A method, system and medium for generating enterprise patent information classification rules

Abstract

The present invention discloses a method, system and medium for generating enterprise patent information classification rules. The method includes: obtaining enterprise patent information and industrial link information of several enterprises, and performing IPC classification number scaling processing on the enterprise patent information belonging to the same industrial link information to obtain scaled patent information; performing frequency threshold screening processing at each level on the scaled patent information corresponding to each enterprise under each industrial link information to obtain a retained patent information data set; performing IPC classification number splitting processing and frequent item extraction processing on the retained patent information data set corresponding to each enterprise under each industrial link information to obtain split patent data and frequent item sets; generating enterprise patent information classification rules based on the split patent data and frequent item sets corresponding to each enterprise under each industrial link information. The present invention significantly improves the speed and accuracy of IPC classification number classification processing.

Description

Technical Field

[0001] The present invention relates to the field of patent classification technology, and in particular to a method, system and medium for generating enterprise patent information classification rules. Background Art

[0002] In the existing technology, most of the enterprise chain rules are written manually, which consumes a lot of manpower. The IPC classification number plays a pivotal role in the enterprise chain rules. The existing enterprise patent classification rules are basically written manually, which is prone to differences or errors due to manual operation, and manual operation is prone to low efficiency and low accuracy.

[0003] Therefore, the prior art still needs to be improved and enhanced. Summary of the invention

[0004] The technical problem to be solved by the present invention is that, in view of the above-mentioned defects of the prior art, a method, system and medium for generating enterprise patent information classification rules are provided, aiming to solve the problem that the rules for patent classification in the prior art are basically manually written, which are prone to differences or errors due to manual operation, and manual operation is prone to low efficiency and low accuracy.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is as follows:

[0006] In a first aspect, the present invention provides a method for generating enterprise patent information classification rules, wherein the method comprises:

[0007] Obtain enterprise patent information and industrial link information of several enterprises, and scale the IPC classification number of enterprise patent information belonging to the same industrial link information to obtain the scaled patent information corresponding to each enterprise under each industrial link information;

[0008] The scaled patent information corresponding to each enterprise under each industrial link information is screened by frequency thresholds at each level to obtain a reserved patent information dataset corresponding to each enterprise under each industrial link information;

[0009] The retained patent information data set corresponding to each enterprise under each industrial link information is processed by IPC classification number splitting and frequent item extraction, and the split patent data and frequent item sets corresponding to each enterprise under each industrial link information are obtained;

[0010] Based on the split patent data corresponding to each enterprise under each industrial link information and the frequent item sets, enterprise patent information classification rules are generated.

[0011] In one implementation, the obtaining of enterprise patent information and industrial link information of several enterprises includes:

[0012] Obtain patent information tables of several enterprises and mapping relationship tables between enterprises and industrial links;

[0013] Deduplication processing is performed on the patent data in the patent information table, and the patent information table is merged with the mapping relationship table to obtain a merged data table;

[0014] The IPC classification numbers of the merged data table are cleaned, and the sub-category IPC classification numbers, large group IPC classification numbers and small group IPC classification numbers are extracted to obtain the enterprise patent information and industrial link information of several enterprises.

[0015] In one implementation, after obtaining the enterprise patent information and industrial link information of several enterprises, the method further includes:

[0016] Based on the industrial link information, the patent names in the enterprise patent information are segmented and filtered to screen out the enterprise patent information related to the industrial link information.

[0017] In one implementation, the enterprise patent information belonging to the same industrial link information is scaled by the IPC classification number to obtain the scaled patent information corresponding to each enterprise under each industrial link information, including:

[0018] Based on the enterprise patent information, the number of patents of each enterprise and the number of IPC classification numbers at different levels are obtained, wherein the number of IPC classification numbers at different levels includes the number of sub-class IPC classification numbers, the number of large group IPC classification numbers and the number of small group IPC classification numbers;

[0019] Calculate the average number of patents belonging to the same industry link information to obtain the average number of patents in the link;

[0020] Based on the number of patents of each enterprise, the number of IPC classification numbers at different levels and the average number of patents in the link, the number of IPC classification numbers at different levels of each enterprise belonging to the same industrial link information is scaled to obtain the scaled patent information corresponding to each enterprise under each industrial link information. The scaled patent information includes the scaled number of sub-category IPC classification numbers, the number of large group IPC classification numbers and the number of small group IPC classification numbers.

