Analysis apparatus

Abstract

To solve difficulty in suppressing costs required when some legal measure should be taken against copyright infringement.SOLUTION: An analysis apparatus according to the present invention has an estimation unit for, in response to input of a similarity calculated between a copyrighted product and a target product and information of a case as information corresponding to a content of a copyright infringement case, estimating a win ratio of a possible litigation and damages thereof, a generation unit for confirming cost performance required if the litigation is carried out based on the estimation result of the estimation unit to generate a proposal corresponding to the confirmation result, and an output unit for outputting the proposal generated by the generation unit.SELECTED DRAWING: Figure 12

Description

[Technical Field]

[0001] The present invention relates to an analysis device, an analysis method, and a program. [Background technology]

[0002] 2. Description of the Related Art Techniques used to protect copyrights and the like are known.

[0003] For example, Patent Document 1 discloses an intellectual property rights management system having a predetermined configuration. According to Patent Document 1, when the system collects infringement information, it requests votes regarding legal action from idea holder terminal devices, investor terminal devices, expert terminal devices, etc. The system then tallies the received votes and makes a decision regarding legal action against the infringement. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2002-133087 Summary of the Invention [Problem to be solved by the invention]

[0005] When an author discovers an infringement of copyright, such as a copyright property right, and seeks advice from an expert using the method described in Patent Document 1, the consultation can be costly. As a result, costs can be incurred even if a lawsuit is not filed, creating the problem that it can be difficult to control the costs involved in deciding whether or not to take legal action against copyright infringement.

[0006] Therefore, one object of the present invention is to provide an analysis device, an analysis method, and a program that can solve the above-mentioned problems. [Means for solving the problem]

[0007] In order to achieve this object, an analytical device according to one embodiment of the present disclosure includes: an estimation unit that estimates the probability of winning and the amount of compensation in a lawsuit based on the input of the similarity calculated based on the copyrighted work and the comparison work and case information that is information based on the content of the copyright infringement case; a generation unit that confirms the cost-effectiveness of a lawsuit based on the estimation result by the estimation unit and generates a proposal based on the confirmation result; an output unit that outputs the proposal generated by the generation unit; have The structure is as follows.

[0008] In addition, an analysis method according to another aspect of the present disclosure includes: The information processing device The system estimates the probability of winning and the amount of compensation in a lawsuit based on the input of the similarity calculated between the copyrighted work and the comparison work, and case information that corresponds to the content of the copyright infringement case. The cost-effectiveness of taking legal action based on the estimated results is confirmed, and proposals are generated based on the confirmation results. Print the generated suggestions The structure is as follows.

[0009] Furthermore, a program according to another aspect of the present disclosure includes: In the information processing device, The system estimates the probability of winning and the amount of compensation in a lawsuit based on the input of the similarity calculated between the copyrighted work and the comparison work, and case information that corresponds to the content of the copyright infringement case. The cost-effectiveness of taking legal action based on the estimated results is confirmed, and proposals are generated based on the confirmation results. Print the generated suggestions It is a program for realizing the processing. [Effects of the Invention]

[0010] According to the above-mentioned configurations, it is possible to reduce the cost involved in determining whether or not to take legal action against copyright infringement. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 illustrates an example of the configuration of an analysis system. [Figure 2] FIG. 2 is a block diagram illustrating an example of the configuration of a learning device. [Figure 3] FIG. 10 is a diagram illustrating an example of processing when learning a first model. [Figure 4] FIG. 10 is a diagram illustrating an example of processing when a second model is learned. [Figure 5] FIG. 2 is a block diagram illustrating an example of the configuration of an analysis device. [Figure 6] FIG. 10 is a diagram illustrating an example of generating a proposal. [Figure 7] FIG. 10 is a diagram illustrating an example of analysis processing. [Figure 8] 10 is a flowchart illustrating an example of the operation of the analysis device. [Figure 9] FIG. 10 is a block diagram showing another example configuration of the learning device. [Figure 10] FIG. 10 is a block diagram showing another example of the configuration of the analysis device. [Figure 11] FIG. 10 is a diagram illustrating an example of a hardware configuration of an analysis device according to a second embodiment of the present disclosure. [Figure 12] FIG. 2 is a block diagram illustrating an example of the configuration of an analysis device. [Figure 13] 10 is a flowchart illustrating an example of the operation of the analysis device. DETAILED DESCRIPTION OF THE INVENTION

[0012] [First embodiment] A first embodiment of the present invention will be described with reference to FIGS. 1 to 10. FIG. 1 is a diagram illustrating an example of the configuration of an analysis system 100. FIG. 2 is a block diagram illustrating an example of the configuration of a learning device 200. FIG. 3 is a diagram illustrating an example of a process for learning a first model. FIG. 4 is a diagram illustrating an example of a process for learning a second model. FIG. 5 is a block diagram illustrating an example of the configuration of an analysis device 300. FIG. 6 is a diagram illustrating an example of generating a proposal. FIG. 7 is a diagram illustrating an example of an analysis process. FIG. 8 is a flowchart illustrating an example of the operation of the analysis device. FIG. 9 is a block diagram illustrating another example of the configuration of the learning device 200. FIG. 10 is a block diagram illustrating another example of the configuration of the analysis device 300. Note that in the present disclosure, the drawings may be associated with one or more of the embodiments.

[0013] In a first embodiment of the present disclosure, as shown in FIG. 1, an analysis system 100 is described that outputs a predetermined recommendation, such as whether or not to consult with a lawyer regarding copyright infringement, in response to input of a copyrighted work to be analyzed. As described below, the analysis system 100 acquires information about the copyrighted work to be analyzed and information about a comparison object to be compared with the copyrighted work. The analysis system 100 then calculates a similarity indicating the degree of similarity between the copyrighted work to be analyzed and the comparison object. The analysis system 100 then inputs the calculated similarity and separately acquired case information, such as the amount of damages, into a pre-trained first model to estimate the probability of winning in a lawsuit and the amount of compensation, such as damages. The analysis system 100 also inputs the estimated results into a pre-trained second model to estimate the costs of litigation and confirm the cost-effectiveness. The analysis system 100 then outputs a recommendation based on the results of the cost-effectiveness check. For example, as described above, analysis system 100 performs two-stage processing consisting of a first process of estimating the amount of compensation based on information about the copyrighted work being analyzed, and a second process of generating a proposal based on the results of cost-effectiveness confirmation determined based on the results of the first process. Note that analysis system 100 may generate a proposal indicating whether or not to go to court instead of or in addition to the proposals exemplified above.

