CN115170353A

CN115170353A - Intellectual property achievement transformation analysis and evaluation system based on big data processing

Info

Publication number: CN115170353A
Application number: CN202210855730.4A
Authority: CN
Inventors: 胥巍然; 邢樱
Original assignee: Land Information Consulting Shanghai Co ltd
Current assignee: Land Information Consulting Shanghai Co ltd
Priority date: 2022-07-12
Filing date: 2022-07-12
Publication date: 2022-10-11

Abstract

The invention provides an intellectual property achievement transformation analysis and evaluation system based on big data processing, and relates to the technical field of data processing. The method comprises the steps of classifying the intellectual property products through a product classification module, obtaining the basic value of the intellectual property products through a product classification module, calculating the conversion value through a conversion value determining module, comprehensively counting according to the setting results of a product classification setting module and a conversion classification setting module through a comprehensive counting module, and calculating to obtain the evaluation result of comprehensive conversion, so that the intellectual property products are automatically evaluated, a large amount of manual intervention is not needed, the meticulous performance of conversion evaluation of intellectual property achievements is improved, the evaluation result can be matched with the actually generated achievement value, and the effectiveness of evaluation is improved.

Description

Intellectual property achievement transformation analysis and evaluation system based on big data processing

Technical Field

The invention relates to the technical field of data processing, in particular to an intellectual property achievement transformation, analysis and evaluation system based on big data processing.

Background

Intellectual property rights are the exclusive rights which the right-holders obey to have with respect to: (ii) a work; (II) invention, utility model, appearance design; (III) trade mark; (IV) a geographical indication; (V) a business secret; (VI) designing the layout of the integrated circuit; (VII) new plant species; (eight) other objects stipulated by law. Enterprises can make profits by carrying out achievement transformation through independently developed intellectual property rights.

With the attention on the intellectual property, the occupation ratio of the intellectual property product in the enterprise is more and more important, and the evaluation of the value of the intellectual property product is more and more important in the aspects of marketing counseling, enterprise financial auditing and the like. However, in the prior art, in the process of performing achievement transformation on intellectual property rights, manual evaluation is generally performed, and the workload is very large, and an enterprise is difficult to evaluate the influence of the enterprise on the final transformation profit, so that a quantitative evaluation method is not available for the transformation value of the intellectual property rights, and therefore, it is difficult for the enterprise to vividly show the benefit of the intellectual property rights on the company, so that the influence of the intellectual property rights on the development of the company is indirectly weakened.

Disclosure of Invention

Aiming at the defects in the prior art, the invention aims to provide an intellectual property result transformation analysis and evaluation system based on big data processing, and a set of evaluation method is set for the transformation of intellectual property, so that the transformation of the value of an intellectual property product is automatically evaluated, and the problem of large workload of manual evaluation of the existing intellectual property transformation is solved.

In order to achieve the purpose, the invention is realized by the following technical scheme: the intellectual property achievement transformation analysis and evaluation system based on big data processing is characterized by comprising a product classification module, a value determination module, a transformation value determination module and a comprehensive statistics module; the product classification module is used for classifying the intellectual property products by using the trained CNN network; the value determining module is used for determining the basic value of the intellectual property product by using the trained CNN network; the conversion value determining module is used for determining the conversion value of the intellectual property product; and the comprehensive statistical module is used for carrying out comprehensive statistics according to the processing results of the product classification module, the value determination module and the conversion value determination module and calculating to obtain an evaluation result of comprehensive conversion.

The product classification module obtains the classification of intellectual property products through the following steps:

step S11, dividing intellectual property products into works, patents, trademarks, geographical signs, trade secrets, integrated circuits, new plant varieties and other types;

step S12, crawling a preset number of samples of each type from the official website through a web crawler program according to the type;

s13, cutting the first sample to obtain two front non-cover pages of each sample, wherein the two front non-cover pages are the two front pages without covers to obtain a second sample;

s14, inputting the second sample into a CNN network for training to obtain a first trained CNN network, wherein the first trained CNN network can classify intellectual property products through the first two pages of non-cover pages of the document;

and S15, cutting the intellectual property product to be processed to obtain the first two non-cover pages of each sample, wherein the first two non-cover pages are the first two pages without covers, and inputting the result into the first trained CNN network to obtain the classification result of each intellectual property product.