[0021] In one implementation, the zoomed-in patent information corresponding to each enterprise under each industrial link information is subjected to frequency threshold screening processing at each level to obtain a retained patent information dataset corresponding to each enterprise under each industrial link information, including:

[0022] For the number of scaled sub-category IPC classification numbers of each enterprise under each industrial link information, calculate the average number of sub-category IPC classification numbers, filter the sub-category IPC classification numbers with a number less than the average, recalculate the average number of the remaining sub-category IPC classification numbers, and repeatedly filter the remaining sub-category IPC classification numbers until the retained sub-category IPC classification numbers meet the threshold requirements;

[0023] Based on the retained sub-category IPC classification numbers, collect the large group IPC classification numbers corresponding to each enterprise under each industrial link information, calculate the average number of large group IPC classification numbers, filter the large group IPC classification numbers with a number less than the average, recalculate the average number of the remaining large group IPC classification numbers, and repeatedly filter the remaining large group IPC classification numbers until the retained large group IPC classification numbers meet the threshold requirements;

[0024] Based on the retained large group IPC classification numbers, the small group IPC classification numbers corresponding to each enterprise under each industrial link information are collected, the average number of small group IPC classification numbers is calculated, the small group IPC classification numbers with a number less than the average are filtered, the average number of the remaining small group IPC classification numbers is recalculated, and the remaining small group IPC classification numbers are filtered repeatedly until the retained small group IPC classification numbers meet the threshold requirements, thus obtaining the retained patent information data set corresponding to each enterprise under each industrial link information.

[0025] In one implementation, the IPC classification number splitting process and frequent item extraction process are performed on the retained patent information data set corresponding to each enterprise under each industrial link information to obtain the split patent data and frequent item sets corresponding to each enterprise under each industrial link information, including:

[0026] For each reserved patent information dataset corresponding to each enterprise under each industrial link information, obtain the sub-category IPC classification number in the reserved patent information dataset, and if the number of types of the large group IPC classification number corresponding to the sub-category IPC classification number is less than the first set value, split the sub-category IPC classification number into the large group IPC classification number;

[0027] Obtain the large group IPC classification number in the retained patent information data set. If the number of types of the small group IPC classification number corresponding to the large group IPC classification number is less than the second set value, split the large group IPC classification number into small group IPC classification numbers to obtain the split patent data corresponding to each enterprise under each industrial link information;

[0028] For the reserved patent information data set corresponding to each enterprise under each industrial link information, the Apriori algorithm is used to extract frequent items from the sub-category IPC classification number, the large group IPC classification number and the small group IPC classification number in the reserved patent information data set to obtain the frequent item set at each level.

[0029] In one implementation, the generating of enterprise patent information classification rules based on the split patent data and the frequent itemsets corresponding to each enterprise under each industrial link information includes:

[0030] For each industry link information, the split patent data of each enterprise and the frequent item sets are matched, and the patent data in the frequent item sets are screened out from the split patent data;

[0031] For each industry link information, the number of IPC classification numbers at different levels in the patent data screened by each enterprise is sorted, and the first several are taken as the final marked IPC classification numbers;

[0032] The enterprise patent information classification rules are generated according to the industrial link information, the final marked IPC classification number and the number of the final marked IPC classification numbers.

[0033] In a second aspect, an embodiment of the present invention further provides a system for generating enterprise patent information classification rules, wherein the system comprises:

[0034] The data acquisition and scaling module is used to obtain the enterprise patent information and industrial link information of several enterprises, and scale the IPC classification number of the enterprise patent information belonging to the same industrial link information to obtain the scaled patent information corresponding to each enterprise under each industrial link information;

[0035] The data frequency threshold screening module is used to perform frequency threshold screening processing at each level on the scaled patent information corresponding to each enterprise under each industrial link information, and obtain the reserved patent information data set corresponding to each enterprise under each industrial link information;

[0036] The data splitting and extraction module is used to perform IPC classification number splitting and frequent item extraction on the reserved patent information data set corresponding to each enterprise under each industrial link information, so as to obtain the split patent data and frequent item sets corresponding to each enterprise under each industrial link information;

[0037] The classification rule generation module is used to generate enterprise patent information classification rules based on the split patent data and the frequent item sets corresponding to each enterprise under each industrial link information.