[0014] In this disclosure, the analysis system 100 analyzes copyrighted works such as illustrations and images as an example of copyrighted works. However, the analysis system 100 may be configured to analyze copyrighted works other than those exemplified in this disclosure, such as music and literary works. The analysis system 100 may also be configured to calculate the similarity between the copyrighted work to be analyzed and the comparison object using a method appropriate for the type of copyrighted work to be analyzed. In this case, the analysis system 100 may calculate the similarity between the copyrighted work and the comparison object using any method. For example, the analysis system 100 may calculate the similarity by comparing feature points or feature quantities extracted from images, or may calculate the similarity between sentences by comparing vector values ​​that can be calculated by performing natural language processing on the sentences. The analysis system 100 may also calculate the similarity using a method other than those exemplified above.

[0015] In addition, in this disclosure, case information refers to information corresponding to the content of a copyright infringement case in which a specified act, such as copying, is performed without the permission of the author who created the copyrighted work being analyzed. For example, case information includes information corresponding to the content of the infringement, such as where and how the copyrighted work and the comparison material are used, such as whether the work is sold as daily necessities or food, whether it is used in design sales or advertising media, and information indicating the amount of damages caused by the use of the comparison material. Case information may also include information other than the above examples.

[0016] FIG. 1 shows an example configuration of analysis system 100. Referring to FIG. 1, analysis system 100 includes a learning device 200 that learns a first model and a second model, and an analysis device 300 that outputs predetermined suggestions in response to input of a work to be analyzed. As shown in FIG. 1, learning device 200 and analysis device 300 can be connected via a wired or wireless connection so that they can communicate with each other. Information exchange between learning device 200 and analysis device 300 may be performed via any recording medium or the like.

[0017] The configuration of analysis system 100 is not limited to the example shown in Fig. 1. For example, analysis system 100 may be composed of a single information processing device that has the functions of learning device 200 and analysis device 300. Analysis system 100 may also be composed of a device that performs analysis according to a first model and a device that performs analysis according to a second model. The configuration of analysis system 100 may be other than the example shown above.

[0018] The learning device 200 is an information processing device that learns a first model based on collected legal precedents and the like, and learns a second model based on collected past cost information and the like. FIG. 2 shows an example configuration of the learning device 200. Referring to FIG. 2, the learning device 200 has, as main components, for example, an operation input unit 210, a screen display unit 220, a communication interface unit 230, a storage unit 240, and a calculation processing unit 250.

[0019] 2 illustrates an example in which the functions of learning device 200 are realized using a single information processing device. However, at least some of the functions of learning device 200 may be realized using multiple information processing devices, for example, on the cloud. For example, learning device 200 may be composed of an information processing device that learns a first model and an information processing device that learns a second model. Furthermore, learning device 200 may not include some of the components exemplified above, such as not having operation input unit 210 or screen display unit 220, or may have components other than those exemplified above.

[0020] Operation input unit 210 is made up of operation input devices such as a keyboard, a mouse, etc. Operation input unit 210 detects operations of the operator operating learning device 200 and outputs the operations to calculation processing unit 250.

[0021] The screen display unit 220 is composed of a screen display device such as a liquid crystal display, an organic EL (electro-luminescence) display, etc. The screen display unit 220 can display various information stored in the storage unit 240 on the screen in response to instructions from the arithmetic processing unit 250.

[0022] The communication interface unit 230 is composed of a data communication circuit, etc. The communication interface unit 230 performs data communication with an external device such as the analysis device 300 connected via a communication line.

[0023] The storage unit 240 is a storage device such as a hard disk or memory. The storage unit 240 stores processing information and programs 244 required for various processes in the arithmetic processing unit 250. The programs 244 are read into the arithmetic processing unit 250 and executed to realize various processing units. The programs 244 are read in advance from an external device or recording medium via a data input / output function such as the communication interface unit 230, and are stored in the storage unit 240. Main information stored in the storage unit 240 includes, for example, a case law database 241, a cost database 242, and model information 243.

[0024] The legal precedent database 241 includes information on past legal precedents and precedents regarding copyright. For example, the legal precedent database 241 stores at least some of the following: information indicating legal outcomes such as victory, defeat, and settlement; information indicating the amount of damages caused by infringement; information indicating the details of copyright infringement such as information about the copyrighted work and the other party's work and information about the infringing act; information indicating the amount of compensation such as damages and the amount of settlement money; information indicating whether a business suspension order has been issued, information indicating the suspension period, and information indicating whether an appeal or a final appeal has been filed. The legal precedent database 241 is updated as the legal precedent collection unit 251 collects legal precedents and precedents.

[0025] Note that the case law database 241 may not include information extracted from legal precedents, but may include only information extracted from legal precedents. Furthermore, the case law database 241 may include information corresponding to legal precedents and legal precedents in multiple countries. In this case, the case law database 241 may have information corresponding to legal precedents and legal precedents for each country.

[0026] The expense database 242 includes information indicating various expenses such as court costs and attorney fees incurred in court proceedings in accordance with past legal precedents and precedents regarding copyright. The expense database 242 may include information indicating various expenses as well as any information corresponding to each case, such as a lawsuit. For example, the expense database 242 may store information indicating various expenses in association with the legal precedents and precedents in the legal precedent database 241. The expense database 242 is updated as the expense information collection unit 252 collects information.

[0027] Like the case precedent database 241, the expense database 242 may include only information indicating various expenses for cases that were taken to the Supreme Court, or may include information indicating various expenses including those for cases that were not taken to the Supreme Court. The expense database 242 may also include information indicating the total amount of various expenses incurred in cases that were taken to the Supreme Court or a high court, or may include information indicating various expenses for each trial. The expense database 242 may also include information indicating various expenses incurred in trials in multiple countries. In this case, the expense database 242 may have information indicating various expenses for each country.

