185 results about "Patent document" patented technology

The invention discloses a patent data analysis method based on a dynamic context window, which belongs to the technical field of text data analysis, and comprises the following steps: extracting domain features to obtain a query quantity q; sorting the patent documents d based on the similarity between the patent documents d and the query quantity q; splitting the patent document into minimum semantic units according to a sorting sequence by using a recursive partitioning algorithm, and keeping a document structure by using a local alignment algorithm and a hierarchical reduction algorithm; performing feature extraction; carrying out soft clustering in combination with the technical field feature weight and the technical relevancy; calculating and storing technical association probabilities among the fragments; establishing a quick retrieval tree based on the established serial numbers; and dynamically adjusting the size of a context window for the obtained core fragments according to the importance of the document, and expanding the context. According to the patent data analysis method based on the dynamic context window, the problem that the analysis effect is poor due to the fact that an existing patent data analysis mode is limited by an upper window and a lower window is solved.

An interactive, dynamic GUI for visualization of patent documents including content-dense graphics illustrating the number, content size, type of a multiplicity of patent documents (issued or granted patent versus published pending application), distributed over time, with comparison to similar patent documents, market events, and expert insights based upon content of specification or detailed description and claims, all within a predetermined technology sector having at least one sub-sector or category within the technology sector.

To address such a problem that it is not easy to generate a suitable prompt to be applied to a patent document.SOLUTION: A program causing a computer including a processor and a storage part to execute processing, the program causes the processor to execute: a task receiving step of receiving task information relating to a task to be executed on a patent document; a query receiving step of receiving query information to be applied to the patent document; a document acquisition step of acquiring a patent document relating to the patent; an extraction step of extracting a prescribed extraction part out of the patent document acquired in the document acquisition step, according to the task received in the task reception step; and a generation step of generating a prompt including the query information received in the query reception step and the extracted part extracted in the extraction step.SELECTED DRAWING: Figure 14

The invention provides a tunnel intelligent construction system and method based on a knowledge enhancement large model, and relates to the technical field of artificial intelligence. The system comprises a data layer (a data acquisition module), a knowledge layer (a knowledge base construction module), a decision-making layer (a decision-making module and an evaluation module) and an application layer (a classification module and an intelligent question and answer module), the knowledge layer constructs a knowledge base and a knowledge graph based on professional specification documents and patent documents, and enhances the generalization ability and reasoning ability of a general large model in the tunnel engineering field; the decision-making layer designs a support decision-making method jointly driven by data and knowledge, and constructs a safety risk grading evaluation system to perform safety evaluation on the support scheme; according to the application layer, an external knowledge base is used for enhancing general large model identification event types, working modules corresponding to different events are called respectively, and the functions of integrating excavation support decision making, safety evaluation, tunnel intelligent question answering and the like are achieved. Therefore, according to the embodiment of the invention, by introducing the knowledge enhancement large model, the utilization rate of the multi-source heterogeneous data of the tunnel is improved, and efficient and safe decision support is provided for intelligent construction of the tunnel.

The invention relates to an automatic patent document generation method and system based on retrieval enhancement, and the method comprises the steps: carrying out the feature extraction of text content inputted by a user, and obtaining keywords and key sentences of the text content; based on the keywords, performing text retrieval in a pre-constructed text database, and sorting text retrieval results; based on the key sentences, vector retrieval is carried out in a pre-constructed vector database, and vector retrieval results are sorted; reordering the text retrieval result and the vector retrieval result through a reciprocal ordering algorithm; determining an auxiliary enhanced document in the reordering result; inputting the text content input by the user and the auxiliary enhanced document into the large language model, and outputting a patent document conforming to the standard template through the large language model; wherein patent documents in a text format are stored in the text database; vectorized patent documents are stored in the vector database; the large language model is trained based on a text database and a vector database.