[0038] In a third aspect, an embodiment of the present invention further provides a computer device, wherein the computer device includes a memory, a processor, and an enterprise patent information classification rule generation program stored in the memory and executable on the processor, and when the processor executes the enterprise patent information classification rule generation program, the steps of the enterprise patent information classification rule generation method of any one of the above-mentioned schemes are implemented.

[0039] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein a program for generating enterprise patent information classification rules is stored on the computer-readable storage medium, and when the program for generating enterprise patent information classification rules is executed by a processor, the steps of the method for generating enterprise patent information classification rules described in any one of the above-mentioned schemes are implemented.

[0040] Beneficial effects: Compared with the prior art, the present invention provides a method for generating enterprise patent information classification rules. The present invention first obtains enterprise patent information and industrial link information of several enterprises, and performs IPC classification number scaling processing on the enterprise patent information belonging to the same industrial link information, and obtains the scaled patent information corresponding to each enterprise under each industrial link information. Then, the frequency threshold screening processing of each level is performed on the scaled patent information corresponding to each enterprise under each industrial link information, and the retained patent information data set corresponding to each enterprise under each industrial link information is obtained. Next, the IPC classification number splitting processing and frequent item extraction processing are performed on the retained patent information data set corresponding to each enterprise under each industrial link information, and the split patent data and frequent item sets corresponding to each enterprise under each industrial link information are obtained. Finally, based on the split patent data and the frequent item sets corresponding to each enterprise under each industrial link information, the enterprise patent information classification rules are generated. The present invention can automatically identify and extract IPC classification numbers, perform intelligent screening and verification on them, analyze and process the extracted IPC classification numbers, remove inaccurate or redundant information, and significantly improve the speed and accuracy of IPC classification number processing, thereby providing solid and powerful support for enterprises' chain-linking work. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A schematic diagram of an application scenario of the method for generating enterprise patent information classification rules provided in an embodiment of the present invention.

[0042] Figure 2 A flowchart of a preferred embodiment of the method for generating enterprise patent information classification rules provided in an embodiment of the present invention.

[0043] Figure 3 The present invention provides a flowchart of the actual application of the method for generating enterprise patent information classification rules provided in the embodiment of the present invention.

[0044] Figure 4 A schematic diagram of the architecture of a system for generating enterprise patent information classification rules provided in an embodiment of the present invention.

[0045] Figure 5 A functional block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and effect of the present invention clearer and more specific, the present invention is further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0047] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations or steps, nor must they be executed in the order described. For example, some operations or steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0048] It should be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0049] It should be understood that, in order to clearly describe the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, words such as "first" and "second" are used to distinguish between identical or similar items with substantially identical functions and effects. For example, the first control information and the second control information are only used to distinguish different control information, and their order is not limited.

[0050] Those skilled in the art can understand that the words "first", "second", etc. do not limit the quantity and execution order, and the words "first", "second", etc. do not necessarily limit the differences.

[0051] It should be further understood that the term “and / or” used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0052] In order to solve the problems of the prior art, this embodiment provides a method for generating enterprise patent information classification rules. First, the enterprise patent information and industrial link information of several enterprises are obtained, and the enterprise patent information belonging to the same industrial link information is scaled by the number of IPC classification numbers to obtain the scaled patent information corresponding to each enterprise under each industrial link information. Then, the scaled patent information corresponding to each enterprise under each industrial link information is screened by frequency thresholds at each level to obtain the retained patent information data set corresponding to each enterprise under each industrial link information. Next, the retained patent information data set corresponding to each enterprise under each industrial link information is split by IPC classification numbers and extracted by frequent items to obtain the split patent data and frequent item sets corresponding to each enterprise under each industrial link information. Finally, based on the split patent data and frequent item sets corresponding to each enterprise under each industrial link information, the enterprise patent information classification rules are generated. This embodiment can automatically identify and extract IPC classification numbers, perform intelligent screening and verification on them, analyze and process the extracted IPC classification numbers, remove inaccurate or redundant information, and significantly improve the speed and accuracy of IPC classification number processing, thereby providing solid and strong support for the enterprise's chain-linking work.

