Patent value analysis method and equipment

Through natural language processing technology, the claims in patent documents are analyzed, the number of characters and features is identified, and the semantic recognition is carried out, which solves the problems of low efficiency and poor accuracy of manual analysis, and achieves efficient and accurate patent value evaluation.

CN119005206AInactive Publication Date: 2024-11-22CHINA AUTOMOBILE INTELLECTUAL PROPERTY (GUANGZHOU) CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411481100.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-23
Publication Date
2024-11-22
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing patent value analysis relies on manual methods, is inefficient and has poor accuracy, and lacks combination with natural language processing technology.

Method used

By using natural language processing technology, the patent value is determined by obtaining patent identification, analyzing the number of characters and features in the claims, semantic recognition, correcting the score, and calculating the target score of the patent.

Benefits of technology

It improves the efficiency and accuracy of patent value analysis, and is more accurate than traditional manual analysis methods.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119005206A_ABST
    Figure CN119005206A_ABST
Patent Text Reader

Abstract

The invention discloses a patent value analysis method and device, and relates to the technical field of computers, and the method comprises the steps: obtaining to-be-analyzed claims of a to-be-analyzed patent; if the claims to be analyzed are independent claims, the number of first characters in the claims to be analyzed is recognized, the number of first sentence fragments in the claims to be analyzed is recognized according to preset punctuation marks, and the number of first features of the claims to be analyzed is determined according to the number of the first sentence fragments; determining a first score of the to-be-analyzed claim according to the number of the first characters and the number of the first features of the to-be-analyzed claim; performing semantic recognition on the to-be-analyzed claims to obtain a second feature number of the to-be-analyzed claims; and according to the size relationship between the number of the first features and the number of the second features of the to-be-analyzed claims, the first score is corrected to obtain a second score, and the second score is used for determining the value of the to-be-analyzed patent. The method can improve the analysis accuracy.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and device for analyzing patent value. Background Art

[0002] At present, the value of patents is generally analyzed manually. This analysis method relies on the analyst's experience and knowledge reserves and is highly subjective. In addition, during the manual analysis process, analysts need to spend a long time reading and understanding the technical solutions.

[0003] Therefore, the current analysis scheme of patent value is not only inefficient but also has poor accuracy. Summary of the invention

[0004] The present invention provides a patent value analysis method and device, which can not only improve the efficiency of patent value analysis, but also improve the accuracy of patent value analysis.

[0005] In order to achieve the above object, the present invention adopts the following technical scheme: In a first aspect, the present invention provides a method for analyzing patent value, the method comprising: Obtain patent identification of the patent to be analyzed; According to the patent identifier, obtaining the patent document of the patent to be analyzed, wherein the patent document at least includes claims, and the claims include multiple claims to be analyzed; Determine whether the claim to be analyzed is an independent claim, and obtain a first determination result; If the first judgment result indicates that the claim to be analyzed is an independent claim, identifying the first number of characters in the claim to be analyzed, and identifying the first number of sentence fragments in the claim to be analyzed according to preset punctuation marks, and determining the first number of features of the claim to be analyzed according to the first number of sentence fragments; Determining a first score of the claim to be analyzed according to the number of first characters and the number of first features of the claim to be analyzed; Performing semantic recognition on the claim to be analyzed to obtain a semantic recognition result, wherein the semantic recognition result includes the number of the second features of the claim to be analyzed; According to the relationship between the number of the first feature and the number of the second feature of the claim to be analyzed, the first score is modified to obtain a second score; Determine a target score of the patent to be analyzed based on the second score; the target score is the second score of a single claim to be analyzed or the average of the second scores of multiple claims to be analyzed; The value of the patent to be analyzed is determined based on the target score.

[0006] Optionally, the value of the patent to be analyzed includes a first value, and determining the value of the patent to be analyzed according to the target score includes:

[0007] in, For the first value, is the R&D cost of the patent to be analyzed, is the estimated profit of the patent to be analyzed, Score the objectives of the patents to be analyzed.

[0008] Optionally, the value of the patent to be analyzed includes a second value, and determining the value of the patent to be analyzed according to the target score includes:

[0009] in, is the second value of the patent to be analyzed, is the benchmark value, For reference rating, The value of the product or process to be protected by the patent to be analyzed, is the average value of various related products available on the market, Score the objectives of the patents to be analyzed.

[0010] Optionally, the value of the patent to be analyzed includes a third value, and determining the value of the patent to be analyzed according to the target score includes:

[0011] in, is the third value of the patent to be analyzed, To score the target of the patent to be analyzed, is the sales revenue of the patent to be analyzed, is the patent contribution rate in the tth time period, is the market supply and demand coefficient in the tth time period, is the remaining protection period of the patent to be analyzed, is the discount rate for the patent to be analyzed.

[0012] Optionally, the value of the patent to be analyzed includes a fourth value, and determining the value of the patent to be analyzed according to the target score includes:

[0013] in, is the fourth value of the patent to be analyzed, To score the target of the patent to be analyzed, is the sales revenue of the patent to be analyzed, is the patent contribution rate in the tth time period, is the market supply and demand coefficient in the tth time period, is the remaining protection period of the patent to be analyzed, is the discount rate of the patent to be analyzed, To compare the company's gross profit margin, is the gross profit margin of the company that owns the patent to be analyzed.

[0014] Optionally, the method further includes: If the first judgment result indicates that the claim to be analyzed is not an independent claim, obtaining a reference relationship between the claim to be analyzed and the independent claim, determining the additional content of the claim to be analyzed relative to the independent claim according to the reference relationship, identifying the number of additional characters in the additional content, and identifying the number of additional sentence fragments in the additional content according to preset punctuation marks, and determining the number of additional features of the claim to be analyzed according to the number of additional sentence fragments; Obtaining the number of features and characters in the independent claim; The sum of the number of features in the independent claim and the number of additional features of the claim to be analyzed is taken as the first number of features of the claim to be analyzed, and the sum of the number of characters in the independent claim and the number of additional characters of the claim to be analyzed is taken as the first number of characters of the claim to be analyzed.