[0028] The model information 243 includes information about trained models, such as parameters such as weight values ​​in the first model and the second model, which are large-scale language models, etc. The model information 243 is updated in response to, for example, the first model training unit 254 performing machine learning using training data generated in accordance with information contained in the case law database 241. The model information 243 is also updated in response to, for example, the second model training unit 255 performing machine learning using training data generated in accordance with information contained in the expense database 242, etc.

[0029] The arithmetic processing unit 250 has an arithmetic device such as a CPU (Central Processing Unit) and its peripheral circuits. The arithmetic processing unit 250 reads and executes a program 244 from the storage unit 240, thereby realizing various processing functions by causing the above hardware and the program 244 to work together. Major processing units realized by the arithmetic processing unit 250 include, for example, a case law collection unit 251, a cost information collection unit 252, a learning data generation unit 253, a first model learning unit 254, a second model learning unit 255, and an output unit 256.

[0030] In addition, the arithmetic processing unit 250 may have a GPU (Graphics Processing Unit), a DSP (Digital Signal Processor), an MPU (Micro Processing Unit), an FPU (Floating point number Processing Unit), a PPU (Physics Processing Unit), a TPU (Tensor Processing Unit), a quantum processor, a microcontroller, or a combination thereof, instead of the above-mentioned CPU.

[0031] The precedent collection unit 251 collects past precedents and legal precedents regarding copyright. For example, the judgment collection unit 251 can collect past precedents and legal precedents regarding copyright in response to collecting information from an external device via the communication interface unit 230 or accepting input of information using the operation input unit 210. In addition, the precedent collection unit 251 stores the collected precedents and legal precedents in the precedent database 241.

[0032] The case law collection unit 251 may extract a portion of the collected information and store the extracted information in the case law database 241. For example, the case law collection unit 251 can extract at least a portion of the following from the collected case law, etc.: information indicating court results such as victory, defeat, or settlement; information indicating the amount of damages caused by infringement; information indicating the details of copyright infringement such as information about the copyrighted work or the other party's work and information about the infringing act; information indicating the amount of compensation such as damages or the amount of settlement money; information indicating whether a business suspension order has been issued, information indicating the suspension period, etc.; and information indicating whether an appeal or a final appeal has been filed. The case law collection unit 251 may extract any information other than the above examples from the case law, etc.

[0033] The precedent collection unit 251 may also be configured to collect only precedents without collecting legal precedents. The precedent collection unit 251 may also collect legal precedents and court cases from multiple countries. In this case, the precedent collection unit 251 can store the collected legal precedents and court cases in the legal precedent database 241 for each country.

[0034] The expense information collection unit 252 collects information indicating various expenses, such as court costs and attorney's fees, required for a trial. The expense information collection unit 252 may collect information indicating various expenses, such as court costs and attorney's fees, required for a trial corresponding to the precedents and legal precedents collected by the precedent collection unit 251. In this case, the expense information collection unit 252 may be configured to calculate the total amount of various expenses required for each trial, such as the first instance and the appeal. For example, the expense information collection unit 252 may collect information indicating various expenses by collecting information from an external device via the communication interface unit 230 or by accepting information input using the operation input unit 210. In addition, the expense information collection unit 252 stores the collected information indicating various expenses in the expense database 242. In this case, the expense information collection unit 252 may store the information indicating various expenses in association with information on the corresponding precedents in the legal precedent database 241.

[0035] The cost information collection unit 252 may collect information indicating various costs as well as any other information corresponding to each case, such as a lawsuit. The cost information collection unit 252 may also be configured to collect only information indicating various costs corresponding to cases that have been contested all the way to the Supreme Court. The cost information collection unit 252 may also collect information indicating various costs from multiple countries. In this case, the cost information collection unit 252 can store the collected information indicating various costs for each country in the cost database 242.

[0036] The learning data generation unit 253 generates learning data to be used when performing machine learning, using information stored in the storage unit 240. For example, the learning data generation unit 253 can generate learning data to be used when performing learning such as fine tuning on a large language model (LLM).

[0037] For example, the training data generation unit 253 can generate training data to be used when training the first model using at least a portion of the information stored in the legal precedent database 241. For example, the training data generation unit 253 extracts information indicating the details of copyright infringement, such as information indicating the amount of damages and information about the infringement, from the legal precedent database 241. Then, the training data generation unit 253 generates training data by, for example, assigning labels, such as court results (e.g., win / loss) and amounts of compensation, to each piece of extracted information. Note that the training data generation unit 253 may generate training data according to the information contained in the legal precedent database 241 using a method other than the above example. For example, the training data generation unit 253 may generate training data by calculating similarities from information about the copyrighted work and the other party's copyrighted work contained in the legal precedent database 241 and labeling the extracted information and the calculated similarities. The training data generation unit 253 may generate any training data other than the above example according to the legal precedent database 241.

[0038] Furthermore, the training data generation unit 253 can generate training data used in training the second model using at least the information stored in the expense database 242. The training data generation unit 253 may generate training data using the information stored in the legal precedent database 241 and the information stored in the expense database 242. For example, the training data generation unit 253 extracts information indicating various expenses from the expense database 242. The training data generation unit 253 then generates training data by attaching labels indicating various expenses to court results such as win / loss and amounts of compensation. The training data generation unit 253 may also generate training data by attaching labels indicating various expenses to arbitrary information such as court results such as win / loss, amounts of compensation, and other information indicating the details of copyright infringement. Note that the training data generation unit 253 may generate training data based at least on the information contained in the expense database 242 using a method other than the above examples.

[0039] As described above, there are cases where information for each country is stored in the legal precedent database 241 and the expense database 242. In this case, the learning data generation unit 253 may generate learning data for each country.

[0040] The first model training unit 254 trains the first model using the training data generated by the training data generation unit 253 and used to train the first model. For example, the first model training unit 254 can perform a training process such as fine-tuning on a predetermined large-scale language model using the training data. As an example, the first model training unit 254 can train a model using the training data so that it can accurately estimate the win rate, the amount of compensation, etc., in response to inputs such as the details of the infringement and the amount of damages. The first model training unit 254 may also train a model so that it can accurately estimate in response to inputs such as the details of the infringement, the amount of damages, and the similarity. Furthermore, the first model training unit 254 can update information corresponding to the first model among the information included in the model information 243 in response to the training results.