[0053] The enterprise patent information classification rule generation method of this embodiment can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers; the enterprise patent information classification rule generation method can be executed by the terminal 102 or the server 104, or by the terminal 102 and the server 104 in collaboration.

[0054] The terminal 102 may be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, an IoT device, and a portable wearable device. The IoT device may be a smart speaker, a smart TV, a smart air conditioner, and a smart vehicle-mounted device, etc. The portable wearable device may be a smart watch, a smart bracelet, a head-mounted device, etc.

[0055] The server 104 may be an independent physical server or a service node in a blockchain system, wherein each service node in the blockchain system forms a peer-to-peer network.

[0056] In addition, server 104 can also be a server cluster composed of multiple physical servers, and can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), as well as big data and artificial intelligence platforms.

[0057] The terminal 102 and the server 104 may be connected via Bluetooth, USB (Universal Serial Bus) or a network or other communication connection method, and this application does not impose any limitation thereto.

[0058] In some embodiments, Figure 2 As shown, a method for generating enterprise patent information classification rules is provided. Figure 1 The server or terminal in the Figure 1 The server and terminal in the method are executed in cooperation with each other. Figure 1 The server execution in is taken as an example to illustrate, including the following steps:

[0059] Step S100, obtaining enterprise patent information and industrial link information of several enterprises, and scaling the IPC classification number of enterprise patent information belonging to the same industrial link information to obtain the scaled patent information corresponding to each enterprise under each industrial link information.

[0060] Combination Figure 3 As shown in , this embodiment first prepares and loads data to obtain patent information tables of several enterprises and a mapping relationship table between enterprises and industrial links. The patent information table is shown in Table 1 below.

[0061] Table 1

[0062]

[0063] As can be seen from Table 1, the patent information table includes: application number, IPC classification number, company name, patent name, document type and abstract. The patent information table can be manually compiled by the staff, or the system can automatically search and organize it from the patent library based on the company name. The mapping relationship table of this embodiment is shown in Table 2 below.

[0064] Table 2

[0065]

[0066] From Table 2, the mapping relationship table reflects the corresponding relationship between the enterprise name and the industrial link. Next, this embodiment can perform deduplication processing on the patent data in the patent information table to delete duplicate patent data. Then, the patent information table is merged with the mapping relationship table to obtain a merged data table, as shown in Table 3.

[0067] Table 3

[0068]

[0069] After obtaining the merged data table, this embodiment cleans the merged data table by IPC classification number, extracts the sub-category IPC classification number, the large group IPC classification number and the small group IPC classification number, and obtains the enterprise patent information and industrial link information of several enterprises. The enterprise patent information and industrial link information at this time include the contents in Table 3 above, namely, the application number, IPC classification number, enterprise name, patent name, document type, abstract and link name.

[0070] In one implementation, Figure 3 As shown in , this embodiment can filter the data. Specifically, this embodiment performs word segmentation filtering on the patent names in the enterprise patent information based on the industrial link information, and screens out the enterprise patent information related to the industrial link information by judging whether the patent name contains the word segmentation of the link name in the industrial link information. If the filtered data set is empty, the filtering step can be skipped.

[0071] Furthermore, the present embodiment can perform IPC classification number scaling processing on the enterprise patent information belonging to the same industrial link information. Specifically, the present embodiment can first obtain the number of patents of each enterprise and the number of IPC classification numbers at different levels based on the enterprise patent information, wherein the number of IPC classification numbers at different levels includes the number of sub-category IPC classification numbers, the number of large group IPC classification numbers, and the number of small group IPC classification numbers. Then calculate the average number of patents belonging to the same industrial link information to obtain the average number of patents in the link. Next, based on the number of patents of each enterprise, the number of IPC classification numbers at different levels (that is, the original number of IPC classification numbers at each level) and the average number of patents at the link, perform IPC classification number scaling processing on the number of IPC classification numbers at different levels of each enterprise belonging to the same industrial link information to obtain the scaled patent information corresponding to each enterprise under each industrial link information. The scaling formula of the present embodiment is:

[0072] ,in Indicates rounding up.

