Innovation evaluation calculation method for enterprises in field

Abstract

The invention relates to an innovation evaluation calculation method for enterprises in the field, and the method comprises the following steps: S1, obtaining intellectual property data: preparing and sorting a plurality of pieces of intellectual property data, and defining each field of the intellectual property data; s2, defining scoring rules and enriching scores; s3, key words and weights are set, a field is selected, the key words and the weights of the field are defined, the key words are expressed as Ki, and the corresponding weights are expressed as Wi and 0 lt; wi < lt >; 1, 1lt; = ilt; = n; wherein the keywords refer to specific vocabularies which are highly related to the field and are easy to appear in intellectual property description; the weight represents the correlation degree of the keyword and the field, and the higher the correlation degree is, the larger the weight is; s4, keyword matching: matching and selecting the intellectual property data related to the field from all the intellectual property data through each keyword; and S5, calculating the innovation score of the enterprise in the selected field.

Description

Technical Field

[0001] The present invention relates to the field of computer application technologies. Specifically, it relates to a method for calculating innovation evaluation for enterprises in a field, aiming to achieve quantitative calculation of the innovation evaluation of each enterprise in a specific professional or industrial field. Background Art

[0002] When analyzing the development status of a certain professional or industrial field, the innovation ability of enterprises is an important evaluation indicator. It not only reflects the comprehensive strength of enterprises in aspects such as technology R & D, product innovation, and market adaptability, but also is a key factor in measuring the future development potential and industry competitiveness of enterprises. Currently, the methods for evaluating the innovation ability of enterprises often evaluate from aspects such as the capital investment, personnel investment, and achievements of enterprises. These methods require collecting relatively detailed data of enterprises, and some data are not open. When conducting analysis of the industrial chain or industrial cluster, it is necessary to evaluate the innovation ability of a large number of enterprises in a large number of sub - fields, and it is often impossible to collect such comprehensive data. This method realizes the quantitative calculation of the innovation ability of enterprises through the analysis of publicly available enterprise intellectual property data.

[0003] Currently, there is no relevant solution in the market. Summary of the Invention

[0004] In view of the above - mentioned technical problems in the related art, the present invention proposes a method for calculating innovation evaluation for enterprises in a field, which can overcome the above - mentioned deficiencies existing in the prior art.

[0005] To achieve the above - mentioned technical objectives, the technical solution of the present invention is realized as follows:

[0006] A method for calculating innovation evaluation for enterprises in a field includes the following steps:

[0007] S1 Obtain intellectual property data: Prepare several pieces of intellectual property data and sort them, and define each field of the intellectual property data; the fields of the intellectual property data include unique identifier id, name title, abstract information brief, type type, status status, application date apply_date, authorization date authorize_date, name of the enterprise to which it belongs ename, and score score.

[0008] S2 Define the scoring rules and enrich the scores:

[0009] S2.1 Define the scoring rules: Define the scoring rules according to type type and status status; in the scoring rules, use t to represent the type type of the intellectual property data, use s to represent the status type of the intellectual property data, and use S(t, s) to represent the score score of the intellectual property data.

[0010] S2.2: Calculate the scores of all the intellectual property data obtained in S1 according to the scoring rules obtained in S2.1, and update the scores to the score fields of the corresponding intellectual property data;

[0011] S3 Set keywords and weights: Select a field, and define the keywords and weights of the field. The keywords are represented as K i , and the corresponding weights are represented as W i and 0 < W i <= 1, 1 <= i <= n; where the keyword refers to a specific word that is highly relevant to the field and is likely to appear in the intellectual property description; the weight represents the degree of association between the keyword and the field, and the higher the degree of association, the greater the weight;

[0012] S4 Match by keywords: Among all the intellectual property data, match and select the intellectual property data related to the field through each keyword;

[0013] S5 Calculate the innovation scores of enterprises in the selected field: Aggregate all the intellectual property data related to the field found in S4. Accumulate the scores score of all the intellectual property data belonging to the same enterprise for each enterprise, so as to obtain the innovation scores of each enterprise in the field. Finally, rank each enterprise according to the innovation scores.

[0014] Preferably, in S1, the categories of the type include invention patents, design patents, utility model patents, and software copyrights.

[0015] Preferably, in S1, the categories of the status include authorized and unauthorized.

[0016] Preferably, in S1, the score is set to NULL or 0 or an empty value.

[0017] Preferably, in S1, it can be obtained by purchasing a database or interface service from enterprises that provide enterprise industrial and commercial data retrieval services such as Tianyancha and Qichacha, so as to complete the preparation of intellectual property data.