The value determining module obtains the basic value of the intellectual property product through the following steps:

s21, crawling quarterly newspapers, annual newspapers and stock books of listed companies through a web crawler, and extracting the intellectual property product part;

step S22, inputting the extracted intellectual property products into a third-party retrieval platform, and acquiring similarity sequences with preset number of similarity degrees;

step S23, inputting the value and the type of the extracted intellectual property product and the corresponding similarity sequence into a second CNN network, training to obtain a second trained CNN network, wherein the second trained CNN network can output evaluation value by inputting the type and the similarity sequence of the intellectual property product;

and S24, inputting the intellectual property achievements to be processed into a third-party retrieval platform, acquiring achievement similarity sequences with preset number of degrees of similarity, and inputting the types and the achievement similarity sequences of the intellectual property achievements to be processed into the second trained CNN network to obtain the basic value of each intellectual property product.

The conversion value determining module determines the conversion value of the intellectual property product by the following steps:

step S31, crawling annual newspapers of listed companies through a web crawler, and extracting contents of intellectual property conversion in the annual newspapers, including intellectual property, type and value of the conversion;

step S32, determining the evaluation value of the transformed intellectual property right through the second trained CNN network and the transformed intellectual property right, dividing each evaluation value by the corresponding transformed value, and averaging the division results to obtain a transformation coefficient of each transformation mode;

and S33, determining the conversion value of each conversion mode according to the basic values and the conversion coefficients of all intellectual property products.

The basic self-conversion value formula is configured as:

Jzxz＝(Jzp+Jzl+Jsb+Jdl+Jsy+Jjc+Jzw+Jqt)×a1；

the underlying transfer others value formula is configured as:

Jzrt＝(Jzp+Jzl+Jsb+Jdl+Jsy+Jjc+Jzw+Jqt)×a2；

the basic license others value formula is configured as:

Jxkt＝(Jzp+Jzl+Jsb+Jdl+Jsy+Jjc+Jzw+Jqt)×a3；

the basic common implementation value formula is configured as:

Jgts＝(Jzp+Jzl+Jsb+Jdl+Jsy+Jjc+Jzw+Jqt)×a4；

the basic conversion investment value formula is configured as follows:

Jzst＝(Jzp+Jzl+Jsb+Jdl+Jsy+Jjc+Jzw+Jqt)×a5；

wherein Jzxz is a self-conversion basic value, jzrt is a transfer others basic value, jxkt is a license others basic value, jgts is a common implementation basic value, jzst is a conversion investment basic value, jzp is a basic work value, jzl is a basic patent value, jsb is a basic trademark value, jdl is a basic geographical sign value, jsy is a basic business secret value, jjc is a basic integrated circuit value, jzw is a basic plant new variety value, jqt is a basic other type value, a1 is a self-conversion coefficient, a2 is a transfer others conversion coefficient, a3 is a license conversion coefficient, a4 is a common implementation conversion coefficient, and a5 is a conversion investment coefficient.

The comprehensive statistical module is configured with an actual setting strategy, and the actual setting strategy comprises the following steps: respectively acquiring the quantity of works, patents, trademarks, geographical signs, trade secrets, integrated circuits, new plant varieties and other types of products, and multiplying the quantity of the products by the corresponding basic product value to obtain the actual product values of the corresponding works, patents, trademarks, geographical signs, trade secrets, integrated circuits, new plant varieties and other types;

and adding the actual product values of works, patents, trademarks, geographic signs, trade secrets, integrated circuits, new varieties of plants and other types to obtain the comprehensive actual value of the product.

The comprehensive statistical module is configured with a comprehensive statistical strategy, and the comprehensive statistical strategy comprises the following steps: substituting the comprehensive actual value of the product into an actual self-conversion value formula to obtain an actual self-conversion value;

substituting the comprehensive actual value of the product into an actual value formula of others to be transferred to obtain the actual value of others to be transferred;

substituting the comprehensive actual value of the product into an actual value formula of the value of the other person to be permitted to obtain the actual value of the other person to be permitted;

substituting the comprehensive actual value of the product into an actual common implementation value formula to obtain an actual common implementation value;

substituting the comprehensive actual value of the product into an actual reduced investment value formula to obtain an actual reduced investment value;

adding the actual self-transformation value, the actual value of others to be transferred, the actual value of others to be licensed, the actual common implementation value and the actual conversion investment value to obtain a comprehensive transformation value, and dividing the comprehensive transformation value by the total sum of the addition of works, patents, trademarks, geographic signs, trade secrets, integrated circuits, new plant varieties and other types of products to obtain a comprehensive transformation value index;

when the comprehensive conversion value index is greater than or equal to the first comprehensive conversion threshold value, outputting a high-grade comprehensive conversion grade; when the comprehensive conversion value index is greater than or equal to a second comprehensive conversion threshold and smaller than a first comprehensive conversion threshold, outputting a medium-grade comprehensive conversion grade; and when the comprehensive conversion index is smaller than the second comprehensive conversion threshold value, outputting a low-grade comprehensive conversion grade.

