JP2020016965A - Information search system and method, and information search program - Google Patents

Abstract

To assist an innovator in creating an innovation by effectively presenting a solution concept to the innovator.SOLUTION: An information search system comprises: mining means for extracting a character string from basic information; and search means which refers to association levels of three or more stages between respective previously acquired character strings for reference and respective solution concepts classified into two or more kinds, and searches for one or more solution concepts upon the basis of the association levels of three or more stages between a character string for reference corresponding to the character string extracted by the mining means and the solution concepts.SELECTED DRAWING: Figure 3

Description

  The present invention relates to an information search system and method, and an information search program capable of efficiently searching for a patent or a group of patents to be newly searched for, or a patentee by artificial intelligence.

  2. Description of the Related Art Conventionally, a search system for patent information has been studied, and for example, a technique disclosed in Patent Document 1 is also disclosed.

JP 2009-003731 A

  However, according to the technology disclosed in Patent Document 1 described above, since it is not assumed that the search for patent information is performed using artificial intelligence, there is room for improvement in terms of search accuracy, and search time becomes longer. However, there is a disadvantage that the search itself becomes inefficient.

  Therefore, the present invention has been devised in view of the above-described problems, and a purpose thereof is to efficiently search for a patent or a group of patents to be newly searched for or a patentee by artificial intelligence. It is an object of the present invention to provide an information search system and method, and an information search program that can perform the above.

  The information search system according to claim 1 is for a combination of any two or more of patent specific information including a technical field of a patent, a solution concept, a solution problem, an effect, an operation, a function, an embodiment, a component of the invention, and a use. A degree of association acquiring means for acquiring in advance a degree of association of three or more stages with each patent or each group of patents, and search target information for acquiring the patent specifying information constituting the above combination in the patent or group of patents to be newly searched for Acquisition means, and a search means for searching for a patent or a group of patents based on the patent specifying information acquired by the search target information acquisition means with reference to the combination association degree acquired by the association degree acquisition means It is characterized by.

  The information search system according to claim 3 is one or more of patent specific information consisting of a technical field of a patent, a solution concept, a problem to be solved, an effect, an action, a function, an embodiment, a component of the invention, and an application. A degree of association acquiring means for acquiring in advance a degree of association of each patent or each group of patents in three or more stages with respect to the combination with the information, and patent identification information constituting the above-mentioned combination in a newly searched patent or group of patents; A search target information acquiring unit for acquiring additional information and a combination association degree acquired by the association degree acquiring unit are referred to, and a patent is obtained based on the patent identification information and the additional information acquired by the search target information acquiring unit. Or a search means for searching for a group of patents.

  The information search system according to claim 8 is for a combination of any two or more of patent specific information consisting of a technical field of a patent, a solution concept, a solution problem, an effect, an action, a function, an embodiment, a component of the invention, and a use. A degree of association acquiring means for acquiring in advance a degree of association of three or more stages with each patentee, and a search target information acquiring means for acquiring the patent identification information constituting the above combination in a patentee who newly tries to search. A search unit that searches for a patent holder based on the patent identification information obtained by the search target information obtaining unit by referring to the combination association degree obtained by the association degree obtaining unit. .

  The information search system according to claim 10 is one or more of patent specific information comprising a technical field of a patent, a solution concept, a problem to be solved, an effect, an action, a function, an embodiment, a component of the invention, and a use. A degree-of-association acquiring means for acquiring in advance a degree of association between each of the patentees in combination with the information in three or more stages, and a patent specifying information and ancillary information constituting the above-mentioned combination in the patentee who newly tries to search. The search target information acquiring means to be acquired, and the combination association degree acquired by the association degree acquisition means are referred to, and based on the patent identification information and the supplementary information acquired by the search object information acquisition means, the patent owner is determined. And a search means for searching.

  The information search method according to the fifteenth aspect is directed to a combination of any two or more of patent specific information including a technical field of a patent, a solution concept, a solution problem, an effect, an operation, a function, an embodiment, a component of the invention, and a use. A degree-of-association acquiring step of acquiring in advance a degree of association of three or more stages with each patent or each group of patents, and search target information for acquiring patent identification information constituting the above-mentioned combination in a newly searched patent or group of patents An acquisition step, and a search means step of searching for a patent or a group of patents based on the patent identification information acquired in the search target information acquisition step with reference to the combination association degree acquired in the association degree acquisition step. Features.

  The information search method according to claim 16 is for a combination of two or more of patent specific information consisting of a technical field of a patent, a solution concept, a solution problem, an effect, an operation, a function, an embodiment, a component of the invention, and a use. A degree-of-coupling acquiring step of acquiring in advance a degree of association of three or more stages with each patentee; and a search target information acquiring step of acquiring the patent specifying information constituting the combination in a patentee who newly attempts a search. A search unit step of searching for a patent holder based on the patent specification information obtained in the search target information obtaining step with reference to the combination association degree obtained in the association degree obtaining step.

  An information search program according to claim 17 is provided for a combination of two or more of patent specific information consisting of a technical field of a patent, a solution concept, a solution problem, an effect, an action, a function, an embodiment, a component of the invention, and a use. A degree-of-association acquiring step of acquiring in advance a degree of association of three or more stages with each patent or each group of patents, and search target information for acquiring patent identification information constituting the above-mentioned combination in a newly searched patent or group of patents The computer executes an acquisition step and a search step for searching for a patent or a group of patents based on the patent specifying information obtained in the search target information obtaining step, with reference to the combination association degree obtained in the association degree obtaining step. It is characterized by making it.