[0018] Preferably, in S3, the acquisition methods of keywords include obtaining them according to expert experience or Internet knowledge.

[0019] Preferably, S4 specifically includes the following steps:

[0020] S4.1: Set a relevance threshold μ, μ >= 0;

[0021] S4.2: Select one from all the intellectual property data in order and define it as the current matching data;

[0022] S4.3: Search for the occurrences of each keyword K one by one from the summary information brief of the current matching data, and represent them as F i (i = 1, 2, …, n) respectively; i (i = 1, 2, …, n);

[0023] S4.4: During the matching process, the field for matching and the correlation coefficient of the current matching data are represented as R, and R is calculated through the following formula (1):

[0024]

[0025] S4.5: If R >= μ, it indicates that the current matching data is relevant to the field, and record successful matching; otherwise, record failed matching;

[0026] S4.6: If the current matching data is the last intellectual property data, then continue with S5; otherwise, return to S4.2.

[0027] Optionally, in S5, the ranking order of each enterprise is in descending order according to each innovation score - that is, it represents the innovation ability ranking list of each enterprise in the field.

[0028] Advantages of the present disclosure: By retrieving intellectual property information such as patents and software copyrights of enterprises, the present disclosure uses keyword matching to establish the association among enterprises, intellectual products, and fields, and then proposes a calculation method for quantitative evaluation, thereby realizing the quantitative evaluation of the innovation ability of enterprises in this field. This method can evaluate the innovation ability of a large number of enterprises in a large number of fields, providing support for the analysis of industrial chains or industrial clusters.

[0029] The present disclosure realizes the quantitative evaluation of the innovation of enterprises in professional or industrial fields through intellectual property data, and has the following effects: (A) It is realized based on the intellectual property data in the publicly available enterprise industrial and commercial data, and the data is easy to obtain, facilitating the innovation evaluation of a large number of enterprises in a large number of fields and providing support for the analysis of industrial chains or industrial clusters; (B) Based on this evaluation result, through simple queries and summations, it is possible to realize the innovation comparison of enterprises in the same field and the innovation comparison among multiple fields, and understand the enterprise investment, industrial layout, etc. Description of the Drawings

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0031] Figure 1Logic flow chart of the innovative evaluation calculation method based on the linkage between the 3D model of the substation and the monitoring camera described in the present disclosure. Figure 2 Example diagram for updating the scoring data to the score field of the intellectual property data in the present disclosure. Figure 3 Example diagram of the matched intellectual property data in the present disclosure. Figure 4 Example diagram of the effect taking the field of "Artificial Intelligence - Autonomous Driving" as an example in the present disclosure. Detailed implementation manners

[0032] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention.

[0033] As Figure 1 shown, in order to facilitate the understanding of the above technical solutions of the present invention, the above technical solutions of the present invention will be described in detail below in terms of specific usage manners.

[0034] The innovative evaluation calculation method for enterprises in the target field includes the following steps:

[0035] S1 Obtain intellectual property data: Prepare several pieces of intellectual property data and sort them, and define each field of the intellectual property data; the fields of the intellectual property data include unique identifier id, name title, abstract information brief, type type, status status, application date apply_date, authorization date authorize_date, name of the affiliated enterprise ename, and score score;

[0036] S2 Define the scoring rules and enrich the scores:

[0037] S2.1 Define the scoring rules: Define the scoring rules according to the type type and status status; in the scoring rules, use t to represent the type type of the intellectual property data, use s to represent the status type of the intellectual property data, and use S(t, s) to represent the score score of the intellectual property data;

[0038] S2.2: According to the scoring rules obtained in S2.1, calculate the scores of all the intellectual property data obtained in S1, and update the scores to the score fields of the corresponding intellectual property data;

[0039] S3 Set keywords and weights: Select a field, and define the keywords and weights of the field. The keywords are represented as K i , and the corresponding weights are represented as W i and 0 < W i<= 1, 1 <= i <= n; where the keyword refers to a specific word that is highly relevant to the field and is likely to appear in the description of intellectual property; the weight represents the degree of association between the keyword and the field, and the higher the degree of association, the greater the weight;

[0040] S4 performs keyword matching: among all intellectual property data, each keyword is used to match and select the intellectual property data related to the field.

[0041] S5 calculates the innovation score of the enterprise in the selected field: summarize all the intellectual property data related to the field found in S4. Taking the enterprise as a unit, the scores score of all the intellectual property data belonging to the same enterprise are accumulated respectively, so as to obtain the innovation score of each enterprise in the field. Finally, each enterprise is ranked according to the innovation scores.