Further, the actual self-conversion value formula is configured to: jszx = Jzhs ^k1 (ii) a The actual transfer others value formula is configured as: jszt = Jzh × k2; the actual license others value formula is configured to: jsxt = Jzh × k3; the actual common implementation value formula is configured as: jsgs = Jzh ^k4 (ii) a The actual reduced investment value formula is configured as: jszt = Jzh ^k5 (ii) a Wherein Jszx is an actual self-conversion value, jszt is an actual value of transferring others, jsxt is an actual value of licensing others, jsgs is an actual common implementation value, jszt is an actual reduced investment value, jzh is a product comprehensive actual value, k1 is a self-conversion growth index, k2 is a multiple of value of transferring others, k3 is a multiple of value of licensing others, k4 is a common implementation growth index, and k5 is a reduced investment growth index.

The invention has the beneficial effects that: the method comprises the steps of classifying the intellectual property products through the product classification module, obtaining the basic value of the intellectual property products through the product classification module, calculating the conversion value through the conversion value determining module, performing comprehensive statistics according to the setting results of the product classification setting module and the conversion classification setting module through the comprehensive statistics module, and obtaining the comprehensive conversion evaluation result through calculation, so that the intellectual property products are automatically evaluated, a large amount of manual intervention is not needed, the conversion evaluation meticulous performance of the intellectual property achievements is improved, the evaluation result can be matched with the actually generated achievement value, and the evaluation effectiveness is improved.

Drawings

Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:

FIG. 1 is a block schematic diagram of the system of the present invention;

fig. 2 is a block diagram of a classification of an intellectual property product of the present invention;

FIG. 3 is a block diagram of the classification of the conversion scheme of the present invention.

Detailed Description

In order to make the technical means, the creation characteristics, the achievement purposes and the effects of the invention easy to understand, the invention is further explained by combining the specific embodiments.

Referring to fig. 1, the intellectual property achievement transformation analysis and evaluation system based on big data processing sets a set of evaluation methods for the transformation of intellectual property, thereby facilitating the evaluation of the importance of intellectual property and solving the problem of the existing intellectual property transformation evaluation.

The evaluation system comprises a product classification module, a value determination module, a conversion value determination module and a comprehensive statistical module.

The product classification module is used for classifying the intellectual property products by using the trained CNN network, and the product classification model obtains the classification of the intellectual property products through the following steps:

step S11, please refer to fig. 2, dividing the intellectual property products into works, patents, trademarks, geographic signs, trade secrets, integrated circuits, new plant varieties and other types;

and S12, crawling a preset number of samples of each type from the official website through a web crawler program according to the type.

In order to train the classification model, a large number of samples are required, official data is the best sample, a certain number of public documents can be downloaded through official websites such as the national intellectual property office, and the downloaded classification documents are determined as the first samples.

And S13, cutting the first sample to obtain the first two non-cover pages of each sample, wherein the first two non-cover pages are the first two pages without covers to obtain a second sample.

Since the original patent, work, trademark and other documents usually have many pages, and the first non-cover page (i.e. the first page counted after the cover is removed) of the patent, work, trademark and other documents is usually a bibliographic item, the type of the document can be determined by the bibliographic item; however, intellectual property products inside the enterprise do not necessarily have bibliographic items, and the second page of the non-cover official document (i.e., the second page with the cover removed from the beginning count) usually contains some specific document format, such as the inclusion of a claim for a patent, and the claim has a specific format, so that the type of document can be further determined by the second page of the non-cover for documents without bibliographic items, so that the intellectual property products inside the enterprise can still be correctly classified when there are no bibliographic items.

And S14, inputting the second sample into a CNN network for training to obtain a first trained CNN network, wherein the first trained CNN network can classify intellectual property products through the first two non-cover pages of the document.