  An information search program according to claim 18 is provided for a combination of two or more of patent specific information consisting of a technical field of a patent, a solution concept, a solution problem, an effect, an operation, a function, an embodiment, a component of the invention, and a use. A degree-of-coupling acquiring step of acquiring in advance a degree of association of three or more stages with each patentee; and a search target information acquiring step of acquiring the patent specifying information constituting the combination in a patentee who newly attempts a search. Referring to the combination association degree acquired in the association degree acquisition step, and causing the computer to execute a search means step for searching for a patent holder based on the patent specification information acquired in the search target information acquisition step. And

  According to the present invention having the above-described configuration, it is possible to search for an optimal patent based on patent specification information.

1 is a diagram illustrating a configuration example in an information search system to which the present invention has been applied. 1 is a diagram illustrating a block configuration of an electronic device of an information search system to which the present invention has been applied. It is a figure which shows the example which acquires the combination association degree of three or more steps with each patent or each patent group with respect to patent specific information. It is a figure showing an example which constituted a combination of an effect and a constituent element of the invention as patent specification information. FIG. 9 is a diagram illustrating an example in which a set of combinations of the technical field, solution concept, solution problem, effect, operation, function, embodiment, component of the invention, and application of a patent is associated with one node. It is a figure which shows the example which drops into a concrete concept from a desire. FIG. 6 is a diagram illustrating an example in which additional information is further added as a combination to the node in FIG. 5. It is a figure which shows the example of formation of the combination associativity with which patent specific information and supplementary information are linked | related. FIG. 11 is a diagram illustrating an example of acquiring a combination association degree of three or more stages with each patentee with respect to patent specification information. It is a figure which shows the example which forms the combination association degree of three or more steps with each patentee with respect to the combination of any one or more of patent specific information and supplementary information.

  Hereinafter, an information search system to which the present invention is applied will be described in detail with reference to the drawings.

  A first embodiment of the information search system 1 to which the present invention is applied will be described. The information search system 1 of the present embodiment is embodied, for example, by a configuration as shown in FIG. The information search system 1 includes a terminal device 11 for a user who uses the system, and a server 13 connected to the terminal device 11 via a public communication network 12.

  The public communication network 12 is an Internet network or the like that connects the terminal devices 11 and the server 13 via a communication line. Incidentally, when the terminal device 11 is operated in a certain narrow area, the public communication network 12 may be constituted by a LAN (Local Area Network). Further, the public communication network 12 may be constituted by a so-called optical fiber communication network. The public communication network 12 is not limited to a wired communication network, but may be realized by a wireless communication network.

  The terminal device 11 is, for example, a mobile phone, a smartphone, a tablet terminal, a wearable terminal, a notebook personal computer (PC), or the like, and is a device that can communicate via the public communication network 12 at least based on a user operation. is there. The terminal device 11 is a device that can be carried around at all times by being portable by a user, but is not limited to this, and is a concept that includes all electronic devices such as a stationary PC.

  The terminal device 11 performs communication via the public communication network 12 when installing package software sold in stores without downloading an information search program described later via the public communication network 12. A device that does not perform this may be used. In the following example, a case where a smartphone is applied to the terminal device 11 will be described as an example.

  FIG. 2 shows a specific configuration example of the terminal device 11. The terminal device 11 includes a ROM (Read Only Memory) 22, a RAM (Random Access Memory) 23 as a work area used for storing and expanding data, and a CPU (Central Processing) for controlling the entire terminal device 11. Unit) 24, an operation unit 25 for inputting various control commands via operation buttons, a keyboard, and the like, an output I / F 16 for controlling display of various information, and a A storage unit 27 for storing a program for performing a search to be performed, and a data input / output unit for externally inputting data into the terminal device 11 or outputting data generated in the terminal device 11 to the outside 29 are connected to the internal bus 21, respectively. Further, a communication I / F 28 is connected to the internal bus 21. The output I / F 16 is connected to a display unit 26 as a monitor for actually displaying information. Further, the audio input / output unit 31 may be connected to the internal bus 21.

  The ROM 22 stores a program for controlling hardware resources of the entire terminal device 11. The RAM 23 temporarily stores various instructions for controlling hardware resources of the entire terminal device 11.

  The CPU 24 is a so-called central processing unit for controlling each component mounted in the terminal device 11 by transmitting a control signal via the internal bus 21. In addition, the CPU 24 transmits various control commands via the internal bus 21 in accordance with a user's operation via the operation unit 25.

  The operation unit 25 is embodied by a touch panel or the like, and receives, for example, patent identification information on a patent that the user actually wants to search, and also inputs from the user an execution instruction for executing the information search program. When the user inputs the execution command, the operation unit 25 notifies the CPU 24 of the input. Upon receiving this notification, the CPU 24 reads the program from the storage unit 27 and executes it.

  The output I / F 16 is configured by a graphic controller that creates a display image based on control by the CPU 24. The display unit 26 connected to the output I / F 16 is realized by, for example, a liquid crystal display (LCD).

  When the storage unit 27 is configured by a hard disk, predetermined information is written to each address under the control of the CPU 24, and is read out as necessary. Further, the storage unit 27 stores an information search program for executing the present invention. This program is read and executed by the CPU 24.