A method may include receiving a plurality of claim texts corresponding to a plurality of claims originating from a patent document; identifying, using a generative artificial intelligence tool (generative AI tool), a common concept shared between a set of claim texts of the plurality of claim texts; presenting the common concept in a tabular form including a first column listing the common concept and additional columns corresponding to respective claim texts of the pluralities of claim texts indicating a presence or absence of the common concept; verifying, using a non-generative AI algorithm that the common concept has corresponding representations within the set of claim texts; and in response to the verifying, generating an interactive matrix, wherein the interactive matrix visually represents a relationship between the common concept and the set of claim texts.

The file is a patent document of an electric power material purchase and inventory optimization management system, the system is mainly introduced to comprise a material information management module, a warehouse-in and warehouse-out management module, an inventory monitoring and analysis module, a purchase demand grading module and an approval process generation module, and comprehensive optimization management of electric power material purchase and inventory is achieved. According to the system, basic information and historical purchasing data of electric power materials are imported, stored and updated through a material information management module; the warehouse-in and warehouse-out management module records warehouse-in and warehouse-out information of the materials and updates inventory data in real time; the inventory monitoring and analysis module monitors the inventory in real time and performs trend analysis, and sets a residual threshold to trigger a purchase application; the purchase demand grading module sets material purchase demands and emergency degrees according to historical purchase data and trend analysis results; and the approval process generation module automatically generates approval process lists of different levels according to the purchase emergency degree. The system improves the efficiency and accuracy of electric power material purchasing, and optimizes inventory management.

Various embodiments disclosed relate to a method of producing an analysis document using generative artificial intelligence, the method comprising: maintaining a database containing multiple language learning models and a collection of prompts; generating a patent prosecution tool user interface integrated with a generative artificial intelligence program; receiving a user input comprising a matter associated with at least one matter dataset, where the matter dataset includes a plurality of patent documents associated with the matter; selecting a language learning model from the database; retrieving a plurality of patent documents for display on the patent prosecution tool user interface; loading at least one of the plurality of patent documents into the artificial intelligence program; displaying more than one prompt from the collection of prompts; initiating a script in the generative artificial intelligence program based on a user selected prompt and the at least one patent document; analyzing the patent document according to the script to produce a preliminary analysis; producing the analysis document according to the preliminary analysis; saving the analysis document.

The invention discloses a patent literature retrieval system, method and equipment and a storage medium, and relates to the field of data processing. The system comprises a data acquisition module for acquiring a retrieval request and historical behavior data of a user; the intention analysis module is used for analyzing the current request through a semantic analysis model and a technical field topic model so as to determine a user intention and an intention matching degree; the user behavior factor generation engine extracts dominant and recessive behavior characteristics from the historical data, and inputs the dominant and recessive behavior characteristics into a pre-trained user portrait model to generate user behavior factors; a recommendation generation engine recall candidate patents according to the intention of the user, and an authority calculation module calculates the authority of each patent according to a patent citation network; and the patent recommendation module fuses the user behavior factors, the user intention matching degree and the authority degree, and comprehensively sorts candidate patents to generate a recommended patent list. The method can meet the precision requirements of different users, and reduces the deviation between the patent recommendation result and the real expectation of the user.

The invention discloses an intellectual property achievement transformation management system, and relates to the technical field of intellectual property management systems, comprising the following steps: S1, storing intellectual property materials; s2, material analysis; s3, feature extraction: carrying out keyword automatic extraction by utilizing a big data patent file, forming a keyword set, carrying out position analysis on a text of the patent file, marking a word segmentation sequence, inserting a user dictionary, recording related proper nouns of the technical field to which the patent file belongs, filtering stop words and virtual words in the text of the patent file, and carrying out feature extraction; calculating and counting feature items in the patent document text; and S4, website display. According to the method, the optimal patent with relatively high matching degree with the demand of the enterprise user can be conveniently provided for the enterprise user, one-time sorting can be performed according to the matching degree, the value degree of multiple patents can be judged at the same time, the rate that the user needs to use keywords to perform knowledge library knowledge retrieval is improved, meanwhile, the scientific and technological achievement conversion efficiency can be improved, and the enterprise user experience is improved. And enterprises can select conveniently.