[0073] This embodiment scales the number of IPC classification numbers to avoid the IPC features of some companies in the same industry link from forming absolute features when these companies have more patents, thereby improving the accuracy of generating patent information classification rules.

[0074] Step S200: Perform frequency threshold screening processing at each level on the scaled patent information corresponding to each enterprise under each industrial link information to obtain a retained patent information dataset corresponding to each enterprise under each industrial link information.

[0075] This embodiment can filter the frequency threshold of the scaled patent information corresponding to each enterprise under each industrial link information, with the purpose of filtering the IPC classification numbers and removing some low-frequency IPC classification numbers. Specifically, for the scaled sub-class IPC classification number number of each enterprise under each industrial link information, the average number of sub-class IPC classification numbers is calculated, the sub-class IPC classification numbers with a number less than the average number are filtered, the average number of the remaining sub-class IPC classification numbers is recalculated, and the remaining sub-class IPC classification numbers are filtered repeatedly until the retained sub-class IPC classification numbers meet the threshold requirements.

[0076] In specific implementation, this embodiment performs tail truncation processing on IPC classification numbers at each level, and the formula for tail truncation processing on sub-class IPC classification numbers is as follows:

[0077] Calculate the initial mean in It is the number of IPC classification numbers of each subcategory of each enterprise under each industrial link information. It is the total number of categories of the sub-category IPC classification number.

[0078] The remaining sub-category IPC classification numbers are screened out by calculating the initial mean, and the above-mentioned tail-cutting formula is repeatedly used on the remaining sub-category IPC classification numbers until the mean of the number of screened sub-category IPC classification numbers meets the preset threshold requirement.

[0079] Similarly, after obtaining the retained sub-category IPC classification numbers, this embodiment can use the same tail-cutting processing method to process the large group IPC classification numbers and the small group IPC classification numbers. Specifically, this embodiment can collect the large group IPC classification numbers corresponding to each enterprise under each industrial link information based on the retained sub-category IPC classification numbers, calculate the average number of large group IPC classification numbers, filter the large group IPC classification numbers with a number less than the average, recalculate the average number of the remaining large group IPC classification numbers, and repeatedly filter the remaining large group IPC classification numbers until the retained large group IPC classification numbers meet the threshold requirements. Then, based on the retained large group IPC classification numbers, collect the small group IPC classification numbers corresponding to each enterprise under each industrial link information, calculate the average number of the small group IPC classification numbers, filter the small group IPC classification numbers with a number less than the average, recalculate the average number of the remaining small group IPC classification numbers, and repeatedly filter the remaining small group IPC classification numbers until the retained small group IPC classification numbers meet the threshold requirements, and obtain the retained patent information data set corresponding to each enterprise under each industrial link information. Based on this, this embodiment removes low-frequency IPC classification numbers.

[0080] Step S300: Perform IPC classification number splitting and frequent item extraction on the retained patent information dataset corresponding to each enterprise under each industrial link information, and obtain the split patent data and frequent item sets corresponding to each enterprise under each industrial link information.

[0081] Specifically, this embodiment obtains the sub-category IPC classification number in the retained patent information data set for each enterprise under each industrial link information. If the number of types of the large group IPC classification number corresponding to the sub-category IPC classification number is less than the first set value, the sub-category IPC classification number is split into the large group IPC classification number; otherwise, the sub-category IPC classification number is retained. Further, the large group IPC classification number in the retained patent information data set is obtained. If the number of types of the small group IPC classification number corresponding to the large group IPC classification number is less than the second set value, the large group IPC classification number is split into the small group IPC classification number; otherwise, the large group IPC classification number is retained. Based on this, this embodiment can obtain the split patent data corresponding to each enterprise under each industrial link information. This embodiment splits the IPC classification number from the small category layer by layer. When the number of types of the IPC classification number of the next level is too large, the upper layer characteristics are retained and no splitting is performed downward, so as to ensure that the granularity of the IPC rule can be consistent with the industrial chain link.