  The communication I / F 28 includes a line control circuit for connecting to the public communication network 12, a signal conversion circuit for performing data communication with another terminal device, and the like. The communication I / F 28 performs conversion processing on various commands from the internal bus 21 and sends them to the public communication network 12 side, and when data from the public communication network 12 is received, performs predetermined conversion processing on the data. And sends it to the internal bus 21 or the CPU 24.

  The data input / output unit 29 is connected with a cord for USB connection with an electronic device such as a PC. Data can be input / output to / from an external device via the data input / output unit 29.

  The voice input / output unit 31 is a device for converting voice input by a user into electronic data.

  A predetermined database is built in the server 13. In this database, information sent via the public communication network 12 is stored. The server 13 transmits the stored information to the terminal device 11 via the public communication network 12 based on a request from the terminal device 11.

  Note that any one or more components of the terminal device 11 or the server 13 may be controlled by artificial intelligence. A specific method of applying artificial intelligence to the present invention may be based on any one or more of all conventionally known information on artificial intelligence.

  The information search system 1 to which the present invention is applied will be executed via an information search program installed in the terminal device 11. That is, the user operates the terminal device 11 to perform various information searches through the information search program installed therein. The information search program is not limited to the case where the information search program is installed and used in the terminal device 11. The information search program is stored in the server 13, and the terminal device 11 accesses the server 13 every time it is used. Needless to say, this may be done.

  The user may manually input a patent or a group of patents to be searched through the operation unit 25 of the terminal device 11, or may input a voice through the voice input / output unit 31.

  In the information search system 1 according to the present invention, a user searches for a desired patent or patent group (patent portfolio) with high accuracy.

  First, as shown in FIG. 3, three or more combinations of degrees of association with each patent or each group of patents for the patent identification information are acquired in advance.

  The patent specification information here includes the technical field of the patent, the solution concept, the solution problem, the effect, the operation, the function, the embodiment, the constituent elements of the invention, and the application.

  The technical field of a patent may be a technical field classified by a patent classification symbol such as IPC, FI, F-term, or the like, or a description of a column of “technical field” in each patent specification may be used for text mining. Data analyzed based on the above, or an embodiment in a patent specification may be analyzed based on text mining to extract descriptions related to a technical field.

  The solution concept is the content described in the claims, the content described in the solution in the patent specification, the content referred to in the embodiment in the solution concept, or the solution in the patent classification symbol. And so on.

  The problem to be solved is the content described in the “problem to be solved by the invention” in the patent specification, the content that refers to the problem to be solved in the embodiment, and the classification of the patent classification symbol related to the problem to be solved. And so on.

  The effects are the contents related to the effects described in the column of “Effects of the Invention” in the patent specification, the contents mentioned in the embodiments for the effects, and the classification of the patent classification symbols related to the effects. .

  The action is the content related to the action described in the column of “Effect of the invention” in the patent specification, the content referred to in the embodiment in the action, the classification related to the action among the patent classification symbols, and the like. .

  The functions are the contents related to the functions described in the column of “Effects of the invention” in the patent specification, the contents referred to in the embodiments in the functions, the classification of the patent classification symbols related to the functions, and the like. .

  Examples are the contents related to the examples described in the column of "Examples" in the patent specification, the contents referred to in the embodiments in the embodiments, and the classification of the patent classification symbols related to the examples. And so on.

  The constituent elements of the invention are the matters specifying the invention (components) described in the claims, the contents referring to the constituent elements of the invention in the patent specification, and the constituent elements of the invention among the patent classification symbols. Related classifications and the like.

  Uses are defined as `` effects of the invention '' in the patent specification, contents related to the use described in the column of `` technical field '', contents referred to in the embodiments for the use, Related classifications and the like.

  In the example of FIG. 3, a combination of a technical field and a solution concept is defined as patent specific information, and this is defined on the left side with the combination association degree as the center. Also, on the right side of the combination association degree, patents (JP 2010-XXX, JP 2011-XXX, JP 2012-XXX), and a group of patents (Patent group F, Groups G) are arranged. The patent group is a group of a plurality of patents classified based on a specific attribute (technical field, application, target, type of embodied product, etc.).

  The patent specifying information and the patent or the group of patents are associated with each other through three or more combinations of association degrees.

  The combination association degree shown in FIG. 3 is a set of combinations of at least one of the F-term ○ ×, F-term Δ □, FI × △... As a technical field and any one or more of the solution concepts. It will be represented as nodes 61a to 61e of the hidden layer. In each of the nodes 61a to 61e, a weight for the patent specifying information and a weight for a patent or a group of patents as an output solution are set.

  This weighting is a combination association degree of three or more stages. For example, in the node 61a, the technical field: the F term × is associated with the combination association degree of 80%, and the solution concept: the asymmetric principle is associated with the combination association degree of 80%. In the node 61c, the technical field: F-term △ is associated with a combination degree of 60%, the solution concept: the principle of time division is associated with the relation degree of 60%, and the solution concept: the self-service principle is associated with a combination degree of 40%. I have. Note that the combination association degree may be configured by a neural network.

  Such a combination association degree is acquired in advance. Then, in the patent or patent group to be newly searched, the patent specifying information constituting the combination is acquired. This patent specifying information may be input by a user. The user inputs a technical field and a solution concept for a patent or a group of patents to be searched.