[0041] If the learning data generation unit 253 generates learning data for each country, the first model learning unit 254 may be configured to learn the first model for each country using the corresponding learning data. In this case, the first model learning unit 254 may store information according to the learning results as model information 243 for each country.

[0042] The second model training unit 255 trains the second model using the training data generated by the training data generation unit 253 and used to train the second model. For example, the second model training unit 255 can use the training data to perform training processes such as fine-tuning on a predetermined large-scale language model. As an example, the second model training unit 255 can use the training data to train a model so that it can accurately estimate various expenses such as legal costs based on inputs such as the win rate and the amount of compensation. The second model training unit 255 can also use the training data to train a model so that it can accurately estimate various expenses such as legal costs based on inputs such as the win rate, the amount of compensation, and other details of the infringement. Furthermore, the second model training unit 255 can compare the estimated expenses with the input amount of compensation, etc., to confirm cost-effectiveness and accurately make suggestions based on the confirmation results. For example, the second model learning unit 255 may learn the model so as to recommend consulting a lawyer when the expected value calculated from the winning rate and the compensation amount exceeds various costs. Note that the second model learning unit 255 may also perform learning other than the above examples. Furthermore, the second model learning unit 255 can update the information corresponding to the second model among the information included in the model information 243 according to the learning results.

[0043] If the learning data generation unit 253 generates learning data for each country, the second model learning unit 255 may be configured to learn the second model for each country using the corresponding learning data. In this case, the second model learning unit 255 may store information according to the learning results as model information 243 for each country.

[0044] The output unit 256 outputs the model information 243 to an external device such as the analysis device 300. In addition to the model information 243, the output unit 256 may output at least a portion of the information stored in the case law database 241, the expense database 242, etc. to the external device such as the analysis device 300.

[0045] The above is an example configuration of learning device 200. In this way, learning device 200 learns a first model, such as a large-scale language model, using learning data generated from information stored in case law database 241 (see FIG. 3). Furthermore, learning device 200 learns a second model, such as a large-scale language model, using learning data generated from information that includes at least information stored in expense database 242, as shown in FIG. 4.

[0046] Analysis device 300 is an information processing device that generates and outputs a predetermined proposal in response to an input such as a copyrighted work, using the first model and the second model learned by learning device 200. FIG. 5 shows an example configuration of analysis device 300. Referring to FIG. 5, analysis device 300 has, as main components, for example, an operation input unit 310, a screen display unit 320, a communication interface unit 330, a storage unit 340, and a calculation processing unit 350.

[0047] 5 illustrates an example in which the functions of the analysis device 300 are realized using one information processing device. However, at least some of the functions of the analysis device 300 may be realized using multiple information processing devices, for example, on the cloud. For example, the analysis device 300 may be composed of an information processing device that performs estimation using a first model and an information processing device that generates proposals using a second model. Furthermore, the analysis device 300 may not include some of the components exemplified above, such as not having the operation input unit 310 or the screen display unit 320, or may have components other than those exemplified above.

[0048] The configurations of the operation input unit 310, the screen display unit 320, and the communication interface unit 330 may be similar to the operation input unit 210, the screen display unit 220, and the communication interface unit 230 that the learning device 200 has.

[0049] The storage unit 340 is a storage device such as a hard disk or memory. The storage unit 340 stores processing information and a program 342 required for various processes in the arithmetic processing unit 350. The program 342 is read into the arithmetic processing unit 350 and executed to realize various processing units. The program 342 is read in advance from an external device or recording medium via a data input / output function such as the communication interface unit 330, and is stored in the storage unit 340. Main information stored in the storage unit 340 includes, for example, trained model information 341.

[0050] The trained model information 341 includes information about the first model and the second model trained in the training device 200. The trained model information 341 is acquired in advance from the training device 200 via the communication interface unit 330 or the like, and is stored in the storage unit 340.

[0051] The arithmetic processing unit 350 has an arithmetic device such as a CPU and its peripheral circuits. The arithmetic processing unit 350 reads and executes a program 342 from the storage unit 340, thereby causing the above hardware and the program 342 to work together to realize various processing units. Major processing units realized by the arithmetic processing unit 350 include, for example, a copyrighted work information acquisition unit 351, a comparison object information acquisition unit 352, a similarity calculation unit 353, a case information acquisition unit 354, a win rate / compensation amount estimation unit 355, a proposal generation unit 356, and an output unit 357. Note that the arithmetic processing unit 350 may have a GPU or the like instead of a CPU, similar to the arithmetic processing unit 250 described above.

[0052] The copyrighted work information acquisition unit 351 acquires information about the copyrighted work to be analyzed, such as an illustration. For example, the copyrighted work information acquisition unit 351 may acquire information about the copyrighted work to be analyzed by accepting input of information using the operation input unit 310, accepting information from an external device via the communication interface unit 330, or the like.

[0053] The comparison object information acquisition unit 352 acquires information about a comparison object, such as an illustration, to be compared with the work to be analyzed. In other words, the comparison object information acquisition unit 352 acquires information about an illustration or the like that is suspected of infringing copyright. For example, the comparison object information acquisition unit 352 may acquire information about the comparison object by accepting input of information using the operation input unit 310, by accepting information from an external device via the communication interface unit 330, or the like.

[0054] The similarity calculation unit 353 calculates a similarity, which is a value indicating how similar the copyrighted work and the comparison object are, based on the copyrighted work acquired by the copyrighted work information acquisition unit 351 and the comparison object acquired by the comparison object information acquisition unit 352. The similarity calculation unit 353 may calculate the similarity using any means.

[0055] For example, the similarity calculation unit 353 extracts feature points from the copyrighted work using any means and calculates feature amounts based on the extracted feature points. Similarly, the similarity calculation unit 353 extracts feature points from the comparison object and calculates feature amounts based on the extracted feature points. Then, the similarity calculation unit 353 calculates the similarity by calculating the distance between the feature amounts calculated from the copyrighted work and the feature amounts calculated from the comparison object. For example, as described above, the similarity calculation unit 353 can calculate the similarity by comparing the copyrighted work and the comparison object. Note that the similarity calculation unit 353 may calculate the similarity between the copyrighted work and the comparison object using a method other than the above examples. For example, the similarity calculation unit 353 may calculate the similarity based on any aspect, such as color, shape, or number, or may calculate the similarity by inputting the copyrighted work and the comparison object into a pre-trained model.

