Patent multi-dimensional analysis method and device and electronic equipment

Abstract

The invention provides a patent multi-dimensional analysis method, a patent multi-dimensional analysis device and electronic equipment, which can realize dynamic integration of multi-source patent data so as to generate a patent knowledge graph. The method comprises the steps of receiving target data input by a user; retrieving a multi-source database based on the target data to obtain a data set, the multi-source database including the patent database; preprocessing each piece of data in the data set to obtain a preprocessed data set; performing natural language processing on each piece of data in the pre-processing data set to obtain a target data set, the target data set comprising patent related data and patent text data; constructing a patent knowledge graph based on the target data set, and analyzing an industry trend corresponding to the target data based on the patent knowledge graph; and constructing the dynamic knowledge graph based on the target data set.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of patent analysis, and in particular to a patent multi-dimensional analysis method and device and electronic equipment. BACKGROUND

[0002] Patent analysis is to analyze, process and combine a large number of scattered patent information in patent specifications and patent bulletins, and to convert these information into competitive intelligence with overall and predictive functions by using statistical methods and techniques, so as to provide reference for decision-making in the development of technology, products and services of enterprises. Patent analysis is not only the premise of enterprises competing for patents, but also provides useful intelligence for enterprises to develop their technology strategies and assess competitors.

[0003] Traditional patent analysis systems rely on keyword search and manual experience judgment, and have problems such as single data dimension, insufficient search accuracy, and lagging technology trend prediction. Especially in complex technical fields (such as new energy, artificial intelligence, etc.), patent layout needs to integrate multiple dimensions such as technology life cycle and infringement risk, and existing tools are difficult to realize dynamic integration of multi-source heterogeneous data. SUMMARY

[0004] The embodiments of the present application provide a patent multi-dimensional analysis method and related equipment, which can realize dynamic integration of multi-source patent data to generate a patent knowledge graph.

[0005] The first aspect of the present application provides a patent multi-dimensional analysis method, comprising:

[0006] receiving target data input by a user;

[0007] searching a multi-source database based on the target data to obtain a data set, wherein the multi-source database comprises the patent database;

[0008] preprocessing each data in the data set to obtain a preprocessed data set;

[0009] performing natural language processing on each data in the preprocessed data set to obtain a target data set, wherein the target data set comprises patent-related data and patent text data;

[0010] constructing a patent knowledge graph based on the target data set, and analyzing an industry trend corresponding to the target data based on the patent knowledge graph;

[0011] constructing a dynamic knowledge graph based on the target data set.

[0012] The second aspect of the present application provides a patent multi-dimensional analysis device, comprising:

[0013] receive a target data input by a user;

[0014] retrieve, based on the target data, a multi-source database to obtain a data set, the multi-source database comprising the patent database;

[0015] pre-process each data in the data set to obtain a pre-processed data set;

[0016] perform natural language processing on each data in the pre-processed data set to obtain a target data set, the target data set comprising patent-related data and patent text data;

[0017] construct, based on the target data set, a patent knowledge graph, and analyze an industry trend corresponding to the target data based on the patent knowledge graph;

[0018] construct, based on the target data set, a dynamic knowledge graph.

[0019] In a possible design, the pre-processing unit is specifically configured to:

[0020] perform data cleaning on each data in the data set to obtain a cleaned data set;

[0021] perform field standardization processing and translation on data in the cleaned data set to obtain the pre-processed data set.

[0022] In a possible design, the first construction unit is specifically configured to:

[0023] determine a target navigation mode selected by the user, the target navigation mode comprising a technical route navigation, a risk of infringement navigation, and an innovation blank navigation;

[0024] construct the patent knowledge graph based on the target navigation mode and the target data set.

[0025] In a possible design, if the target navigation mode is the technical route navigation, the first construction unit constructs the patent knowledge graph based on the target navigation mode and the target data set, which comprises:

[0026] perform clustering analysis on the target data set based on a technical branch to obtain a clustering result;

[0027] determine a technical branch relationship and a technical maturity degree according to the clustering result;

[0028] According to the technical branch relationship and the technical maturity, a technology roadmap is constructed, and the technology roadmap is a patent knowledge graph corresponding to the technology roadmap navigation.