[0015] Optionally, the first score is modified according to the relationship between the number of the first features and the number of the second features of the claim to be analyzed, including: If the first number of features is greater than the second number of features, a first correction coefficient is determined according to a first difference between the first number of features and the second number of features and a first preset mapping relationship, wherein the first preset mapping relationship is a mapping relationship between a first reference difference and a first reference correction coefficient, and the first score is corrected according to the first correction coefficient; or If the first number of features is less than the second number of features, a second correction coefficient is determined based on a second difference between the first number of features and the second number of features and a second preset mapping relationship, where the second preset mapping relationship is a mapping relationship between a second reference difference and a second reference correction coefficient, and the first score is corrected according to the second correction coefficient.

[0016] Optionally, determining the first number of features of the claim to be analyzed according to the first number of sentence fragments includes: Obtaining the number of characters in each sentence fragment in the claim to be analyzed; Determine a third correction coefficient corresponding to each sentence fragment according to the number of characters in each sentence fragment and a third preset mapping relationship, wherein the third preset mapping relationship is a mapping relationship between the number of reference characters and the third reference correction coefficient; Correcting each sentence fragment using the third correction coefficient of each sentence fragment; The sum of the corrected values ​​of each sentence fragment is taken as the first feature number of the claim to be analyzed.

[0017] Optionally, the method further includes: Obtaining the classification number of the patent to be analyzed; Compare the features in the claim to be analyzed with the feature library corresponding to the classification number of the patent to be analyzed to obtain the hit rate of the features in the claim to be analyzed in the feature library corresponding to the classification number of the patent to be analyzed; Determine a fourth correction coefficient corresponding to the hit rate according to a fourth preset mapping relationship, wherein the fourth preset mapping relationship is a mapping relationship between a reference hit rate and a fourth reference correction coefficient; Correcting the second score according to the fourth correction coefficient to obtain a third score; According to the second score, the target score of the patent to be analyzed is determined as: Based on the third score obtained by correcting the second score, the target score of the patent to be analyzed is determined, and the target score is the third score of a single claim to be analyzed or the average of the third scores of multiple claims to be analyzed.

[0018] In a second aspect, the present invention provides a computing device, including a memory and a processor; One or more computer programs are stored in the memory, and the one or more computer programs include instructions; when the instructions are executed by the processor, the computing device executes the method as described in any one of the first aspects.

[0019] In a third aspect, the present invention provides a computer-readable storage medium for storing a computer program for executing the method as described in any one of the first aspects.

[0020] It can be seen from the above technical solution that the present invention has at least the following beneficial effects: In the present invention, a patent identifier of a patent to be analyzed is first obtained, for example, it may be a patent application number or a patent publication number, and then the patent document of the patent to be analyzed is searched based on the patent identifier, the patent document at least includes a claim, and the claim includes multiple claims to be analyzed. If the claim to be analyzed is an independent claim, the number of first characters in the claim to be analyzed is identified, and the number of first sentence fragments in the claim to be analyzed is identified according to preset punctuation marks. According to the number of first sentence fragments, the number of first features in the claim to be analyzed is determined, and then according to the number of first characters and the number of first features of the claim to be analyzed, the first score of the claim to be analyzed is determined, and then the claim to be analyzed is semantically recognized to obtain a semantic recognition result, and the semantic recognition result includes the number of second features of the claim to be analyzed. Finally, based on the size relationship between the number of first features and the number of second features of the claim to be analyzed, the first score is corrected to obtain a second score, and the target score of the patent to be analyzed is determined according to the second score; the target score is the second score of a single claim to be analyzed or the average of the second scores of multiple claims to be analyzed, and the value of the patent to be analyzed is determined according to the target score. In this method, the patent document of the patent to be analyzed is processed through the relevant technology of natural language processing, and then the revised score of the claim to be analyzed in the patent document is obtained, and the target score of the patent to be analyzed is determined based on the revised score. Since the second score is more accurate, the determined target score is also more accurate. The value of the patent to be analyzed is evaluated based on the more accurate target score, and the accuracy is higher. It can be seen that compared with the traditional manual analysis method, the scheme of the present invention not only improves the analysis efficiency, but also improves the accuracy of the analysis.

[0021] It should be understood that the description of technical features, technical solutions, beneficial effects or similar language in the present invention does not imply that all features and advantages can be realized in any single embodiment. On the contrary, it is understood that the description of features or beneficial effects means that specific technical features, technical solutions or beneficial effects are included in at least one embodiment. Therefore, the description of technical features, technical solutions or beneficial effects in this specification does not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions and beneficial effects described in the present embodiment can also be combined in any appropriate manner. Those skilled in the art will understand that the embodiment can be realized without one or more specific technical features, technical solutions or beneficial effects of a specific embodiment. In other embodiments, additional technical features and beneficial effects can also be identified in specific embodiments that do not embody all embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A flow chart of a method for analyzing patent value provided by an embodiment of the present invention; Figure 2 A schematic diagram of an analysis device of patent value provided by an embodiment of the present invention; Figure 3 A schematic diagram of a computing device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The terms "first", "second", "third", etc. in the specification of the present invention and the accompanying drawings are used to distinguish different objects rather than to limit a specific order.

[0024] In the embodiments of the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0025] In order to make the description of the following embodiments clear and concise, a brief introduction to the related technology is first given: Natural language processing is a discipline that uses computer technology to analyze, understand and process natural language. That is, it uses computers as a powerful tool for language research, conducts quantitative research on language information with the support of computers, and provides language descriptions that can be used by both humans and computers. Natural language processing mainly includes two core tasks: Natural Language Understanding (NLU) and Natural Language Generation (NLG). Among them, natural language understanding includes text parsing and semantic analysis. Text parsing refers to the pre-processing of input text such as word segmentation, part-of-speech tagging, and syntactic analysis to understand the basic structure and composition of the text. Semantic analysis refers to a deep semantic understanding of the text based on grammatical analysis, including identifying the polysemy and ambiguity of vocabulary, and understanding the theme, emotion, intention and other information of the text.

[0026] At present, the process of analyzing the value of patents mainly relies on manual analysis, which is not well combined with natural language processing technology. Manual analysis is not only inefficient but also has poor accuracy.

