is queried using the original name of the specified chemical raw material as a keyword, and there are a total of P public opinion texts on that day; Collect relevant public opinion text collection based on the upstream chemical raw material names of the designated chemical raw materials ,in It means that the qth public opinion text on the i-th day is queried using the upstream raw material name of the specified chemical raw material as a keyword, and there are a total of Q public opinion texts on that day; Collect relevant public opinion text collection based on the names of downstream products of the designated chemical raw materials ,in It means that the zth public opinion text on the i-th day is queried using the name of the downstream product of the specified chemical raw material as the keyword, and there are a total of Z public opinion texts on that day; The process of constructing the public opinion factors of the public opinion text collected by different search keywords includes: The public opinion factor NX, public opinion factor NY and public opinion factor NZ of the public opinion text with the original name of the specified chemical raw material as the keyword are constructed according to the following formula: ； ； ； Among them, NX i represents the public opinion importance of the keyword of the designated chemical raw material on day i, Rd represents the reading volume, represents the impact of the p-th public opinion text on the price of the specified chemical raw material on the i-th day, Lk represents the number of likes, Ct represents the number of collections, and Fd represents the number of reposts. Indicates historical 1 year reader feedback ( ) value sequence, If , then the value is 1, otherwise it is 0; Among them, NY i represents the importance of public opinion with the name of the upstream chemical raw material as the keyword on the i-th day, e represents a constant, and a represents the influencing factor of the channel; Among them, NZ i represents the importance of public opinion with the downstream product name as the keyword on the i-th day, and b represents the influencing factor of the channel.

2. The method for constructing a public opinion factor of chemical raw materials based on an adaptive threshold according to claim 1, characterized in that: The inputting each public opinion text in the public opinion text set into the inference model and outputting the price impact results of the designated chemical raw materials respectively include: Each of the public opinion texts is normalized and encoded and input into the reasoning model, and the positive impact, neutral impact and negative impact are output according to the impact on the price of the designated chemical raw materials.

3. The method for constructing a public opinion factor of chemical raw materials based on an adaptive threshold according to claim 1, characterized in that: The using of the public opinion factor to determine the public opinion importance of the price impact result of the designated chemical raw material includes: According to the sum of the public opinion factors of the public opinion text with the name of the designated chemical raw material as keywords, the public opinion factors of the public opinion text with the name of the upstream chemical raw material as keywords and the public opinion factors of the public opinion text with the name of the downstream product as keywords, the public opinion importance of the public opinion text set on the price impact of the designated chemical raw material is obtained.

4. A device for constructing public opinion factors of chemical raw materials based on adaptive thresholds, characterized in that: include: A collection unit, used to collect public opinion text sets related to designated chemical raw materials according to different search keywords; An inference unit, used for inputting each public opinion text in the public opinion text set into an inference model, and outputting the price impact results on the designated chemical raw materials respectively; A construction unit, used to construct public opinion factors of the public opinion text collected by different search keywords; A determination unit, configured to determine the public opinion importance of the price impact result of the designated chemical raw material by using the public opinion factor; The public opinion text set related to the designated chemical raw materials collected according to different search keywords includes: Collect relevant public opinion text collection based on the original name of the specified chemical raw materials ,in It means that the pth public opinion text on the i-th day is queried using the original name of the specified chemical raw material as a keyword, and there are a total of P public opinion texts on that day; Collect relevant public opinion text collection based on the upstream chemical raw material names of the designated chemical raw materials ,in It means that the qth public opinion text on the i-th day is queried using the upstream raw material name of the specified chemical raw material as a keyword, and there are a total of Q public opinion texts on that day; Collect relevant public opinion text collection based on the names of downstream products of the designated chemical raw materials ,in It means that the zth public opinion text on the i-th day is queried using the name of the downstream product of the specified chemical raw material as the keyword, and there are a total of Z public opinion texts on that day; The process of constructing the public opinion factors of the public opinion text collected by different search keywords includes: The public opinion factor NX, public opinion factor NY and public opinion factor NZ of the public opinion text with the original name of the specified chemical raw material as the keyword are constructed according to the following formula: ； ； ； Among them, NX i represents the public opinion importance of the keyword of the designated chemical raw material on day i, Rd represents the reading volume, represents the impact of the p-th public opinion text on the price of the specified chemical raw material on the i-th day, Lk represents the number of likes, Ct represents the number of collections, and Fd represents the number of reposts. Indicates historical 1 year reader feedback ( ) value sequence, If , then the value is 1, otherwise it is 0; Among them, NY i represents the importance of public opinion with the name of the upstream chemical raw material as the keyword on the i-th day, e represents a constant, and a represents the influencing factor of the channel; Among them, NZ i represents the importance of public opinion with the downstream product name as the keyword on the i-th day, and b represents the influencing factor of the channel.

5. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, it implements the method for constructing a public opinion factor for chemical raw materials based on an adaptive threshold as described in any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, enables the processor to execute the method for constructing a public opinion factor for chemical raw materials based on an adaptive threshold as described in any one of claims 1 to 3.

Images