CN111242494A - Patent infringement detection method and system based on game theory - Google Patents
Patent infringement detection method and system based on game theory Download PDFInfo
- Publication number
- CN111242494A CN111242494A CN202010053358.6A CN202010053358A CN111242494A CN 111242494 A CN111242494 A CN 111242494A CN 202010053358 A CN202010053358 A CN 202010053358A CN 111242494 A CN111242494 A CN 111242494A
- Authority
- CN
- China
- Prior art keywords
- game
- infringement
- payment
- data
- technical features
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3346—Query execution using probabilistic model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services; Handling legal documents
- G06Q50/184—Intellectual property management
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Development Economics (AREA)
- Probability & Statistics with Applications (AREA)
- Educational Administration (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of information retrieval, and discloses a game theory-based patent infringement detection method and system, which are used for acquiring data and preprocessing the acquired data; carrying out infringement risk calculation through novelty and non-obvious characteristics of calculation technology and games among claims and patents; and the payment obtained by the game result is the patent infringement risk. The invention simultaneously detects novelty and non-obviousness in the infringement detection process, overcomes the technical prejudice, and obtains good experimental results by combining profound laws and relevant professional knowledge of patents; the rational decision process of the patent applicant is considered in the infringement risk calculation process, and the technical problem about the actual detection process, which is always desired to be solved but always unsuccessful, is solved; the invention fills the blank at home and abroad, and provides a new strategy for comparing patent texts.
Description
Technical Field
The invention belongs to the technical field of information retrieval and database structures thereof, and particularly relates to a patent infringement detection method and system based on game theory.
Background
Currently, the current state of the art commonly used in the industry is such that: with the progress of the times, people pay more attention to the protection of intellectual property rights, and the number of applications of patents as important means for the protection of intellectual property rights is increased sharply. And the patent can bring huge loss to companies and individuals once the patent is found to have infringement after being granted. However, the manual review of the patent is not only slow, but also misjudgment may occur in the process of patent review due to the limitation of the knowledge in the field of patent reviewers, so that the loss of the patent applicant can be greatly reduced by performing automatic infringement detection before the patent application. Therefore, automation of patent infringement detection is realized, the patent applicant can perform pre-detection before applying for a patent, and possible infringement patents can be searched in the process of patent examination, so that the patent examination period is shortened. Patent review mainly reviews three characteristics: usefulness, novelty and creativity. Usefulness means that the technical solution described in the patent is workable and judged from the description of the patent itself. And the infringement detection is to detect whether the patent infringes other patents and judge according to the relationship between the patents, so the patent infringement detection only considers novelty and creativity and does not consider the detection of usefulness. At present, the common patent infringement detection is mainly to detect the infringement of a patent by improving a structure and a method of similarity detection, and the methods take a patent text as a research object.
At present, the common patent infringement detection is mainly to detect the infringement of a patent by improving a structure and a method of similarity detection, and the methods take a patent text as a research object.
The defects of the prior method are as follows:
(1) since the innovation of the patent law, substantial examination of patent contents has been added, which essentially examines three characteristics of the patent: usefulness, novelty and non-obviousness, while infringement detection is directed to the relationship of the patent to other patents, and may temporarily override usefulness, past methods overlook detection of non-obviousness.
(2) The prior method does not distinguish the patent text from other common texts, only the text per se is considered in the comparison process, and the rational decision of the patent applicant is not considered. The process of applying for patent invalid judgment is a two-way process, a suspected infringer can control and report the infringement of the suspected infringer, and the suspected infringer also has the right to generate dissimilarities for the judgment of the court, and can lift the lawsuits of the patent review committee of the national intellectual property bureau. In this process both parties will make the most favorable choice for themselves in conjunction with the choice of the other.
(3) The comparison of past methods does not take into account that the process of determining the novelty of a patent is a two-way process, taking into account not only the technical features of the patent more than the previous patent, but also those of the patent less than the previous patent.
(4) The hierarchy is omitted, and the accuracy of the infringing object representation is reduced. In the past, only the claims of which the most important part is composed of the claims are considered, in fact, for the patent, the patent is mainly composed of the claims, and the claims are mainly composed of technical features, and the omission of the hierarchy of the patent text leads to the reduction of the accuracy of the infringing object, namely the characterization of the patent.
(5) Neglecting pertinence, this loss of information reduces the accuracy of the experimental results. In the past, the overall similarity result of the claims is taken as the basis for patent infringement judgment, in fact, patent infringement detection is performed on a single claim, as long as one claim infringes other patents in the patent, the patent is judged to be infringed, and the lack of pertinence on a judgment object causes the accuracy of an experimental result to be reduced.
In summary, the problems of the prior art are as follows:
(1) the automatic methods of patent infringement detection in the past have been ineffective at detecting non-obvious.
(2) The prior method does not distinguish the patent text from other common texts, only the text per se is considered in the comparison process, and the rational decision of the patent applicant is not considered.
(3) The comparison of past methods does not take into account that the process of determining the novelty of a patent is a two-way process, and does not involve the technical features of the patent less than those of previous patents. The above problems lead to inaccurate results of patent infringement detection.
(4) The inaccuracy of the characteristic information of the infringing object in the detection method in the prior art causes the accuracy of the experimental result to be low.
(5) Inaccurate expression of real infringement scene information in the detection method in the prior art causes low reliability of experimental results.
(6) The loss of targeted information in the detection method in the prior art causes low accuracy of experimental results.
The difficulty of solving the technical problems is as follows: traditional contrast methods are difficult to perform for non-obvious detection; the method of considering only the comparison cannot embody the decision making process of the applicant. The traditional comparison method is difficult to express the hierarchy of patent composition; the infringement real scene is difficult to embody; there are difficulties in the targeted expression of patent infringement decisions.
The significance of solving the technical problems is as follows: by combining legal knowledge and the actual process of patent examination and verification, the patent infringement is more accurately detected, the result accuracy can be improved, and the loss of patent applicants is reduced. By combining legal knowledge, a patent text structure and the actual process of patent examination, the patent infringement is more accurately detected, the result accuracy can be improved, the loss of a patent applicant is reduced, and the patent examination period is shortened.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a patent infringement detection method and system based on game theory. According to the steps of natural language processing, data needs to be preprocessed, numerical values used in the game process need to be calculated, and finally the final result is obtained through the game. According to the steps of natural language processing, firstly, searching and preprocessing collected patent data through a computer technology, then using the similarity obtained by word2vec as a similarity relation between technical features, constructing a game tree based on a patent structure and the similarity relation, and obtaining infringement risks by calculating the technical features and the claims in a patent selected by expecting payment. And repeating the process, and summarizing the infringement risks to generate an infringement risk detection report.
The invention is realized in such a way, and provides a patent infringement detection method and a system based on a game theory, wherein the patent infringement detection method based on the game theory specifically comprises the following steps:
step one, data acquisition is carried out, and the acquired data need to be preprocessed because the acquired data do not conform to the structure of experimental data.