[0027] In view of this, an embodiment of the present invention provides a method for analyzing the value of a patent, which can be executed by a processing device, which can be a terminal or a server. Terminals include but are not limited to smart phones, tablet computers, laptops, personal digital assistants, or smart wearable devices. The server can be a cloud server, such as a central server in a central cloud computing cluster, or an edge server in an edge cloud computing cluster. Of course, the server can also be a server in a local data center. A local data center refers to a data center that is directly controlled by the user.

[0028] In this method, the patent document of the patent to be analyzed is processed through relevant natural language processing technologies, and then the revised score of the claims to be analyzed in the patent document is obtained. Compared with the traditional manual analysis method, not only the analysis efficiency is improved, but also the accuracy of the analysis is improved.

[0029] In order to make the technical solution of the present invention clearer and easier to understand, the technical solution of the present invention is introduced below in conjunction with the accompanying drawings. Figure 1 As shown in FIG. 1 , the figure is a flow chart of a method for analyzing patent value provided by an embodiment of the present invention, the method comprising: S101. The processing device obtains the patent identification of the patent to be analyzed.

[0030] In some embodiments, the processing device may provide a user with an interface supporting human-computer interaction, on which the user may input the patent identifier of the patent to be analyzed, and the processing device may obtain the patent identifier of the patent to be analyzed input by the user. The patent identifier may be the patent application number, publication number, authorization number, etc., and the patent identifier is used to uniquely mark the patent to be analyzed.

[0031] It should be noted that the present invention does not specifically limit the manner in which the processing device obtains the patent identification of the patent to be analyzed.

[0032] S102: The processing device obtains the patent document of the patent to be analyzed according to the patent identification.

[0033] The patent document at least includes a claim set, which includes multiple claims to be analyzed.

[0034] After the processing device obtains the patent identifier, it can search for the patent document corresponding to the patent identifier in the public database, wherein the public database includes all patent documents that have been in the public state.

[0035] It should be noted that the acquisition of patent documents by the processing device based on patent identification is only an example. In other embodiments, the user may also directly provide the patent documents of the patent to be analyzed to the processing device instead of providing patent identification.

[0036] S103. The processing device determines whether the claim to be analyzed is an independent claim.

[0037] If the first judgment result is obtained that the claim to be analyzed is an independent claim, S104 is executed; if the first judgment result is obtained that the claim to be analyzed is not an independent claim, S106 is executed.

[0038] After the processing device obtains the patent document, it can know the claims of the patent to be analyzed, and then know the claims to be analyzed. Before analyzing the claims to be analyzed, the processing device needs to determine whether the claims to be analyzed are independent claims or dependent claims, so as to analyze each claim more accurately.

[0039] In some embodiments, the processing device can determine whether the claim to be analyzed is an independent claim by searching for reference words such as "according to the claim", "according to the claim", "based on the claim" in the claim to be analyzed. If the claim to be analyzed includes the above-mentioned reference words, it is considered not to be an independent claim. If it does not include the above-mentioned reference words, it is considered to be an independent claim.

[0040] Furthermore, the processing device can further determine the position of the above-mentioned quoted words in the claim to be analyzed. If the above-mentioned quoted words appear before "herein, it is characterized by" in the claim to be analyzed, it is considered not to be an independent claim. If it appears after "herein, it is characterized by" in the claim to be analyzed, it is considered to be an independent claim.

[0041] It should be noted that the processing device can complete the retrieval of the above-mentioned reference words and the determination of the position of the reference words in the text based on the relevant technology of natural semantic processing. "Its characteristics are" can also be replaced by similar meanings, for example, "Its characteristics are".

[0042] S104: The processing device identifies the number of first characters in the claim to be analyzed, and identifies the number of first sentence fragments in the claim to be analyzed according to preset punctuation marks.

[0043] The first character number refers to the number of characters in the claim to be analyzed. The processing device can identify the first character number in the claim to be analyzed in a variety of ways, such as by using a regular expression to determine the first character number in the claim to be analyzed.

[0044] The preset punctuation marks may include a period, a comma, a semicolon, a colon, etc. The processing device may segment the claim to be analyzed according to the preset punctuation marks, thereby obtaining a plurality of sentence fragments, thereby identifying the first number of sentence fragments in the claim to be analyzed. The first number of sentence fragments refers to the number of sentence fragments obtained after segmenting the claim to be analyzed.

[0045] In some embodiments, the processing device may also pre-process multiple sentence fragments and delete fragments that only include preset words. For example, the preset word may be "wherein". For example, after the processing device processes the claim to be analyzed, the obtained sentence fragments are "obtain H", "obtain B according to H", "wherein" and "B is B1". It can be seen that the sentence fragment "wherein" only includes preset words, so the processing device may delete the sentence fragment, and then determine the number of the first sentence fragments after deleting the sentence fragment.

[0046] S105. The processing device determines the number of first features of the claim to be analyzed according to the number of first sentence fragments.

[0047] The first feature number refers to the number of technical features included in the claim to be analyzed. In some embodiments, the processing device can directly use the first sentence fragment number as the first feature number of the claim to be analyzed.

[0048] In other embodiments, the number of characters (number of words) in each sentence fragment in the claim to be analyzed can be further obtained, and then the third correction coefficient corresponding to each sentence fragment can be determined based on the number of characters in each sentence fragment and a third preset mapping relationship. The third preset mapping relationship is a mapping relationship between the reference number of characters and the third reference correction coefficient. After obtaining the third correction coefficient of each sentence fragment, each sentence fragment is corrected using the third correction coefficient of each sentence fragment, and then the sum of the corrected values ​​of each sentence fragment is used as the first characteristic number of the claim to be analyzed.

