30 results about "Patent classification" patented technology

The invention discloses a city innovation mode identification method, system and device and a storage medium. The method comprises the following steps: acquiring patent data of all cities, and preprocessing the patent data; based on patent classification standard codes, knowledge changes and knowledge types of the patent data are evaluated, and new knowledge entry ability indexes are determined; wherein the knowledge type comprises new knowledge and old knowledge; combining the patent classification standard codes, determining a knowledge recombination type of each combination based on the two knowledge types of the new knowledge and the old knowledge, and further determining a knowledge recombination capability index; and determining an innovation mode of the target city according to the new knowledge entry capability index and the knowledge recombination capability index. According to the invention, accurate identification and evaluation of the city innovation mode are realized, and the depth of city innovation mode evaluation is improved. The method can be widely applied to the technical field of urban innovation evaluation.

The invention provides a regional industrial structure optimization method and device, equipment and a storage medium. In some embodiments of the present disclosure, the industrial endowment analysis of the target area is performed by combining the international patent classification and custom industry classification relationship table and the international patent classification and strategic emerging industry classification relationship table to obtain the industrial endowment analysis result of the target area; in combination with the strategic emerging industrial map and the user-defined industrial map, according to the industrial endowment analysis result of the target region, carrying out industrial structure optimization analysis on the target region to obtain a key industrial development direction of the target region; according to the invention, based on patent big data and industrial and commercial big data, regional industrial endowment quantitative analysis is carried out from the technical level, the current industrial situation of a target region can be efficiently and intuitively found, the analysis precision is high, the effectiveness and logicality are high, and comprehensiveness, systematicness, objectivity and scientificity are realized; in addition, the regional industrial structure optimization method provided by the invention has implementability.

The invention discloses an enterprise main business positioning method and system based on patent text data. The method comprises the following steps: acquiring authorized patent data of a target enterprise and dynamically updating the authorized patent data in real time; performing data preprocessing on the acquired authorized patent data, forming a basic mapping relation between patents and industries according to patent classification and industry classification information, extracting patent text content of the authorized patent data by utilizing a Chinese big model, and mapping a patent text extraction result to a corresponding industry; calculating a patent availability score of the target enterprise based on the attribute information of the target enterprise, the basic mapping relation and the patent text extraction result; and according to the basic mapping relationship between the patent and the industry, the distribution of the number of patents of the target enterprise in each field and the patent availability score of the target enterprise, constructing a comprehensive positioning model, and outputting an industry chain node to which the target enterprise belongs. According to the scheme, the positioning accuracy of the node position of the industry chain to which the enterprise belongs is improved.

The invention relates to the technical field of intelligent control of automobile part machining defects, in particular to a defect control system of an automobile brake caliper body high-pressure casting process and a control method of the defect control system, and relates to the aspects of high-pressure casting, defect control, brake caliper bodies, process optimization and the like, and the patent classification number of the intelligent control system is B22D17 or G05B19. The system comprises a sensor data acquisition module, a defect prediction module, a process parameter optimization module, a control execution module and a quality feedback module. The method comprises the steps of data acquisition, defect prediction, parameter optimization, parameter adjustment and feedback calibration. The porosity and shrinkage porosity defect indexes are predicted in real time through a mathematical model, process parameters are optimized, and closed-loop control is achieved. The problems of low yield and unstable performance in the casting process are effectively solved, the product quality and the production efficiency are improved, and the method is suitable for batch production of automobile brake caliper bodies.

Embodiments of the present application disclose a patent hierarchical classification method and device, electronic equipment and storage medium. The method comprises: receiving patent text information to be classified, wherein the patent text information comprises a title and / or an abstract and / or a claim of a patent; preprocessing the patent text information to obtain preprocessed patent text information; inputting the preprocessed patent text information into a patent classification model to obtain a patent hierarchical classification result and a corresponding prediction probability value; wherein the patent classification model independently classifies the preprocessed patent text information at each level, and obtains the patent hierarchical classification result and the corresponding prediction probability value according to the result of each independent classification. The above technical solution solves the technical problems that the patent classification effect is not ideal and the accuracy of the classification result cannot be accurately predicted, and achieves the technical effects of patent automatic classification and prediction of probability value, and improvement of classification efficiency.