  The search program performs an operation of selecting one or more patents or patent groups as the optimal solution from the output solutions based on the input patent specifying information. In selecting this optimal solution, a combination association degree acquired in advance and shown in FIG. 3 is referred to. For example, if the input patent specifying information is the technical field: F-term ○ × and the solution concept: the nesting principle is input, the node 61b is associated via the combination association, and the node 61b Japanese Patent Application Laid-Open No. 2012-XXX is associated with a combination association degree of 60%, and the patent group G is associated with a combination association degree of 40%. An optimal solution is searched based on such a combination association degree. It is not necessary to output the optimal solution having the highest degree of association, and a solution having a lower degree of association may be selected. In addition, it goes without saying that an output solution to which no arrow is connected may be selected. That is, the selection of the output solution is not limited to the case where the combination association degree is selected in descending order, and may be the case where the combination association degree is selected in ascending order according to the case. However, any other priority may be selected.

  Note that the degree of combination association formed between the patent specification information and the patent or the group of patents is, for example, how many words and keywords constituting the patent specification information are included in the patent specification, The degree of association with a patent may be defined based on, for example, the degree to which the patent classification symbol representing the technical field is applied. In addition, if the "solution concept: the principle of nesting" does not have the keyword of "nesting principle", the degree of combination association is set high for a patent that is likely to solve the problem using the principle. If the probability is to be solved by using the nesting principle, a configuration that is likely to be adopted if it is used (if the nesting principle is used, a large-diameter pipe and a Is determined based on whether or not a small-diameter pipe to be used is disclosed).

  The group of patents is grouped based on arbitrary items, such as for each applicant, for each technical field, and for each patent in which a common keyword is described. The degree of association with the group of patents may be set higher for a group of patents in which the words or keywords constituting the patent-specific information are used at a higher rate. The higher the number of patents in which the symbol is used, the higher the setting may be. If "Solution Concept: Nesting Principle", even if there is no "Nesting Principle" keyword, the higher the percentage of patents that are likely to solve the problem using that principle, the higher the ratio of patent associations May be set higher.

  Such a combination association degree may be obtained from patent information (patent publications, patent publications, patent classifications, etc.). In such a case, a character string described in the patent gazette is analyzed using a text mining technique, or a patent classification is extracted. Then, based on the analyzed character string and the extracted patent classification, the combination degree of association with the patent specification information is set. The setting of the combination association degree may be performed on the user side or the system side, or may be automatically set. The rules for the automatic setting of the combination association degree may be any rules. For example, both the description of “technical field: F-term XX” and “solution concept: principle of time division” described in the patent specification information May be automatically set according to the presence / absence and the description frequency. These processes are executed by acquiring from patent information (patent publications, patent publications, patent classifications, etc.).

  In the example of FIG. 4, the combination of the effect and the constituent elements of the invention is defined as the patent specification information, and the combination is defined on the left side with the combination association degree as the center. Patents and patent groups are arranged on the right side of the combination association degree. Similarly, the patent specification information and the patent or the group of patents are associated with each other through three or more combinations of degrees of association.

  The combination association degree shown in FIG. 4 is a set of combinations of at least one of the effect 〜, the effect △, the effect △,. 61e. In each of the nodes 61a to 61e, a weight for the patent specifying information and a weight for a patent or a group of patents as an output solution are set.

  This weighting is a combination association degree of three or more stages. For example, in the node 61a, the effect × is associated with the combination association degree of 80%, and the component: feedback means is associated with the combination association degree of 80%. In the node 61c, the effect △ is associated with the combination association degree of 60%, the component: the storage step is associated with the combination association degree of 60%, and the component: the drawing unit is associated with the combination association degree of 40%.

  Such a combination association degree is acquired in advance. Then, in the patent or patent group to be newly searched, the patent specifying information constituting the combination is acquired. This patent specifying information may be input by a user. The user inputs an effect and a component for a patent or a group of patents to be searched.

The search program performs an operation of selecting one or more patents or patent groups as the optimal solution from the output solutions based on the input patent specifying information. In selecting this optimal solution, a combination association degree acquired in advance and shown in FIG. 4 is referred to. For example, if the input patent specifying information is effect: × and a component: case component specifying step is input, a node 61b is associated via a combination association degree, and this node 61b Japanese Patent Application Laid-Open No. 2012-XXX is associated with a combination association degree of 60%, and the patent group G is associated with a combination association degree of 40%. An optimal solution is searched based on such a combination association degree.
Such a combination association degree may be obtained from patent information (patent publication, patent publication, patent classification, etc.). In such a case, the character string described in the patent gazette is analyzed using a text mining technique, and it is determined whether or not there is a character string that matches the effect and the component. Then, based on the analyzed character string, the degree of association with the patent specifying information is set. The combination degree of association may be set on the user side or the system side, or may be set automatically. The rules for automatic setting of the combination association degree may be any rules. For example, whether or not both “effect XX” and “component: case component specifying step” described in the patent specification information are described, and The combination degree of association may be automatically set according to the description frequency. These processes are executed by acquiring from patent information (patent publications, patent publications, patent classifications, etc.).

  The node 61 linked to the patent specifying information is not limited to the examples in FIGS. FIG. 5 shows an example in which a set of combinations of the technical field, the solution concept, the solution problem, the effect, the action, the function, the embodiment, the component of the invention, and the use of the patent is associated with one node 61. All types of these patent specifying information may be associated with this node 61 with respective combinations of association degrees. Further, the type of each patent specifying information may be two or more.

  Incidentally, the node 61 is limited to a case where the node 61 is configured by a combination of all kinds of the patent specific information (the technical field of the patent, the solution concept, the solution problem, the effect, the function, the function, the embodiment, the component of the invention, and the use). It is only necessary that the association be made in a combination of two or more of these types. Each of the patent specifying information associated with the node 61 is defined by the above-described combination association degree.