[0082] Furthermore, this embodiment can also extract frequent items from the reserved patent information dataset corresponding to each enterprise under each industrial link information using the Apriori algorithm for the sub-category IPC classification number, the large group IPC classification number, and the small group IPC classification number in the reserved patent information dataset to obtain frequent item sets at each level. Specifically, this embodiment can extract frequent item sets by setting the minimum support. Taking the small group IPC classification number as an example, the calculation formula for the support is:

[0083] ,in, is a certain group IPC classification number. Based on the above support formula, the support of each enterprise group IPC classification number under each industrial link information can be calculated, and then the group IPC classification number with the smallest support in each enterprise can be deleted to obtain the frequent items of the group IPC classification number in each enterprise. Based on this, this embodiment can use the same method to extract frequent items for the sub-category IPC classification number and the large group IPC classification number of each enterprise under each industrial link information, and obtain the frequent item set of each level in each enterprise under each industrial link information, so as to avoid classification deviations caused by subjective factors or one-sided information. If frequent item screening is not performed, the IPC characteristics of some enterprises may directly determine the result of the generation of patent information classification rules for the entire industrial link.

[0084] Step S400: Generate enterprise patent information classification rules based on the split patent data corresponding to each enterprise under each industrial link information and the frequent item sets.

[0085] In this embodiment, for each industrial link information, the split patent data of each enterprise and the frequent item set are matched, and the patent data in the frequent item set is screened out from the split patent data. Only the patent data belonging to the frequent item set can be used to generate enterprise patent information classification rules. Specifically, for each industrial link information, the number of IPC classification numbers of different levels in the patent data screened out by each enterprise is sorted respectively, and the first several are taken as the final marked IPC classification numbers. Finally, according to the industrial link information, the final marked IPC classification number and the number of final marked IPC classification numbers, the enterprise patent information classification rules are generated, that is, Figure 3 Generate IPC rules in and export patent information based on the enterprise patent information classification rules, as shown in Table 4 below.

[0086] Table 4

[0087]

[0088] As can be seen from Table 4, the enterprise patent information classification rules generated by this embodiment include information such as the link name of the industrial link, the IPC classification number after algorithm annotation, and the frequency ranking of the IPC classification number, which is convenient for sorting the enterprise's patent information. Different from the general IPC classification number extraction method, this method aims to more accurately extract representative IPC rules under each industrial link, and automatically use the Apriori algorithm to screen patents corresponding to the IPC classification number, so as to ensure the correctness and stability of the screening and reduce the cost and uncertainty of manual screening.

[0089] Based on the above embodiments, the present invention also provides a system for generating enterprise patent information classification rules, such as Figure 4 As shown, the system includes: a data acquisition and scaling module 10, a data frequency threshold screening module 20, a data splitting and extraction module 30, and a classification rule generation module 40. Specifically, the data acquisition and scaling module 10 is used to acquire the enterprise patent information and industrial link information of several enterprises, and perform IPC classification number scaling processing on the enterprise patent information belonging to the same industrial link information, so as to obtain the scaled patent information corresponding to each enterprise under each industrial link information. The data frequency threshold screening module 20 is used to perform frequency threshold screening processing of each level on the scaled patent information corresponding to each enterprise under each industrial link information, so as to obtain the reserved patent information data set corresponding to each enterprise under each industrial link information. The data splitting and extraction module 30 is used to perform IPC classification number splitting processing and frequent item extraction processing on the reserved patent information data set corresponding to each enterprise under each industrial link information, so as to obtain the split patent data and frequent item sets corresponding to each enterprise under each industrial link information. The classification rule generation module 40 is used to generate enterprise patent information classification rules based on the split patent data and frequent item sets corresponding to each enterprise under each industrial link information.

[0090] The working principles of each module in the enterprise patent information classification rule generation system of this embodiment are the same as the principles of each step in the above method embodiment, and will not be repeated here.