[0056] The case information acquisition unit 354 acquires case information such as information indicating the amount of damages caused by the comparison object, information according to the details of the infringement, etc. For example, the case information acquisition unit 354 may acquire the above-mentioned case information by accepting input of information using the operation input unit 310, by accepting information from an external device via the communication interface unit 330, etc.

[0057] For example, the case information acquisition unit 354 can acquire information indicating the amount of damages incurred by the sale of the comparison item, etc., in response to input to the operation input unit 310, etc. Here, the amount of damages may include the amount of damages calculated by multiplying the profit per unit by the quantity that the copyright holder can actually sell, as well as the amount of license fees depending on the number of the comparison item that is an infringing product transferred, etc.

[0058] Furthermore, the case information acquisition unit 354 can acquire, as case information, information according to the details of the infringing act, such as where and how the copyrighted work or comparable material is used, such as whether it is sold as daily necessities or food, whether it is used in design sales or advertising media, etc. The case information acquisition unit 354 may acquire information according to the details of the infringing act, such as those exemplified above, by accepting selection of a category corresponding to the case from among a plurality of predetermined categories using the operation input unit 310 or the like.

[0059] The case information acquisition unit 354 may acquire information by estimating part of the information, such as estimating the amount of damages based on the details of the infringement. In this case, the case information acquisition unit 354 may make the above estimation using any method, such as estimating the amount of damages based on inputting the details of the infringement into a pre-trained model. The case information acquisition unit 354 may also make estimations other than those exemplified above.

[0060] The win rate / compensation amount estimation unit 355 estimates the win rate and the amount of compensation in response to inputting into the first model the case information acquired by the case information acquisition unit 354, the similarity calculated by the similarity calculation unit 353, and the like. For example, the win rate / compensation amount estimation unit 355 can estimate the win rate and the amount of compensation in response to inputting into the first model the details of the infringement act and the amount of damages acquired by the case information acquisition unit 354, and the similarity calculated by the similarity calculation unit 353, and the like.

[0061] The proposal generation unit 356 generates a predetermined proposal indicating whether or not to recommend consulting a lawyer, etc., in response to inputting the estimation results, etc., by the win rate / compensation amount estimation unit 355 into the second model. For example, the proposal generation unit 356 estimates various expenses such as legal costs and checks cost-effectiveness in response to inputting the estimation results, etc., by the win rate / compensation amount estimation unit 355 into the second model. Thereafter, the proposal generation unit 356 generates a proposal in response to the confirmation results of cost-effectiveness, etc.

[0062] For example, the proposal generation unit 356 estimates various expenses, such as legal costs, by inputting the win rate and compensation amount estimated by the win rate / compensation amount estimation unit 355, as well as at least a portion of the case information acquired by the case information acquisition unit 354, into the second model. At this time, the proposal generation unit 356 may estimate the expected value of various expenses according to the probability of an appeal or a final appeal and the associated costs. The proposal generation unit 356 also confirms cost-effectiveness by comparing the estimated various expenses with the expected value calculated from the win rate and compensation amount estimated by the win rate / compensation amount estimation unit 355. The proposal generation unit 356 then generates a proposal based on the confirmed results. For example, as shown in FIG. 6, the proposal generation unit 356 generates a proposal recommending consulting a lawyer when the calculated expected value exceeds the estimated various expenses. On the other hand, the proposal generation unit 356 generates a proposal not recommending consulting a lawyer when the calculated expected value is equal to or less than the estimated various expenses. The proposal generating unit 356 may be configured to generate a proposal recommending consultation with a lawyer when the calculated expected value exceeds the estimated various costs by a predetermined value or more.

[0063] The output unit 357 outputs the proposal generated by the proposal generation unit 356. For example, the output unit 357 may display the proposal generated by the proposal generation unit 356 on the screen display unit 320 or transmit it to an external device via the communication interface unit 330.

[0064] The output unit 357 may output the winning rate and compensation amount estimated by the winning rate / compensation amount estimation unit 355, an expected value that can be calculated based on the winning rate and compensation amount, various estimated costs, a value indicating cost-effectiveness, and other arbitrary information, together with the proposal generated by the proposal generation unit 356. In other words, the output unit 357 can output information that serves as the basis for the proposal, such as the estimated winning rate, compensation amount, and value indicating cost-effectiveness, together with the proposal generated by the proposal generation unit 356.

[0065] The above is an example configuration of the analysis device 300. In this way, the analysis device 300 can perform two-stage processing consisting of a first process of making an estimation in response to inputting the case information acquired by the case information acquisition unit 354, the similarity calculated by the similarity calculation unit 353, and the like into a first model, and a second process of generating a predetermined proposal in response to inputting the result of the first process, and the like into a second model (see FIG. 7 ).

[0066] Next, an example of the operation of the analysis device 300 will be described with reference to Fig. 8. Fig. 8 is a flowchart showing an example of the operation of the analysis device 300. Referring to Fig. 8, the copyrighted work information acquisition unit 351 acquires information about a copyrighted work, such as an illustration, to be analyzed. Furthermore, the comparison object information acquisition unit 352 acquires information about a comparison object, such as an illustration, to be compared with the copyrighted work to be analyzed. Furthermore, the case information acquisition unit 354 acquires case information indicating the amount of damage caused by the comparison object, etc. As described above, for example, the analysis device 300 acquires information about the copyrighted work to be analyzed, the comparison object, the amount of damage, etc. (step S101).

[0067] The similarity calculation unit 353 calculates a similarity, which is a value indicating how similar the work and the comparison object are, based on the work acquired by the work information acquisition unit 351 and the comparison object acquired by the comparison object information acquisition unit 352 (step S102). The similarity calculation unit 353 may calculate the similarity using any means.

[0068] The win rate / compensation amount estimation unit 355 estimates the win rate and the amount of compensation such as damages by inputting the case information acquired by the case information acquisition unit 354, the similarity calculated by the similarity calculation unit 353, and the like into the first model (step S103). For example, the win rate / compensation amount estimation unit 355 can estimate the win rate and the amount of compensation by inputting the case information acquired by the case information acquisition unit 354 and the similarity calculated by the similarity calculation unit 353 into the first model, and the like.