  In inputting the patent specification information on the user side, only the input of the predetermined patent specification information linked to the node 61 may be accepted, but the invention is not limited to this. Even if the predetermined patent identification information associated with the node 61 has not been input, if a keyword or a patent classification similar to this is input, it is assumed that the similar patent identification information has been input. It may be.

  The user may naturally input what patent he / she wants to search through a character string (free keyword) without being conscious of the patent specifying information. For example, if you enter a "software-related invention that can quantify the breadth of the technical scope" as a free keyword for search, it will be analyzed using a well-known text mining technology to create a "technical scope" or "quantification" It is possible to drop it into keywords of elements and effects. Further, from the result of the text mining, a patent classification symbol in the technical field of software may be searched and specified. In addition, when an input of a desired or desired free keyword such as “cost can be reduced” or “easy to use” is received, it may be linked to patent identification information of a solution problem or an effect. When a free keyword related to a patent to be searched is input, the free keyword is analyzed based on various methods such as a well-known text mining method, and these are linked to patent specifying information having a high degree of similarity. become.

The free keyword mentioned here is when the technical information on the technical field of the patent, the solution concept, the problem to be solved, the effect, the function, the function, the embodiment, the component of the invention, and the use is input as a character string, a free keyword, a word, or the like. In addition, information on marketing, information on target customers, information on sales, information on business models, information on companies with which we cooperate, information on companies we want to cooperate with, information on manufacturing, information on manufacturing, research and development General information, other information that constitutes the value chain, fragmentary information about products and services to be sold, user's wants that can be fulfilled by the products and services, and desires of users for the products and services, etc. included.
For example, as shown in FIG. 6, the desire itself of “I want to make bread that is thinner just by eating” may be input. In such a case, as specific measures for realizing this, specific measures such as "reducing the calories of bread", "reducing the amount of digestion and absorption of bread into the body", and "reducing the intake of bread itself", etc. Solution concept comes out. If you want to dig deeper from there, for "reducing the calories of bread", as a concrete solution to "replace some of the ingredients with small calories", and for "reducing the amount of digestion and absorption of bread into the body" As a concrete solution, "Consist with indigestible ingredients" and "Reduce the intake of bread itself" as a specific solution "Increase the volume while increasing the number of pores inside To make you feel full. "
The search for such a concept may be performed by the system side and the user side by human power. For example, in response to a desire from a client to “make bread that is just eaten,” a skilled consultant delves into the concept to fulfill that desire as shown in FIG. The patent specifying information may be defined and input for "a bread that gives a feeling of fullness by increasing the volume while increasing the amount."
Further, a search from such a desire to a specific concept may be automatically performed. In such a case, the relationship between the desire, the rough solution, and the specific concept is defined in the same way by the degree of association, and when actually searching, the degree of association is referred to, A rough solution or a specific concept may be searched.

  FIG. 7 shows a combination of the patent specific information including the technical field, the solution concept, the solution problem, the effect, the operation, the function, the embodiment, the component of the invention, the use, and the like for one node 61 and the supplementary information. The example which is related with is shown.

  If the patent specifying information associated with this node 61 is one that is associated with any one or more of the technical field of the patent, the solution concept, the solution problem, the effect, the function, the function, the embodiment, the component of the invention, the use, etc. Good.

  The supplementary information is information other than the patent identification information, and includes all information relating to the business utilizing the patent or the group of patents described above. This collateral information includes information on marketing of the business utilizing the patent or patent group, information on target customers, information on sales, information on the market environment where the business is located, and political and economic background of the market where the business is located. Information about the business and social background, information about the business model, information about the partner company to cooperate, information required by the partner company to cooperate, information about manufacturing, information about research and development in general, and other value chains. Information is included. These supplementary information may be obtained from an information source accessible via the Internet, or may be input by the system or user from information in an electronic information medium or information printed on a paper medium. It may be used.

  FIG. 8 shows an example of forming a combination association degree in which the patent specification information and the supplementary information are associated with the node 61. Patent-specific information is a component of an effect or an invention, and as additional information, market information, a business model, a social background, and the like are defined on the left side with a focus on the degree of association. Patents and patent groups are arranged on the right side of the combination association degree. Similarly, the patent specification information and the patent or the group of patents are associated with each other through three or more combinations of degrees of association.

  In the combination association degree shown in FIG. 8, in each of the nodes 61a to 61e, a weight for the patent specifying information and the accompanying information and a weight for the patent or the patent group as the output solution are set.

  This weighting is a combination association degree of three or more stages. For example, in the node 61a, the effect XX is associated with a combination degree of 80%, and the "business model: joint production of an office chair height adjustment mechanism with a partner" is associated with a combination degree of 80%. For node 61c, the effect △ is 60% for combination, and “Market information: the need for headrests is particularly increasing in the office chair field” is 60% for combination, and “Social background: A subsidy will be issued to companies that have developed friendly chairs. "

  Such a combination association degree is acquired in advance. Then, in the patent or patent group to be newly searched, the patent specifying information constituting the combination is acquired. This patent specifying information may be input by a user. The user inputs an effect and a component for a patent or a group of patents to be searched.