And step two, through analyzing the patent text, the technical characteristics of the patent are generally expressed by terms, so that the terms are taken as the technical characteristics of the patent, and the infringement risk calculation is carried out through calculating the novelty and the non-obvious property of the technical characteristics and the game among the claims and among the patents.
And step three, the payment obtained by the game result is the patent infringement risk.
Further, in the first step, data required by the experiment is provided, and the data acquisition includes:
(1) the United States Patent and Trademark Office (USPTO) contains the most comprehensive and complete patent application and patent granting information, and the patent of the patent and trademark office (USPTO) is selected as the source of data herein.
(2) Patent data of a patent and trademark office (USPTO) is obtained in batches by a web crawler-based method.
Further, the data preprocessing comprises:
(1) the core technology of a patent is written in the claim part of the patent text, so that the claims in the patent data are extracted.
(2) The data required by the experiment is the noun of the claim part, so that the extracted text data is subjected to stop word, word segmentation and noun extraction processing.
(3) For subsequent computational novelty and non-obvious, words are vectorized using word2 vec.
Further, in the second step, data support is provided for a subsequent gaming process, and the novel and non-obvious computing method of the technical features specifically comprises:
(1) by calculating the distance using the word vector, a word in a claim is selected because the novelty of two words is low as long as they are close, and therefore the shortest distance (i.e., 1-maximum similarity) from the word to the word in the other claim is calculated as the novelty paid by the technical feature corresponding to the word.
(2) The distance is calculated by using the word vector, a certain word in the claim is selected, because the non-obvious performance of two words is low as long as the two words are close, the shortest distance (namely 1-maximum similarity) from the word to other words in the claim where the word is located is calculated as the non-obvious performance of the technical feature corresponding to the word, and the non-obvious performance of the technical feature is normalized to be used as the selection probability of the technical feature.
(3) And regarding the payment of the claim, the payment of the technical characteristics obtained by the technical characteristic game result is taken as the payment of the claim.
(4) For the selection probability of the claim, according to the analysis of the patent text, the importance of the claim is inversely proportional to the technical characteristic number contained in the claim besides whether the claim is the independent claim or not, so that the technical characteristic number contained in the claim and whether the claim is the independent claim or not are calculated, and the claim selection probability is obtained after normalization.
Further, in the second step, the game between the claims and the game between the patents specifically includes:
(1) the node A, B is used to indicate the player who is the player's claim to play or the patent to play. The branches on the nodes represent the policies of the participants, with a probability of selection for each policy, and the leaves nodes represent the payment of the participants.
(2) Based on the analysis of the patent text, the constituent elements of the technology are taken as technical features.
1) When t is the technical feature F, the calculation of the payment function is as follows:
wherein σiRepresenting a mixing strategy of the participant i; -i represents a participant other than participant i;
expressed in a hybrid strategy sigmaiAnd
paying by a lower participant i;
representing participant-i selection mixing strategy sigma-iTime participant i selection strategy
The payment of (2);
to represent
And
using word2vec to represent words as word vectors, and using the distance of the word vectors as a calculation result;
2) when t is claim C, the calculation of the payment function is as follows:
other calculation methods are the same as those when t is the technical feature F;
express claims
The number of technical features involved;
represents an independent claim;
showing the dependent claims.
Further, the patent infringement detection system based on the game theory specifically comprises:
the system comprises a data acquisition and preprocessing module, a risk calculation module and a result output module.
The data acquisition and preprocessing module comprises: and the risk calculation module is connected with the data source and is used for selecting the data source, crawling the data and processing the crawled data.
A risk calculation module: is connected with the data acquisition and preprocessing module and the result output module; the novelty and non-obvious of the method for calculating technical features, the game between the claims and the patents is played.
A result output module: and the risk calculation module is connected with the game module and is used for outputting the payment obtained by the game result as the patent infringement risk.
Another object of the present invention is to provide a terminal implementing the processor of the game theory-based patent infringement detection method.
Another object of the present invention is to provide a computer-readable storage medium, comprising instructions which, when run on a computer, cause the computer to perform the method for patent infringement detection based on game theory.
The invention also aims to provide a patent retrieval device for realizing the patent infringement detection method based on the game theory.
Another objective of the present invention is to provide a method for detecting patent infringement based on game theory, further comprising: searching and preprocessing the collected patent data by a computer technology;
similarity obtained by using word2vec is used as a similarity relation between technical features for the patent data after searching and preprocessing, a game tree is constructed based on a patent structure and the similarity relation, and infringement risk data is obtained by calculating the technical features and the claims in the expected payment selected patent;
and summarizing the obtained infringement risk data to generate an infringement risk detection report.
The patent infringement detection method based on the game theory further comprises the following steps:
firstly, acquiring patent data, retrieving uploaded patents, and preprocessing claim data in the retrieved patent data;
step two, calling an external word vector database to calculate the similarity relation between the technical features as the novelty and creativity of the technical features;
step three, constructing a game tree with the claims as nodes and the technical characteristics as edges, carrying out game among the claims, and taking payment among the technical characteristics selected in the game result as a risk of infringing the claims;
step four, constructing a game tree with patents as nodes and claims as edges, carrying out game among the patents, and using payment among the claims selected in the game result as a patent infringement risk;
and step five, summarizing results and generating an infringement risk report.
Further, in the first step, the method for acquiring patent data includes: saving the downloaded patent text full-text patent data in an XML format as a patent database;
analyzing the uploaded patent text, extracting a CPC classification number of the patent according to a label in the XML format text, and searching potential counter-party patents in a patent database according to the extracted CPC classification number;
extracting text data of uploaded patents in XML format and potential counter-party patents to obtain claim claims in patent texts, then preprocessing the extracted claim claims, and storing the preprocessed texts in a computer storage device in a document form;
the method for preprocessing the claim data in the retrieved patent data comprises the following steps: the computer text processing technology is used for carrying out word segmentation, part of speech tagging and word stop removal on words in the claims, and words with parts of speech being nouns are selected and stored in a computer storage device.
Further, in step two, the external word vector database includes: using Word2Vec to train a Word vector database obtained by a wiki English corpus, wherein words in the Word vector database are expressed in a vector form; the selected nouns are represented by word vectors searched from a word vector database;
the novel and inventive method of computing technical features specifically comprises: (1) the similarity between words is represented by a module obtained by training a word vector database and a genim library, the technical features in each patent claim are selected in sequence, the technical features are selected nouns, then the value with the maximum similarity between the selected technical features and other technical features in the claim where the nouns are located is selected, and finally the distance between the value and 1 is the creativity of the technical features;
(2) the similarity between words is represented by a module obtained by training through a word vector database and a genim library, technical features in claims in two patents are sequentially selected, and the distance from the similarity of the two selected technical features to 1 is the novelty of the corresponding technical features;
(3) the calculated creativity and novelty are stored in a computer storage device in a form of a document.