[0042] In a certain embodiment, in S1, the categories of the type include invention patents, design patents, utility model patents, and software copyrights.

[0043] In a certain embodiment, in S1, the categories of the status include authorized and unauthorized.

[0044] In a certain embodiment, in S1, the score is set to NULL or 0 or an empty value.

[0045] In a certain embodiment, in S1, it can be obtained by purchasing a database or interface service from enterprises that provide enterprise industrial and commercial data retrieval services such as Tianyancha and Qichacha, so as to complete the preparation of intellectual property data.

[0046] In a certain embodiment, in S3, the acquisition method of keywords includes obtaining them according to expert experience or Internet knowledge.

[0047] In a certain embodiment, S4 specifically includes the following steps:

[0048] S4.1: Set a relevance threshold μ, μ >= 0;

[0049] S4.2: Select one from all the intellectual property data in sequence and define it as the current matching data;

[0050] S4.3: Sequentially search for the occurrences of each keyword K i (i = 1, 2,..., n) in the abstract information brief of the current matching data, and represent them as F i (i = 1, 2,..., n);

[0051] During the matching process, the field for matching and the correlation coefficient of the current matching data are represented as R, and R is calculated through the following formula 1:

[0052]

[0053] S4.5: If R >= μ, it indicates that the current matching data is relevant to the field, and record a successful match; otherwise, record a failed match.

[0054] S4.6: If the current matching data is the last intellectual property data, then continue with S5; otherwise, return to S4.2.

[0055] In a certain embodiment, in S5, the ranking order of each enterprise is from largest to smallest according to each innovation score - that is, it represents the innovation ability ranking list of each enterprise in the field.

[0056] Illustrate with examples:

[0057] Step (1): Prepare a number of intellectual property data. The types of intellectual property data can include invention patents, design patents, utility model patents, software copyrights, etc. The intellectual property data can be obtained by purchasing a database or interface service from enterprises such as Tianyancha and Qichacha that provide enterprise industrial and commercial data retrieval services. The fields of the intellectual property data are shown in Table 1 below:

[0058] Field Name Description Type id Unique Identifier string title Name string brief Abstract Information string type Type, including invention patents, design patents, utility model patents, and software copyrights string status Status, including authorized and unauthorized string apply_date Application Time date authorize_date Authorization Time date ename Name of the Patentee string score Score float

[0059] Table 1: Fields of intellectual property data

[0060] Among them, the field data of title, brief, type, status, apply_date, and authorize_date can all be obtained from industrial and commercial data, and the field data of score is obtained according to Step 2.

[0061] Step (2): Define the scoring rules for intellectual property. The scoring rules can be defined according to the intellectual property type and status of the intellectual property data. Use t to represent the intellectual property type, s to represent the intellectual property status, and S(t, s) to represent the score of the intellectual property. The examples are shown in Table 2 below:

[0062]

[0063] Table 2: Scoring rules

[0064] According to the above rules, the scores of all intellectual property data can be calculated, and the score data is updated to the score field of the intellectual property data. The example data is as Figure 2 shown.

[0065] Step (III): Select a specific field, define relevant keywords and their weights in the specific field. The keywords are represented as Ki (i = 1, 2, …, n), and the corresponding weights are represented as Wi (i = 1, 2, …, n), and 0 < Wi <= 1. Keywords refer to specific words that are highly relevant to this field and are likely to appear in intellectual property descriptions. Keywords can be obtained based on expert experience or Internet knowledge. The weight represents the degree of association of the keyword with this field. The higher the degree of association, the greater the weight.

[0066] Taking the field of "Artificial Intelligence - Autonomous Driving" as an example, its keywords and weights are as follows:

[0067] Keywords Weight Automobile 0.5 Artificial Intelligence 0.5 Autopilot 0.5 Driverless 0.5 Automatic Control 0.2 Automatic Parking 0.2 Intelligent Network Connection 0.2 Driving Task 0.2 Autonomous Navigation 0.2

[0068] Table III: Keywords and Weights

[0069] Step (IV): Match the intellectual property related to this field through keyword matching. The matching method is as follows:

[0070] (A) From the abstract information of each intellectual property data, search for the number of times the keyword Ki (i = 1, 2, …, n) appears one by one, which is represented as Fi (i = 1, 2, …, n).

[0071] (B) The relevance is represented as R, and the calculation formula for its value is:

[0072]

[0073] (C) Set a relevance threshold μ (μ >= 0). When R >= μ, it means that this intellectual property is relevant to the current field and the matching is successful; otherwise, the matching fails.