[0029] In a possible design, if the target navigation mode is the infringement risk navigation, the first construction unit constructs the patent knowledge graph according to the target navigation mode and the target data set, including:

[0030] extracting a first technical feature corresponding to the target data and a second technical feature in the target data set;

[0031] determining semantic similarity between the first technical feature and the second technical feature;

[0032] determining an infringement probability of the target data according to the semantic similarity;

[0033] generating a risk radar chart based on the infringement probability, and the risk radar chart is a patent knowledge graph corresponding to the infringement risk navigation.

[0034] In a possible design, if the target navigation mode is the innovation blank navigation, the first construction unit constructs the patent knowledge graph according to the target navigation mode and the target data set, including:

[0035] determining a target technical term in the target data set;

[0036] analyzing the target technical term to determine a patent coverage degree;

[0037] analyzing the patent coverage degree by an LSTM model to determine a development trend of a blank technology;

[0038] generating an opportunity heat map based on the development trend of the blank technology, and the opportunity heat map is a patent knowledge graph corresponding to the innovation blank navigation.

[0039] In a possible design, the second construction unit is specifically configured to:

[0040] performing text analysis on the patent text data to obtain text analysis data;

[0041] determining an entity set and a relationship set corresponding to the text analysis data based on a preset model;

[0042] processing the entity set and the relationship set by a graph neural network to generate the dynamic knowledge graph.

[0043] In a possible design, the first construction unit is further configured to:

[0044] Periodically acquire incremental patent data corresponding to the target data;

[0045] Preprocess and NLP process the incremental patent data to obtain incremental data;

[0046] Update and iterate the patent knowledge graph based on the incremental data.

[0047] The third aspect of the present application provides an electronic device comprising a memory and a processor, wherein the processor is configured to execute a computer management program stored in the memory to implement the steps of the patent multi-dimensional analysis method according to any one of the above aspects.

[0048] The fourth aspect of the present application provides a computer readable storage medium having a computer management program stored thereon, wherein the computer management program is executed by a processor to implement the steps of the patent multi-dimensional analysis according to any one of the above aspects.

[0049] In summary, it can be seen that, in the embodiments of the present application, a multi-source database is searched based on user input target data to obtain a data set; each data in the data set is preprocessed to obtain a preprocessed data set; each data in the preprocessed data set is subjected to natural language processing to obtain a target data set, which includes patent-related data and patent text data; a patent knowledge graph is constructed based on the target data set, and an industry trend corresponding to the target data is analyzed based on the patent knowledge graph; and a dynamic knowledge graph is constructed based on the target data set. Thus, the technical life cycle, infringement risk and other multi-dimensional indicators of patents can be comprehensively analyzed, the dynamic integration of multi-source data can be realized, and a patent knowledge graph can be generated. BRIEF DESCRIPTION OF DRAWINGS

[0050] Figure 1 The architecture of the patent multi-dimensional analysis system provided by the embodiments of the present application is shown in the figure;

[0051] Figure 2 The flowchart of the patent multi-dimensional analysis method provided by the embodiments of the present application is shown in the figure;

[0052] Figure 3 The virtual structure of the patent multi-dimensional analysis device provided by the embodiments of the present application is shown in the figure;

[0053] Figure 4 The hardware structure of the patent multi-dimensional analysis device provided by the embodiments of the present application is shown in the figure;

[0054] Figure 5 The embodiment of the electronic device provided by the embodiments of the present application is shown in the figure;

[0055] Figure 6An embodiment of the computer readable storage medium provided by the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0056] The technical solutions in the embodiments of the present application will be clearly and completely described in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present application.

[0057] In the following description, specific embodiments of the present application will be described with reference to steps and symbolic representations of operations that are performed by one or more computers. Unless specifically stated otherwise, as is apparent from the following discussions, it is appreciated that throughout the specification, discussions utilizing terms such as "processing," "computing," "calculating," "determining," "displaying," and / or "determining," involve the actions and / or processes of a computer system, or similar electronic computing device.

[0058] The principles of the present application are operable utilizing a multitude of other general purpose or special purpose computing devices, environments, or configurations. Examples of well known computing systems, environments, and / or configurations that can be suitable for use with the present application include, but are not limited to, handheld or laptop computers, personal computers, servers, multiprocessor systems, microcomputer-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments that include any of the above systems or devices.