Further, in step three, creativity of the technical features represented by the edges is taken as weight values of corresponding edges in the game tree, novelty between the technical features represented by the edges is taken as payment of the corresponding former technical features, and the distance from a value of the novelty to 1 is taken as payment of the latter technical features; storing the calculated payment in a computer storage device in a document form;
v(s) represents the expected payment for a certain technical feature s claimed in patent 1, where σ(s) represents the weight on the corresponding side of the technical feature s; v (s, s ') represents the payment of the applicant when the applicant of patent 1 selects technical feature s and the applicant of patent 2 selects technical feature s'; s' represents all the technical features of claim 2 in patent 2;
obtaining the expected payment of each technical characteristic of claim 1 in the patent 1 through the operation of a computer, and selecting the technical characteristic with the maximum expected payment in the claim as the technical characteristic 1 which is most beneficial to a patent applicant in the claim; the most advantageous technical feature 2, technical feature 1 and technical feature 2 of claim 2 in patent 2 are selected by the game in claim 1 of patent 1 and claim 2 of patent 2, and the results are stored in a computer storage device in a document form.
Further, in step four, the weight of the claim represented by the edge is taken as the weight of the edge, and the game result between the claims represented by the edge is taken as the payment of the corresponding claim; the game result between the claims is two technical characteristics of the selected most favorable technical characteristic 1 and the most favorable technical characteristic 2;
combining the type of the claims and the number of technical features contained in the claims as the weight of the claims:
in the formula
Express claims
The number of technical features involved;
represents an independent claim;
representing the dependent claims; and stores the weights in a file form in a computer storage device.
Further, in step four, the game between patent 1 and patent 2 is played, and the claims selected in patent 1 and patent 2 are obtained through the following processes according to the game result:
v (c) represents the expected payment of a certain claim in patent 1, where σ (c) represents the weight on the corresponding side of claim c; v (c, c ') represents the payment of the patent applicant 1 when the applicant of patent 1 selects claim c and the applicant of patent 2 selects claim c'; c' represents all claims in patent 2.
Calculating the expected payment of each claim in the patent 1, selecting the claim with the largest expected payment in the patent as the claim 1 which is the most beneficial to the applicant of the patent 1 in the patent, selecting the most beneficial claim 2 in the patent 2, wherein the claims 1 and 2 are the two claims selected by the game of the patent 1 and the patent 2, and the payment of the patent 1 corresponding to the two claims is the infringement risk of the patent. The calculation process is obtained by running a computer, and the infringement probability of the patent is stored on computer storage equipment in percentage form as a result;
and step five, sequentially detecting the infringement risks of potential counter-party patents and the patents uploaded by the user, storing all results in a computer storage device in a document form, returning the document as a detection report, and printing the detection report through a printing device.
Another object of the present invention is to provide a patent infringement detection system based on game theory for a patent infringement detection method based on game theory, the patent infringement detection system based on game theory comprising:
the data acquisition and preprocessing module is used for acquiring patent data, retrieving uploaded patents and preprocessing claim data in the retrieved patent data;
the similarity relation acquisition module among the technical features is connected with the data acquisition and preprocessing module and is used for calling the similarity relation among the technical features calculated by the external word vector database to serve as the novelty and creativity of the technical features;
the claim infringement risk analysis module is connected with the similarity relation acquisition module among the technical characteristics and used for constructing a game tree which takes the claims as nodes and the technical characteristics as edges, the claims are subjected to game, and payment among the technical characteristics selected in the game result is used as the claim infringement risk;
the patent infringement risk analysis module is connected with the claim infringement risk analysis module and is used for constructing a game tree with patents as nodes and claims as edges, games are carried out among the patents, and payment among the claims selected in the game result is used as the patent infringement risk;
and the infringement risk report generation module is used for summarizing results and generating an infringement risk report.
In summary, the advantages and positive effects of the invention are: the invention provides a method for detecting patent claim infringement risk, which comprises the steps of 1) utilizing a computer technology to collect and store patent data into a patent database, uploading patents by a user, searching potential counter-parties according to the patents uploaded by the user, and preprocessing the patent claims of patent text data; step 2) carrying out automatic information processing on patent claims through a computer to obtain key words, namely technical characteristics of the patent, and calculating the similarity relation between the technical characteristics by calling an external word vector database to serve as novelty and creativity of the technical characteristics; step 3) using a computer to construct a game tree which takes the claims as nodes, the technical characteristics as edges, the creativity of the technical characteristics as edges and the novelty between the technical characteristics as payment, under the structure, the game is carried out between the claim nodes, and the infringement probability of the patent claims is detected by adopting the Nash equilibrium principle; and 4) constructing a game tree which takes the patent as a node, the claim as an edge, the weight occupied by the claim as the weight of the edge and the infringement probability among the claims as payment by using a computer, carrying out game among the patent nodes under the structure, and detecting whether the patent infringes or not by adopting a Nash equilibrium principle. And 5) summarizing the uploaded patents and the infringement risks of all potential counterparty patents, and generating an infringement risk report. The method takes a patent text database and an external word vector database as data supports, takes a data mining technology as a means, takes a computer and a storage medium as a platform, takes the claims of the most important part of the patent as main research objects, considers the novelty and creativity of the patent, constructs a game tree by processing the patent claims, realizes game among claim nodes and patent nodes by the computer, and finally judges whether the patent infringes according to the Nash equilibrium principle. The method realizes automation of patent infringement detection, improves infringement detection efficiency and result accuracy, and can be effectively applied to the practice of patent applicant pre-detection and patent examination.
In the infringement detection process, the most important part of the patent claims are taken as a main analysis object, and the accuracy of the infringement object representation is improved through the hierarchical representation of the patent; considering a real infringement scene, using a game method to embody the bidirectionality of the real scene; the infringement judgment basis is carefully studied, and the information of the infringement judgment aiming at the claim is supplemented. The invention comprehensively considers the influence of various factors on the accuracy and reliability of the result, effectively improves the efficiency and accuracy of patent infringement detection, and can be well applied to the patent infringement pre-detection and patent verification process of the patent applicant.
The invention simultaneously detects novelty and non-obviousness in the infringement detection process, overcomes the technical prejudice, and obtains good experimental results by combining profound laws and relevant professional knowledge of patents; the invention considers the rational decision process of the patent applicant in the infringement risk calculation process, and solves the technical problem about the actual detection process which people are eager to solve but can not succeed all the time. The invention comprehensively considers the two-way process of the patent novelty, not only considers the technical characteristics of the patent more than the prior patent, but also considers the technical characteristics of the patent less than the prior patent, and comprehensively considers the influence of various factors on the result accuracy; fills up the blank at home and abroad, and provides a new strategy for comparing patent texts.