[0069] The proposal generation unit 356 generates a predetermined proposal indicating whether or not to recommend consulting a lawyer, etc., in response to inputting the estimation results, etc., by the win rate / compensation amount estimation unit 355 into the second model (step S104). For example, the proposal generation unit 356 estimates various expenses, such as legal costs, and checks the cost-effectiveness in response to inputting the estimation results, etc., by the win rate / compensation amount estimation unit 355 into the second model. Thereafter, the analysis system 100 generates a proposal in response to the results of the cost-effectiveness check.

[0070] The output unit 357 outputs the proposal generated by the proposal generation unit 356 (step S105). For example, the output unit 357 may display the proposal generated by the proposal generation unit 356 on the screen display unit 320 or transmit the proposal to an external device via the communication interface unit 330.

[0071] The above is an example of the operation of the analysis device 300.

[0072] As described above, the analysis device 300 includes a win rate / compensation amount estimation unit 355, a proposal generation unit 356, and an output unit 357. With this configuration, the proposal generation unit 356 can generate a proposal based on the results of a cost-effectiveness check based on the estimation results from the win rate / compensation amount estimation unit 355 and the estimated various expenses. Furthermore, the output unit 357 can output the proposal generated by the proposal generation unit 356. As a result, copyright holders and others can decide whether to take legal action or consult with a lawyer based on the output proposal. This reduces the risk of consultations that do not lead to legal action, thereby reducing costs.

[0073] The configurations of the learning device 200 and the analysis device 300 are not limited to those illustrated in Figures 2 and 5. For example, Figure 9 shows another example configuration of the learning device 200. Referring to Figure 9, the arithmetic processing unit 250 of the learning device 200 can have a relearning unit 257 in addition to the configuration illustrated in Figure 2 by reading and executing program 244.

[0074] The re-learning unit 257 re-learns at least one of the first model and the second model in accordance with information indicating the results according to the output by the analysis device 300. For example, the re-learning unit 257 acquires information indicating whether or not a lawyer was actually consulted in accordance with the proposal output by the analysis device 300. The re-learning unit 257 can re-learn at least the second model in accordance with the acquired information. For example, the re-learning unit 257 can re-learn the second model so as to make proposals that are as close to actual behavior as possible. Note that the re-learning unit 257 may re-learn the first model together with the second model.

[0075] 10 shows another example configuration of the analysis apparatus 300. Referring to Fig. 10, the calculation processing unit 350 of the analysis apparatus 300 can have a contrast object information search unit 358 in addition to the configuration exemplified in Fig. 5 by reading and executing the program 342. Note that the analysis apparatus 300 may have the contrast object information search unit 358 instead of the contrast object information acquisition unit 352 or the similarity calculation unit 353, or may have the contrast object information search unit 358 together with the contrast object information acquisition unit 352 or the similarity calculation unit 353.

[0076] The comparison object information search unit 358 acquires information about the comparison object by performing a search process according to the information about the copyrighted work to be analyzed acquired by the copyrighted work information acquisition unit 351. For example, the comparison object information search unit 358 has functions such as a predetermined image comparison engine, and acquires information about comparison objects that are similar to the key image using the copyrighted work to be analyzed as a key image. In this case, the comparison object information search unit 358 may acquire the information about the comparison object and calculate information indicating the similarity between the copyrighted work and the acquired comparison object.

[0077] The contrast object information search unit 358 may be configured to accept selection of a contrast object for which a proposal is desired to be generated from among the contrast objects acquired as a search result. For example, the contrast object information search unit 358 can display a list of contrast objects acquired as a search result on the screen display unit 320, and accept selection of a contrast object in response to an operation on the operation input unit 310, etc.

[0078] Furthermore, when the analysis device 300 has the contrast object information search unit 358, the case information acquisition unit 354 may be configured to estimate the amount of damages and the like in accordance with the information searched for by the contrast object information search unit 358. For example, the case information acquisition unit 354 may be configured to estimate the amount of damages and the like in accordance with inputting information that can be acquired as a result of the search by the contrast object information search unit 358 into a trained model.

[0079] For example, the learning device 200 and the analysis device 300 may have the modified examples exemplified above, or may have modified examples other than those exemplified above. For example, the analysis device 300 may be configured to estimate the winning rate and the amount of compensation after making a determination on the reliance, etc. In other words, the winning rate / compensation amount estimation unit 355 may be configured to determine the reliance based on the copyrighted work and the comparison work, and then estimate the winning rate and the amount of compensation based on the determination result. Note that the determination on the reliance may be made using a trained model using past information stored in the case law database 241, etc.

[0080] Furthermore, in the present disclosure, an example has been given in which analysis system 100 has a first model and a second model. However, analysis system 100 may be configured to generate a predetermined proposal in response to inputting case information, similarity, etc., into a model that performs two-stage processing consisting of a first process and a second process at once. In this way, the model does not necessarily have to be divided into two.

[0081] Furthermore, as described above, there are cases where the first model and the second model are learned for each country in the learning device 200. In this case, the analysis device 300 may be configured to identify countries where copyright infringements are occurring, and to generate proposals using models corresponding to the identified countries.

[0082] [Second embodiment] Next, a second embodiment of the present disclosure will be described with reference to Fig. 11 to Fig. 13. Fig. 11 is a diagram illustrating an example of the hardware configuration of an analysis device 400. Fig. 12 is a block diagram illustrating an example of the configuration of the analysis device 400. Fig. 13 is a flowchart illustrating an example of the operation of the analysis device 400.