The CNN network is a convolutional neural network, the CNN network is widely applied in sample classification at present, any CNN network structure with a classification function can be used in the method, the method can be used as long as classification can be carried out, the specific structure is not specifically limited, and the CNN network has the capacity of classifying intellectual property product documents by labeling the samples according to the categories of intellectual property and training the CNN network.

When the model is actually trained, the data to be classified needs to be processed into a structure similar to the sample in advance, and the processed data is input into the trained CNN network, so that the CNN network can provide the classification result of the intellectual property product.

The value determining module is used for determining the basic value of the intellectual property product by using the trained CNN network, and the value determining module is obtained by the following steps:

and S21, crawling quarterly newspapers, annual newspapers and stock books of listed companies through a web crawler, and extracting the intellectual property product part.

The quarterly newspaper, annual newspaper and stock book of the listed company usually disclose the product status, product transaction condition and the like of the company, and particularly the stock book usually has a very detailed product description table, so that the market value of the corresponding intellectual property product can be obtained through the documents.

And S22, inputting the extracted intellectual property product into a third-party retrieval platform, and acquiring a similarity sequence with the number of preset values before similarity.

At present, more and more intellectual property platforms provide rapid intellectual property evaluation interfaces, for example, platforms such as an intelligent bud and the like can search for the similarity of patents and the like and return patent lists with higher similarity; generally, the value of the intellectual property with less similarity on the market is higher, a third platform is called for automatic retrieval in order to evaluate the intellectual property achievement, and for example, a third party API can be called or automatic submission can be carried out through a crawler technology; after the similarity is obtained, for subsequent processing, the method only needs to extract a certain number of similarities, such as 5 similarity (80%, 78%,76%,75%, 60%) before extraction;

and S23, inputting the value and the type of the extracted intellectual property product and the corresponding similarity sequence into a second CNN network, training to obtain a second trained CNN network, and outputting the evaluation value by the second trained CNN network through inputting the type and the similarity sequence of the intellectual property product.

The value of intellectual property in quarterly newspapers, annual newspapers, and posters is sometimes in the form of a pool of patents, a set of trademarks, etc., with a price given by a set of patents and trademarks, which is averaged to approximate the price of each product for ease of handling.

Specifically, a basic work value Jzp, a basic patent value Jzl, a basic trademark value Jsb, a basic geographic marking value Jdl, a basic business secret value Jsy, a basic integrated circuit value Jjc, a basic plant new variety value Jzw and a basic other type value Jqt are obtained.

Because the values of different types of intellectual property products are different, two CNN models are trained according to the existing public data, and classification and basic value evaluation are performed on the existing intellectual property results through the two CNN models, so that the automation of the evaluation is realized.

The conversion value determining module is used for determining the conversion value of the intellectual property product, and is obtained by the following steps:

referring to fig. 3, the conversion is generally self-converting, transferring others, licensing others, co-implementing, and converting investment types.

step S32, determining the evaluation value of the transformed intellectual property right through the second trained CNN network and the transformed intellectual property right, dividing each of the all evaluation values and the corresponding transformed values, and averaging the divided results to obtain a transformation coefficient of each transformation mode;

Specifically, the method comprises the following steps:

step S331, setting a basic self-transformation value formula for self-transformation, and calculating through the basic self-transformation value formula to obtain a self-transformation basic value; the base self-conversion value formula is configured as: jzxz = (Jzp + Jzl + Jsb + Jdl + Jsy + jjjc + Jzw + Jqt) × a1; jzxz is the self-transformation base value; a1 is a self-conversion coefficient;

step S332, setting a basic value formula of others to be transferred, and calculating to obtain the basic value of others to be transferred according to the basic value formula of others to be transferred; the underlying transfer others value formula is configured to: jztt = (Jzp + Jzl + Jsb + Jdl + Jsy + jjjc + Jzw + Jqt) × a2; jzrt is the base value for transferring others; a2 is a conversion coefficient of other people;

step S333, setting a basic value formula of the permitted others for the permitted others, and calculating the basic value of the permitted others according to the basic value formula of the permitted others; the base license others value formula is configured to: jxkt = (Jzp + Jzl + Jsb + Jdl + Jsy + jjjjc + Jzw + Jqt) × a3; jxkt is the base value of the licence of others; a3 is the conversion coefficient of the allowed others;

step S334, setting a basic common implementation value formula for common implementation, and calculating the basic common implementation value formula through the basic common implementation value formula to obtain a common implementation basic value; the base common enforcement value formula is configured as: jgts = (Jzp + Jzl + Jsb + Jdl + Jsy + jjjc + Jzw + Jqt) × a4; jgts is the common implementation base value; a4 is a co-implementation transformation coefficient;

step S335, setting a basic conversion investment value formula for the conversion investment, and calculating through the basic conversion investment value formula to obtain a conversion investment basic value; the base reduced investment value formula is configured as: jzst = (Jzp + Jzl + Jsb + Jdl + Jsy + jjjc + Jzw + Jqt) × a5; jzst is the conversion investment basic value; and a5 is a conversion coefficient of the reduced investment.