[0074] (D) Search through all the knowledge product data according to steps (A), (B), and (C), and all the intellectual properties related to this field can be obtained.

[0075] Taking the field of "Artificial Intelligence - Autonomous Driving" as an example, the threshold μ is set to 1, and the matched intellectual property data is as Figure 3 shown.

[0076] Step (V): Calculate the innovation evaluation score of each enterprise in this field: For all the intellectual properties related to this field found in step (IV), sum up the scores of the intellectual properties belonging to the same enterprise, and the score of the enterprise in this field can be obtained. It can be sorted from high to low according to the scores, which is the innovation ability ranking list of enterprises in this field. Taking the field of "Artificial Intelligence - Autonomous Driving" as an example, the effect Figure 4 is shown.

[0077] In summary, through the above unique technical solution, the present disclosure retrieves the intellectual property information such as patents and software copyrights of enterprises, uses keyword matching to realize the association among enterprises, intellectual products, and fields, and then proposes a calculation method for quantitative evaluation, so as to realize the quantitative evaluation of the innovation ability of enterprises in this field. This method can realize the evaluation of the innovation ability of a large number of enterprises in a large number of fields, and provide support for the analysis of industrial chains or industrial clusters.

[0078] The above are only the preferred embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An innovative evaluation calculation method for enterprises in the field, characterized in that, It includes the following steps: S1 Obtain intellectual property data: Prepare several pieces of intellectual property data and sort them, and define each field of the intellectual property data; The fields of the intellectual property data include unique identifier id, name title, abstract information brief, type type, status status, application date apply_date, authorization date authorize_date, name of the affiliated enterprise ename, and score score; S2 Define scoring rules and enrich scores: S2.1 Define scoring rules: Define scoring rules according to the type type and status status; In the scoring rules, use t to represent the type type of the intellectual property data, use s to represent the status type of the intellectual property data, and use S(t, s) to represent the score score of the intellectual property data; S2.2: According to the scoring rules obtained in S2.1, calculate the scores of all the intellectual property data obtained in S1, and update the scores to the score fields corresponding to the intellectual property data; S3 Set keywords and weights: Select a field and define the keywords and weights for the field. The keywords are represented as K i , and the corresponding weights are represented as W i and 0 < W i <= 1, 1 <= i <= n; where the keyword refers to a specific word that is highly relevant to the field and likely to appear in the intellectual property description; the weight represents the degree of association between the keyword and the field, and the higher the degree of association, the greater the weight S4 Match by keywords: Among all the intellectual property data, match and select the intellectual property data related to the field through each keyword; S5 Calculate the innovation scores of enterprises in the selected field: Aggregate all the intellectual property data related to the field found in S4. For each enterprise, accumulate the scores score of all the intellectual property data belonging to the same enterprise, so as to obtain the innovation scores of each enterprise in the field. Finally, rank each enterprise according to each innovation score.

2. The innovative evaluation calculation method according to claim 1, characterized in that, In S1, the categories of the type type include invention patents, design patents, utility model patents, and software copyrights.

3. The innovative evaluation calculation method according to claim 1, characterized in that, In S1, the categories of the status status include authorized and unauthorized.

4. The innovative evaluation calculation method according to claim 1, characterized in that, In S1, the score score is set to NULL or 0 or an empty value.

5. The innovative evaluation calculation method according to claim 1, characterized in that, In S1, it can be obtained by purchasing database or interface services from Tianyancha or Qichacha to complete the preparation of the intellectual property data.

6. The innovative evaluation calculation method according to claim 1, characterized in that In S3, the acquisition method of the keywords includes obtaining them according to expert experience or Internet knowledge.

7. The innovative evaluation calculation method according to claim 1, characterized in that, S4 specifically includes the following steps: S4.1: Set a correlation threshold μ, μ >= 0; S4.2: Select one from all the intellectual property data in sequence and define it as the current matching data; S4.3: Search for the occurrences of each of the keywords K one by one from the summary information brief of the current matching data i (i = 1, 2, …, n) respectively, and represent them as F i (i = 1, 2, …, n); S4.4: During the matching process, the correlation coefficient between the field being matched and the current matching data is represented as R, and R is calculated through the following formula 1: (Formula 1); S4.5: If R >= μ, it means that the current matching data is relevant to the field, and record a successful match; otherwise, record a failed match; S4.6: If the current matching data is the last piece of intellectual property data, then continue with S5; otherwise, return to S4.

2.

8. The innovative evaluation calculation method according to claim 1, characterized in that, In S5, the ranking order of each enterprise is from largest to smallest according to each innovation score - that is, it represents the innovation ability ranking list of each enterprise in the field.

Images