[0049] Among them, the third preset mapping relationship can be obtained by pre-fitting, for example, the third preset mapping relationship is a linear function relationship, and the third preset mapping relationship is: y=0.1x-0.2. Among them, y is the third correction coefficient of the sentence fragment, and x is the number of characters in the sentence fragment. Taking sentence fragment 1 "obtain B according to H" and sentence fragment 2 "input H into the big data model to obtain C" as an example, the number of characters in sentence fragment 1 is x=6. Through the above third preset mapping relationship, y=0.4 can be obtained, and the number of characters in sentence fragment 2 is x=13. Through the above third preset mapping relationship, y=1.1 can be obtained. For sentence fragment 1, its third correction coefficient is 0.4, therefore, sentence fragment 1 is equivalent to 0.4 sentences, that is, the corrected value of sentence fragment 1 is 0.4; for sentence fragment 2, its third correction coefficient is 1.1, therefore, sentence fragment 2 is equivalent to 1.1 sentences, that is, the corrected value of sentence fragment 2 is 1.1. The sum of the corrected values ​​of sentence fragment 1 and sentence fragment 2 is 1.5. If the claim to be analyzed only includes the above sentence fragment 1 and sentence fragment 2, then the number of the first features of the claim to be analyzed is 1.5.

[0050] In the embodiment of the present invention, the number of features in the claim is associated with the sentence fragment in the claim, and in order to weigh the sentence fragments of different lengths, the number of characters included in the sentence fragment is also considered, so that a more accurate number of features can be identified. The more features there are, the smaller the protection scope and the smaller the value of the patent. The fewer features there are, the larger the protection scope and the greater the value of the patent.

[0051] It should be noted that the embodiment of the present invention is a process of analyzing the value of patents that have been granted patent rights.

[0052] S106. The processing device obtains a reference relationship between the claim to be analyzed and the independent claim.

[0053] Continuing with the above embodiment, when the processing device determines whether the claim to be analyzed is an independent claim, it needs to determine whether the claim to be analyzed includes a reference word, and in this step, the processing device also needs to determine the reference number. The reference word and the reference number together reflect the reference relationship between the dependent claim and the independent claim. The following is an example:

[0054] The processing device may first search for the reference words in claim 2, and then search for the reference number after the reference words. Taking the claim to be analyzed as the above-mentioned claim 2 as an example, the processing device may first search for "as claimed", and then search for "1" after "as claimed", wherein "as claimed" is the reference word and "1" is the reference number. The processing device may then obtain the reference relationship of the claim to be analyzed as follows: claim 2 references independent claim 1.

[0055] Taking claim 3 to be analyzed as an example, the processing device can first retrieve "as claimed", and then retrieve "2" after "as claimed", and then the processing device continues to search claim 2. The retrieval process is similar to the above example. In this case, the processing device can obtain the reference relationship of the claim to be analyzed: claim 3 references dependent claim 2, and dependent claim 2 references independent claim 1.

[0056] S107. The processing device determines, according to the reference relationship, the additional content of the claim to be analyzed relative to the independent claim.

[0057] After the processing device determines the above-mentioned reference relationship, it can determine the additional content of the claim to be analyzed relative to the independent claim, wherein, if the reference relationship of the claim to be analyzed is a single layer, the additional content is the content after "herein, it is characterized by" in the claim to be analyzed; if the reference relationship of the claim to be analyzed includes multiple layers, the additional content is the content after "herein, it is characterized by" in the claim to be analyzed and the dependent claims cited in sequence by the claim to be analyzed.

[0058] Continuing with the above example, for claim 2, the additional content of claim 2 is "the said S1 includes S11; S12", and for claim 3, the additional content of claim 3 is "the said S1 includes S11; S12", and "the said S2 includes S21; S22". It should be noted that the present invention does not specifically limit the way in which the processing device determines the position of "characterized by" in the claim to be analyzed. For example, it can be performed by converting the text into a vector for similarity matching, or directly matching the "characterized by" with the characters in the claim to be analyzed, thereby determining the position of "characterized by" in the claim to be analyzed.

[0059] S108: The processing device identifies the number of additional characters in the additional content, and identifies the number of additional sentence fragments in the additional content according to preset punctuation marks.

[0060] The number of additional characters refers to the number of characters in the additional content, and the number of additional sentence fragments refers to the number of sentence fragments in the additional content. In the embodiment of the present invention, the processing device identifies the number of additional characters in the additional content in a similar manner to the recognition process in the above embodiment, and the processing device identifies the number of additional sentence fragments in the additional content in a similar manner to the recognition process in the above embodiment, which will not be repeated here.

[0061] S109. The processing device determines the number of additional features of the claim to be analyzed according to the number of additional sentence fragments.

[0062] The number of additional features refers to the number of technical features in the additional content.

[0063] In some embodiments, the processing device may directly use the number of additional sentence fragments as the number of additional features of the claim to be analyzed. In other embodiments, the processing device may further obtain the number of characters of each additional sentence fragment in the additional content, and then determine the correction coefficient of each additional sentence fragment based on the number of characters of each additional sentence fragment, and then correct the additional sentence fragment, and then use the sum of the corrected values ​​of each additional sentence fragment as the number of additional features of the claim to be analyzed. It should be noted that the above processing process can be referred to S105, which will not be repeated here.

[0064] S110. The processing device obtains the number of features and the number of characters in the independent claim.

[0065] If the processing device has analyzed the independent claim, the number of features and the number of characters in the independent claim can be directly obtained. If the processing device has not analyzed the independent claim but directly analyzes the dependent claim, the number of features and the number of characters in the independent claim can be obtained according to S104.

[0066] S111. The processing device uses the sum of the number of features in the independent claim and the number of additional features of the claim to be analyzed as the first number of features of the claim to be analyzed, and uses the sum of the number of characters in the independent claim and the number of additional characters of the claim to be analyzed as the first number of characters of the claim to be analyzed.

[0067] After the processing device obtains the number of features and the number of characters in the independent claim, it can use the sum of the number of features in the independent claim and the number of additional features in the claim to be analyzed as the first number of features of the claim to be analyzed, and use the sum of the number of characters in the independent claim and the number of additional characters of the claim to be analyzed as the first number of characters of the claim to be analyzed.

[0068] S112. The processing device determines a first score of the claim to be analyzed according to the first character number and the first feature number of the claim to be analyzed.

[0069] The first number of characters refers to the number of characters in the claim to be analyzed. After the processing device obtains the first number of characters and the first number of features in the claim to be analyzed, it can determine the first score of the claim to be analyzed. In some examples, the functional relationship between the number of characters, the number of features and the score can be pre-fitted, and then the first score corresponding to the above-mentioned first number of characters and the first number of features can be determined based on the pre-fitted functional relationship. Among them, the more the first number of characters and the more the first number of features, the lower the first score, and the fewer the first number of characters and the fewer the first number of features, the higher the first score.