[0059] The terms "first", "second", and "third" and the like in the present application are used to distinguish one object from another, rather than to describe a particular sequential order. In addition, the terms "comprises", "comprising", and "having" and any variations thereof are intended to cover a non-exclusive inclusion.

[0060] Referring to Figure 1 , Figure 1 The system structure of the patent multidimensional analysis system provided by the present application is shown in the figure. The patent multidimensional analysis system 100 includes a multimodal data integration module 101, an intelligent retrieval and semantic analysis module 102, a visual decision engine 103, and a dynamic strategy optimization module 104.

[0061] The multi-modal data integration module 101 is used for integrating heterogeneous data sources such as patent texts (claims, specifications), technical maps (IPC classification, technology node association), market intelligence (competitor dynamics, technology conversion rate), and the like, constructing a dynamic semantic network through knowledge graph technology, for example, using a graph neural network (GNN) to perform clustering analysis on technical hotspots, and automatically generating a technology evolution path diagram.

[0062] The intelligent retrieval and semantic analysis module 102 is used for realizing deep semantic understanding of patent texts based on a BERT model, supporting cross-language retrieval and high-precision matching (such as claim similarity calculation). For example, after inputting a technical keyword, the system automatically expands synonyms, associated technical terms, and outputs the infringement risk level of related patents.

[0063] The visual decision engine 103 is used for embedding a technology life cycle prediction module (based on time series analysis) and an infringement risk early warning matrix (combined with a legal case database), and providing a three-dimensional dynamic visualization interface. For example, a user can view patent application trends, core inventor distribution, and potential legal controversy hotspots in a certain technical field through an interactive chart.

[0064] The dynamic strategy optimization module 104 is used for adjusting a patent layout strategy in real time by using a reinforcement learning algorithm (such as DQN), and generating an optimal solution by comprehensively considering target functions such as technical value, market barriers, and legal compliance. For example, the system recommends claim modification suggestions or technical avoidance paths according to the patent disclosure dynamics of competitors.

[0065] The patent multi-dimensional analysis method provided by the present application will be described below from the perspective of a patent multi-dimensional analysis device, which can be a server or a service unit in a server, and the specific implementation is not limited.

[0066] Please refer to Figure 2 , Figure 2 The flowchart of the patent multi-dimensional analysis method provided by the embodiment of the present application includes:

[0067] 201, receiving target data input by a user.

[0068] In this embodiment, the patent multi-dimensional analysis device can receive target data input by a user, which can be a technical keyword or a patent, or a claim of a patent, and the specific implementation is not limited, for example, the user inputs the technical keyword "solid-state electrolyte material".

[0069] 202, retrieving a multi-source database based on the target data to obtain a data set.

[0070] In this embodiment, after the patent multidimensional analysis device receives the target data input by the user, it can search the multi-source database based on the target data to obtain a data set, wherein the multi-source database includes a patent database. For example, the target data is "solid-state electrolyte material". The patent multidimensional analysis device can automatically expand synonyms, associated technical terms, and automatically associate sub-fields such as "lithium ion conductivity" and "interface stability", and search the multi-source database to obtain related patents to obtain all patent sets corresponding thereto, that is, a data set. The multi-source database may, for example, be Derwent, PatSnap, and IncoPat, which are three different patent databases. Derwent patent database provides World Patents Index (WPI) and Patent Citation Index (PCI), covering 100 million patent data in more than 40 countries around the world, supporting in-depth search in the fields of chemistry, electronics, engineering, etc. PatSnap global patent search and analysis database integrates 157 million patent data in 126 countries / regions. IncoPat provides 1.5 billion patent data sets in 120 countries around the world, including legal status, corporate business information, pledge guarantee, and other value-added data.

[0071] It should be noted that the above three patent databases are only for illustration, and of course other patent databases can also be used, and the specific implementation is not limited.

[0072] 203. Preprocess each data in the data set to obtain a preprocessed data set.

[0073] In this embodiment, after the patent multidimensional analysis device searches the patent database to obtain a data set, it can preprocess each data in the data set to obtain a preprocessed data set. Specifically, the patent multidimensional analysis device first performs data cleaning on each data in the data set to obtain a cleaned data set, and performs field standardization (uniform field label and attribute value through semantic mapping rules) and translation processing on the data in the cleaned data set to obtain a preprocessed data set. Of course, the preprocessing can also be appropriately increased according to the actual situation, for example, data enhancement, and the specific implementation is not limited.