  The search program performs an operation of selecting one or more patents or patent groups as the optimal solution from the output solutions based on the input patent specifying information. In selecting this optimal solution, a combination association degree acquired in advance and shown in FIG. 8 is referred to. For example, if the input patent specification information is “Technical field: effect XX” and “Market information: the need to mesh the seat is increasing especially in the office chair field” is input, the combination association degree is determined. The node 61b is associated with the Japanese Patent Application Laid-Open No. 2012-XXX with a combination association degree of 60% and the patent group G with a combination association degree of 40%. An optimal solution is searched based on such a combination association degree.

  In forming the association degree via the above-described nodes, the supplementary information includes keywords that define the technology (“Make the seat particularly mesh in the office chair field ...”; ... "," the height adjustment mechanism of the office chair ... "). These keywords may be analyzed through text mining, and a combination association with each patent or each group of patents may be created for a combination of the keyword and the patent identification information.

  In the supplementary information, there is no term related to the patent or each patent group. For example, the name of the partner company that cooperates in the business, the age and gender of the customer, the sales form (mail order or direct sale), and the name of the industry If there is a comment from a person or a politician, a related keyword may be linked thereto. In the case of a partner company, collaborative information should be obtained from keywords that are found by searching for the name of the company with an Internet search engine, technical information described on the company's site, patent information filed by the company, etc. It may be. If the age group of the customer is a teenage woman, the object that is prevalent in the generation, the technology related to the object, and the like may be supplementary information. By combining such supplementary information and patent specifying information, a patent or a group of patents having a high degree of association with the information is narrowed down.

  Such a combination association degree may be obtained from patent information (patent publications, patent publications, patent classifications, etc.). In such a case, a character string described in the patent gazette is analyzed using a text mining technique, or a patent classification is extracted. Then, based on the analyzed character string and the extracted patent classification, the combination degree of association with the patent specification information is set. The setting of the combination association degree may be performed on the user side or the system side, or may be automatically set. The rules for the automatic setting of the combination association degree may be any rules. For example, "Effects: XX" and "Market information: Needs for headrests are increasing especially in the field of office chairs" described in patent specific information. May be automatically set in accordance with the presence / absence of both of them and the frequency of the description. These processes are executed by acquiring from patent information (patent publications, patent publications, patent classifications, etc.).

  At this time, additional information includes information on business marketing, information on target customers, information on sales, information on the market environment where the business is located, information on the political and economic background and social background of the market where the business is located , Information on business models, information on partner companies to cooperate, information required for partner companies to cooperate, information on manufacturing, information on general R & D, and other information that constitutes the value chain are posted on the Internet. It may be obtained from a site or the like.

  In the case where the server 13 is controlled by artificial intelligence, the degree of association between each patent or each group of patents for any two or more combinations of the patent specifying information may be learned by the artificial intelligence. . Similarly, the degree of association of the combination with the patent specifying information and the supplementary information with the patent or the group of patents may be learned by artificial intelligence.

  The artificial intelligence performs learning based on information provided from the outside to the server 13 via the public communication network 12. The information provided from the outside to the server 13 may be, for example, information transmitted from the terminal device 11 using the present system. As a result of the use of the information search program to which the present invention is applied by the terminal device 11, the relationship between each patent or each patent group for any combination of two or more of the patent specifying information selected by the user or the system, or the patent The relationship between each combination of the specific information and the supplementary information and each patent or each group of patents is acquired, and based on this, the above-described combination association degree is updated. That is, the relationship selected by the user or the system is updated to have a higher association, and the relationship not selected by the user or the system is updated to have a lower association. For this update, artificial intelligence or a neural network may be used.

  This update may be performed periodically or irregularly each time patent information is newly disclosed. Patent information is sequentially disclosed, for example, through a patent publication. Each time the patent information is disclosed, a combination association of the patent specifying information and the supplementary information may be linked to the patent information. This combination association degree is updated each time a new patent is published through a patent publication. As a result, Japanese Patent Application Laid-Open No. 2011-XXX has the highest combination association degree with respect to a node of certain patent specific information (or a node composed of a combination of certain specific information and certain supplementary information). %, The newly disclosed Japanese Patent Application Laid-Open No. 2018-XXXXX has a higher combination association degree, and sometimes becomes 100%. As a result, the combination association degree in Japanese Patent Application Laid-Open No. 2011-XXX, which had the highest combination association degree until now, relatively decreases to 80%.

  As described above, according to the present invention, in the process of updating the combination relevance when patent information is newly disclosed, when a newly disclosed patent is added to the combination relevance, a combination of other patents is added. The degree of association may be relatively increased or decreased. In such a case, the degree of combination association of another patent connected to the node 61 to which one newly disclosed patent is linked is relatively increased or decreased. At this time, when the degree of association of one patent is higher than the degree of association of another patent, the degree of association of another patent is reduced, and the degree of association of another patent is reduced. However, when the degree of association of one patent is low, the degree of association of another patent may be increased.

  The same applies to patents. When a newly disclosed patent is added to a group of patents, the degree of association changes similarly. At this time, the combination relevance of another group of patents connected to the same node 61 may be relatively changed with respect to the combination relevance of one newly added patent group. This group of patents may be defined by the system side or user side and separately input, or automatically based on a specific attribute (technical field, application, target, type of embodied product, etc.). It may be classified.