The invention searches and preprocesses the collected patent data by computer technology; similarity obtained by using word2vec is used as a similarity relation between technical features for the patent data after searching and preprocessing, a game tree is constructed based on a patent structure and the similarity relation, and infringement risk data is obtained by calculating the technical features and the claims in the expected payment selected patent; and summarizing the obtained infringement risk data to generate an infringement risk detection report. The invention realizes the game between the claim nodes and the patent nodes through the computer, and finally judges whether the patent infringes the right according to the Nash equilibrium principle; the method realizes automation of patent infringement detection, improves infringement detection efficiency and result accuracy, and can be effectively applied to the practice of patent applicant pre-detection and patent examination.
Drawings
Fig. 1 is a flowchart of a patent infringement detection method based on game theory according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of patent infringement detection based on game theory provided by an embodiment of the invention.
Fig. 3 is a schematic diagram of a gaming process provided by an embodiment of the present invention.
Fig. 4 is a schematic structural diagram of a patent infringement detection system based on game theory according to an embodiment of the present invention.
Fig. 5 is a flowchart of a method for detecting patent claim infringement risk according to an embodiment of the present invention.
Fig. 6 is a schematic diagram of a technical feature gaming tree provided by an embodiment of the present invention.
Fig. 7 is a diagram of a claim gaming tree provided by an embodiment of the present invention.
Fig. 8 is an illustration of an infringement detection report sample of a method for detecting infringement risk of patent claims according to an embodiment of the present invention.
Fig. 9 is a technical solution diagram provided by an embodiment of the present invention.
Fig. 10 is a schematic diagram of a patent infringement detection system based on game theory provided by an embodiment of the invention.
In the figure: 1. a data acquisition and preprocessing module; 2. a risk calculation module; 3. a result output module; 4. A similarity relation obtaining module among the technical characteristics; 5. a claim infringement risk analysis module; 6. a patent infringement risk analysis module; 7. and an infringement risk report generation module.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The automatic methods of patent infringement detection in the past have been ineffective at detecting non-obvious. The prior method does not distinguish the patent text from other common texts, only the text per se is considered in the comparison process, and the rational decision of the patent applicant is not considered. The comparison of past methods does not take into account that the process of determining the novelty of a patent is a two-way process, and does not involve the technical features of the patent less than those of previous patents. The above problems lead to inaccurate results of patent infringement detection.
Aiming at the problems in the prior art, the invention provides a patent infringement detection method based on game theory, and the invention is described in detail below with reference to the attached drawings.
As shown in fig. 1, the method for detecting patent infringement based on game theory provided in the embodiment of the present invention specifically includes:
s101: and acquiring data and preprocessing the acquired data.
S102: the infringement risk calculation is carried out through novelty and non-obvious characteristics of calculation technology and games between claims and patents.
S103: and the payment obtained by the game result is the patent infringement risk.
In step S101, the data acquisition and data preprocessing provided by the embodiment of the present invention specifically include:
data acquisition: (1) the patent of the patent and trademark office (USPTO) was chosen as the source of data. (2) Patent data of a patent and trademark office (USPTO) is obtained in batches by a web crawler-based method.
Data preprocessing: (1) claim in the patent data is extracted. (2) And performing stop word and word segmentation processing on the extracted text data. (3) The word is vectorized using word2 vec.
In step S102, the novel and non-obvious calculation method for technical features provided by the embodiment of the present invention specifically includes:
(1) and calculating the distance by using the word vector, and selecting the shortest distance from the technical feature to the technical feature of other claims as the novelty of the technical feature, namely the payment of the technical feature.
(2) By calculating the distance using the word vector, the shortest distance of the technical feature to the other technical features of the claims is selected as the non-obviousness of the technical feature, i.e. the selection probability of the technical feature.
(3) And regarding the payment of the claim, the payment of the technical characteristics obtained by the technical characteristic game result is taken as the payment of the claim.
(4) For the selection probability of the claim, the technical characteristic number contained in the claim and whether the technical characteristic number is the independent claim are combined to calculate the selection probability of the claim.
In the embodiment of the invention, fig. 2 is a patent infringement detection principle based on game theory.
As shown in fig. 3, in step S102, the game between claims and patents provided in the embodiment of the present invention specifically includes:
(1) the claim or patent that the gambler gambles is, respectively, identified as node A, B. The branches on the nodes represent the policies of the participants, with a probability of selection for each policy, and the leaves nodes represent the payment of the participants.
(2) Based on the analysis of the patent text, the constituent elements of the technology are taken as technical features.
1) When t is the technical feature F, the calculation of the payment function is as follows:
wherein σiRepresenting the mixing strategy of participant i. -i represents a participant other than participant i.
Expressed in a hybrid strategy sigmaiAnd
and (5) paying by the lower participant i.
Representing participant-i selection mixing strategy sigma-iTime participant i selection strategy
The payment of (2).
To represent
And
the distance between words is represented as word vectors using word2vec, and the distance of the word vectors is used as a calculation result.
2) When t is claim C, the calculation of the payment function is as follows:
the other calculation methods are the same as those when t is the technical feature F.
Express claims
The number of technical features involved.
Representing the independent claims.
Showing the dependent claims.
As shown in fig. 4, the patent infringement detection system based on the game theory provided in the embodiment of the present invention specifically includes:
the system comprises a data acquisition and preprocessing module 1, a risk calculation module 2 and a result output module 3.
The data acquisition and preprocessing module 1: and the risk calculation module 2 is connected with the data source and is used for selecting the data source, crawling the data and processing the crawling data.
Risk calculation module 2: is connected with the data acquisition and preprocessing module 1 and the result output module 3. The novelty and non-obvious of the method for calculating technical features, the game between the claims and the patents is played.
The result output module 3: and the risk calculation module 2 is connected with the game result and used for outputting the payment obtained by the game result as the patent infringement risk.
The technical solution of the present invention is further described below with reference to the accompanying drawings.
As shown in fig. 5, the method for detecting patent infringement based on game theory provided in the embodiment of the present invention specifically includes:
s501: and (4) acquiring patent data, uploading and retrieving patents by a user, and preprocessing claim data in the retrieved patent data.
S502: and calling an external word vector database to calculate the similarity relation between the technical features as the novelty and creativity of the technical features.
S503: and (3) constructing a game tree with the claims as nodes and the technical characteristics as edges, playing games among the claims, and taking payment among the technical characteristics selected in the game result as the infringement risk of the claims.
S504: and (3) constructing a game tree with patents as nodes and claims as edges, carrying out game among the patents, and using payment among the claims selected in the game result as a patent infringement risk.
S105: and summarizing results and generating an infringement risk report.