[0074] 204. Perform natural language processing on each data in the preprocessed data set to obtain a target data set.

[0075] In this embodiment, the patent multi-dimensional analysis device can perform natural language processing (NLP) on each data in the pre-processed data set to obtain a target data set, which includes patent related data and patent text data. The patent related data includes IPC classification number, applicant, current right holder, legal effect, and cited number of times, etc. The patent text data is the specific content of the patent.

[0076] 205、constructing a patent knowledge graph based on the target data set.

[0077] In this embodiment, after the patent multi-dimensional analysis device performs NLP on each data in the pre-processed data set to obtain a target data set, it can determine a target navigation mode selected by a user and construct a patent knowledge graph according to the target navigation mode and the target data set. Different patent knowledge graphs can be constructed according to different navigation modes. Here, the target navigation mode is taken as an example of technical route navigation, infringement risk navigation, and innovation blank navigation to explain in detail how to construct a patent knowledge graph.

[0078] 1. When the target navigation mode is technical route navigation, the patent multi-dimensional analysis device constructs the patent knowledge graph according to the target navigation mode and the target data set, which includes:

[0079] performing clustering analysis on the target data set based on technical branches to obtain a clustering result;

[0080] determining technical branch relationships and technical maturity according to the clustering result;

[0081] constructing a technical route map according to the technical branch relationships and the technical maturity, the technical route map being the patent knowledge graph corresponding to the technical route navigation.

[0082] In this embodiment, when performing technical branch clustering, the patent multidimensional analysis device obtains the IPC classification number corresponding to each patent, and clusters the patents by technical field through the IPC classification number, thereby obtaining the clustering result; then the branch relationship between each technical branch in the clustering result is mined, which includes the "derivation, substitution, complement" relationship, such as "fast charging technology" and "high energy density battery", fast charging relies on the popularization of high energy density battery; "fuel engine" and "pure electric drive" are "substitution relationship"; and the technology maturity is evaluated, and when evaluating the technology maturity of the technical branch, the number of patents in the technical branch, the number of patent citations, and the number of applicants corresponding to the patent can be combined to give the "maturity score" for the corresponding technical branch; finally, a technology roadmap is constructed based on the technical branch relationship and the technology maturity, and the technology roadmap is the patent knowledge graph corresponding to the technology roadmap navigation.

[0083] 2. When the target navigation mode is infringement risk navigation, the patent multidimensional analysis device constructs the patent knowledge graph according to the target navigation mode and the target data set, which includes:

[0084] extracting the first technical feature corresponding to the target data and the second technical feature in the target data set;

[0085] determining the semantic similarity between the first technical feature and the second technical feature;

[0086] determining the infringement probability of the target data according to the semantic similarity;

[0087] generating a risk radar chart based on the infringement probability, and the risk radar chart is the patent knowledge graph corresponding to the infringement risk navigation.

[0088] In this embodiment, the patent multidimensional analysis device can extract the first technical feature corresponding to the target data and the second technical feature of each patent in the target data set, and calculate the semantic similarity between the first technical feature and the second technical feature of each patent. Here, the semantic similarity of the feature items can be calculated by Siamese twin network, and the "similar feature proportion" is counted, and the infringement probability is calculated in combination with the legal status of existing patents (whether valid, whether the patentee has the right to maintain the right, etc. State) and generate a risk radar chart based on the infringement probability, and the risk radar chart is the patent knowledge graph corresponding to the infringement risk navigation.

[0089] 3. When the target navigation mode is innovation blank navigation, the patent multidimensional analysis device constructs the patent knowledge graph according to the target navigation mode and the target data set, which includes:

[0090] determining the target technical term in the target data set;

[0091] analyzing the target technical term to determine patent coverage;

[0092] analyzing the patent coverage by an LSTM model to determine the development trend of the blank technology;

[0093] generating an opportunity heat map based on the development trend of the blank technology, the opportunity heat map being a patent knowledge graph corresponding to the innovation blank navigation.