As described in steps S331-S335, wherein Jzp is the basic work value, jzl is the basic patent value, jsb is the basic trademark value, jdl is the basic geographic marker value, jsy is the basic business secret value, jjjjc is the basic integrated circuit value, jzw is the basic plant new variety value, jqt is the basic other type value, and a1, a2, a3, a4, a5 are transformed according to the transformation coefficient obtained in step S32.

And the comprehensive statistical module is used for carrying out comprehensive statistics according to the processing results of the product classification module, the value determination module and the conversion value determination module and calculating to obtain an evaluation result of comprehensive conversion.

Step S41, classifying the intellectual property products according to the product classification module, respectively obtaining the quantity of works, patents, trademarks, geographic signs, trade secrets, integrated circuits, new plant varieties and other types of products, and obtaining the actual product values of the corresponding works, patents, trademarks, geographic signs, trade secrets, integrated circuits, new plant varieties and other types according to the value determination module;

and S42, adding the actual product values of works, patents, trademarks, geographic signs, trade secrets, integrated circuits, new plant varieties and other types to obtain the comprehensive actual value of the product.

And S43, obtaining a conversion coefficient of each conversion mode according to the conversion value determining module, and multiplying the conversion coefficient by the comprehensive actual value of the product to obtain the comprehensive conversion value of the product.

And obtaining the comprehensive conversion value of the product of the intellectual property right as described in the steps S41-S42. Through the steps, the achievement transformation of the intellectual property product is comprehensively evaluated and analyzed, the comprehensive transformation value of each transformation mode is automatically obtained, data support is provided for the operation of the intellectual property with extremely low labor cost, and references are provided for activities such as enterprise marketing, financing evaluation and the like.

Preferably, the comprehensive statistical module is configured with a comprehensive statistical strategy, and the comprehensive statistical strategy includes the following steps:

s51, substituting the comprehensive actual value of the product into an actual self-conversion value formula to obtain an actual self-conversion value; the actual self-conversion value formula is configured as: jszx = Jzhs × k1; jszx is the actual self-transformation value; will produceThe comprehensive actual value of the product is substituted into an actual value formula of others to be transferred to obtain the actual value of others to be transferred; the actual transfer others value formula is configured as: jszt = Jzh × k2; jszt is the actual value of transferring others; substituting the comprehensive actual value of the product into an actual value formula of the value of the other person to be permitted to obtain the actual value of the other person to be permitted; the actual license others value formula is configured to: jsxt = Jzh × k3; jsxt is the actual value of the licensed person; substituting the comprehensive actual value of the product into an actual common implementation value formula to obtain an actual common implementation value; the actual common enforcement value formula is configured to: jsgs = Jzh ^k4 (ii) a Jsgs is the actual common implementation value; substituting the comprehensive actual value of the product into an actual reduced investment value formula to obtain an actual reduced investment value; the actual reduced investment value formula is configured as: jszt = Jzh ^k5 (ii) a Jszt is the actual reduced investment value; as shown in step S1, jzh is the product integrated actual value, k1 is the self-conversion growth index, k2 is the value multiple of transferring others, k3 is the value multiple of licensing others, k4 is the co-implementation growth index, and k5 is the reduced investment growth index. As described in step S41, since the self-conversion, the approval of others, the mutual implementation, and the conversion of investment have long-term income, a calculation method with normal index is adopted, but it is necessary to limit the period within a certain period and transfer others to one-time income, and therefore a calculation method with multiplication of coefficients is adopted;

and S52, adding the actual self-transformation value, the actual transfer value, the actual license value, the actual common implementation value and the actual conversion investment value to obtain a comprehensive transformation value, and dividing the comprehensive transformation value by the total sum of the works, patents, trademarks, geographical signs, trade secrets, integrated circuits, new plant varieties and other types of products to obtain a comprehensive transformation value index.