  Similarly, when additional information is newly disclosed, the combination association degree may be updated. In the process of updating this combination association degree when additional information is newly disclosed, when adding the additional information newly disclosed through the Internet or the like to this combination association degree, the combination association degree of other additional information is May be raised and lowered relatively. In such a case, the degree of combination association of other supplementary information connected to the node 61 to which the newly disclosed supplementary information is linked is relatively increased or decreased. At this time, when the combination associativity of one supplementary information is higher than the combination associativity of the other supplementary information up to now, the combination associativity of the other supplementary information is reduced, and the other supplementary information until now is combined. When the combination association degree of one patent is lower than the combination association degree, the combination association degree of another supplementary information may be increased.

  Note that, in the above-described example, a case has been described as an example where the degree of combination and association is relatively increased or decreased between patents or patent groups connected to the same node 61 and supplementary information, but the present invention is not limited to this. Other patents, patent groups, and additional information connected to the node 61 other than the node 61 to which the newly disclosed patents, patent groups, and additional information are connected may be combined to increase or decrease the degree of association.

  As described above, according to the present invention, it is possible to efficiently search for a patent or a group of patents or patent holders who are to attempt a new search. In particular, according to the present invention, it is possible to easily search for a patent or a group of patents without special skill. Further, according to the present invention, it is possible to search for a patent or a group of patents with higher accuracy. Further, by configuring the above-described combination association degree with artificial intelligence, it is possible to further improve the discrimination accuracy by learning this.

  Further, according to the present invention, it is characterized in that a search for a patent or a group of patents is performed based on a combination degree of association set in three or more stages. The combination association degree can be described by, for example, a numerical value from 0 to 100%, but is not limited to this, and may be configured at any stage as long as it can be described by a numerical value of three or more stages. .

  By performing the search based on the combination degree of association represented by such a numerical value of three or more stages, in a situation where the determination result of a plurality of patents or patent groups is selected, the search and display are performed in descending order of the combination degree of association. It is also possible to do. If it is possible to display to the user in the descending order of the combination association degree, it is possible to prompt the user to preferentially select the more likely patent or patent group determination result. On the other hand, even a discrimination result of a patent or a group of patents having a low degree of association can be displayed in the sense of a second opinion, and can be useful when a first opinion cannot be successfully analyzed.

  In addition to this, according to the present invention, it is possible to make a determination without overlooking the determination result of a patent or a group of patents having an extremely low combination association degree such as 1%. Even a patent or a group of patents with a very low degree of association is connected as a slight sign, and it may be useful as a result of discrimination of a patent or a group of patents tens or hundreds of times. The user can be alerted.

  Further, according to the present invention, there is an advantage that a search policy can be determined in a manner of setting a threshold value by performing a search based on such a combination of three or more stages. If the threshold value is set low, even if the above-described combination association degree is 1%, it can be picked up without omission, but the possibility of appropriately detecting the discrimination result is low, and a lot of noise may be picked up. On the other hand, if the threshold value is increased, it is highly likely that the optimal discrimination result can be detected with high probability, but the combination association degree is usually low, and though it is passed through though it is low, it appears once every tens or hundreds of times. In some cases, you may miss a solution. Which one to give more weight can be determined based on the ideas of the user and the system, but it is possible to increase the degree of freedom in selecting such a point to be emphasized.

  In the present invention, the search target is not limited to a patent or a group of patents. For example, as shown in FIG. 9, a patentee may be searched. In such a case, three or more combinations of degrees of association with each patentee for any two or more combinations of the patent specification information are acquired in advance. The patent owner is linked to the patent held by the patent owner and Internet information posted on the patent owner.

  In forming the degree of combination association, the patent holder may obtain the patent information (patent publications, patent publications, patent classifications, etc.) held by the patent holder, or Internet information posted about the patent holder. . In such a case, a character string described in a patent gazette or Internet information is analyzed using a text mining technique, or a patent classification is extracted. Then, based on the analyzed character string and the extracted patent classification, the combination degree of association with the patent specification information is set. The setting of the combination association degree may be performed on the user side or the system side, or may be automatically set. The rules for automatically setting the combination association degree may be any rules. For example, whether or not both “effect: ○” and “component: storage step” described in the patent specification information are described, and the description is made The combination degree of association may be automatically set according to the frequency. These processes are executed by acquiring from patent information (patent publications, patent publications, patent classifications, etc.) and Internet information. The more patent holders possess more patent information with a higher degree of combination, and the higher the number of Internet information posted on the Internet, the higher the degree of combination as a patent holder. Set to be.

  FIG. 10 illustrates an example in which a combination association of three or more stages with each patentee for a combination of any one or more of the patent specifying information and the supplementary information is formed. In the example of FIG. 9 as well, the method of setting the association degree with the patentee is the same as described above.

DESCRIPTION OF SYMBOLS 1 Information search system 11 Terminal device 12 Public communication network 13 Server 21 Internal bus 22 ROM
23 RAM
24 CPU
25 operation unit 26 display unit 27 storage unit 29 data input / output unit 31 voice input / output unit

Claims (18)