[0094] In this embodiment, the patent multi-dimensional analysis device can find the target technical term with high frequency and rapid growth rate from the patent text by using word frequency analysis + trend model, and check the patent coverage of the target technical term (i.e. hot technology), thereby obtaining which directions in the technical subdivision have a large number of patents and which directions have almost no patents, and combining the LSTM model to determine the development trend of the blank technology (i.e. to predict the development trend of the direction with almost no patents), and then constructing an opportunity heat map according to the development trend of the blank technology.

[0095] It should be noted that when constructing the opportunity heat map, the heat block + label is presented, and the color of the block = opportunity density (red = high potential blank, yellow = medium potential, green = low potential / dense area). For example, in the "artificial intelligence technology heat map", the "industrial scene large model fine-tuning" area is marked red, and marked "50 existing patents, predicted annual growth rate 85%", directly pointing to the innovation opportunity.

[0096] It should be noted that after the patent multi-dimensional analysis device constructs the patent knowledge graph, it can also incrementally update the patent knowledge graph. Specifically, it can periodically obtain incremental patent data corresponding to the target data; pre-process and NLP process the incremental patent data to obtain incremental data; and update and iterate the patent knowledge graph based on the incremental data.

[0097] 206、Based on the patent knowledge graph, analyze the industry trend corresponding to the target data.

[0098] In this embodiment, after the patent multi-dimensional analysis device constructs the patent knowledge graph, it can analyze the industry trend corresponding to the target data based on the patent knowledge graph, i.e. by predicting through LSTM and Monte Carlo model, combining the predicted number of patents and the frequency of technology iteration to determine whether it is in the embryonic stage, growth stage, mature stage or decline stage. If the annual growth rate of patents has been more than 50% for three years, it is judged to be in the growth stage, and if the annual growth rate is less than 30%, it is judged to be in the decline stage. From the development speed of each branch value in the patent knowledge graph and the LSTM prediction, the corresponding industry trend can be obtained.

[0099] 207. Constructing the dynamic knowledge graph corresponding to the target data based on the text data.

[0100] In this embodiment, the patent multidimensional analysis device can perform text analysis on the text data to obtain text analysis data, and process the text analysis data through a Bert plus transformer model to identify an entity set and a relationship set therein, and then process the entity set and the relationship set through a GNN graph neural network to construct a dynamic knowledge graph.

[0101] It should be noted that the association logic of the patent data is to associate the patent data with other data through "technical terms", "applicants", "application time", for example, to map the IPC classification number of the patent with the technical category in the industry standard file, and to process the legal status data specific to the patent and associate it with the "intellectual property protection regulations" in the policy data.

[0102] In summary, it can be seen that in the embodiments provided by the present application, the target data input by the user is used to search the multi-source database to obtain a data set, each data in the data set is preprocessed to obtain a preprocessed data set, each data in the preprocessed data set is subjected to natural language processing to obtain a target data set, the target data set includes patent related data and patent text data, a patent knowledge graph is constructed based on the target data set, and an industry trend corresponding to the target data is analyzed based on the patent knowledge graph, and a dynamic knowledge graph is constructed based on the target data set. Therefore, the technical life cycle, infringement risk and other multi-dimensional indexes of the patent can be comprehensively analyzed, the dynamic integration of multi-source data is realized, and the patent knowledge graph is generated.

[0103] The above describes the embodiments of the present application from the patent multidimensional analysis method, and the following describes the embodiments of the present application from the patent multidimensional analysis device.

[0104] Please refer to Figure 3 , Figure 3 The virtual structure schematic diagram of the patent multidimensional analysis device in the embodiments of the present application, the patent multidimensional analysis device 300 includes:

[0105] The receiving unit 301 is configured to receive the target data input by the user;

[0106] The searching unit 302 is configured to search the multi-source database based on the target data to obtain a data set, and the multi-source database includes the patent database.

[0107] The preprocessing unit 303 is configured to preprocess each data in the data set to obtain a preprocessed data set.

[0108] The natural language processing unit 304 is configured to perform natural language processing on each data in the preprocessed data set to obtain a target data set, and the target data set includes patent-related data and patent text data.

[0109] The first construction unit 305 is configured to construct a patent knowledge graph based on the target data set, and analyze an industry trend corresponding to the target data based on the patent knowledge graph.