This program is to be executed by a computer provided with a processor and a storage unit, wherein the processor executes: a task receiving step for receiving task information pertaining to a task to be executed with respect to a patent document; a query receiving step for receiving query information to be applied to the patent document; a document acquisition step for acquiring a patent document pertaining to a patent; an extraction step for extracting a predetermined extraction place, from the patent document acquired in the document acquisition step, in accordance with the task received in the task receiving step; and a generation step for generating a prompt including the query information received in the query receiving step and the extraction place extracted in the extraction step.

Mutual authentication and CSR verification techniques are described in this patent document. When a first person calls a second person, neither of them know that the other person is who he or she says he or she is. After a second person receives the call, the second person can log into a provider portal using a user device. After the second person logs in, the second person can see a verification of the call, can input on the user device a time passcode, or can receive such as passcode from a central system to authenticate the first person. The first person can provide the passcode to the second person. Upon receiving the inputted passcode, the second person can use his or her user device to indicate that the time passcode is correct so that the second person can be authenticated to access the first person's account.

Systems and methods for reducing duplication of data in a data repository storing evidence corresponding to claim elements of a patent document. The systems and methods include a first user interface with a first plurality of rows corresponding to a plurality of first claim elements of a first patent document and a second plurality of columns corresponding to a plurality of second claim elements of a second patent document. The first plurality of rows and the first plurality of columns are arranged in a matrix format and form a plurality of cells. The user interface includes a user selectable input area for the plurality of cells. A pointer can be created in the data repository that links a first claim element of the plurality of first claim elements with a second claim element of the plurality of second claim elements responsive to an input in the user selectable input area.

A method and a computing device for extracting the objective and solution of patent document based on artificial intelligence AI is disclosed. The method for extracting objectives and solutions from patent documents performed by a computing device, comprising: extracting objectives and solutions from the technical content included in a first patent document; receiving a viewing request for the first patent document; displaying the objectives and solutions of the first patent document in response to the viewing request; searching for at least one second patent document having the same or similar solution as the patent document and having different objectives, in response to a searching request for the objective form a user; and providing at least one second patent documents.

An artificial leather flame-retardant detection device is used for solving the technical problems that a device in a background technology patent document can only detect one piece of cloth at the same time and cannot detect a plurality of different pieces of cloth at the same time to achieve a comparison effect, so that the device is low in flame-retardant detection efficiency and is not visual. The protection box is provided with an ignition and flaming assembly, the protection box is rotatably provided with a clamping assembly for clamping leathers with different proportions and formulae, and the clamping assembly is rotatably installed on one side of the protection box, and the leather flame-proof testing device is simple in structure and mainly used for performing flame-proof testing on the leathers to be tested.

This patent document describes a method and system which enables website operators to classify the behaviors of website visitors using a measurement script, without the use of third party cookies. The method includes providing multiple user-behavior-classification rule sets, each rule set including user actions for a corresponding behavior class, and including the rule sets in a measurement script. The script is configured to cause each user electronic device on which it is installed to, in response to detecting device interaction that correspond with at least one predefined user action of a behavior class, store, in a first party cookie, identifiers corresponding to the behavior classes. The method further includes making the script available to multiple web servers, each of which serves a unique website including one or more pages that provide access to the script, wherein the network server is not provided access to the first party cookies.

The present disclosure relates generally to image signal processing including digital watermarking. Digital watermarking can be used to detect manifest swapping in, e.g., C2PA protected content. Various combinations and technology are described in this patent document and claims.

To address such a problem that it is not easy to generate a suitable prompt to be applied to a patent document.SOLUTION: A program causing a computer including a processor and a storage part to execute processing, the program causes the processor to execute: a task receiving step of receiving task information relating to a task to be executed on a patent document; a query receiving step of receiving query information to be applied to the patent document; a document acquisition step of acquiring a patent document relating to the patent; an extraction step of extracting a prescribed extraction part out of the patent document acquired in the document acquisition step, according to the task received in the task reception step; and a generation step of generating a prompt including the query information received in the query reception step and the extracted part extracted in the extraction step.SELECTED DRAWING: Figure 14