[0091] Each module in the above-mentioned enterprise patent information classification rule generation system can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0092] In some embodiments, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 5As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for generating enterprise patent information classification rules is implemented. The display unit of the computer device is used to form a visually visible image, and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse, etc.

[0093] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0094] In some embodiments, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0095] Obtain enterprise patent information and industrial link information of several enterprises, and scale the IPC classification number of enterprise patent information belonging to the same industrial link information to obtain the scaled patent information corresponding to each enterprise under each industrial link information;

[0096] The scaled patent information corresponding to each enterprise under each industrial link information is screened by frequency thresholds at each level to obtain a reserved patent information dataset corresponding to each enterprise under each industrial link information;

[0097] The retained patent information data set corresponding to each enterprise under each industrial link information is processed by IPC classification number splitting and frequent item extraction, and the split patent data and frequent item sets corresponding to each enterprise under each industrial link information are obtained;

[0098] Based on the split patent data corresponding to each enterprise under each industrial link information and the frequent item sets, enterprise patent information classification rules are generated.

[0099] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0100] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0101] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for generating enterprise patent information classification rules, characterized in that: The method comprises: Obtain enterprise patent information and industrial link information of several enterprises, and scale the IPC classification number of enterprise patent information belonging to the same industrial link information to obtain the scaled patent information corresponding to each enterprise under each industrial link information; The scaled patent information corresponding to each enterprise under each industrial link information is screened by frequency thresholds at each level to obtain a reserved patent information dataset corresponding to each enterprise under each industrial link information; The retained patent information data set corresponding to each enterprise under each industrial link information is processed by IPC classification number splitting and frequent item extraction, and the split patent data and frequent item sets corresponding to each enterprise under each industrial link information are obtained; Based on the split patent data and the frequent itemsets corresponding to each enterprise under each industrial link information, generating enterprise patent information classification rules; The patent information of enterprises belonging to the same industrial link information is scaled by the IPC classification number to obtain the scaled patent information corresponding to each enterprise under each industrial link information, including: Based on the enterprise patent information, the number of patents of each enterprise and the number of IPC classification numbers at different levels are obtained, wherein the number of IPC classification numbers at different levels includes the number of sub-class IPC classification numbers, the number of large group IPC classification numbers and the number of small group IPC classification numbers; Calculate the average number of patents belonging to the same industry link information to obtain the average number of patents in the link; Based on the number of patents of each enterprise, the number of IPC classification numbers at different levels and the average number of patents in the link, the number of IPC classification numbers at different levels of each enterprise belonging to the same industrial link information is scaled to obtain the scaled patent information corresponding to each enterprise under each industrial link information, wherein the scaled patent information includes the scaled number of sub-category IPC classification numbers, the number of large group IPC classification numbers and the number of small group IPC classification numbers; The scaling formula is: ,in Indicates rounding up; The IPC classification number splitting process and frequent item extraction process are performed on the retained patent information data set corresponding to each enterprise under each industrial link information to obtain the split patent data and frequent item sets corresponding to each enterprise under each industrial link information, including: For each reserved patent information dataset corresponding to each enterprise under each industrial link information, obtain the sub-category IPC classification number in the reserved patent information dataset, and if the number of types of the large group IPC classification number corresponding to the sub-category IPC classification number is less than the first set value, split the sub-category IPC classification number into the large group IPC classification number; Obtain the large group IPC classification number in the retained patent information data set. If the number of types of the small group IPC classification number corresponding to the large group IPC classification number is less than the second set value, split the large group IPC classification number into small group IPC classification numbers to obtain the split patent data corresponding to each enterprise under each industrial link information; For the reserved patent information data set corresponding to each enterprise under each industrial link information, the Apriori algorithm is used to extract frequent items from the sub-category IPC classification number, the large group IPC classification number and the small group IPC classification number in the reserved patent information data set to obtain the frequent item set at each level; The generating of enterprise patent information classification rules based on the split patent data and the frequent itemsets corresponding to each enterprise under each industrial link information includes: For each industry link information, the split patent data of each enterprise and the frequent item sets are matched, and the patent data in the frequent item sets are screened out from the split patent data; For each industry link information, the number of IPC classification numbers at different levels in the patent data screened by each enterprise is sorted, and the first several are taken as the final marked IPC classification numbers; The enterprise patent information classification rules are generated according to the industrial link information, the final marked IPC classification number and the number of the final marked IPC classification numbers.