[0083] In the second embodiment of the present disclosure, an analysis device 400 will be described, which is an information processing device that outputs a recommendation indicating whether or not to consult with a lawyer regarding copyright infringement in response to input of a copyrighted work to be analyzed. Fig. 11 shows an example of the hardware configuration of the analysis device 400. Referring to Fig. 11, the analysis device 400 has, as an example, the following hardware configuration. ·CPU(Central Processing Unit)401(Arithmetic unit) ROM (Read Only Memory) 402 (storage device) RAM (Random Access Memory) 403 (storage device) Programs 404 loaded into RAM 403 A storage device 405 for storing the program group 404 A drive device 406 that reads and writes data from a recording medium 410 outside the information processing device A communication interface 407 for connecting to a communication network 411 outside the information processing device Input / output interface 408 for inputting and outputting data Bus 409 connecting each component

[0084] 12 by the CPU 401 acquiring and executing the program group 404. The program group 404 is stored in advance in, for example, the storage device 405 or the ROM 402, and is loaded into the RAM 403 or the like by the CPU 401 for execution as needed. The program group 404 may be supplied to the CPU 401 via the communication network 411, or may be stored in advance in the recording medium 410, and the drive device 406 may read out the program and supply it to the CPU 401.

[0085] 11 shows an example of the hardware configuration of the analysis device 400. The hardware configuration of the analysis device 400 is not limited to the above-described case. For example, the analysis device 400 may be configured with only a part of the above-described configuration, such as excluding the drive device 406. Furthermore, the CPU 401 may be a GPU or the like exemplified in the first embodiment.

[0086] The estimation unit 421 estimates the winning rate and the amount of compensation in a lawsuit based on the input of the similarity calculated between the copyrighted work and the comparison work and case information, which is information according to the content of the copyright infringement case. For example, the estimation unit 421 may estimate the winning rate and the amount of compensation by inputting the similarity and case information into a pre-trained model.

[0087] The generation unit 422 confirms the cost-effectiveness of holding a trial in accordance with the estimation result by the estimation unit 421, and generates a proposal in accordance with the confirmation result. For example, the generation unit 422 can confirm the cost-effectiveness by estimating the costs required to hold a trial in accordance with the estimation result by the estimation unit 421, and comparing the estimated costs with an expected value calculated from the estimation result by the estimation unit 421.

[0088] The output unit 423 outputs the proposal generated by the generation unit 422 .

[0089] The above is an example of the configuration of the analysis device 400. Next, an example of the operation of the analysis device 400 will be described with reference to FIG.

[0090] Fig. 13 is a flowchart showing an example of the operation of analysis device 400. Referring to Fig. 13, estimation unit 421 estimates the probability of winning and the amount of compensation in a lawsuit based on input of the similarity calculated based on the copyrighted work and the comparison object, and case information that is information based on the content of the copyright infringement case (step S201).

[0091] The generating unit 422 checks the cost-effectiveness of a lawsuit based on the estimation result by the estimating unit 421, and generates a proposal based on the result of the check (step S202).

[0092] The output unit 423 outputs the proposal generated by the generation unit 422 (step S203).

[0093] The above is an example of the operation of the analysis device 400.

[0094] As described above, the analysis device 400 includes an estimation unit 421, a generation unit 422, and an output unit 423. With this configuration, the generation unit 422 can confirm the cost-effectiveness of a lawsuit based on the estimation result by the estimation unit 421 and generate a proposal based on the confirmation result. Furthermore, the output unit 423 can output the proposal generated by the generation unit 422. As a result, the copyright holder can accurately determine whether or not to consult with a lawyer by checking the output. This reduces the risk of consulting a lawyer that does not lead to legal action, thereby reducing costs.

[0095] The above-described analysis device 400 can be realized by incorporating a predetermined program into an information processing device such as the analysis device 400. Specifically, a program according to another aspect of the present invention is a program for implementing processing in an information processing device such as the analysis device 400, which estimates the success rate and amount of compensation in the event of a lawsuit in response to input of the similarity calculated based on the copyrighted work and the comparison object and case information, which is information based on the content of the copyright infringement case, confirms the cost-effectiveness of the lawsuit in response to the estimated results, generates a proposal in response to the confirmation results, and outputs the generated proposal.

[0096] In addition, the analysis method executed by an information processing device such as the above-mentioned analysis device 400 is a method in which the information processing device estimates the success rate and amount of compensation in the event of a lawsuit based on the input of the similarity calculated based on the copyrighted work and the comparison object and case information that is information based on the content of the copyright infringement case, confirms the cost-effectiveness of the lawsuit based on the estimated results, generates a proposal based on the confirmation results, and outputs the generated proposal.

[0097] Even if the invention is a program having the above-described configuration, or a computer-readable recording medium having the program recorded thereon, or an analysis method, it can achieve the same functions and effects as the above-described analysis device 400, and therefore can achieve the above-described object of the present disclosure.

[0098] <Additional Notes> A part or all of the above-described embodiments can be described as follows: An outline of the analyzer and the like according to the present invention will be described below. However, the present invention is not limited to the following configuration.

[0099] (Appendix 1) an estimation unit that estimates the probability of winning and the amount of compensation in a lawsuit based on input of the similarity calculated based on the copyrighted work and the comparison work and case information that is information based on the content of the copyright infringement case; a generation unit that confirms the cost-effectiveness of a lawsuit based on the estimation result by the estimation unit and generates a proposal based on the confirmation result; an output unit that outputs the proposal generated by the generation unit; have Analyzer. (Appendix 2) The generation unit estimates the costs required for conducting a trial based on the estimation result by the estimation unit, and confirms cost-effectiveness by comparing the estimated costs with an expected value calculated from the estimation result by the estimation unit. 2. The analytical device of claim 1. (Appendix 3) The generating unit generates a recommendation to consult with a lawyer if the calculated expected value exceeds the estimated cost. 10. The analytical device of claim 2. (Appendix 4) The generating unit estimates an expected value of costs calculated according to the probability of an appeal or a final appeal and the costs required by the appeal or final appeal as costs required when conducting a trial. 4. The analytical device of claim 2 or 3. (Appendix 5) The generation unit confirms the cost-effectiveness of holding a trial based on the estimation result by the estimation unit and at least a part of the case information. 10. The analytical device according to claim 1, wherein the first and second electrodes are connected to a first electrode. (Appendix 6) a copyrighted work acquisition unit that acquires information about the copyrighted work; a comparison object acquisition unit that acquires information about the comparison object; a similarity calculation unit that calculates a similarity between the work acquired by the work acquisition unit and the comparison object acquired by the comparison object acquisition unit; and The estimation unit estimates the winning rate and the amount of compensation in a lawsuit based on the input of the similarity calculated by the similarity calculation unit and the case information. 6. The analytical device according to any one of claims 1 to 5. (Appendix 7) The estimation unit estimates the probability of winning and the amount of compensation in a lawsuit based on the similarity and the details of the infringement and the amount of damages included in the case information input into a pre-trained model. 10. The analytical device according to claim 1, wherein the first and second electrodes are connected to a first electrode. (Appendix 8) a search unit that searches for the comparison material similar to the copyrighted work according to the copyrighted work; The estimation unit estimates the probability of winning and the amount of compensation in a lawsuit based on the input of the similarity calculated between the copyrighted work and the comparison object searched by the search unit and the case information. 1. An analytical device according to any one of claims 1 to 7. (Appendix 9) The information processing device The system estimates the probability of winning and the amount of compensation in a lawsuit based on the input of the similarity calculated between the copyrighted work and the comparison work, and case information that corresponds to the content of the copyright infringement case. The cost-effectiveness of taking legal action based on the estimated results is confirmed, and proposals are generated based on the confirmation results. Print the generated suggestions Analysis method. (Appendix 10) In the information processing device, The system estimates the probability of winning and the amount of compensation in a lawsuit based on the input of the similarity calculated between the copyrighted work and the comparison work, and case information that corresponds to the content of the copyright infringement case. The cost-effectiveness of taking legal action based on the estimated results is confirmed, and proposals are generated based on the confirmation results. Print the generated suggestions A program to realize the processing.