Three stages with each patent or each patent group for any combination of two or more of patent specific information consisting of the technical field of the patent, the solution concept, the solution problem, the effect, the function, the function, the embodiment, the components of the invention, and the application A degree-of-association acquiring means for acquiring the above-described degree of association in advance,
Search target information acquisition means for acquiring patent identification information constituting the above combination in a patent or a group of patents to be newly searched,
A search unit that searches for a patent or a group of patents based on the patent identification information obtained by the search target information obtaining unit by referring to the combination association degree obtained by the association degree obtaining unit. Information search system. 2. The search target information acquiring means, wherein a free keyword relating to a patent or a group of patents to be newly searched is inputted, and the patent specifying information having a high similarity to the inputted free keyword is acquired. Information search system. Patents or patents for a combination of at least one of patent specific information consisting of the technical field of a patent, a solution concept, a solution problem, an effect, an action, a function, an embodiment, a component of the invention, and a use, and supplementary information A degree-of-association acquiring means for acquiring in advance a degree of association of three or more stages with the group,
Search target information acquisition means for acquiring patent identification information and supplementary information constituting the combination in a patent or a group of patents to be newly searched,
A search unit that searches for a patent or a group of patents based on the patent identification information and the supplementary information obtained by the search target information obtaining unit with reference to the combination association degree obtained by the association degree obtaining unit. An information search system characterized by the following. The information search system according to claim 1, wherein the association degree acquisition unit acquires the combination association degree from patent information. 2. The information search according to claim 1, wherein the association degree acquiring unit acquires, from the patent information, a combination association degree of three or more stages with each patent group for any two or more combinations of the patent specification information. 3. system. The said association degree acquisition means is provided with information on the relationship between each patent or each group of patents with respect to any two or more combinations of the patent specification information from the outside, and reflects this in the combination association degree. 1. The information search system according to 1. The above-mentioned association degree acquisition means provides that information on the relationship between each patent or each patent group with respect to a combination of at least one of the patent specifying information and the supplementary information is provided from the outside, and reflects this in the combination association degree. 4. The information search system according to claim 3, wherein: Three or more steps with each patentee for a combination of any two or more of the patent specification information consisting of the technical field of the patent, the solution concept, the solution problem, the effect, the function, the function, the embodiment, the components of the invention, and the application An association degree acquiring means for acquiring a combination association degree in advance;
Search target information acquisition means for acquiring patent identification information constituting the combination in a patentee who newly attempts a search,
A search unit for searching for a patent holder based on the patent specifying information obtained by the search target information obtaining unit with reference to the combination association degree obtained by the association degree obtaining unit. Search system. 9. The search target information acquiring means, wherein a free keyword related to a patent owner who is newly trying to search is inputted, and the patent specific information having a high similarity to the inputted free keyword is acquired. Information search system. Each patentee for the combination of at least one of the patent specification information consisting of the technical field of the patent, the solution concept, the solution problem, the effect, the function, the function, the embodiment, the component of the invention, and the use, and the supplementary information A degree-of-association acquiring means for acquiring in advance a degree of combination of three or more stages;
A search target information acquisition unit for acquiring the patent identification information and the supplementary information constituting the combination in a patentee who newly attempts a search,
A search unit that searches for a patentee based on the patent identification information and the supplementary information obtained by the search target information obtaining unit with reference to the combination association degree obtained by the association degree obtaining unit. A featured information search system. The information search system according to claim 8, wherein the association degree acquisition unit acquires the combination association degree from patent information. 9. The association degree acquisition means, wherein information relating to the relationship of each patentee with respect to any two or more combinations of the patent specification information is provided from the outside, and the information is reflected in the combination association degree. Information search system. The association degree acquisition means is provided with information on the relationship between each patentee with respect to a combination of any one or more of the patent specifying information and the supplementary information from the outside, and reflects this in the combination association degree. The information search system according to claim 10, wherein The information search system according to any one of claims 1 to 13, wherein the association degree acquisition unit and / or the search unit are controlled by artificial intelligence. Three stages with each patent or each patent group for any combination of two or more of patent specific information consisting of the technical field of the patent, the solution concept, the solution problem, the effect, the function, the function, the embodiment, the components of the invention, and the application An association degree acquisition step of acquiring the combination association degree in advance,
A search target information acquisition step of acquiring patent identification information constituting the combination in a patent or a group of patents to be newly searched,
A search unit step of searching for a patent or a group of patents based on the patent identification information obtained in the search target information obtaining step with reference to the combination association degree obtained in the above-described association degree obtaining step. Search method. Three or more steps with each patentee for a combination of any two or more of the patent specification information consisting of the technical field of the patent, the solution concept, the solution problem, the effect, the function, the function, the embodiment, the components of the invention, and the application An association degree acquisition step of acquiring a combination association degree in advance;
A search target information acquisition step of acquiring patent specification information constituting the combination in a patentee who newly attempts a search,
A search means for searching for a patent holder based on the patent specification information obtained in the search target information obtaining step with reference to the combination association degree obtained in the association degree obtaining step. Method. Three stages with each patent or each patent group for any combination of two or more of patent specific information consisting of the technical field of the patent, the solution concept, the solution problem, the effect, the function, the function, the embodiment, the components of the invention, and the application An association degree acquisition step of acquiring the combination association degree in advance,
A search target information acquisition step of acquiring patent identification information constituting the combination in a patent or a group of patents to be newly searched,
A search unit step for searching for a patent or a group of patents based on the patent specification information obtained in the search target information obtaining step with reference to the combination association degree obtained in the association degree obtaining step. Information search program. Three or more steps with each patentee for a combination of any two or more of the patent specification information consisting of the technical field of the patent, the solution concept, the solution problem, the effect, the function, the function, the embodiment, the components of the invention, and the application An association degree acquisition step of acquiring a combination association degree in advance;
A search target information acquisition step of acquiring patent specification information constituting the combination in a patentee who newly attempts a search,
A search unit step for searching for a patent holder based on the patent identification information obtained in the search target information obtaining step, with reference to the combination association degree obtained in the association degree obtaining step. Information search program.

Images