In step S501, the data acquisition includes: the invention relates to a method for processing patent data, which comprises the steps of downloading U.S. patent data from the United States Patent and Trademark Office (USPTO), wherein the data comprises the full text of a patent and is stored as a patent database in an XML format, and because the XML format has labels for all parts of the patent text, the invention can obtain the corresponding part of a required patent by extracting the content of a specific label, retrieve the patent meeting the conditions from the patent database as a potential opponent according to the uploaded patent of a user, and then extract the right claim and perform preprocessing operation on the searched patent and the uploaded patent. The retrieval operation includes: for the united states patent, the CPC classification number is determined according to the application field of the patent, so the application field of the patent can be determined according to the CPC classification number of the patent uploaded by the label extraction in the XML, and the extracted CPC classification number is used for searching the patent with the same CPC classification number in the patent database, namely searching the patent under the same field. The preprocessing operation comprises the following steps: the computer text processing technology is used for carrying out word segmentation, part of speech tagging and word deactivation on words in the claims, most words in the claims can represent the technical characteristics of patents most, and therefore the words with parts of speech as nouns are selected and stored.
In step S502, the wiki english corpus is the most comprehensive database with the largest data size, the Word2Vec Word vector representation can well represent the semantic relationship between words, based on the above consideration, the Word vector database obtained by training the wiki english corpus using the Word2Vec in the present invention, and the words in the database are represented in a vector form. The nouns obtained after preprocessing are represented by word vectors searched from a word vector database.
The distance relationship between words can be embodied by calculating word vectors, the similarity obtained by the computer represents the similarity degree between words, in addition, the distance between words is used for representing the distance degree of words, and the distance between the calculated similarity and 1 is used for representing. Based on the novelty and creativity of the technical characteristics (i.e. the terms obtained after the preprocessing, and the technical characteristics are used to represent the corresponding terms in the following description) can be obtained. The specific method comprises the following steps:
(1) the modules obtained by training with the word vector database and the genim library represent the similarity between words. The creativity of the technical characteristics means that the technology has obvious advancement in the field. The invention uses the technical features of the claims to represent the technical field, and uses the minimum distance between a technical feature and the technical feature in the claim as the creativity of the technical feature. Firstly, selecting a technical feature, and then selecting the minimum distance between the technical feature and other technical features in the claims where the technical feature is located as creativity of the technical feature;
(2) the novelty of a technical feature means that the technique does not belong to the prior art. The present invention uses the claims of other patents to represent prior art, and uses the distance between technical features and technical features in other patents as relative novelty between them. Firstly, one technical feature is selected, the technical features in other patents are selected, and the distance between the two technical features is the novelty of the technical feature.
In step S503, in the process of claiming, the patent applicant selects the most creative technical feature in the patent claims as the claiming evidence, so that the creativity of the technical feature represented by the edge is used as the weight of the corresponding edge in the game tree, and the weight of the edge represents the probability of the patent applicant selecting the technical feature. When the technical features of the patents are compared with the technical features of other patents, the novelty shows the possibility of winning the technical features relative to the technical features of other patents, so the novelty between the technical features represented by edges is taken as the corresponding payment of the technical features of the former patents, the comparison result of the two patents is the state of the trade-off, the similarity between the technical features is taken as the payment of the technical features of the latter patents, and the constructed technical feature game tree is shown in fig. 6.
Assuming that patent 1 represents a user uploading patent and patent 2 represents one of potential counterparty patents, a game is played by using claim 1 in patent 1 and claim 2 in patent 2, and the technical characteristics selected in claim 1 in patent 1 are obtained by the following process according to the game result:
v(s) represents the expected payment for a certain technical feature s claimed in patent 1, where σ(s) represents the weight on the corresponding side of the technical feature s; v (s, s ') represents the payment of the applicant when the applicant of patent 1 selects technical feature s and the applicant of patent 2 selects technical feature s'; s' represents all the technical features of claim 2 in patent 2.
Calculating the expected payout of each technical feature of claim 1 in patent 1, selecting the technical feature with the largest expected payout in the claim as the most advantageous technical feature 1 in the claim for the patent applicant, and similarly, selecting the most advantageous technical feature 2 in the claim 2 in patent 2, wherein the technical feature 1 and the technical feature 2 are two technical features selected by the game in the claims 1 and 2 in patent 1 and 2.
In step S504, a game tree is constructed with patents as nodes and claims as edges, the games are performed among the patents, and the payments among the claims selected in the game result are used as patent infringement risks.
The patent text is hierarchical, the patent contains the claims, the claims contain technical characteristics, and therefore after the game tree with the claims as nodes and the technical characteristics as edges is established, the game tree with the patents as nodes and the claims as edges needs to be established. The weight of the claims represented by the edge is used as the weight of the edge, the game result between the claims represented by the edge is used as the payment of the corresponding claims, and the constructed claim game tree is shown in fig. 7.
The claims are divided into independent claims and dependent claims, the dependent claims being refinements of the independent claims, in which case protection of the independent claims is emphasized. And less critical claims will be presented than more critical claims. The invention therefore takes the type of the claims and the number of technical features contained in the claims as the weight of the claims:
in the formula
Express claims
The number of technical features involved;
represents an independent claim;
showing the dependent claims.
The result of the game between the claims is the two technical features selected in claim 7.
For example, the game is played between the patent 1 and the patent 2, and the claims selected according to the game result in the patent 1 and the patent 2 are obtained through the following processes:
v (c) represents the expected payment of a certain claim in patent 1, where σ (c) represents the weight on the corresponding side of claim c; v (c, c ') represents the payment of the patent applicant 1 when the applicant of patent 1 selects claim c and the applicant of patent 2 selects claim c'; c' represents all claims in patent 2.
Calculating the expected payment of each claim in the patent 1, selecting the claim with the largest expected payment in the patent as the claim 1 which is the most beneficial to the applicant of the patent 1 in the patent, similarly, selecting the most beneficial claim 2 in the patent 2, wherein the claims 1 and 2 are the two claims selected by the game of the patent 1 and the patent 2, and the payment of the patent 1 corresponding to the two claims is the infringement risk of the patent. The final result of the game is that each patent applicant selects the most advantageous technical features in the claims which are most advantageous to the patent applicant, and the distance between the technical features is used as the infringement risk of the patent applicant.
In step S505, the patents searched according to the CPC classification number sequentially pass through the computer to obtain the infringement risk with the patents uploaded by the user, all the results are stored in the computer storage device in a document form, and the document form is used as a detection report returned to the user, and the user can print the detection report through the printing device. Fig. 8 shows an example of an infringement risk detection report.
The general technical scheme flow of the invention is shown in figure 9.
As shown in fig. 10, an embodiment of the present invention provides a patent infringement detection system based on game theory, including:
the data acquisition and preprocessing module 1 is used for acquiring patent data, retrieving uploaded patents and preprocessing claim data in the retrieved patent data.
And the similarity relation acquisition module 4 among the technical features is connected with the data acquisition and preprocessing module 1 and is used for calling the external word vector database to calculate the similarity relation among the technical features as the novelty and creativity of the technical features.