Step S53, when the comprehensive conversion value index is greater than or equal to the first comprehensive conversion threshold value, outputting a high-level comprehensive conversion level; when the comprehensive conversion value index is greater than or equal to the second comprehensive conversion threshold and smaller than the first comprehensive conversion threshold, outputting a medium-grade comprehensive conversion grade; and when the comprehensive conversion index is smaller than the second comprehensive conversion threshold value, outputting a low-grade comprehensive conversion grade.

As set forth in steps S51-S53, wherein the first integrated conversion threshold is greater than the second integrated conversion threshold, the conversion value of the high-level integrated conversion level is greater than the conversion value of the medium-level integrated conversion level, and the conversion value of the medium-level integrated conversion level is greater than the conversion value of the low-level integrated conversion level.

Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that the following descriptions are only illustrative and not restrictive, and that the scope of the present invention is not limited to the above embodiments: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.

Claims

1. The intellectual property achievement transformation analysis and evaluation system based on big data processing is characterized by comprising a product classification module, a value determination module, a transformation value determination module and a comprehensive statistics module;

the product classification module is used for classifying the intellectual property products by using the trained CNN network;

the value determining module is used for determining the basic value of the intellectual property product by using the trained CNN network;

the conversion value determining module is used for determining the conversion value of the intellectual property product;

2. The system of claim 1, wherein the product classification module obtains the classification of the intellectual property product by:

step S11, dividing the intellectual property products into works, patents, trademarks, geographical signs, trade secrets, integrated circuits, new plant varieties and other types;

s12, crawling a preset number of samples of each type from an official website through a web crawler program according to the type;

and S15, cutting the intellectual property product to be processed to obtain the first two pages of non-cover pages of each sample, wherein the first two pages of non-cover pages are the first two pages without covers, and inputting the result into the first trained CNN network to obtain the classification result of each intellectual property product.

3. The system of claim 2, wherein the value determining module obtains the base value of the intellectual property product by:

s22, inputting the extracted intellectual property products into a third-party retrieval platform, and acquiring a similarity sequence with preset number of values before similarity;

step S23, inputting the value and the type of the extracted intellectual property product and the corresponding similarity sequence into a second CNN network, training to obtain a second trained CNN network, wherein the second trained CNN network can output evaluation value by inputting the type of the intellectual property product and the similarity sequence;

4. The system of claim 3, wherein the transformation value determination module determines the transformation value of the intellectual property product by:

step S31, crawling the annual report of the listed company through a web crawler, and extracting the content of the intellectual property conversion in the annual report, including the intellectual property, the type and the value of the conversion;

5. The intellectual property achievement transformation analysis and evaluation system based on big data processing of claim 4, wherein the basic self-transformation value formula is configured to:

Jzxz＝(Jzp+Jzl+Jsb+Jdl+Jsy+Jjc+Jzw+Jqt)×a1；

the underlying transferred others value formula is configured as:

Jzrt＝(Jzp+Jzl+Jsb+Jdl+Jsy+Jjc+Jzw+Jqt)×a2；

the basic license others value formula is configured as:

Jxkt＝(Jzp+Jzl+Jsb+Jdl+Jsy+Jjc+Jzw+Jqt)×a3；

the basic common enforcement value formula is configured as:

Jgts＝(Jzp+Jzl+Jsb+Jdl+Jsy+Jjc+Jzw+Jqt)×a4；

the underlying reduced investment value formula is configured as:

Jzst＝(Jzp+Jzl+Jsb+Jdl+Jsy+Jjc+Jzw+Jqt)×a5；

6. The intellectual property result conversion analysis and evaluation system based on big data processing as claimed in claim 5, wherein the comprehensive statistics module performs comprehensive statistics by:

step S41, classifying the intellectual property products according to the product classification module, respectively obtaining the quantity of works, patents, trademarks, geographic signs, trade secrets, integrated circuits, new plant varieties and other types of products, and obtaining the actual product value of each work, patent, trademark, geographic sign, trade secrets, integrated circuits, new plant varieties and other types according to the value determination module;

and S42, adding the actual product values of the works, the patents, the trademarks, the geographic signs, the trade secrets, the integrated circuits, the new plant varieties and other types to obtain the comprehensive actual value of the product.

And S43, obtaining the conversion coefficient of each conversion mode according to the conversion value determining module, and multiplying the conversion coefficient by the comprehensive actual value of the product to obtain the comprehensive conversion value of the product.