[0110] The second construction unit 306 is configured to construct a dynamic knowledge graph based on the target data set.

[0111] In a possible design, the preprocessing unit 303 is specifically configured to:

[0112] perform data cleaning on each data in the data set to obtain a cleaned data set;

[0113] perform field standardization processing and translation on the data in the cleaned data set to obtain a preprocessed data set.

[0114] In a possible design, the first construction unit 305 is specifically configured to:

[0115] determine a target navigation mode selected by the user, and the target navigation mode includes a technical route navigation, an infringement risk navigation, and an innovation blank navigation;

[0116] construct the patent knowledge graph based on the target navigation mode and the target data set.

[0117] In a possible design, if the target navigation mode is the technical route navigation, the first construction unit 305 constructs the patent knowledge graph based on the target navigation mode and the target data set, including:

[0118] perform clustering analysis on the target data set based on a technical branch to obtain a clustering result;

[0119] determine a technical branch relationship and a technical maturity degree according to the clustering result;

[0120] construct a technical route map according to the technical branch relationship and the technical maturity degree, and the technical route map is the patent knowledge graph corresponding to the technical route navigation.

[0121] In a possible design, if the target navigation mode is the infringement risk navigation, the first construction unit 305 constructs the patent knowledge graph based on the target navigation mode and the target data set, including:

[0122] extract a first technical feature corresponding to the target data and a second technical feature in the target data set;

[0123] determine semantic similarity between the first technical feature and the second technical feature;

[0124] determine infringement probability of the target data according to the semantic similarity;

[0125] generate a risk radar chart based on the infringement probability, the risk radar chart being a patent knowledge graph corresponding to the infringement risk navigation.

[0126] In a possible design, if the target navigation mode is the innovation blank navigation, the first construction unit 305 constructs the patent knowledge graph according to the target navigation mode and the target data set, and the construction includes:

[0127] determine a target technical term in the target data set;

[0128] analyze the target technical term to determine patent coverage;

[0129] analyze the patent coverage by an LSTM model to determine a development trend of a blank technology;

[0130] generate an opportunity heat map based on the development trend of the blank technology, the opportunity heat map being a patent knowledge graph corresponding to the innovation blank navigation.

[0131] In a possible design, the second construction unit 306 is specifically configured to:

[0132] perform text analysis on the patent text data to obtain text analysis data;

[0133] determine an entity set and a relationship set corresponding to the text analysis data based on a preset model;

[0134] process the entity set and the relationship set by a graph neural network to generate the dynamic knowledge graph.

[0135] In a possible design, the first construction unit 305 is further configured to:

[0136] periodically acquire incremental patent data corresponding to the target data;

[0137] perform preprocessing and NLP processing on the incremental patent data to obtain incremental data;

[0138] update and iterate the patent knowledge graph based on the incremental data.

[0139] The aboveFigure 3 The patent multi-dimensional analysis device in the embodiment of the application is described from the perspective of a modular functional entity, and the patent multi-dimensional analysis device in the embodiment of the application is described in detail from the perspective of hardware processing. Please refer to FIG. 400, which is an embodiment schematic diagram of the patent multi-dimensional analysis device 400 in the embodiment of the application. The patent multi-dimensional analysis device 400 includes:

[0140] an input device 401, an output device 402, a processor 403, and a memory 404 (wherein the number of the processor 403 can be one or more, Figure 4 for example, one processor 403). In some embodiments of the application, the input device 401, the output device 402, the processor 403, and the memory 404 can be connected through a communication bus or other means, wherein, Figure 5 for example, the communication bus is taken as an example.

[0141] wherein, by calling the operation instructions stored in the memory 404, the processor 403 is configured to perform the following steps:

[0142] receiving target data input by a user;

[0143] searching a multi-source database based on the target data to obtain a data set, wherein the multi-source database includes the patent database;

[0144] preprocessing each data in the data set to obtain a preprocessed data set;

[0145] performing natural language processing on each data in the preprocessed data set to obtain a target data set, wherein the target data set includes patent-related data and patent text data;

[0146] constructing a patent knowledge graph based on the target data set, and analyzing an industry trend corresponding to the target data based on the patent knowledge graph;

[0147] constructing a dynamic knowledge graph based on the target data set.