[0070] S113. The processing device performs semantic recognition on the claims to be analyzed and obtains semantic recognition results.

[0071] The semantic recognition result includes the number of the second features of the claim to be analyzed. In some examples, the claim to be analyzed may have the following situations:

[0072] In the claim to be analyzed, features 3 and 4 together constitute the subordinates of feature 2. It is obviously unreasonable to count features 2, 3 and 4 as 3 features. In view of this situation, the processing device can perform semantic recognition on the claim to be analyzed and obtain a semantic recognition result, that is, the number of features included in the claim to be analyzed.

[0073] In some embodiments, a semantic recognition model can be pre-trained, the input of the semantic recognition model is the claim to be analyzed, and the output is the number of features. In other embodiments, the processing device may also first vectorize each sentence fragment of the claim to be analyzed, and then calculate the similarity between each sentence fragment, determine the number of sentence fragment pairs whose similarity is higher than the preset similarity threshold, and subtract 2 from the first number of features for each pair of similar sentence fragments. If there are no similar sentence fragments, add 0.1 multiplied by the number of sentence fragments to the first number of features. Assume that the first number of features is 10, the number of sentence fragments is 15, and there are 2 pairs of similar sentence fragments, then the second number of features is 6. If there are no similar sentence fragments, then the second number of features is 11.5.

[0074] It should be noted that the above specific values ​​are only for illustrative purposes.

[0075] S114. The processing device modifies the first score according to the relationship between the number of the first feature and the number of the second feature of the claim to be analyzed to obtain a second score.

[0076] The size relationship between the first feature number and the second feature number of the claim to be analyzed includes that the first feature number is greater than the second feature number, the first feature number is equal to the second feature number, and the first feature number is less than the second feature number.

[0077] If the first number of features is greater than the second number of features, the processing device determines a first correction coefficient based on a first difference between the first number of features and the second number of features and a first preset mapping relationship, where the first preset mapping relationship is a mapping relationship between a first reference difference and a first reference correction coefficient, and the first score is corrected according to the first correction coefficient.

[0078] Among them, the first preset mapping relationship can be obtained by pre-fitting. Exemplarily, the first correction coefficient is between 1-2. The larger the first difference is, the closer the first correction coefficient is to 2, and the smaller the first difference is, the closer the first correction coefficient is to 1.

[0079] If the number of first features is less than the number of second features, the second correction coefficient is determined based on the second difference between the first and second feature numbers and a second preset mapping relationship, the second preset mapping relationship being a mapping relationship between the second reference difference and the second reference correction coefficient, and the first score is corrected according to the second correction coefficient.

[0080] Among them, the second preset mapping relationship can be obtained by pre-fitting. Exemplarily, the second correction coefficient is between 0-1. The larger the second difference is, the closer the second correction coefficient is to 0, and the smaller the second difference is, the closer the second correction coefficient is to 1.

[0081] When the first feature number is equal to the second feature number, the processing device does not perform correction, or the correction coefficient is 1.

[0082] The processing device may correct the first score by multiplying the first score by the first correction coefficient or the second correction coefficient to obtain the second score.

[0083] In the embodiment of the present invention, the processing device further identifies the number of features in the claim to be analyzed by means of semantic recognition, thereby further reducing the impact of the error in the number of features, thereby further improving the accuracy of the analysis.

[0084] In some embodiments, the processing device may obtain the second score of each claim according to the above embodiments, and then display the second score of each claim to the user through a human-computer interaction interface.

[0085] In some embodiments, the processing device may also obtain the classification number of the patent to be analyzed, and then compare the features in the claim to be analyzed with the feature library corresponding to the classification number to obtain the hit rate of the features in the claim to be analyzed in the feature library, and then determine the fourth correction coefficient corresponding to the hit rate based on the fourth preset mapping relationship, the fourth preset mapping relationship is the mapping relationship between the reference hit rate and the fourth reference correction coefficient, wherein the fourth preset mapping relationship can be pre-fitted. After obtaining the fourth correction coefficient, the processing device can correct the second score again to obtain a third score.

[0086] In an embodiment of the present invention, after completing the second score of the claim to be analyzed, the processing device continues to analyze the novelty of the claim from the perspective of stability, and then obtains a fourth correction coefficient. The fourth correction coefficient is used to correct the aforementioned second score, thereby further improving the analysis accuracy of the claim to be analyzed.

[0087] In some embodiments, the processing device may also obtain the examination status of the patent to be analyzed based on the patent identification of the patent to be analyzed, obtain the number of invalidation requests for the patent to be analyzed based on the examination status, and further revise the second score or the third score based on the number of invalidation requests. Furthermore, the processing device may also obtain the number of evidences cited in each invalidation request process. The more evidences cited, the more points will be added based on the second score or the third score.

[0088] In an embodiment of the present invention, the more times the claim to be analyzed is requested to be declared invalid, and the more evidence is cited each time the invalidation is requested, the higher the stability and the higher the value of the patent to be analyzed. Therefore, the second score or the third score is further corrected to improve the accuracy of the analysis.

[0089] It should be noted that, in this embodiment, the claims to be analyzed refer to the claims in the patent to be analyzed that remain valid after the invalidation request is made.

[0090] S115. The processing device determines a target score for the patent to be analyzed based on the second score.

[0091] In the embodiment of the present invention, the processing device may also determine the target score of the patent to be analyzed based on the second score. Exemplarily, after obtaining the score of each claim (e.g., the second score), the processing device may use the score of the independent claim as the target score of the patent to be analyzed. If the patent to be analyzed includes multiple independent claims, the average score of the multiple independent claims may be used as the target score of the patent to be analyzed.

[0092] The processing device may also use the score of the independent claim as the basic score and the score of the dependent claim as the additional score, and then obtain the target score of the patent to be analyzed based on the basic score and the additional score. In some examples, the processing device may convert the additional score into an impact factor, and then use the impact factor to modify the basic score to obtain the target score. Specifically, the functional relationship between the additional score and the impact factor may be pre-fitted, and then the impact factor corresponding to the additional score may be determined based on the fitted functional relationship.