To address such a problem that it is not easy to generate a suitable prompt to be applied to a patent document.SOLUTION: A program causing a computer including a processor and a storage part to execute processing, the program causes the processor to execute: a task receiving step of receiving task information relating to a task to be executed on a patent document; a query receiving step of receiving query information to be applied to the patent document; a document acquisition step of acquiring a patent document relating to the patent; an extraction step of extracting a prescribed extraction part out of the patent document acquired in the document acquisition step, according to the task received in the task reception step; and a generation step of generating a prompt including the query information received in the query reception step and the extracted part extracted in the extraction step.SELECTED DRAWING: Figure 14

Provided are a computer program, an information processing method, and an information processing device that can be expected to assist in generating additional information such as a tag or a label for textual information including a patent document.　A computer program according to the present embodiment causes a computer to execute processing for: acquiring textual information pertaining to a patent; extracting text including a prescribed term from the acquired textual information; and generating one or more labels indicating the content of the text using a language model which has been machine-trained in advance on the basis of the extracted text.

The invention relates to a science and technology development stage identification and prediction method based on a life cycle matrix. The method comprises the steps of determining a direction involved in the science and technology field; scientific and technological papers and patent literatures are retrieved, time sequence data of the publication quantity of the scientific and technological papers and the application quantity of patents are obtained, S curve fitting is carried out, and time nodes of the scientific and technological field in the germination stage, the growth stage, the mature stage and the decline stage of basic research and technology application are identified; taking the basic research stage and the technical application stage as horizontal and vertical coordinates, and constructing a life cycle matrix according to a time overlapping region division result of the basic research stage and the technical application stage; and according to the life cycle matrix and the duration of each stage, an evolution trend curve of the fundamental research and technology application stage is drawn, and field growth pattern recognition and development law prediction are carried out. According to the method, the interaction relationship between the basic research and the technical application in the scientific and technological development process is demonstrated, and guidance is provided for identifying and predicting the scientific and technological development stage and trend.

The embodiment of the application relates to a processing method and device for mining patent information in combination with a large language model, the method comprising: selecting a large language model as a first model, assigning five target tasks to the first model, and constructing five task data sets to fine-tune the first model; receiving a PDF file of a small molecule drug patent after fine-tuning is completed and performing image, text block and table extraction on the PDF file; then performing molecular image / molecular label / irrelevant table screening and molecular activity table splicing based on the model; then constructing a label-image corresponding relationship table based on the molecular image / molecular label / spliced table information sequence and the first model, and constructing a label-activity information corresponding relationship table based on the first model and the spliced table information sequence; and merging the two corresponding relationship tables to obtain a multi-modal comprehensive information table; finally, a corresponding mining report is fed back by the patent file and the multi-modal comprehensive information table. Through the application, the data mining efficiency can be improved.

To address such a problem that it is not easy to generate a suitable prompt to be applied to a patent document.SOLUTION: A program causing a computer including a processor and a storage part to execute processing, the program causes the processor to execute: a task receiving step of receiving task information relating to a task to be executed on a patent document; a query receiving step of receiving query information to be applied to the patent document; a document acquisition step of acquiring a patent document relating to the patent; an extraction step of extracting a prescribed extraction part out of the patent document acquired in the document acquisition step, according to the task received in the task reception step; and a generation step of generating a prompt including the query information received in the query reception step and the extracted part extracted in the extraction step.SELECTED DRAWING: Figure 14

The invention discloses an auxiliary system and method based on data mining for technology identification, and relates to the field of data matching analysis. The invention trains and tests a recurrent neural network model to construct a final recurrent neural network model, and provides a model for extracting keywords from patent document data to be analyzed later; trains and tests an SVM classification model to construct a final SVM classification model, and provides a classification model for classifying keywords from patent document data to be analyzed extracted by the final recurrent neural network model later; and simultaneously stores the queried technology identification data in separate libraries, and allocates different permissions to different users according to the number of times different users call these different types of technology identification data, thereby reducing invalid calls by users, avoiding resource occupation, and improving the efficiency of calls.