The invention relates to a patent classification method, a patent classification model training method and electronic equipment, and the method comprises the steps: constructing a first cue word which comprises the patent information, expert knowledge, classification standards and a first chain type classification thought of a to-be-classified first patent; and taking the cue word as the input of a pre-trained classification large model, and enabling the classification large model to analyze the patent information of the first patent by using expert knowledge and a classification standard based on a first chain type classification thought so as to obtain a classification result of the first patent. According to the method, the cue word is constructed based on chain thinking, so that the model can better learn and use expert knowledge and classification standards based on a chain classification thought, and the accuracy of a classification result is improved.

This invention belongs to the field of data processing and artificial intelligence technology, specifically a method and system for automatic classification of medical device patents based on deep learning. The method includes the following steps: acquiring textual data of medical device patents and performing preprocessing; introducing medical device classification standards as an external knowledge base, and calibrating the labels of the preprocessed text data to form a standard dataset; for categories with insufficient sample numbers in the standard dataset, generating synthetic data based on the patent text using a generative model; constructing a deep learning classification model that integrates global and local semantic features; training the deep learning classification model using the enhanced dataset, and inputting the medical device patent text to be classified into the trained model for classification prediction, outputting its corresponding medical device classification standard category. This invention solves the problems of mismatch between existing patent classification systems and industry regulatory standards, and low classification accuracy.

The invention relates to the technical field of patent classification and artificial intelligence, in particular to an intelligent system for improving patent classification quality, which comprises a patent information extraction module, a patent information synchronization and retrieval module, a patent information extraction module and a patent classification module, all the modules work cooperatively and are in communication connection with the local patent database, the authoritative patent data source and the LLM. The patent information extraction module supports multi-format input and obtains complete patent information; the synchronization and retrieval module realizes patent information synchronization, storage and vector search; the information extraction module is combined with the optimization cue word to call LLM, and patent core key points are extracted in a specified length; and the classification module adopts a patentClassifier model subjected to patent data fine adjustment, and outputs a multi-classification label with possibility. According to the system, the problems of low recall rate and single input format caused by input length limitation in the prior art are solved, patent classification accuracy, integrity and efficiency are improved, and the system is suitable for various application scenes and high in practical value.

The invention discloses a patent grading and classification evaluation method, system and device and a storage medium. The method comprises the following steps: step 1, constructing a training data set; 2, constructing a patent evaluation index system as an index of an input layer of the neural network model; 3, selecting a neural network model, and training the training data set; and 4, carrying out grading and classification evaluation on the to-be-evaluated patent by adopting the neural network trained in the step 3, and giving a grading and classification result of the corresponding patent data according to a grading and classification evaluation standard. According to the method, the neural network model is constructed, the historical data is subjected to model training, the patent grading and classification evaluation model is obtained, the evaluation efficiency is improved, meanwhile, the one-sidedness of quantitative evaluation is avoided, and the result uniformity is guaranteed through unified model evaluation.

The invention discloses a pre-training model bert-based patent classification method and system. The method comprises the steps of dividing patent documents into a plurality of technical scheme entity pairs through a pre-training model bert; and setting a keyword score calculation model, calculating the keyword score of each vocabulary in each technical scheme entity pair, performing similarity comparison on the vocabulary with the highest keyword score and the technical classification vocabulary in the IPC, and taking the technical classification vocabulary with the highest similarity in the IPC as the technical classification of the patent literature.

The invention provides a financial science and technology patent classification method based on the technical field, and the method comprises the steps: building a three-stage classification system, obtaining a text, carrying out the keyword extraction, carrying out the text classification based on the three-stage classification system, and setting a corresponding three-stage label for a financial science and technology patent based on a classification result, the three-level classification system comprises a first-level key technology, a second-level technology application and a third-level technology point, systematized and subdivided classification is carried out on the financial science and technology patents, different technology ranges of the financial science and technology patents are reasonably defined, and therefore the accuracy and efficiency of financial science and technology patent classification are remarkably improved; the classified financial science and technology patents are retrieved, different types of financial science and technology patents can be rapidly and accurately recognized from massive patent data, financial science and technology patent information management and application are optimized, and financial science and technology innovation development analysis in different technical fields is promoted.

The invention belongs to the technical field of patent classification method conversion, and particularly relates to a method for converting an international patent classification method and a Chinese library classification method. The method comprises the following steps of: 1, constructing an international patent classification semantic vector set I: fusing various target word vector sets Iw, concept vector sets Ic and phrase vector sets Ip of an international patent classification (IPC); 2, constructing a Chinese library classification semantic vector set C: fusing various target word vector sets Cw, concept vector sets Cc and phrase vector sets Cp of a Chinese library classification method CLC; step 3, performing IPC and CLC category mapping; and 4, verifying the mapping result by using an IPC and CLC category mapping sample set established by an expert. According to the method, the patent and the scientific and technical literature can be retrieved and analyzed uniformly in the precise subdivision field limited by the same classification number, switching operation in different databases is not needed, information separation is avoided, retrieval and analysis efficiency is improved, comprehensive and accurate intelligence support is provided, and integrity and continuity of intelligence information are guaranteed.

The present invention relates to the technical field of patent classification retrieval, and specifically discloses a patent classification retrieval method and system based on multi-source data fusion, including real-time updating of the domain knowledge base, dynamically adjusting the definition and application of terms to ensure the consistency and accuracy of terms in different technical fields; the present invention combines intelligent analysis technology to deeply analyze the terms and their contexts in patent documents, accurately understand the meanings of terms, and evaluate the semantic accuracy of patent texts, avoiding understanding deviations caused by term ambiguity or unclear context; by analyzing the technical problems and solutions in patent texts and combining the technical context and the technical background information of the domain knowledge base, the precision of patent text analysis is further improved, thereby enhancing the precision of patent classification and the relevance of retrieval results; the present invention optimizes the classification and retrieval processes of patent documents by establishing an accurate semantic recognition mechanism.

The present invention discloses a device for weighing live shrimp, both for harvesting the animal and for transferring the animal, wherein the device comprises a main support structure, a secondary support structure and a weighing box that is opened and closed by a gate controlled by a four-bar mechanism. The present invention further relates to a weighing process that uses the device of the invention. International patent classification: Weighing apparatus or methods using mechanical computational means (G01G 13 / 41) and support or suspension of weighing platforms (G01G 21 / 23). The invention belongs to the technical field of mechanics.

The present invention relates to a method for measuring water depth and flow velocity of a spur dike, belonging to the technical field of levee and dike emergency rescue, and its IPC international patent classification numbers are E02B 1 / 00 and E02B 3 / 00. The water depth and flow velocity measuring ship adopted by the present invention includes a buoyancy system, a power system, an overall connection system, an anti-collision system, an anti-overturning water depth calibration system, a flow velocity calibration device, and a flow velocity and water depth remote measurement system. Aiming at the problems existing in the current water depth and flow velocity measurement, manual measurement and automatic measurement are carried out synchronously, making up for the disadvantages that the data of current automatic measurement cannot be calibrated in time, and can quickly and effectively measure the water depth and flow velocity, providing accurate data support for scientific and effective emergency rescue of river regulation projects such as spur dikes in large rivers and has a wide application prospect and great potential for social benefits.

The present invention discloses a thermal embedding stud kit for a fused deposition modeling 3D printed part, which relates to the technical fields of 3D printing and additive manufacturing equipment, and the specific international patent classification number that may be involved is B29C67 / 00. It includes: a stud body, with an embedding cap fixed at the lower end of the stud body; the diameter of the upper end surface of the embedding cap is larger than the diameter of the stud body; the embedding cap has a tapered hollow structure that is larger at the top and smaller at the bottom in the vertical direction; a number of diversion holes penetrating the inner cavity of the embedding cap are arranged on the outer side surface of the embedding cap in the circumferential direction; a heat conducting member, which includes a heat conducting sleeve sleeved on the outside of the stud body and a heat conducting backing plate fixed at the lower end of the heat conducting sleeve; the diameter of the heat conducting backing plate is larger than the diameter of the upper end surface of the embedding cap; a guide rod is fixed in the axial direction on the top surface of the inner cavity of the embedding cap; the lower end of the guide rod is tapered and extends to the outside of the inner cavity of the embedding cap. Compared with traditional connectors, the present invention has higher space utilization rate, greater connection strength and is not easy to slip off.

The invention relates to a hydraulic model, in particular to a hydraulic model for studying the coarse particle conveying characteristic of sand-containing water flow of a bifurcated pipeline, and belongs to the field of hydraulic engineering, and the IPC (International Patent Classification) number of the hydraulic model is E02B 1 / 02. According to the hydraulic model, through the water inlet and outlet pool system, the water transfer pipeline system, the coarse particle feeding port, the movable and telescopic supports and the like, rapid, convenient and stable conversion of test working conditions of different branch pipeline angles, different overall inclination angles and different pipeline inflow and outflow forms can be achieved. By adopting the closed rectangular glass water tank, the distortion of shot pictures caused by refractive indexes of different materials such as organic glass and water flow is reduced, and the observation precision of the high-speed camera can be improved. Water can be transferred back and forth among the three groups of water inlet and outlet pools through the transfer pipelines and the transfer valves, so that the cyclic utilization of water flow is realized, and the effect of saving water resources is achieved.

The application discloses a construction method and a system of a classification co-occurrence network and a technical opportunity identification method, and belongs to the field of technical opportunity identification. Semantic information and co-occurrence information of a joint patent classification (CPC) are combined to form a CPC co-occurrence network, hidden connection modes between CPC nodes are mined through a graph neural network model, then CPC nodes that are likely to be connected with an artificial node representing a target field are predicted, and finally technical development points that are likely to appear in the future in the target field are identified, so that certain decision support is provided for the formulation of a technical development strategy. The application can fully combine the semantic information and the co-occurrence information of the CPC to mine potential correlations between technologies, rich node features provide a good basis for learning of the model, and the technical opportunity identification can be better performed.

The application provides a method for improving the multi-level patent text classification effect based on a BERT-ALMG model, an electronic device and a storage medium, comprising: constructing a label set corresponding to patent classification, and establishing a label feature vector for each label; obtaining a patent text to be classified; analyzing the patent text to obtain a text feature vector of the patent text; analyzing the relationship between the text feature vector and the label feature vector to obtain a label text vector of the patent text; and performing multi-granularity feature convolution operation on the label text vector to classify the patent text. For the multi-level classification task of Chinese patents, the BERT pre-training model is used to fully capture the context semantic features of long text, solving the problem that the length of Chinese patent text is long and the semantic of professional vocabulary is difficult to understand. The label attention module fully excavates the label semantic information, and uses a matrix to dynamically update the label text vector closely related to the hierarchical content, which can fully model the hierarchical structure.

The present invention relates to a method for simulating the transportation characteristics of coarse particles in sediment-laden flow in bifurcated pipelines, belonging to the field of hydraulic engineering, and its IPC international patent classification number is E02B 1 / 00. The hydraulic model adopted in the method of the present invention can quickly, conveniently and stably switch test conditions with different bifurcated pipeline angles, different overall inclination angles, and different pipeline inflow and outflow forms through an advance and retreat water tank system, a water diversion pipeline system, a coarse particle feeding port, a movable and telescopic support, etc. A sealed rectangular glass water tank is adopted to reduce the distortion of camera pictures caused by different refractive indexes of different materials such as plexiglass and water flow, and can improve the observation accuracy of a high-speed camera. Water can be recycled between the three groups of advance and retreat water tanks by using pipelines and valves to divert water back and forth between the advance and retreat water tanks, playing a role in saving water resources.

The present invention discloses a disassembly device for training, which relates to the technical field of disassembly tools and belongs to the field of the international patent classification number B25B. It includes a drive motor, an electric wrench handle, a transmission mechanism, and a socket head. For this disassembly device for training, the pull rod drives the pull sleeve and the positioning pin to move along the chute on the side of the transmission shaft. At this time, the quadrangular prism pin is withdrawn from the docking part of the socket head, and when the finger rubs the knob, the worm drives the worm wheel disc, so that the rotating worm wheel disc drives the large synchronous wheel to rotate, thereby driving the movable sleeve on the outer wall of the synchronous belt to perform a position conversion. When the movable sleeves at different positions drive the socket heads of different specifications to move to the position of the through port, it is convenient for the transmission mechanism to switch and dock with different socket heads for use, convenient for clamping the socket heads of different specifications in the storage box, and there is no need to repeatedly search for socket heads of different specifications to complete the replacement operation, which facilitates the quick disassembly of bolts of different specifications on the training equipment by this disassembly device.

(12) INTERNATIONAL APPLICATION PUBLISHED UNDER THE PATENT COOPERATION TREATY (PCT) (19) World Intellectual Property Organization International Bureau (10) International Publication Number (43) International Publication Date WO 2025 / 096028 A1 08 May 2025 (08.05.2025) WIPOIPCT (51) International Patent Classification: (72) Inventors: LU, He; 2300 Harrison Street, San Francisco, G06F 40 / 10 (2020.01) G06N 20 / 00 (2019.01) California 94110 (US). SCALES, Jordan; 2300 Harrison G06F 40 / 166 (2020.01) Street, San Francisco, California 94110 (US). VARMA, At- ul; 2300 Harrison Street, San Francisco, California 94110 (21) International Application Number: (US). PCT / US2024 / 038250 (74) Agent: SIITONEN, Anni et al.; P.O. Box 1247, Patent Pro- (22) International Filing Date: curement, Seattle, Washington 98111-1247 (US). 16 July 2024 (16.07.2024) (81) Designated States (unless otherwise indicated, for every (25) Filing Language: English kind of national protection available): AE, AG, AL, AM, (26) Publication Language: English AO, AT, AU, AZ, BA, BB, BG, BH, BN, BR, BW, BY, BZ, CA, CH, CL, CN, CO, CR, CU, CV, CZ, DE, DJ, DK, DM, (30) Priority Data: DO, DZ, EC, EE, EG, ES, FI, GB, GD, GE, GH, GM, GT, 63 / 594,524 31 October 2023 (31.10.2023) US HN, HR, HU, ID, IL, IN, IQ, IR, IS, IT, JM, JO, JP, KE, KG, 18 / 408,429 09 January 2024 (09.01.2024) US KH, KN, KP, KR, KW, KZ, LA, LC, LK, LR, LS, LU, LY, 18 / 408,449 09 January 2024 (09.01.2024) US MA, MD, MG, MK, MN, MU, MW, MX, MY, MZ, NA, 18 / 408,454 09 January 2024 (09.01.2024) US NG, NI, NO, NZ, OM, PA, PE, PG, PH, PL, PT, QA, RO, 18 / 408,479 09 January 2024 (09.01.2024) US RS, RU, RW, SA, SC, SD, SE, SG, SK, SL, ST, SV, SY, TH, (71) Applicant: NOTION LABS, INC. [US / US]; 2300 Harri- TJ, TM, TN, TR, TT, TZ, UA, UG, US, UZ, VC, VN, WS, son Street, San Francisco, California 94110 (US). ZA, ZM, ZW. (54) Title: PROVIDING GENERATIVE ARTIFICIAL INTELLIGENCE (AI) CONTENT BASED ON EXISTING IN-PAGE CON- TENT IN A WORKSPACE 300 Compan. / / Al bio. Share is 305 AI Blocks 306 Al blocks are placed like ordinary Notion blocks, but contain as part of their metadata a prompt to a large language model. By default, the blocks display their intent (e.g. Summary this page) and a button to do SO. When the result of the large language model appears, the block updates to be a "container" of the AI output, with the ability to edit the prompt and re-run... + # "= Summarize this page with AI 302 Generate 304 309 308 Link The AI feature provides advantages such as displaying AI output at a specific position in the page and WO 2025 / 096028 A1 FIG. 3A (57) Abstract: A method for creating in-block content presented in a block on a page of a workspace. The block is configured to initiate a generative process to create in-block content of a particular type. The method includes determining a selection of in-page content based on a location of the block relative to the in-page content and the particular type of in-block content. The method can include causing a generative function to create generative content of the particular type based on the selection of the in-page content. The method can further include populating a block area to present the generative content. [Continued on next page] 20 26 20 54 06 08 J ul 2 02 6 0 8 J u l 2 0 2 6 W O 2 0 2 5 / 0 9 6 0 2 8 A 1 W I P O I P C T P C T / U S 2 0 2 4 / 0 3 8 2 5 0 2 0 2 6 2 0 5 4 0 6 U S M A , M D , M G , M K , M N , M U , M W , M X , M Y , M Z , N A , ( 5 4 ) T i t l e : P R O V I D I N G G E N E R A T I V E A R T I F I C I A L I N T E L L I G E N C E ( A I ) C O N T E N T B A S E D O N E X I S T I N G I N - P A G E C O N - 3 0 0 i s 3 0 5 3 0 6 + # A I 3 0 2 3 0 9 3 0 8 W O 2 0 2 5 / 0 9 6 0 2 8 A 1 F I G . 3 A

The application discloses a kind of detection sub-technology in the method and device of application in target industry, which comprises: obtaining target patent data set of target industry;Each patent data in the target patent data set is labeled using a predetermined patent classification system, to obtain the patent technology field corresponding to each patent data;The patent technology field contains at least one sub-technology;Each patent technology field is clustered to obtain multiple industrial sub-fields;For each industrial sub-field, the comprehensive application score of each sub-technology in the target industry technology is calculated.The application evaluates and measures the key of the sub-technology in the industry from four dimensions, such as the use frequency of a certain sub-technology, the general degree of the sub-technology, the contact degree of the sub-technology with other sub-technologies, and the probability of the sub-technology becoming a core technology, to avoid the subjectivity of expert evaluation and the problem of insufficient objectivity.

The invention discloses a liquid cooling device, a control method, a control system and a readable storage medium, relates to the field of heat dissipation, belongs to a heat exchange device in strategic emerging industry classification and international patent classification, and is used for enabling liquid supply back pressure of a distributed liquid cooling device to meet requirements. The liquid cooling device comprises a first flow path, a second flow path, a first pressure adjusting device, a back pressure pump and at least one heat exchange assembly. The second flow path communicates with the first flow path and is configured to receive the fluid passing through the heat exchange assembly. The first pressure adjustment device is attached to the first flow path. The back pressure pump is attached to the first flow path. Each heat exchange assembly comprises a first branch, a second branch, a heat exchanger, a liquid supply pump and a second pressure adjusting device. The second branch is located at the downstream of the first branch, and the heat exchanger is arranged between the first branch and the second branch; the liquid supply pump is positioned between the first branch and the heat exchanger; the second pressure adjusting device communicates with the first branch and is located on the upstream of the liquid supply pump. The scheme is flexible to adjust.

The application discloses a Chinese patent IPC classification method based on SBERT, comprising the following steps: corpus data preprocessing: extracting specific words and sentences from patent text to form first corpus data, and extracting term descriptions corresponding to categories from an IPC classification table according to categories to form second corpus data; data enhancement processing of the corpus data; text vectorization coding: inputting the first corpus data and the second corpus data into a first BERT pre-training model and a second BERT pre-training model under an SBERT framework respectively for vectorization coding to obtain vector representation of the patent text; similarity comparison: selecting a classification number according to a similarity ranking obtained by calculation. The application adopts SBERT with a twin structure as a framework of automatic classification of Chinese patents, takes patent text and term descriptions in an IPC classification table as two inputs of SBERT, and determines the patent category according to the closeness of two vectors after BERT vectorization coding, so that the calculation amount is reduced, the classification accuracy is improved, and multiple relevant IPC classification numbers are given.

The present invention relates to a depth and velocity measurement ship for damaged spur dikes, belonging to the technical field of levee and dike emergency rescue, and its IPC international patent classification numbers are E02B 1 / 00 and E02B 3 / 00. The depth and velocity measurement ship of the present invention includes a buoyancy system, a power system, an overall connection system, an anti-collision system, an anti-overturning depth calibration system, a flow rate calibration device, and a flow velocity and depth remote measurement system. Aiming at the problems existing in the current depth and velocity measurement, manual measurement and automatic measurement are carried out synchronously, making up for the disadvantage that the data of current automatic measurement cannot be calibrated in time, and can quickly and effectively measure the water depth and flow velocity, providing accurate data support for scientific and effective emergency rescue of river regulation projects such as spur dikes in large rivers and has broad application prospects and great potential for social benefits.

The invention provides a patent text classification method, system and device, a storage medium and a program product, and the method comprises the steps: inputting a to-be-classified patent text into a pre-trained IPC classification integration model for IPC first-level classification, obtaining at least one IPC label, and achieving the pre-classification of patent IPC subclasses; all the IPC labels are matched with IPC label descriptions in a label database, and the IPC label descriptions corresponding to all the IPC labels are obtained; inputting the at least one IPC label, the IPC label description corresponding to each IPC label and the first target field in the patent text to be classified into a pre-trained IPC classification selection large model to carry out IPC second-level classification to obtain an IPC label classification result of the patent text to be classified, thereby realizing fine classification of the patent IPC group. And adaptability and accuracy of patent IPC classification can be effectively improved.

The invention relates to a patent technology classification method and device and computer equipment. The method comprises the following steps: acquiring a core screen patent data set, and preprocessing the core screen patent data set to obtain target data of each patent; based on the patent target data, constructing a first technology tree and a second technology tree through a two-process patent classification strategy; and based on the first technology tree and the second technology tree, through a double-process fusion strategy, performing fusion optimization processing on the patent target data to obtain a target patent technology classification result corresponding to the core screen patent data set. By adopting the method, the real-time updating flexibility of patent classification can be improved.

An apparatus for selecting promising technology according to the present invention comprises: an input interface for receiving a patent classification code and an industrial technology classification code; and a central processing unit for calculating a score or grade by extracting the number of company M&A transactions indicating acquisition of a company classified under the industrial technology classification code, or calculating a score or grade on the basis of the number of patents matching the patent classification code among patents of companies to be acquired, classified under the industrial technology classification code.

The invention provides a patent text data set construction method and device and a storage medium. The method comprises the steps of collecting patent text data to be processed; constructing a data classification tree based on the patent classification number corresponding to the patent text data to be processed; according to leaf nodes of the data classification tree, sample patent texts are extracted, and the sample patent texts can cover all patent technical feature information corresponding to the corresponding classification numbers; on the basis of a preset large language model, the sample patent text is converted into a patent text data set, the patent text data set comprises at least one text pair, and the text pair is used for representing interpretation type data and incidence relation data of the patent text; the association relationship data is used for describing one or more of association relationships among the technical problems, the technical schemes and the technical effects, and the interpretation class data is used for expressing one or more of the technical problems, the technical schemes and the technical effects. The problem that in the prior art, a patent text data set is low in quality is solved.