[0093] It should be noted that in order to further improve the accuracy of the analysis, the second score can be replaced by a third score. Specifically, the processing device can determine the target score of the patent to be analyzed based on the third score obtained by correcting the second score, and the target score is the third score of a single claim to be analyzed or the average of the third scores of multiple claims to be analyzed.

[0094] S116. The processing device determines the value of the patent to be analyzed based on the target score.

[0095] After the processing device obtains the target score, it can further analyze the value of the patent to be analyzed from multiple dimensions. The following are introduced respectively.

[0096] In some examples, the processing device may determine the first value of the patent to be analyzed by the following formula:

[0097] in, For the first value, is the R&D cost of the patent to be analyzed, is the estimated profit of the patent to be analyzed, Score the target of the patent to be analyzed. In the case of multiple patents to be analyzed, Can be replaced by the following formula:

[0098] in, Score the target of the i-th patent to be analyzed among multiple patents to be analyzed, is the patent portfolio adjustment factor, is the number of multiple patents to be analyzed. Can be based on Determine, for example, The bigger, The bigger.

[0099] In some examples, the processing device may determine the second value of the patent to be analyzed by the following formula:

[0100] in, is the second value of the patent to be analyzed, is the benchmark value, is a reference score, which may be the average score of all patents in the technical field (determined by classification number, for example) to which the patent to be analyzed belongs; The value of the product or process to be protected by the patent to be analyzed, The average value of multiple related products available on the market.

[0101] In other examples, the processing device may determine the third value of the patent to be analyzed by the following formula:

[0102] in, is the third value of the patent to be analyzed, To score the target of the patent to be analyzed, is the sales revenue of the patent to be analyzed, is the patent contribution rate in the tth time period, is the market supply and demand coefficient in the tth time period, is the remaining protection period of the patent to be analyzed, is the discount rate for the patent to be analyzed.

[0103] In other examples, the processing device may determine the fourth value of the patent to be analyzed by the following formula:

[0104] in, is the fourth value of the patent to be analyzed, To score the target of the patent to be analyzed, is the sales revenue of the patent to be analyzed, is the patent contribution rate in the tth time period, is the market supply and demand coefficient in the tth time period, is the remaining protection period of the patent to be analyzed, is the discount rate of the patent to be analyzed, To compare the company's gross profit margin, is the gross profit margin of the company that owns the patent to be analyzed.

[0105] In the present invention, a patent identifier of a patent to be analyzed is first obtained, for example, it may be a patent application number or a patent publication number, and then the patent document of the patent to be analyzed is searched based on the patent identifier, the patent document at least includes a claim, and the claim includes multiple claims to be analyzed. If the claim to be analyzed is an independent claim, the number of first characters in the claim to be analyzed is identified, and the number of first sentence fragments in the claim to be analyzed is identified according to preset punctuation marks, and the number of first features in the claim to be analyzed is determined according to the number of first sentence fragments, and then the first score of the claim to be analyzed is determined according to the number of first characters and the first number of features of the claim to be analyzed, and then the claim to be analyzed is semantically recognized to obtain a semantic recognition result, and the semantic recognition result includes the second number of features of the claim to be analyzed, and finally, based on the size relationship between the first number of features and the second number of features of the claim to be analyzed, the first score is corrected to obtain a second score, and the target score of the patent to be analyzed is determined according to the second score; and the value of the patent to be analyzed is determined according to the target score. In this method, the patent document of the patent to be analyzed is processed through the relevant technology of natural language processing, and then the revised score of the claim to be analyzed in the patent document is obtained, and the target score of the patent to be analyzed is determined based on the revised score. Since the second score is more accurate, the determined target score is also more accurate. The value of the patent to be analyzed is evaluated based on the more accurate target score, and the accuracy is higher. It can be seen that compared with the traditional manual analysis method, the scheme of the present invention not only improves the analysis efficiency, but also improves the accuracy of the analysis.

[0106] like Figure 2 As shown, this figure is a schematic diagram of a patent value analysis device provided by an embodiment of the present invention, and the device includes: The acquisition module 201 is used to acquire the patent identification of the patent to be analyzed; according to the patent identification, the patent document of the patent to be analyzed is acquired, the patent document at least includes the claims, and the claims include multiple claims to be analyzed; A judgment module 202 is used to judge whether the claim to be analyzed is an independent claim, and obtain a first judgment result; The identification module 203 is used to identify the first number of characters in the claim to be analyzed, and to identify the first number of sentence fragments in the claim to be analyzed according to preset punctuation marks if the first judgment result indicates that the claim to be analyzed is an independent claim, and to determine the first number of features of the claim to be analyzed according to the first number of sentence fragments; A first scoring module 204, configured to determine a first score of the claim to be analyzed according to the first character number and the first feature number of the claim to be analyzed; A semantic recognition module 205, configured to perform semantic recognition on the claim to be analyzed to obtain a semantic recognition result, wherein the semantic recognition result includes the second feature number of the claim to be analyzed; A second scoring module 206, configured to modify the first score according to the magnitude relationship between the first feature number and the second feature number of the claim to be analyzed to obtain a second score; A target score determination module 207 is used to determine a target score of the patent to be analyzed according to the second score, wherein the target score is the second score of a single claim to be analyzed or the average of the second scores of multiple claims to be analyzed; The patent value determination module 208 is used to determine the value of the patent to be analyzed according to the target score.

[0107] Optionally, the patent value determination module 208 is specifically configured to determine the first value by the following formula:

[0108] in, For the first value, is the R&D cost of the patent to be analyzed, is the estimated profit of the patent to be analyzed, Score the objectives of the patents to be analyzed.

[0109] Optionally, the patent value determination module 208 is specifically configured to determine the second value by the following formula:

[0110] in, is the second value of the patent to be analyzed, is the benchmark value, For reference rating, The value of the product or process to be protected by the patent to be analyzed, is the average value of various related products available on the market, Score the objectives of the patents to be analyzed.