[0148] by calling the operation instructions stored in the memory 404, the processor 403 is further configured to perform Figure 2 any one of the corresponding embodiments.

[0149] Please refer to Figure 5 , Figure 5 which is an embodiment schematic diagram of an electronic device provided by the embodiment of the application.

[0150] As Figure 5As shown, the embodiment of the present application provides an electronic device, comprising a memory 510, a processor 520, and a computer program 511 stored in the memory 510 and executable on the processor 520, and the processor 520 implements the following steps when executing the computer program 511:

[0151] receiving target data input by a user;

[0152] searching a multi-source database based on the target data to obtain a data set, wherein the multi-source database comprises the patent database;

[0153] preprocessing each data in the data set to obtain a preprocessed data set;

[0154] performing natural language processing on each data in the preprocessed data set to obtain a target data set, wherein the target data set comprises patent-related data and patent text data;

[0155] constructing a patent knowledge graph based on the target data set, and analyzing an industry trend corresponding to the target data based on the patent knowledge graph;

[0156] constructing a dynamic knowledge graph based on the target data set.

[0157] In the specific implementation process, when the processor 520 executes the computer program 511, the following steps can be implemented Figure 2 any of the embodiments.

[0158] Since the electronic device introduced in the embodiment is the device used by the computing device for implementing the array antenna frequency point unit excitation method in the embodiment of the present application, based on the method introduced in the embodiment of the present application, those skilled in the art can understand the specific implementation of the electronic device of the embodiment and its various forms, so the implementation of the electronic device in the method of the embodiment of the present application is not introduced in detail, as long as the device used by those skilled in the art to implement the method in the embodiment of the present application belongs to the scope of the present application.

[0159] Please refer to FIG. 600, which is an embodiment of a computer readable storage medium provided by the embodiment of the present application.

[0160] As shown in FIG. 600, the embodiment of the present application further provides a computer readable storage medium 600, which stores a computer program 611, and the computer program 611 is executed by a processor to implement the following steps:

[0161] receiving target data input by a user;

[0162] searching a multi-source database based on the target data to obtain a data set, the multi-source database comprising the patent database;

[0163] preprocessing each data in the data set to obtain a preprocessed data set;

[0164] performing natural language processing on each data in the preprocessed data set to obtain a target data set, the target data set comprising patent-related data and patent text data;

[0165] constructing a patent knowledge graph based on the target data set, and analyzing an industry trend corresponding to the target data based on the patent knowledge graph;

[0166] constructing a dynamic knowledge graph based on the target data set.

[0167] In the specific implementation process, the computer program 611 is executed by the processor to implement Figure 2 any embodiment of the corresponding embodiment.

[0168] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0169] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0170] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices produce a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one flow or multiple flows and / or blocks Figure 1 an apparatus that performs the functions specified in one block or multiple blocks.

[0171] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the flow Figure 1 The flow or flows and / or blocks Figure 1 The functions specified in the flow or flows and / or blocks

[0172] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flow Figure 1 The flow or flows and / or blocks Figure 1 The functions specified in the flow or flows and / or blocks

[0173] The embodiments of the present application also provide a computer program product, which includes computer software instructions, when the computer software instructions are run on a processing device, cause the processing device to execute the flow Figure 1 in the corresponding embodiments.

[0174] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function described in the embodiments of the present application is produced. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium that can be stored by the computer or data storage device such as server, data center, etc. integrated with one or more available media sets. The available media can be magnetic media (for example, floppy disk, hard disk, magnetic tape), optical media (for example, DVD), or semiconductor media (for example, solid state disk (SSD)) and the like.

[0175] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above described system, device and unit can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0176] In several embodiments provided by the present application, it should be understood that the disclosed system, device and method can be implemented in other manners. For example, the described device embodiments are merely schematic. For example, the division of the units is only a logical function division. There can be another division manner for the actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0177] The units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments.

[0178] In addition, each functional unit in the various embodiments of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0179] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or substantially, or all or part of the technical solutions that make contributions to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, and various media that can store program codes.