[0100] Note that some or all of the configurations described in Supplementary Notes 2 to 8 that are dependent on the analytical device described in Supplementary Note 1 may also be dependent in a similar dependent relationship on the analytical method described in Supplementary Note 9 and the program described in Supplementary Note 10. Furthermore, not limited to Supplementary Notes 9 and 10, some or all of the configurations described as Supplements may also be dependent on various hardware, software, various recording means for recording software, or systems within the scope of the above-mentioned embodiments.

[0101] The programs described in the above embodiments and appendices may be stored in a storage device or a computer-readable recording medium, such as a portable medium such as a flexible disk, an optical disk, a magneto-optical disk, or a semiconductor memory.

[0102] Although the present invention has been described above with reference to the above-mentioned embodiments, the present invention is not limited to the above-mentioned embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention. [Explanation of symbols]

[0103] 100 Analysis Systems 200 Learning Device 210 Operation input section 220 Screen display section 230 Communication interface unit 240 Storage section 241 Case Law Database 242 Cost Database 243 Model Information 244 Programs 250 Processing Unit 251 Case Collection Department 252 Cost Information Collection Department 253 Learning Data Generation Unit 254 First Model Learning Section 255 Second Model Learning Section 256 output section 257 Re-learning Section 300 Analyzer 310 Operation input section 320 Screen display section 330 Communication Interface Unit 340 Storage section 341 Trained Model Information 342 Programs 350 Processing Unit 351 Copyright Information Acquisition Department 352 Comparison object information acquisition unit 353 Similarity calculation unit 354 Case Information Acquisition Department 355 Win rate / compensation amount estimation department 356 Proposal generation section 357 Output Section 358 Comparison Object Information Retrieval Department 400 Analyzer 401 CPU 402 ROM 403 RAM 404 Programs 405 Storage device 406 Drive Unit 407 Communication Interface 408 Input / Output Interface 409 Bus 410 Recording Media 411 Communication Network 421 Estimation Department 422 Generation part 423 Output Section

Claims

1. an estimation unit that estimates the probability of winning and the amount of compensation in a lawsuit based on input of the similarity calculated based on the copyrighted work and the comparison work and case information that is information based on the content of the copyright infringement case; a generation unit that confirms the cost-effectiveness of a lawsuit based on the estimation result by the estimation unit and generates a proposal based on the confirmation result; an output unit that outputs the proposal generated by the generation unit; have Analyzer.

2. The generation unit estimates the costs required for conducting a trial based on the estimation result by the estimation unit, and confirms cost-effectiveness by comparing the estimated costs with an expected value calculated from the estimation result by the estimation unit. The analytical device of claim 1 .

3. The generating unit generates a recommendation to consult with a lawyer if the calculated expected value exceeds the estimated cost. The analytical device according to claim 2 .

4. The generating unit estimates an expected value of costs calculated according to the probability of an appeal or a final appeal and the costs required by the appeal or final appeal as costs required when conducting a trial. The analytical device according to claim 2 .

5. The generation unit confirms the cost-effectiveness of holding a trial based on the estimation result by the estimation unit and at least a part of the case information. The analytical device of claim 1 .

6. a copyrighted work acquisition unit that acquires information about the copyrighted work; a comparison object acquisition unit that acquires information about the comparison object; a similarity calculation unit that calculates a similarity between the work acquired by the work acquisition unit and the comparison object acquired by the comparison object acquisition unit; and The estimation unit estimates the winning rate and the amount of compensation in a lawsuit based on the input of the similarity calculated by the similarity calculation unit and the case information. The analytical device of claim 1 .

7. The estimation unit estimates the probability of winning and the amount of compensation in a lawsuit based on the similarity and the details of the infringement and the amount of damages included in the case information input into a pre-trained model. The analytical device of claim 1 .

8. a search unit that searches for the comparison material similar to the copyrighted work according to the copyrighted work; The estimation unit estimates the probability of winning and the amount of compensation in a lawsuit based on the input of the similarity calculated between the copyrighted work and the comparison object searched by the search unit and the case information. The analytical device according to claim 1.

9. The information processing device The system estimates the probability of winning and the amount of compensation in a lawsuit based on the input of the similarity calculated between the copyrighted work and the comparison work, and case information that corresponds to the content of the copyright infringement case. The cost-effectiveness of taking legal action based on the estimated results is confirmed, and proposals are generated based on the confirmation results. Print the generated suggestions Analysis method.

10. In the information processing device, The system estimates the probability of winning and the amount of compensation in a lawsuit based on the input of the similarity calculated between the copyrighted work and the comparison work, and case information that corresponds to the content of the copyright infringement case. The cost-effectiveness of taking legal action based on the estimated results is confirmed, and proposals are generated based on the confirmation results. Print the generated suggestions A program to realize the processing.

Images