[0111] Optionally, the patent value determination module 208 is specifically configured to determine the third value by the following formula:

[0112] in, is the third value of the patent to be analyzed, To score the target of the patent to be analyzed, is the sales revenue of the patent to be analyzed, is the patent contribution rate in the tth time period, is the market supply and demand coefficient in the tth time period, is the remaining protection period of the patent to be analyzed, is the discount rate for the patent to be analyzed.

[0113] Optionally, the patent value determination module 208 is specifically configured to determine the fourth value by the following formula:

[0114] in, is the fourth value of the patent to be analyzed, To score the target of the patent to be analyzed, is the sales revenue of the patent to be analyzed, is the patent contribution rate in the tth time period, is the market supply and demand coefficient in the tth time period, is the remaining protection period of the patent to be analyzed, is the discount rate of the patent to be analyzed, To compare the company's gross profit margin, is the gross profit margin of the company that owns the patent to be analyzed.

[0115] Optionally, the acquisition module 201 is further configured to acquire a reference relationship between the claim to be analyzed and the independent claim if the first judgment result indicates that the claim to be analyzed is not an independent claim, and determine, based on the reference relationship, additional content of the claim to be analyzed relative to the independent claim; The identification module 203 is further used to identify the number of additional characters in the additional content, and to identify the number of additional sentence fragments in the additional content according to preset punctuation marks, and to determine the number of additional features of the claim to be analyzed according to the number of additional sentence fragments; The acquisition module 201 is also used to acquire the number of features and the number of characters in the independent claim; the sum of the number of features in the independent claim and the number of additional features of the claim to be analyzed is used as the first number of features of the claim to be analyzed, and the sum of the number of characters in the independent claim and the number of additional characters of the claim to be analyzed is used as the first number of characters of the claim to be analyzed.

[0116] Optionally, the second scoring module 206 is specifically used to determine a first correction coefficient based on a first difference between the first number of features and the second number of features and a first preset mapping relationship if the first feature number is greater than the second feature number, the first preset mapping relationship being a mapping relationship between a first reference difference and a first reference correction coefficient, and correcting the first score according to the first correction coefficient; or, if the first feature number is less than the second feature number, determine a second correction coefficient based on a second difference between the first number of features and the second number of features and a second preset mapping relationship, the second preset mapping relationship being a mapping relationship between a second reference difference and a second reference correction coefficient, and correcting the first score according to the second correction coefficient.

[0117] Optionally, the identification module 203 is specifically used to obtain the number of characters in each sentence fragment in the claim to be analyzed; determine the third correction coefficient corresponding to each sentence fragment according to the number of characters in each sentence fragment and a third preset mapping relationship, wherein the third preset mapping relationship is a mapping relationship between a reference number of characters and a third reference correction coefficient; correct each sentence fragment using the third correction coefficient of each sentence fragment; and take the sum of the corrected values ​​of each sentence fragment as the first characteristic number of the claim to be analyzed.

[0118] Optionally, the device further comprises a comparison module and a third scoring module; The acquisition module 201 is also used to obtain the classification number of the patent to be analyzed; The comparison module is used to compare the features in the claim to be analyzed with the feature library corresponding to the classification number of the patent to be analyzed, and obtain the hit rate of the features in the claim to be analyzed in the feature library corresponding to the classification number of the patent to be analyzed; The acquisition module 201 is further used to determine a fourth correction coefficient corresponding to the hit rate according to a fourth preset mapping relationship, where the fourth preset mapping relationship is a mapping relationship between a reference hit rate and a fourth reference correction coefficient; The third scoring module is used to correct the second score according to the fourth correction coefficient to obtain a third score.

[0119] The patent value analysis device according to the embodiment of the present invention may correspond to the method described in the embodiment of the present invention, and the above-mentioned other operations and / or functions of each module / unit of the patent value analysis device are respectively to realize Figure 1 For the sake of brevity, the corresponding processes of each method in the illustrated embodiment are not described in detail here.

[0120] The embodiment of the present invention also provides a computing device. Figure 3As shown, this figure is a schematic diagram of a computing device provided by an embodiment of the present invention, and the computing device 300 includes a bus 301, a processor 302, a communication interface 303 and a memory 304. The processor 302, the memory 304 and the communication interface 303 communicate with each other through the bus 301.

[0121] The bus 301 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0122] The processor 302 may be any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0123] The communication interface 303 is used for communicating with the outside.

[0124] The memory 304 may include a volatile memory, such as a random access memory (RAM). The memory 304 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0125] The memory 304 stores executable codes, and the processor 302 executes the executable codes to perform the aforementioned patent value analysis method.

[0126] Specifically, in implementing Figure 2 In the case of the embodiment shown, and Figure 2 When each module or unit of the patent value analysis device described in the embodiment is implemented by software, the execution Figure 2The software or program code required for the functions of each module / unit in the system may be partially or completely stored in the memory 304. The processor 302 executes the program code corresponding to each unit stored in the memory 304 to perform the aforementioned patent value analysis method.

[0127] The embodiment of the present invention also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that can be stored by a computing device or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid-state hard disk). The computer-readable storage medium includes instructions that instruct the computing device to execute the above-mentioned patent value analysis method.

[0128] The embodiment of the present invention further provides a computer program product, which includes one or more computer instructions. When the computer instructions are loaded and executed on a computing device, the process or function described in the embodiment of the present invention is fully or partially generated.

[0129] The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer or data center to another website, computer or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0130] When the computer program product is executed by a computer, the computer executes any of the aforementioned methods for analyzing the value of a patent. The computer program product may be a software installation package, and when any of the aforementioned methods for analyzing the value of a patent is required, the computer program product may be downloaded and executed on a computer.

[0131] The descriptions of the processes or structures corresponding to the above-mentioned figures have different emphases. For parts that are not described in detail in a certain process or structure, please refer to the relevant descriptions of other processes or structures.

[0132] The above description is only a specific implementation of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions within the technical scope disclosed by the present invention should be included in the protection scope of the present invention.