[0180] The above-described and above-embodied examples are only used to illustrate the technical solutions of the present application, and are not intended to limit the present application; although the present application has been described in detail with reference to the foregoing examples, those skilled in the art should understand that the technical solutions recorded in the foregoing examples can still be modified, or some technical features thereof can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method of patent multidimensional analysis, characterized by, The method comprises the following steps: receiving target data input by a user; searching a multi-source database based on the target data to obtain a data set, the multi-source database comprising the patent database; preprocessing each data in the data set to obtain a preprocessed data set; performing natural language processing on each data in the preprocessed data set to obtain a target data set, the target data set comprising patent-related data and patent text data; constructing a patent knowledge graph based on the target data set and analyzing an industry trend corresponding to the target data based on the patent knowledge graph; constructing a dynamic knowledge graph based on the target data set.

2. The method of claim 1, wherein, The preprocessing of each data in the data set to obtain a preprocessed data set comprises the following steps: performing data cleaning on each data in the data set to obtain a cleaned data set; performing field standardization processing and translation on the data in the cleaned data set to obtain a preprocessed data set.

3. The method of claim 1, wherein, The construction of the patent knowledge graph based on the target data set comprises the following steps: determining a target navigation mode selected by the user, the target navigation mode comprising a technology roadmap navigation, an infringement risk navigation, and an innovation blank navigation; constructing the patent knowledge graph according to the target navigation mode and the target data set.

4. The method of claim 3, wherein, If the target navigation mode is the technology roadmap navigation, the construction of the patent knowledge graph according to the target navigation mode and the target data set comprises the following steps: performing cluster analysis on the target data set based on a technology branch to obtain a cluster result; determining a technology branch relationship and a technology maturity degree according to the cluster result; constructing a technology roadmap according to the technology branch relationship and the technology maturity degree, the technology roadmap being the patent knowledge graph corresponding to the technology roadmap navigation.

5. The method of claim 3, wherein, If the target navigation mode is the infringement risk navigation, the construction of the patent knowledge graph according to the target navigation mode and the target data set comprises the following steps: extracting a first technology feature corresponding to the target data and a second technology feature in the target data set; determining a semantic similarity between the first technology feature and the second technology feature; determining an infringement probability of the target data according to the semantic similarity; generating a risk radar chart based on the infringement probability, the risk radar chart being the patent knowledge graph corresponding to the infringement risk navigation.

6. The method of claim 3, wherein, If the target navigation mode is the innovation blank navigation, the construction of the patent knowledge graph according to the target navigation mode and the target data set comprises the following steps: determining a target technology term in the target data set; analyzing the target technology term to determine a patent coverage degree; analyzing the patent coverage degree through an LSTM model to determine a development trend of a blank technology; generating an opportunity heat map based on the development trend of the blank technology, the opportunity heat map being the patent knowledge graph corresponding to the innovation blank navigation.

7. The method according to any one of claims 1 to 6, characterized in that, The construction of the dynamic knowledge graph based on the target data set comprises the following steps: performing text analysis on the patent text data to obtain text analysis data; determine an entity set and a relation set corresponding to the text analysis data based on a preset model; process the entity set and the relation set through a graph neural network to generate the dynamic knowledge graph.

8. The method according to any one of claims 1 to 6, characterized in that, After the patent knowledge graph is constructed based on the target data set, the method further comprises: periodically acquire incremental patent data corresponding to the target data; preprocess and NLP process the incremental patent data to obtain incremental data; update and iterate the patent knowledge graph based on the incremental data.

9. A patent multidimensional analysis apparatus, characterized by, comprises: a receiving unit configured to receive target data input by a user; a retrieving unit configured to retrieve a multi-source database based on the target data to obtain a data set, the multi-source database comprising the patent database; a preprocessing unit configured to preprocess each data in the data set to obtain a preprocessed data set; a natural language processing unit configured to perform natural language processing on each data in the preprocessed data set to obtain a target data set, the target data set comprising patent-related data and patent text data; a first constructing unit configured to construct a patent knowledge graph based on the target data set and analyze industry trends corresponding to the target data based on the patent knowledge graph; a second constructing unit configured to construct a dynamic knowledge graph based on the target data set.

10. An electronic device, comprising: comprises: a memory and a processor, the processor being configured to execute a computer management program stored in the memory to implement the steps of the patent multi-dimensional analysis method according to any one of claims 1 to 8.

Images