The invention relates to a method and system for automatically generating a patent document based on a large language model, and the method comprises the steps: training a patent large language model for patent document writing in advance, and directly generating patent claims and patent specifications through the patent large language model according to a patent technical scheme provided by a user, and the accuracy of the claims and the details of the specification are ensured through work of compliance proofreading, content processing and typesetting processing, and the method is particularly suitable for patent application scenes of complex technical schemes. According to the technical scheme, common users can be helped to directly generate patent documents, and the labor cost of patent writing is reduced. And the writing work of new people in the industry can be assisted, and the writing quality of the new people in the industry is improved.

Disclosed in this patent document are, among other things, techniques, and apparatuses for improving the efficiency of wireless communication. In one aspect, a method of wireless communication is disclosed. The method includes determining, by a wireless node, a control channel monitoring constraint based on a first condition. The method further includes monitoring, by the wireless device, one or more control channel candidates at a control channel monitoring occasion, wherein a maximum number of the control channel candidates within a resource unit or a maximum number of non-overlapped control channel elements within a resource unit satisfies the control channel monitoring constraint.

The specification discloses a patent retrieval method, device and equipment for multiple retrieval scenarios. Patent field language models are obtained by training general language models with fields of patent documents as training data. For multiple retrieval scenarios, positive and negative samples of each patent document are screened through different weight multi-path recall and random sampling, and training data of a patent semantic representation model of each retrieval scenario is constructed to train the patent field language models, and then the patent semantic representation model of each retrieval scenario is obtained to generate semantic vectors of each field of the patent, and the semantic vectors are stored in a patent retrieval vector database of each retrieval scenario. According to the semantic vectors of the retrieval fields, similar patent documents are searched from the patent retrieval vector database of the target retrieval scenario. Through the above scheme, the semantic representation ability of the patent semantic representation model for the patent fields of different retrieval scenarios is improved, and the retrieval precision is improved.

To provide a patent document creation device, etc. being further user-friendly in supporting creation of a patent document.SOLUTION: A patent document creation device for supporting creation of a patent document using a large-scale language model, includes an acquisition unit that acquires patent information relating to a patent to be described in the patent document, a question generation unit that generates a first question for requesting a detailed description of the patent using the large-scale language model on the basis of the patent information, an answer acquisition unit that acquires an answer to the first question from a user, an answer generation unit that when the answer to the first question is not acquired from the user, generates an answer to the first question using the large-scale language model, and a creation unit that creates the patent document using the large-scale language model on the basis of the patent information and a first user answer to the first question acquired from the user or a first automatic answer to the first question generated by the answer generation unit.SELECTED DRAWING: Figure 2

The invention provides a patent document attached drawing display method, device and equipment and a storable medium, and is suitable for the technical field of computers.The method comprises the steps that a patent document attached drawing display request of a user is received, and the patent document attached drawing display request comprises retrieval text information and an attached drawing number set, the attached drawing number set is composed of at least two attached drawing numbers; determining an initial to-be-displayed attached drawing according to the mutual inclusion relationship between the attached drawing number of the patent document attached drawing and the attached drawing number set; based on a plurality of preset scale feature windows, respectively performing semantic feature extraction on the initial to-be-displayed attached drawings and the retrieval text information, and generating to-be-displayed attached drawing alignment features and retrieval text alignment features; and performing matching analysis on the alignment features of the to-be-displayed attached drawings and the alignment features of the retrieval texts, and determining a target to-be-displayed attached drawing for displaying to a user. The method is used for displaying the patent drawings conforming to the retrieval content and helping the user to quickly know the technical scheme.

The invention provides a patent document database construction method and device based on technical description. The method comprises the following steps: identifying a main body tag and a description tag of each patent document based on a named entity identification model; carrying out punctuation mark-based feature statement division on the technical description part, and combining all main body tags and / or all description tags belonging to the same feature statement to obtain a technical description combination; and associating the patent number of the patent file with all the technical description combinations to form a patent file database based on the technical description. The patent document is subjected to entity recognition, the feature statements are used as the combination range of the main tags and the description tags, and the technical description of the patent document is combined by using more simplified main information, so that complete coverage of the feature information is realized; and the problem that the retrieval precision is influenced by redundant descriptions or interference words in traditional independent keywords or key sentences is avoided.