2. The method for generating enterprise patent information classification rules according to claim 1, characterized in that: The acquisition of enterprise patent information and industrial link information of several enterprises includes: Obtain patent information tables of several enterprises and mapping relationship tables between enterprises and industrial links; Deduplication processing is performed on the patent data in the patent information table, and the patent information table is merged with the mapping relationship table to obtain a merged data table; The IPC classification numbers of the merged data table are cleaned, and the sub-category IPC classification numbers, large group IPC classification numbers and small group IPC classification numbers are extracted to obtain the enterprise patent information and industrial link information of several enterprises.

3. The method for generating enterprise patent information classification rules according to claim 2, characterized in that: After obtaining the enterprise patent information and industrial link information of several enterprises, it also includes: Based on the industrial link information, the patent names in the enterprise patent information are segmented and filtered to screen out the enterprise patent information related to the industrial link information.

4. The method for generating enterprise patent information classification rules according to claim 1, characterized in that: The zoomed patent information corresponding to each enterprise under each industrial link information is subjected to frequency threshold screening processing at each level to obtain a retained patent information data set corresponding to each enterprise under each industrial link information, including: For the number of scaled sub-category IPC classification numbers of each enterprise under each industrial link information, calculate the average number of sub-category IPC classification numbers, filter the sub-category IPC classification numbers with a number less than the average, recalculate the average number of the remaining sub-category IPC classification numbers, and repeatedly filter the remaining sub-category IPC classification numbers until the retained sub-category IPC classification numbers meet the threshold requirements; Based on the retained sub-category IPC classification numbers, collect the large group IPC classification numbers corresponding to each enterprise under each industrial link information, calculate the average number of large group IPC classification numbers, filter the large group IPC classification numbers with a number less than the average, recalculate the average number of the remaining large group IPC classification numbers, and repeatedly filter the remaining large group IPC classification numbers until the retained large group IPC classification numbers meet the threshold requirements; Based on the retained large group IPC classification numbers, the small group IPC classification numbers corresponding to each enterprise under each industrial link information are collected, the average number of small group IPC classification numbers is calculated, the small group IPC classification numbers with a number less than the average are filtered, the average number of the remaining small group IPC classification numbers is recalculated, and the remaining small group IPC classification numbers are filtered repeatedly until the retained small group IPC classification numbers meet the threshold requirements, thus obtaining the retained patent information data set corresponding to each enterprise under each industrial link information.

5. A system for generating enterprise patent information classification rules, characterized in that: The system is used to implement the steps of the method for generating enterprise patent information classification rules according to any one of claims 1 to 4, and the system includes: The data acquisition and scaling module is used to obtain the enterprise patent information and industrial link information of several enterprises, and scale the IPC classification number of the enterprise patent information belonging to the same industrial link information to obtain the scaled patent information corresponding to each enterprise under each industrial link information; The data frequency threshold screening module is used to perform frequency threshold screening processing at each level on the scaled patent information corresponding to each enterprise under each industrial link information, and obtain the reserved patent information data set corresponding to each enterprise under each industrial link information; The data splitting and extraction module is used to perform IPC classification number splitting and frequent item extraction on the reserved patent information data set corresponding to each enterprise under each industrial link information, so as to obtain the split patent data and frequent item sets corresponding to each enterprise under each industrial link information; The classification rule generation module is used to generate enterprise patent information classification rules based on the split patent data and the frequent item sets corresponding to each enterprise under each industrial link information.

6. A computer device, characterized in that: The computer device includes a memory, a processor, and an enterprise patent information classification rule generation program stored in the memory and executable on the processor. When the processor executes the enterprise patent information classification rule generation program, the steps of the enterprise patent information classification rule generation method as described in any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program for generating enterprise patent information classification rules. When the program for generating enterprise patent information classification rules is executed by a processor, the steps of the method for generating enterprise patent information classification rules as described in any one of claims 1 to 4 are implemented.

Images