The claim infringement risk analysis module 5 is connected with the similarity relation acquisition module among the technical features, and is used for constructing a game tree which takes the claims as nodes and the technical features as edges, wherein the claims are played, and payment among the technical features selected in the game result is used as the claim infringement risk.
And the patent infringement risk analysis module 6 is connected with the claim infringement risk analysis module 5 and is used for constructing a game tree which takes patents as nodes and claims as edges, games are carried out among the patents, and payment among the claims selected in the game result is used as the patent infringement risk.
And the infringement risk report generation module 7 is used for summarizing results and generating an infringement risk report.
The inventive and prior art process comparison is shown in table 1.
TABLE 1
The technical effects of the present invention will be described in detail with reference to experiments.
The experimental data of the present invention are patents downloaded from USPTO, wherein both patent US7645279 and patent US6652523 are valid patents, i.e. do not relate to infringement problems, and patent US6736759 is determined to be invalid patents, i.e. relate to infringement problems, because of patent US 6002982. In order to verify the effectiveness of the method proposed by the present invention, the experiments were compared with the more advanced methods in the prior art (references disclosing the method: Changyong Lee, Bomi Song, Yonggtae park. how to assign a patent in a knowledge series of analysis using dependency relationships. Tech. analysis & Strat. Manag.25(1):23-38 (2013)).
Table 2 shows the results of comparative experiments of the process of the invention with the prior art process with respect to patent US7645279 and patent US 6652523.
TABLE 2
Table 3 shows the results of comparative experiments of the process of the invention with the prior art process with respect to patent US6002982 and patent US 6736759.
TABLE 3
Wherein M is1Represents the method proposed by the invention, M2Showing the prior art described aboveMethod, as can be seen from the table, M2The end result of (1) is the overall similarity of the two patents, M1The end result of (1) is to calculate the risk of infringement according to the claims and technical characteristics selected by the method, for the experimental results of patent US7645279 and patent US6652523, M1Is less than M2Combining the fact that the two patents do not infringe, M1The result is better than M2. For the experimental results of patent US6002982 and patent US6736759, M1Risk of infringement higher than M2Combining the infringement of two patents, M1The result is better than M2. The table further analyzes the experimental course of two methods, M2Method for calculating risk of infringement, M, of technical features, claims and patents according to overall similarity1The most advantageous technical features, claims, of each of the two patents are selected as patent infringement risks. Due to M1Considering that patent examination process takes claim as unit, namely, only one claim infringes patent to infringe right is infringed, and both patent applicants choose to complain most favorably for themselves, M1To M2The accuracy is higher.
In summary, M1The method has the advantages that the characterization of the infringing object is more accurate, the expression of the real infringing scene information is more accurate, the targeted information of the claims is not lost, and M is based on the advantages1Compared with M2The reliability and the accuracy are higher.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When used in whole or in part, can be implemented in a computer program product that includes one or more computer instructions. When loaded or executed on a computer, cause the flow or functions according to embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL), or wireless (e.g., infrared, wireless, microwave, etc.)). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that includes one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (18)
1. A patent infringement detection method based on game theory is characterized by specifically comprising the following steps:
step one, data acquisition is carried out, and the acquired data is preprocessed;
step two, using the noun as the technical characteristic of the patent, and carrying out infringement risk calculation by calculating novelty and non-obviousness of the technical characteristic and games among claims and patents;
and step three, obtaining a patent infringement risk game result.
2. A patent infringement detection method based on game theory as defined in claim 1, wherein in step one, the data collection comprises: selecting a patent text as a data source; patent data of a patent and trademark office are obtained in batches based on a web crawler method.
3. A patent infringement detection method based on game theory as defined in claim 1, wherein in step one, the data preprocessing comprises: extracting claims in the patent data; performing stop word and word segmentation processing on the extracted text data; the word is vectorized using word2 vec.
4. A patent infringement detection method based on game theory as defined in claim 1, wherein in step two, the novelty and non-obvious calculation method of the technical features specifically comprises:
(1) calculating the distance by using the word vector, selecting a certain word in the claim, and calculating the shortest distance from the word to the word in the other claims as the novelty of technical characteristic payment corresponding to the word;
(2) calculating the distance by using the word vector, selecting a certain word in the claim, and calculating the shortest distance from the word to other words in the claim where the word is located as the novelty of technical characteristic payment corresponding to the word;
(3) for the payment of the claim, the payment of the technical characteristics obtained by the technical characteristic game result is taken as the payment of the claim;
(4) for the selection probability of the claim, the technical feature number contained in the claim is combined with whether the selection probability of the claim is calculated for the independent claim.
5. A patent infringement detection method based on game theory as claimed in claim 1, wherein in step two, the game between claims and patents specifically includes:
1) the node A, B is used to indicate the player who is the player's claim to play or the patent to play; the branches on the nodes represent the strategies of the participants, each strategy has a selection probability, and the payment of the participants is represented at the leaf nodes;
2) based on the analysis of the patent text, the constituent elements of the technology are taken as technical features.
6. A patent infringement detection method based on game theory as claimed in claim 5, wherein the step 1) specifically comprises:
I) when t is the technical feature F, the calculation formula of the payment function is:
wherein σiRepresenting a mixing strategy of the participant i; -i represents a participant other than participant i;
expressed in a hybrid strategy sigmaiAnd
paying by a lower participant i;
representing participant-i selection mixing strategy sigma-iTime participant i selection strategy
The payment of (2);
to represent
And
using word2vec to represent words as word vectors, and using the distance of the word vectors as a calculation result;
II) when t is claim C, the calculation of the payment function is:
7. A patent infringement detection system based on game theory and implementing the patent infringement detection method based on game theory as claimed in claim 1, wherein the patent infringement detection system based on game theory specifically comprises:
the system comprises a data acquisition and preprocessing module, a risk calculation module and a result output module;
the data acquisition and preprocessing module comprises: the risk calculation module is connected with the data source and used for selecting a data source, crawling data and processing the crawling data;
a risk calculation module: is connected with the data acquisition and preprocessing module and the result output module; novelty and non-obvious for computing technical features, gaming between claims, between patents;
a result output module: and the risk calculation module is connected with the game module and is used for outputting the payment obtained by the game result as the patent infringement risk.
8. A terminal, characterized in that the terminal implements a processor of a game theory-based patent infringement detection method according to any one of claims 1-6.
9. A computer-readable storage medium comprising instructions that, when executed on a computer, cause the computer to perform a game theory-based patent infringement detection method as defined in any one of claims 1-6.
10. Patent retrieval equipment for implementing the patent infringement detection method based on the game theory as claimed in any one of claims 1-6.