Claims

1. A method for analyzing patent value, characterized in that: The method comprises: Obtain patent identification of the patent to be analyzed; According to the patent identifier, obtaining the patent document of the patent to be analyzed, wherein the patent document at least includes claims, and the claims include multiple claims to be analyzed; Determine whether the claim to be analyzed is an independent claim, and obtain a first determination result; If the first judgment result indicates that the claim to be analyzed is an independent claim, identifying the first number of characters in the claim to be analyzed, and identifying the first number of sentence fragments in the claim to be analyzed according to preset punctuation marks, and determining the first number of features of the claim to be analyzed according to the first number of sentence fragments; Determining a first score of the claim to be analyzed according to the number of first characters and the number of first features of the claim to be analyzed; Performing semantic recognition on the claim to be analyzed to obtain a semantic recognition result, wherein the semantic recognition result includes the number of the second features of the claim to be analyzed; According to the relationship between the number of the first feature and the number of the second feature of the claim to be analyzed, the first score is modified to obtain a second score; Determine a target score of the patent to be analyzed according to the second score, wherein the target score is the second score of a single claim to be analyzed or the average of the second scores of multiple claims to be analyzed; The value of the patent to be analyzed is determined based on the target score.

2. The method according to claim 1, characterized in that The value of the patent to be analyzed includes a first value, and determining the value of the patent to be analyzed according to the target score includes: in, For the first value, is the R&D cost of the patent to be analyzed, is the estimated profit of the patent to be analyzed, Score the objectives of the patents to be analyzed.

3. The method according to claim 1, characterized in that The value of the patent to be analyzed includes a second value, and determining the value of the patent to be analyzed according to the target score includes: in, is the second value of the patent to be analyzed, is the benchmark value, For reference rating, The value of the product or process to be protected by the patent to be analyzed, is the average value of various related products available on the market, Score the objectives of the patents to be analyzed.

4. The method according to claim 1, characterized in that The value of the patent to be analyzed includes a third value, and the value of the patent to be analyzed is determined according to the target score, including: in, is the third value of the patent to be analyzed, To score the target of the patent to be analyzed, is the sales revenue of the patent to be analyzed, is the patent contribution rate in the tth time period, is the market supply and demand coefficient in the tth time period, is the remaining protection period of the patent to be analyzed, is the discount rate for the patent to be analyzed.

5. The method according to claim 1, characterized in that The value of the patent to be analyzed includes a fourth value, and the value of the patent to be analyzed is determined according to the target score, including: in, is the fourth value of the patent to be analyzed, To score the target of the patent to be analyzed, is the sales revenue of the patent to be analyzed, is the patent contribution rate in the tth time period, is the market supply and demand coefficient in the tth time period, is the remaining protection period of the patent to be analyzed, is the discount rate of the patent to be analyzed, To compare the company's gross profit margin, is the gross profit margin of the company that owns the patent to be analyzed.

6. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: If the first judgment result indicates that the claim to be analyzed is not an independent claim, obtaining a reference relationship between the claim to be analyzed and the independent claim, determining the additional content of the claim to be analyzed relative to the independent claim according to the reference relationship, identifying the number of additional characters in the additional content, and identifying the number of additional sentence fragments in the additional content according to preset punctuation marks, and determining the number of additional features of the claim to be analyzed according to the number of additional sentence fragments; Obtaining the number of features and characters in the independent claim; The sum of the number of features in the independent claim and the number of additional features of the claim to be analyzed is taken as the first number of features of the claim to be analyzed, and the sum of the number of characters in the independent claim and the number of additional characters of the claim to be analyzed is taken as the first number of characters of the claim to be analyzed.

7. The method according to any one of claims 1 to 5, characterized in that: The modifying of the first score according to the relationship between the number of the first features and the number of the second features of the claim to be analyzed comprises: If the first number of features is greater than the second number of features, a first correction coefficient is determined according to a first difference between the first number of features and the second number of features and a first preset mapping relationship, wherein the first preset mapping relationship is a mapping relationship between a first reference difference and a first reference correction coefficient, and the first score is corrected according to the first correction coefficient; or If the first number of features is less than the second number of features, a second correction coefficient is determined based on a second difference between the first number of features and the second number of features and a second preset mapping relationship, where the second preset mapping relationship is a mapping relationship between a second reference difference and a second reference correction coefficient, and the first score is corrected according to the second correction coefficient.

8. The method according to any one of claims 1 to 5, characterized in that: Determining the first feature number of the claim to be analyzed according to the first sentence fragment number includes: Obtaining the number of characters in each sentence fragment in the claim to be analyzed; Determine a third correction coefficient corresponding to each sentence fragment according to the number of characters in each sentence fragment and a third preset mapping relationship, wherein the third preset mapping relationship is a mapping relationship between the number of reference characters and the third reference correction coefficient; Correcting each sentence fragment using the third correction coefficient of each sentence fragment; The sum of the corrected values ​​of each sentence fragment is taken as the first feature number of the claim to be analyzed.

9. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: Obtaining the classification number of the patent to be analyzed; Compare the features in the claim to be analyzed with the feature library corresponding to the classification number of the patent to be analyzed to obtain the hit rate of the features in the claim to be analyzed in the feature library corresponding to the classification number of the patent to be analyzed; Determine a fourth correction coefficient corresponding to the hit rate according to a fourth preset mapping relationship, wherein the fourth preset mapping relationship is a mapping relationship between a reference hit rate and a fourth reference correction coefficient; Correcting the second score according to the fourth correction coefficient to obtain a third score; According to the second score, the target score of the patent to be analyzed is determined as: According to the third score obtained by correcting the second score, the target score of the patent to be analyzed is determined, and the target score is the third score of a single claim to be analyzed or the average of the third scores of multiple claims to be analyzed.

10. A computing device, characterized in that including memory and processor; One or more computer programs are stored in the memory, and the one or more computer programs include instructions; when the instructions are executed by the processor, the computing device executes the method as claimed in any one of claims 1 to 9.

Citation Information

Patent Citations

  • A method and device for automatically obtaining a high-value patent

    CN109325100A

  • Patent value evaluation method, system and device and storage medium

    CN112231549A

  • Technical scheme creativity assessment method, medium and device

    CN115908060A

  • Information processor, information processing method, and program

    JP2006065882A

  • Droppingstep grate for incinerator that includes a protrusion on the back of the shear wall and droppingstep installation structure using the same

    KR102709220B1