11. The game theory-based patent infringement detection method as defined in claim 1, further comprising: searching and preprocessing the collected patent data by a computer technology;
similarity obtained by using word2vec is used as a similarity relation between technical features for the patent data after searching and preprocessing, a game tree is constructed based on a patent structure and the similarity relation, and infringement risk data is obtained by calculating the technical features and the claims in the expected payment selected patent;
and summarizing the obtained infringement risk data to generate an infringement risk detection report.
12. The game theory-based patent infringement detection method as defined in claim 11, further comprising:
firstly, acquiring patent data, retrieving uploaded patents, and preprocessing claim data in the retrieved patent data;
step two, calling an external word vector database to calculate the similarity relation between the technical features as the novelty and creativity of the technical features;
step three, constructing a game tree with the claims as nodes and the technical characteristics as edges, carrying out game among the claims, and taking payment among the technical characteristics selected in the game result as a risk of infringing the claims;
step four, constructing a game tree with patents as nodes and claims as edges, carrying out game among the patents, and using payment among the claims selected in the game result as a patent infringement risk;
and step five, summarizing results and generating an infringement risk report.
13. The patent infringement detection method based on game theory as defined in claim 12, wherein in the first step, the method for collecting patent data comprises: saving the downloaded patent text full-text patent data in an XML format as a patent database;
analyzing the uploaded patent text, extracting a CPC classification number of the patent according to a label in the XML format text, and searching potential counter-party patents in a patent database according to the extracted CPC classification number;
extracting text data of uploaded patents in XML format and potential counter-party patents to obtain claim claims in patent texts, then preprocessing the extracted claim claims, and storing the preprocessed texts in a computer storage device in a document form;
the method for preprocessing the claim data in the retrieved patent data comprises the following steps: the computer text processing technology is used for carrying out word segmentation, part of speech tagging and word stop removal on words in the claims, and words with parts of speech being nouns are selected and stored in a computer storage device.
14. A game theory based patent infringement detection method as claimed in claim 12, wherein in step two, said foreign word vector database includes: using Word2Vec to train a Word vector database obtained by a wiki English corpus, wherein words in the Word vector database are expressed in a vector form; the selected nouns are represented by word vectors searched from a word vector database;
the novel and inventive method of computing technical features specifically comprises: (1) the similarity between words is represented by a module obtained by training a word vector database and a genim library, the technical features in each patent claim are selected in sequence, the technical features are selected nouns, then the value with the maximum similarity between the selected technical features and other technical features in the claim where the nouns are located is selected, and finally the distance between the value and 1 is the creativity of the technical features;
(2) the similarity between words is represented by a module obtained by training through a word vector database and a genim library, technical features in claims in two patents are sequentially selected, and the distance from the similarity of the two selected technical features to 1 is the novelty of the corresponding technical features;
(3) the calculated creativity and novelty are stored in a computer storage device in a form of a document.
15. A patent infringement detection method based on game theory as defined in claim 12, wherein in step three, creativity of technical features represented by edges is taken as weight of corresponding edges in the game tree, novelty between the technical features represented by the edges is taken as payment of corresponding former technical features, and distance from value of the novelty to 1 is taken as payment of the latter technical features; storing the calculated payment in a computer storage device in a document form;
patent 1 shows the patent of uploading, patent 2 shows one of the patents of potential opponents, claim 1 in patent 1 and claim 2 in patent 2 play the game, and the technical characteristics selected in claim 1 of patent 1 are obtained by the following processes according to the game result:
v(s) represents the expected payment for a certain technical feature s claimed in patent 1, where σ(s) represents the weight on the corresponding side of the technical feature s; v (s, s ') represents the payment of the applicant when the applicant of patent 1 selects technical feature s and the applicant of patent 2 selects technical feature s'; s' represents all the technical features of claim 2 in patent 2;
obtaining the expected payment of each technical characteristic of claim 1 in the patent 1 through the operation of a computer, and selecting the technical characteristic with the maximum expected payment in the claim as the technical characteristic 1 which is most beneficial to a patent applicant in the claim; the most advantageous technical feature 2, technical feature 1 and technical feature 2 of claim 2 in patent 2 are selected by the game in claim 1 of patent 1 and claim 2 of patent 2, and the results are stored in a computer storage device in a document form.
16. A patent infringement detection method based on game theory as defined in claim 12, wherein in step four, the weight of the claim represented by the edge is taken as the weight of the edge, and the game result between the claims represented by the edge is taken as the payment of the corresponding claim; the game result between the claims is two technical characteristics of the selected most favorable technical characteristic 1 and the most favorable technical characteristic 2;
combining the type of the claims and the number of technical features contained in the claims as the weight of the claims:
in the formula
Express claims
The number of technical features involved;
represents an independent claim;
representing the dependent claims; and stores the weights in a file form in a computer storage device.
17. Patent infringement detection method based on game theory as claimed in claim 12, characterized in that in step four, the game between patent 1 and patent 2 is played, and the claims selected according to the game result patent 1 and patent 2 are obtained through the following processes:
v (c) represents the expected payment of a certain claim in patent 1, where σ (c) represents the weight on the corresponding side of claim c; v (c, c ') represents the payment of the patent applicant 1 when the applicant of patent 1 selects claim c and the applicant of patent 2 selects claim c'; c' represents all claims in patent 2.
Calculating the expected payment of each claim in the patent 1, selecting the claim with the largest expected payment in the patent as the claim 1 which is the most beneficial to the applicant of the patent 1 in the patent, selecting the most beneficial claim 2 in the patent 2, wherein the claims 1 and 2 are the two claims selected by the game of the patent 1 and the patent 2, and the payment of the patent 1 corresponding to the two claims is the infringement risk of the patent. The calculation process is obtained by running a computer, and the infringement probability of the patent is stored on computer storage equipment in percentage form as a result;
and step five, sequentially detecting the infringement risks of potential counter-party patents and the patents uploaded by the user, storing all results in a computer storage device in a document form, returning the document as a detection report, and printing the detection report through a printing device.
18. A patent infringement detection system based on game theory for implementing the patent infringement detection method based on game theory according to any one of claims 11 to 17, wherein the patent infringement detection system based on game theory comprises:
the data acquisition and preprocessing module is used for acquiring patent data, retrieving uploaded patents and preprocessing claim data in the retrieved patent data;
the similarity relation acquisition module among the technical features is connected with the data acquisition and preprocessing module and is used for calling the similarity relation among the technical features calculated by the external word vector database to serve as the novelty and creativity of the technical features;
the claim infringement risk analysis module is connected with the similarity relation acquisition module among the technical characteristics and used for constructing a game tree which takes the claims as nodes and the technical characteristics as edges, the claims are subjected to game, and payment among the technical characteristics selected in the game result is used as the claim infringement risk;
the patent infringement risk analysis module is connected with the claim infringement risk analysis module and is used for constructing a game tree with patents as nodes and claims as edges, games are carried out among the patents, and payment among the claims selected in the game result is used as the patent infringement risk;
and the infringement risk report generation module is used for summarizing results and generating an infringement risk report.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910510958 | 2019-06-13 | ||
| CN2019105109588 | 2019-06-13 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111242494A true CN111242494A (en) | 2020-06-05 |
| CN111242494B CN111242494B (en) | 2023-04-07 |
Family
ID=70876211
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010053358.6A Active CN111242494B (en) | 2019-06-13 | 2020-01-17 | Patent infringement detection method and system based on game theory |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111242494B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115879441A (en) * | 2022-11-10 | 2023-03-31 | 中国科学技术信息研究所 | Text novelty detection method and device, electronic equipment and readable storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040158559A1 (en) * | 2002-10-17 | 2004-08-12 | Poltorak Alexander I. | Apparatus and method for identifying potential patent infringement |
| CN101296359A (en) * | 2007-04-24 | 2008-10-29 | 宋亚民 | Video program digital copyright management method based on advertisement paying |
| US20100241501A1 (en) * | 2000-11-27 | 2010-09-23 | Marshall T Thaddeus | Method and system for tracking and providing incentives for tasks and activities and other behavioral influences related to money, individuals, technology and other assets |
| CN103502969A (en) * | 2009-06-13 | 2014-01-08 | 罗莱斯塔尔有限公司 | System for sequential juxtaposition of separately recorded scenes |
| CN104199809A (en) * | 2014-04-24 | 2014-12-10 | 江苏大学 | Semantic representation method for patent text vectors |
| CN106294639A (en) * | 2016-08-01 | 2017-01-04 | 金陵科技学院 | Method is analyzed across the newly property the created anticipation of language patent based on semantic |
| CN107521501A (en) * | 2017-07-11 | 2017-12-29 | 上海蔚来汽车有限公司 | Driver assistance system decision-making technique, system based on game theory and other |
| CN109165190A (en) * | 2018-07-11 | 2019-01-08 | 南京邮电大学 | A kind of electronic data based on block chain intelligence contract deposits card method |
| CN109670989A (en) * | 2017-10-13 | 2019-04-23 | 南京畅远信息科技有限公司 | A kind of patent infringement system for prompting |
-
2020
- 2020-01-17 CN CN202010053358.6A patent/CN111242494B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100241501A1 (en) * | 2000-11-27 | 2010-09-23 | Marshall T Thaddeus | Method and system for tracking and providing incentives for tasks and activities and other behavioral influences related to money, individuals, technology and other assets |
| US20040158559A1 (en) * | 2002-10-17 | 2004-08-12 | Poltorak Alexander I. | Apparatus and method for identifying potential patent infringement |
| CN101296359A (en) * | 2007-04-24 | 2008-10-29 | 宋亚民 | Video program digital copyright management method based on advertisement paying |
| CN103502969A (en) * | 2009-06-13 | 2014-01-08 | 罗莱斯塔尔有限公司 | System for sequential juxtaposition of separately recorded scenes |
| CN104199809A (en) * | 2014-04-24 | 2014-12-10 | 江苏大学 | Semantic representation method for patent text vectors |
| CN106294639A (en) * | 2016-08-01 | 2017-01-04 | 金陵科技学院 | Method is analyzed across the newly property the created anticipation of language patent based on semantic |
| CN107521501A (en) * | 2017-07-11 | 2017-12-29 | 上海蔚来汽车有限公司 | Driver assistance system decision-making technique, system based on game theory and other |
| CN109670989A (en) * | 2017-10-13 | 2019-04-23 | 南京畅远信息科技有限公司 | A kind of patent infringement system for prompting |
| CN109165190A (en) * | 2018-07-11 | 2019-01-08 | 南京邮电大学 | A kind of electronic data based on block chain intelligence contract deposits card method |
Non-Patent Citations (4)
| Title |
|---|
| HYUNSEOK PARK 等: "Identifying patent infringement using SAO based semantic technological similarities", 《SCIENTOMETRICS》 * |
| ZAOLI YANG 等: "Analysis of intellectual property cooperation behavior and its simulation under two types of scenarios using evolutionary game theory", 《COMPUTERS & INDUSTRIAL ENGINEERING》 * |
| 王真: "专利等同侵权判定研究——兼评澳诺（中国）制药有限公司V.湖北午时药业股份有限公司、王军社案", 《中国优秀硕士学位论文全文数据库 社会科学Ⅰ辑》 * |
| 赵联宁 等: "专利权保护的博弈分析", 《电子知识产权》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115879441A (en) * | 2022-11-10 | 2023-03-31 | 中国科学技术信息研究所 | Text novelty detection method and device, electronic equipment and readable storage medium |
| CN115879441B (en) * | 2022-11-10 | 2024-04-12 | 中国科学技术信息研究所 | Text novelty detection method and device, electronic equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111242494B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108073568B (en) | Keyword extraction method and device | |
| WO2019218514A1 (en) | Method for extracting webpage target information, device, and storage medium | |
| CN103914494B (en) | Method and system for identifying identity of microblog user | |
| US10169331B2 (en) | Text mining for automatically determining semantic relatedness | |
| CN110532352B (en) | Text duplication checking method and device, computer readable storage medium and electronic equipment | |
| CN107491436A (en) | A kind of recognition methods of title party and device, server, storage medium | |
| CN107644010A (en) | A kind of Text similarity computing method and device | |
| CN107704512A (en) | Financial product based on social data recommends method, electronic installation and medium | |
| CN110347790B (en) | Text duplicate checking method, device and equipment based on attention mechanism and storage medium | |
| CN109271524B (en) | Entity linking method in knowledge base question-answering system | |
| CN112885478B (en) | Medical document retrieval method, medical document retrieval device, electronic device and storage medium | |
| CN110309234A (en) | A kind of client of knowledge based map holds position method for early warning, device and storage medium | |
| CN110737821B (en) | Similar event query method, device, storage medium and terminal equipment | |
| CN110909540B (en) | Method and device for identifying new words of short message spam and electronic equipment | |
| CN114265932A (en) | Event context generation method and system integrating deep semantic relation classification | |
| CN105205163A (en) | Incremental learning multi-level binary-classification method of scientific news | |
| CN111158692B (en) | Ordering method, ordering system and storage medium for intelligent contract function similarity | |
| CN116166806A (en) | False shadow evaluation detection method based on graph attention neural network | |
| CN115618866A (en) | Method and system for paragraph identification and subject extraction of engineering project bid document | |
| CN108717459A (en) | A kind of mobile application defect positioning method of user oriented comment information | |
| CN111242494B (en) | Patent infringement detection method and system based on game theory | |
| CN114328800A (en) | Text processing method and device, electronic equipment and computer readable storage medium | |
| CN107515928A (en) | A kind of method, apparatus, server, storage medium for judging assets price tendency | |
| CN109062905A (en) | A kind of barrage value of edition evaluation method, device, equipment and medium | |
| CN113448918B (en) | Enterprise scientific research result management method, management platform, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |