System and method for evaluating patent commercialization value

Abstract

The invention belongs to the technical field of intellectual property, and discloses a patent commercialization value evaluation system and method, and the system comprises a patent information obtaining unit which is used for obtaining target patent information from a patent database; the patent technical analysis unit is used for extracting keyword features in the patent text and analyzing technical features of the patent text according to a similarity comparison result; the market potential prediction unit is used for analyzing the technical field in the patent text and predicting a market response demand conforming to the technical field by using a time sequence analysis technology; and the value comprehensive evaluation unit is used for establishing a comprehensive evaluation model by taking the technical characteristics of the patent text and the market response demand as evaluation indexes, and evaluating the value degree of the target patent by utilizing the comprehensive evaluation model. Through combination of technical characteristics and market response demands, the technical innovation and commercialization potential of patents are comprehensively measured.

Description

Background Art

[0002] The conversion value of patents focuses on the potential of patents to transform from knowledge concepts into actual productivity and economic benefits. The commercial value of patents further emphasizes the commercial returns and sustainable development capabilities that patents can derive in market operations. Such patents generally have high technical content, strong stability, and market competitiveness.

[0003] However, in the process of considering the commercial value of a patent, market response demand forecast is an important basis for evaluating patent application scenarios. If market demand cannot be accurately predicted, not only will the patent's applicability analysis and potential market positioning become blurred, but it can only statically reflect the current value of the patent, and cannot effectively predict its future development trends and potential commercialization prospects.

[0004] Therefore, how to provide an evaluation system and method for the commercialization value of patents is an urgent problem to be solved. Summary of the invention

[0005] The embodiments of the present invention provide a system and method for evaluating the commercialization value of a patent to solve the problem in the prior art that the market demand cannot be accurately predicted, resulting in fuzzy analysis of the applicability of the patent and potential market positioning.

[0006] In order to have a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not a general review, nor is it intended to identify key / important components or to describe the scope of protection of these embodiments. Its only purpose is to present some concepts in a simple form as a prelude to the detailed description that follows.

[0007] According to a first aspect of an embodiment of the present invention, a system for evaluating the commercialization value of a patent is provided.

[0008] In one embodiment, the patent commercialization value evaluation system comprises: A patent information acquisition unit, used to acquire target patent information from a patent database, wherein the target patent information includes a patent text; Patent technical analysis unit, used to extract keyword features in patent texts using natural language processing technology, compare the keyword features with relevant documents for similarity, and analyze the technical features of the patent texts based on the similarity comparison results; Market potential prediction unit, which is used to analyze the technical fields in the patent text and use time series analysis technology to predict the market response needs that match the technical fields; The comprehensive value assessment unit is used to establish a comprehensive assessment model using the technical features of the patent text and market response requirements as assessment indicators, and use the comprehensive assessment model to assess the value of the target patent.

[0009] In one embodiment, the patent technical analysis unit includes a data preprocessing module, a keyword extraction module, a similarity calculation module and a technical feature analysis module, wherein: The data preprocessing module is used to perform data cleaning and stop word removal on the patent text in turn, and convert the patent text into a standardized format; Keyword extraction module, used to calculate the word frequency-inverse document frequency of each word in the patent text, and analyze the keyword features in the patent text based on the word frequency-inverse document frequency; A similarity calculation module is used to convert the keyword features of the patent text into a text vector, and compare the text vector with the relevant literature to obtain a similarity comparison result; The technical feature analysis module is used to analyze the technical difficulty of the patent text based on keyword features, and to analyze the innovativeness of the patent text based on similarity comparison results.

[0010] In one embodiment, the keyword extraction module calculates the word frequency-inverse document frequency of each word in the patent text and analyzes the keyword features in the patent text based on the word frequency-inverse document frequency, including: Use word segmentation tools to segment the patent text into several words, remove meaningless words in the patent text and generate a word list; Calculate the word frequency and inverse document frequency of each word in the patent text respectively, and multiply the word frequency and inverse document frequency to obtain the word frequency-inverse document frequency value of each word; All words in the patent text are sorted according to the word frequency-inverse document frequency value, and words within the preset range of the sorting list are selected as keyword features in the patent text.

[0011] In one embodiment, the market potential prediction unit includes a technical field analysis module, a market demand analysis module and a mapping relationship analysis module, wherein: The technical field analysis module is used to identify the technical field to which the patent text belongs based on keyword features; The market demand forecasting module is used to collect market demand data within a preset time period and establish a multivariate time series model, and use the multivariate time series model to predict the market response demand in the future time period; The mapping relationship analysis module is used to calculate the Pearson correlation coefficient between the technical field to which the patent text belongs and the market response demand, and to measure the mapping relationship between the technical field to which the patent text belongs and the market response demand based on the Pearson correlation coefficient.

[0012] In one embodiment, the market demand data includes market size data, market growth data, consumer behavior data, technology hotspot data and social environment data.

[0013] In one embodiment, the calculation formula of the Pearson correlation coefficient is: ; In the formula, r The Pearson correlation coefficient between the technical field to which the patent text belongs and the market response demand; x i Indicates i The characteristic value of the technical field to which the patent text belongs; y i Indicates i The characteristic value of the market response demand; Indicates the average feature value of the technical field to which the patent text belongs; The average characteristic value representing the average market response demand.

[0014] In one embodiment, the market demand forecasting module, when establishing a multivariate time series model and using the multivariate time series model to forecast the market response demand in a future time period, includes: Convert the market demand data into market time series and perform a stationarity test on the market time series. If the market time series is not stationary, perform a differential analysis on the market time series. Test the truncation characteristics of the autocorrelation function and partial autocorrelation function of the market time series after differential analysis, and determine the value range of the multivariate time series model parameters based on the truncation characteristics; The seasonal characteristics of inter-market sequences are analyzed to establish a multivariate time series model, which takes the market demand data model as input and predicts the market response demand in future time periods through the multivariate time series model.

[0015] In one embodiment, the comprehensive value assessment unit includes an assessment indicator construction module, a comprehensive value assessment module and a result generation module, wherein: Evaluation indicator construction module, which is used to convert the technical features of patent texts and market response requirements into quantitative evaluation indicators; The comprehensive value evaluation module is used to assign weights to evaluation indicators, establish a comprehensive evaluation model based on the weights and contributions of the evaluation indicators, and calculate the value of the target patent using the comprehensive evaluation model; The result generation module is used to generate an evaluation report on the value of the target patent and to visualize the evaluation report.

[0016] In one embodiment, the comprehensive value evaluation module assigns weights to evaluation indicators, establishes a comprehensive evaluation model based on the weights and contributions of the evaluation indicators, and calculates the value of the target patent using the comprehensive evaluation model, including: The hierarchical analysis method is used to construct a comparison matrix of evaluation indicators, and the contribution of evaluation indicators is calculated after consistency test of the comparison matrix; Assign weights to the evaluation indicators, integrate the evaluation indicators according to their contribution and weight values ​​to obtain a comprehensive evaluation model, calculate the stability index of the comprehensive evaluation model, and grade the comprehensive evaluation model based on the stability index of the comprehensive evaluation model; The graded comprehensive evaluation model is converted into a tree structure, and the tree structure is traversed to obtain a multi-branch sub-level model of the comprehensive evaluation model, and the multi-branch sub-level model is used to calculate the value of the target patent.

[0017] According to a second aspect of an embodiment of the present invention, a method for evaluating the commercialization value of a patent is provided.

[0018] In one embodiment, the method for evaluating the commercialization value of a patent comprises: Acquire target patent information from a patent database, wherein the target patent information includes patent text; Use natural language processing technology to extract keyword features from patent texts, compare the keyword features with relevant literature for similarity, and analyze the technical features of patent texts based on the similarity comparison results; Analyze the technical fields in patent texts and use time series analysis techniques to predict market response needs that match the technical fields; A comprehensive evaluation model is established by taking the technical features of the patent text and the market response needs as evaluation indicators, and the comprehensive evaluation model is used to evaluate the value of the target patent.

[0019] According to a third aspect of an embodiment of the present invention, a computer device is provided.

[0020] In one embodiment, the computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0021] According to a fourth aspect of embodiments of the present invention, a computer-readable storage medium is provided.

[0022] In one embodiment, the computer-readable storage medium stores a computer program, and the computer program implements the steps of the above method when executed by a processor.

[0023] The technical solution provided by the embodiment of the present invention may have the following beneficial effects: 1. The present invention utilizes natural language processing technology to efficiently extract technical keywords from patent texts, which can quickly identify the core technical content of patents. By extracting keyword features, it avoids omissions or deviations in manual analysis, ensures the comprehensiveness and accuracy of technical feature extraction, and compares the similarity between patent keywords and related literature, which can clarify the technical field or branch to which the patent belongs, thereby helping to analyze the position of the patent in the prior art and determine whether it has technical innovation and uniqueness.

[0024] 2. The present invention comprehensively measures the technological innovation and commercialization potential of patents by combining technical features with market response needs, avoids the limitations of single indicator evaluation, improves the accuracy of describing the actual value of patents by refining technical indicators and market indicators, and can adjust weights as the market changes by constructing a comprehensive model to more accurately reflect the value performance of patents at different times or in different fields, helping enterprises and research institutions to prioritize resources in patents with high technological value and high market potential, improve R&D and intellectual property management efficiency, and improve the efficiency of patent transformation from potential resources to actual commercial assets by deeply exploring and accurately evaluating the commercialization value of patents, effectively driving the transformation process of patent results and promoting their rapid circulation and appreciation in the market.

[0025] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0027] Figure 1 is a principle block diagram of a patent commercialization value evaluation system according to an exemplary embodiment; Figure 2 is a flow chart of a method for evaluating the commercialization value of a patent according to an exemplary embodiment; Figure 3 The figure is a schematic diagram showing the structure of a computer device according to an exemplary embodiment. DETAILED DESCRIPTION

[0028] The following description and accompanying drawings fully illustrate the specific embodiments of this article so that those skilled in the art can practice them. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. The scope of the embodiments of this article includes the entire scope of the claims, as well as all available equivalents of the claims. Herein, the terms "first", "second", etc. are only used to distinguish one element from another, without requiring or implying any actual relationship or order between these elements. In fact, the first element can also be called the second element, and vice versa. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the structure, device or equipment including a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also include elements inherent to such structure, device or equipment. In the absence of more restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the structure, device or equipment including the elements. Each embodiment is described in a progressive manner herein, and each embodiment focuses on the differences from other embodiments, and the same and similar parts between the embodiments can be referred to each other.

[0029] The terms "longitudinal", "lateral", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc. in this document indicate the orientation or position relationship based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing this document and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In the description of this document, unless otherwise specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a mechanical connection or an electrical connection, it can also be the internal communication of two elements, it can be a direct connection, or it can be an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0030] As used herein, the term "plurality" means two or more than two, unless otherwise specified.

[0031] In this document, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B means: A or B.

[0032] In this article, the term "and / or" is a description of the association relationship between objects, indicating that three relationships may exist. For example, A and / or B means: A or B, or, A and B.

[0033] It should be understood that, although the various steps in the flow chart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the figure may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0034] Each module in the device or system of the present application can be implemented in whole or in part by software, hardware, or a combination thereof. The above modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to the above modules.

[0035] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0036] Figure 1 An embodiment of a patent commercialization value evaluation system of the present invention is shown.

[0037] In this optional embodiment, the patent commercialization value evaluation system includes: The patent information acquisition unit 101 is used to acquire target patent information from a patent database, wherein the target patent information includes patent text; Patent technical analysis unit 103, used to extract keyword features in patent text by using natural language processing technology, compare the keyword features with relevant documents for similarity, and analyze the technical features of the patent text according to the similarity comparison results; The market potential prediction unit 105 is used to analyze the technical field in the patent text and use time series analysis technology to predict the market response demand that meets the technical field; The comprehensive value evaluation unit 107 is used to establish a comprehensive evaluation model using the technical features of the patent text and the market response requirements as evaluation indicators, and use the comprehensive evaluation model to evaluate the value of the target patent.

[0038] Among them, the extraction of keyword features is performed according to the preset index path. The preset index path includes: industrial chain map, dynamic technology word cloud, etc. At the level of the industrial chain map index path, professional map analysis tools are used to deeply mine the key element vocabulary closely connected to each level of the industrial chain in the patent text. For example, the specific substance name and ingredient description related to the starting end of raw material supply, the terminology corresponding to the core process technology and equipment in the production and manufacturing process, and then to the distribution channels, target audience groups and other related terms involved in the sales and market development links, index and locate to the corresponding levels of the industrial chain map, and extract the content that meets the corresponding conditions as keywords. At the level of the dynamic technical word cloud index path, the technical word cloud library is a word cloud model trained based on a massive patent and technical literature corpus. The word cloud model is used to screen high-frequency and distinctive technical representative words in the patent text, such as unique words that appear for the first time in a specific technical field or have recently emerged. By comparing with the existing vocabulary library, innovative and differentiated keyword features are extracted. At the same time, the technical word cloud library has a dynamic update mechanism to timely capture emerging technical terms and new semantic connotations derived from existing words in the process of technological evolution, so as to ensure the timeliness and technological advancement of keyword extraction. Through this extraction mechanism, the keyword features in the target patent text can be more fully extracted. Not only can the technical keywords be accurately located based on the technical word library, but also the industrial chain map is combined to deeply explore the related words of the industrial scene, including the key elements of production, application, market and other links, so as to build a multi-dimensional analysis foundation for the evaluation of the commercial value of patents, and comprehensively consider key dimensions such as technological innovation and industrial adaptability. Correspondingly, the relevant literature used for similarity comparison is also compared in the technical and market dimensions to expand the database. Including but not limited to, patent documents on similar technical subjects, which can be compared with the target patent in all aspects in terms of technical solutions, technical effects, etc.; industrial chain technical documents, which include technical reports, R&D records, production process manuals, etc. of upstream and downstream enterprises, as well as market feedback technical analysis reports, etc.; also including professional academic journals and conference papers focusing on cutting-edge technological research results and in-depth theoretical discussions; industry standards and specification documents are also within the comparison scope, which define the basic requirements and general criteria in specific technical fields, and can be used to measure whether the target patent complies with industry common norms and the degree of innovation and differentiated advantages within the standard framework.

[0039] In this optional embodiment, the patent technical analysis unit 103 includes a data preprocessing module (not shown in the figure), a keyword extraction module (not shown in the figure), a similarity calculation module (not shown in the figure) and a technical feature analysis module (not shown in the figure), wherein: The data preprocessing module is used to perform data cleaning and stop word removal on the patent text in turn, and convert the patent text into a standardized format; the keyword extraction module is used to calculate the word frequency-inverse document frequency of each word in the patent text, and analyze the keyword features in the patent text based on the word frequency-inverse document frequency; the similarity calculation module is used to convert the keyword features of the patent text into a text vector, and compare the text vector with the relevant literature to obtain the similarity comparison result; the technical feature analysis module is used to analyze the technical difficulty of the patent text based on the keyword features, and analyze the innovativeness of the patent text based on the similarity comparison result.

[0040] In this optional embodiment, the keyword features of the patent text are converted into a text vector, and the text vector is compared with the relevant documents for similarity. The similarity comparison results include: After extracting the core keyword features through preprocessing the patent text (including cleaning, word segmentation, etc.), the keyword is converted into a high-dimensional text vector using a word embedding model (such as Word2Vec, BERT), and the related document text is processed in the same way to generate a document vector. In the same semantic space, the cosine similarity is used to calculate the vector similarity between the patent text and the document, and the output results are sorted according to the similarity score, so as to determine the technical relevance and matching degree between the patent text and the document.

[0041] In this optional embodiment, the keyword extraction module calculates the word frequency-inverse document frequency of each word in the patent text and analyzes the keyword features in the patent text based on the word frequency-inverse document frequency, including: The patent text is divided into several words using a word segmentation tool, and the meaningless words in the patent text are removed to generate a word list; the word frequency and inverse document frequency of each word in the patent text are calculated separately, and the word frequency and inverse document frequency are multiplied to obtain the word frequency-inverse document frequency value of each word; all words in the patent text are sorted according to the word frequency-inverse document frequency value, and the words within the preset range of the sorting list are selected as keyword features in the patent text.

[0042] In this optional embodiment, the term frequency and inverse document frequency of each word in the patent text are calculated respectively, and the term frequency and the inverse document frequency are multiplied to obtain the term frequency-inverse document frequency value of each word, including: The term frequency (TF, i.e., the frequency of occurrence of a term in the text) and the inverse document frequency (IDF, i.e., the rarity of a term in all documents, obtained by taking the logarithm of the ratio of the total number of documents to the number of documents containing the term) of each term in the patent text are calculated. The TF-IDF value is obtained by multiplying the term frequency and the inverse document frequency. This value is used to measure the importance of a term in the current patent text. It not only takes into account the frequency of occurrence of a term in the text, but also reduces the impact of common terms on the results, ensuring that keywords related to the text topic are more prominent.

[0043] In this optional embodiment, the market potential prediction unit 105 includes a technical field analysis module (not shown in the figure), a market demand analysis module (not shown in the figure) and a mapping relationship analysis module (not shown in the figure), wherein: The technical field analysis module is used to identify the technical field to which the patent text belongs based on keyword features; the market demand prediction module is used to collect market demand data within a preset time period and establish a multivariate time series model, and use the multivariate time series model to predict the market response demand in the future time period; the mapping relationship analysis module is used to calculate the Pearson correlation coefficient between the technical field to which the patent text belongs and the market response demand, and measure the mapping relationship between the technical field to which the patent text belongs and the market response demand based on the Pearson correlation coefficient.

[0044] Among them, the span of the preset time period can be determined according to the duration characteristics of the life cycle stage of a specific technology. For example, in the growth stage of rapid technology iteration, given the high rate and frequency of technology updates, the preset time period should be short, so as to accurately capture subtle changes and innovative highlights in the process of technology development, such as breakthroughs in emerging processes and the emergence of innovative functions. When the technology is mature and stable, its evolution pace slows down and the update amplitude is small, the preset time period can be appropriately extended to avoid missing key information such as the extension trend of the application scope of the technology at different development stages, the diversified expansion of adaptation scenarios, and the evolution of market demand derived from it due to the limited collection time.

[0045] In this optional embodiment, the market demand data includes market size data, market growth data, consumer behavior data, technology hotspot data, social environment data, and benchmark enterprise information in the target patent technology field, potential target customer information, application scenarios, core technical problems to be solved, competition among peers, investment heat in the field, commercial activity heat, R&D investment and other information.

[0046] Specifically, the preset time period can be the market demand data within the time period between the patent application date and the publication date. In the process of evaluating the patent value and predicting the market response, it is important to use the market demand data within the time period between the patent application date and the publication date (including market size data, market growth data, consumer behavior data, technology hotspot data and social environment data) as input data. The analysis and use of these data can reveal the potential market value, technology trends and social acceptance of patented technologies, thereby providing a basis for corporate strategies, investment decisions and technology evaluations.

[0047] For example, by understanding the market size of the industry in which the target patent technology is located, the economic potential of the patent technology in the market can be roughly estimated. If the market size is large, the commercial value of the patent technology may be higher. A larger market size usually indicates that there are greater commercial development opportunities in this field. Combining the uniqueness of the patent technology and the market size, it is possible to estimate the market share it may occupy in the future.

[0048] Market growth data reflects the growth rate or trend change of demand in a certain industry or market (such as annual growth rate, quarterly change trend, etc.). A rapidly growing market indicates that the field has strong development potential, which helps to determine the future value of patented technology. Based on historical growth data, the future expansion trend of the market can be predicted through methods such as time series analysis.

[0049] Consumer behavior data describes the specific sources of market demand, including consumer preferences, purchasing habits, ability to pay, and acceptance of new technologies. By analyzing consumer attitudes toward related technologies or products, it can help patent holders optimize their marketing strategies. If consumer behavior data shows that users show high concern and willingness to buy similar technologies or products, the market acceptance of the target patent will be higher.

[0050] Technology hotspot data refers to the technology directions, R&D dynamics and technology innovation trends of related patents that are of concern in the current market or industry. Analyzing the hotness of the technology field to which the target patent belongs helps to evaluate whether the patent technology is at the forefront of industry technology. If the target patent technology fits the current technology hotspot, it may have higher market competitiveness.

[0051] In this optional embodiment, the calculation formula of the Pearson correlation coefficient is: ; In the formula, r The Pearson correlation coefficient between the technical field to which the patent text belongs and the market response demand; x i Indicates i The characteristic value of the technical field to which the patent text belongs; yi Indicates i The characteristic value of the market response demand; Indicates the average feature value of the technical field to which the patent text belongs; The average characteristic value representing the average market response demand.

[0052] In this optional embodiment, the market demand forecasting module includes: establishing a multivariate time series model and using the multivariate time series model to forecast the market response demand in the future time period: Convert the market demand data into market time series, and perform a stationarity test on the market time series. If the market time series is not stationary, perform a differential analysis on the market time series. Test the truncation characteristics of the autocorrelation function and partial autocorrelation function of the market time series after the differential analysis, and determine the value range of the multivariate time series model parameters based on the truncation characteristics. Analyze the seasonal characteristics of the market series to establish a multivariate time series model, take the market demand data model as input, and use the multivariate time series model to predict the market response demand in the future time period.

[0053] In order to facilitate understanding of the above technical solution of the present invention, the following is a detailed description of the establishment of a multivariate time series model in the actual process of the present invention and the use of the multivariate time series model to predict the market response demand in the future time period: Step 1: Convert market demand data into market time series: Construction of time series: Group market demand data by time (such as day, month, quarter, etc.); calculate the total amount or average value in each time period to form a continuous time series; if the data has multiple dimensions (such as different market areas or product categories), organize it into a multivariate time series and draw a time series graph to observe the overall trend, volatility and seasonal characteristics of market demand.

[0054] Step 2: Stability test: The basic assumption of time series analysis is the stationarity of data, so the sequence needs to be tested for stationarity. The mean and variance of a stationary time series remain unchanged over the entire time period. If the sequence is not stationary, there may be trend or seasonal changes. For example, the stationarity test method uses statistical tests (such as unit root tests) to determine whether the time series is stationary; if the mean or variance of the sequence changes significantly over time, the series is considered non-stationary. The characteristics of a non-stationary series are significant trends (such as gradual increases or decreases) and periodic or seasonal changes.

[0055] Step 3: Perform differential analysis on non-stationary time series: If the stationarity test shows that the time series is not stationary, it needs to be stabilized through the difference operation; the difference is to eliminate the trend or seasonality by calculating the change between adjacent time points; the new value of the time series after the difference is equal to the current value minus the previous value. Among them, the difference order includes the first-order difference and the second-order difference. The first-order difference is used to eliminate linear trends, and the second-order difference is used to eliminate nonlinear trends.

[0056] Re-test the stationarity of the differenced series to ensure that its mean and variance are stable. If it is still not stationary, try further differences or other data transformation methods (such as logarithmic transformation).

[0057] Step 4: Analysis of truncation characteristics of autocorrelation function and partial autocorrelation function: Autocorrelation function (ACF): describes the correlation between time series at different lags.

[0058] Partial autocorrelation function (PACF): describes the pure correlation between different lags after removing the influence of the intermediate lag terms.

[0059] The shape of the ACF and PACF graphs helps identify the characteristics of the time series model. They quickly become zero after a certain lag point and gradually decay with the lag. Specifically, the order of the model can be preliminarily determined based on the characteristics of the ACF and PACF. The location of the truncated lag is usually the candidate value range of the model parameters. Different orders correspond to different forms of the model, such as the autoregressive (AR) order and the moving average (MA) order in ARIMA.

[0060] Step 5: Establish a multivariate time series model: Select a suitable model based on the stationarity, seasonality and lag characteristics of the time series. For example, ARIMA (Autoregressive Integrated Moving Average) is used for univariate stationary series; SARIMA (Seasonal Autoregressive Integrated Moving Average) is used for seasonal series; VAR (Vector Autoregression) is used for multivariate time series to capture the mutual influence between variables.

[0061] Determine the initial values ​​of the parameters based on ACF and PACF, use maximum likelihood estimation or least squares method to optimize the parameters, check whether the model residuals are white noise (no correlation, no systematicity), and evaluate the quality of the model through information criteria (such as AIC or BIC).

[0062] In this optional embodiment, the value comprehensive evaluation unit 107 includes an evaluation index construction module (not shown in the figure), a value comprehensive evaluation module (not shown in the figure) and a result generation module (not shown in the figure), wherein: The evaluation indicator construction module is used to convert the technical features of the patent text and the market response requirements into quantitative evaluation indicators; the value comprehensive evaluation module is used to assign weights to the evaluation indicators, establish a comprehensive evaluation model based on the weights and contributions of the evaluation indicators, and use the comprehensive evaluation model to calculate the value of the target patent; the result generation module is used to generate an evaluation report based on the value of the target patent and to visualize the evaluation report.

[0063] In this optional embodiment, the comprehensive value evaluation module assigns weights to evaluation indicators, establishes a comprehensive evaluation model based on the weights and contributions of the evaluation indicators, and calculates the value of the target patent using the comprehensive evaluation model, including: A hierarchical analysis method is used to construct a comparison matrix of evaluation indicators, and the contribution of the evaluation indicators is calculated after a consistency check on the comparison matrix; weights are assigned to the evaluation indicators, and the evaluation indicators are integrated according to the contribution and weight values ​​to obtain a comprehensive evaluation model, the stability index of the comprehensive evaluation model is calculated, and the comprehensive evaluation model is graded based on the stability index of the comprehensive evaluation model; the graded comprehensive evaluation model is converted into a tree structure, and the tree structure is traversed to obtain a multi-branch sub-level model of the comprehensive evaluation model, and the multi-branch sub-level model is used to calculate the value of the target patent.

[0064] In order to facilitate understanding of the above technical solution of the present invention, the following is a detailed description of how the present invention allocates weights to evaluation indicators in the actual process, establishes a comprehensive evaluation model based on the weights and contributions of the evaluation indicators, and calculates the value of the target patent using the comprehensive evaluation model: Step 1: Construct a comparison matrix of evaluation indicators: Determine the evaluation goal: Determine the ultimate goal of the problem, such as evaluating the "value of the target patent."

[0065] Decompose the problem and determine the evaluation indicators: Decompose it into several dimensions according to the evaluation objectives (such as economic value, technical value, legal value, etc.). Further decompose each dimension into specific indicators (such as technological advancement, market potential, possibility of rights protection, etc.).

[0066] Construct a pairwise comparison matrix: Use the pairwise comparison method to compare each pair of indicators based on importance or contribution. Use expert scoring methods, questionnaires, and other means to assign relative weights to each pair of indicators. Construct a matrix in which the elements represent the relative importance of the indicators. For example, if indicator A is more important than indicator B, the weights assigned may be 3:13:1.

[0067] Step 2: Consistency test: Calculate the consistency index (CI): The consistency index reflects whether the matrix meets the consistency requirements. If the consistency deviation is too large, the weight distribution of the comparison matrix needs to be readjusted. Use the random consistency ratio (CR) as a reference value; if CR < 0.1, the matrix is ​​considered consistent and can continue; if CR ≥ 0.1, it is necessary to return to adjust the comparison matrix; for inconsistent comparison matrices, re-examine the pairwise comparison relationship of the indicators, and revise the matrix in combination with expert opinions until the consistency requirements are met.

[0068] Step 3: Calculate the contribution of the evaluation indicators and assign weights: Contribution calculation: Calculate the relative importance score of each indicator based on the comparison matrix. These scores are the contribution of each indicator. Contribution is usually expressed as a percentage, reflecting the importance of a certain indicator to the evaluation target.

[0069] Weight allocation: Weights are allocated based on contribution, ensuring that the total weight is 1. The weight value reflects the actual influence of the evaluation indicator.

[0070] Step 4: Build a comprehensive evaluation model: Integrate contribution and weight values: All indicators are calculated comprehensively according to contribution and weight values ​​to form a unified evaluation model, and the stability index of the comprehensive evaluation model is calculated. The stability index is used to measure the reliability of the model. By analyzing the model performance under different data inputs or weight disturbances, the robustness of the model is verified, and the model is graded according to the stability index, for example: high stability (excellent); medium stability (good); low stability (needs improvement).

[0071] Step 5: Convert the comprehensive evaluation model into a tree structure: Construction of tree structure: the evaluation target is taken as the root node of the tree; each dimension (such as economic, technical, and legal value) is taken as the first-level child node; the specific indicators under each dimension are taken as the second-level child nodes, and so on.

[0072] Clarification of node relationships: The evaluation value of each parent node is obtained by weighted summing up the contribution values ​​of all its child nodes. The weight distribution rule follows the weight ratio calculated in the previous stage.

[0073] Step 6: Obtain the multi-branch sub-level model and calculate the value of the target patent: Generate multi-branch sub-models by traversing the tree structure and calculate the value of the target patent. Use the depth-first search (DFS) or breadth-first search (BFS) algorithm to traverse the tree structure and extract any non-leaf node in the tree and all its subordinate nodes as a sub-model (the sub-model represents the local evaluation of the target by this part of the indicator). Calculate the local value of the target patent according to the weight and contribution of the sub-model. Finally, merge the local values ​​of all sub-models to obtain the overall value of the target patent.

[0074] Figure 2 An embodiment of a method for evaluating the commercialization value of a patent of the present invention is shown.

[0075] In this optional embodiment, the method for evaluating the commercialization value of a patent comprises: Step S201, obtaining target patent information from a patent database, wherein the target patent information includes patent text; Step S203, extracting keyword features from the patent text using natural language processing technology, performing similarity comparison between the keyword features and related documents, and analyzing the technical features of the patent text based on the similarity comparison results; Step S205, analyzing the technical field in the patent text, and using time series analysis technology to predict the market response needs that meet the technical field; Step S207, using the technical features of the patent text and the market response requirements as evaluation indicators to establish a comprehensive evaluation model, and using the comprehensive evaluation model to evaluate the value of the target patent.

[0076] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store static information and dynamic information data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the steps in the above method embodiment are implemented.

[0077] Those skilled in the art will understand that Figure 3The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0078] In addition, the present invention also provides a computer device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiment when executing the computer program.

[0079] In addition, the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiment are implemented.

[0080] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0081] The present invention is not limited to the structures which have been described above and shown in the drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A patent commercialization value evaluation system, characterized in that: The system includes: A patent information acquisition unit, used to acquire target patent information from a patent database, wherein the target patent information includes a patent text; Patent technical analysis unit, used to extract keyword features in patent text, compare the keyword features with relevant documents for similarity, and analyze the technical features of the patent text based on the similarity comparison results; Market potential prediction unit, which is used to analyze the technical fields in the patent text and use time series analysis technology to predict the market response needs that match the technical fields; The comprehensive value assessment unit is used to establish a comprehensive assessment model using the technical features of the patent text and market response requirements as assessment indicators, and use the comprehensive assessment model to assess the value of the target patent.

2. The patent commercialization value evaluation system according to claim 1, characterized in that: The patent technical analysis unit includes a data preprocessing module, a keyword extraction module, a similarity calculation module and a technical feature analysis module, wherein: The data preprocessing module is used to perform data cleaning and stop word removal on the patent text in sequence, and convert the patent text into a standardized format; Keyword extraction module, used to calculate the word frequency-inverse document frequency of each word in the patent text, and analyze the keyword features in the patent text based on the word frequency-inverse document frequency; A similarity calculation module is used to convert the keyword features of the patent text into a text vector, and compare the text vector with the relevant literature to obtain a similarity comparison result; The technical feature analysis module is used to analyze the technical difficulty of the patent text based on keyword features, and to analyze the innovativeness of the patent text based on similarity comparison results.

3. The patent commercialization value evaluation system according to claim 2, characterized in that: The keyword extraction module calculates the word frequency-inverse document frequency of each word in the patent text and analyzes the keyword features in the patent text based on the word frequency-inverse document frequency, including: Use word segmentation tools to segment the patent text into several words, remove meaningless words in the patent text and generate a word list; Calculate the word frequency and inverse document frequency of each word in the patent text respectively, and multiply the word frequency and inverse document frequency to obtain the word frequency-inverse document frequency value of each word; All words in the patent text are sorted according to the word frequency-inverse document frequency value, and words within the preset range of the sorting list are selected as keyword features in the patent text.

4. The patent commercialization value evaluation system according to claim 3, characterized in that: The market potential prediction unit includes a technical field analysis module, a market demand analysis module and a mapping relationship analysis module, wherein: The technical field analysis module is used to identify the technical field to which the patent text belongs based on keyword features; The market demand forecasting module is used to collect market demand data within a preset time period and establish a multivariate time series model, and use the multivariate time series model to predict the market response demand in the future time period; The mapping relationship analysis module is used to calculate the Pearson correlation coefficient between the technical field to which the patent text belongs and the market response demand, and to measure the mapping relationship between the technical field to which the patent text belongs and the market response demand based on the Pearson correlation coefficient.

5. The patent commercialization value evaluation system according to claim 4, characterized in that: The market demand data includes market size data, market growth data, consumer behavior data, technology hotspot data and social environment data.

6. The patent commercialization value evaluation system according to claim 5, characterized in that: The calculation formula of the Pearson correlation coefficient is: ； In the formula, r The Pearson correlation coefficient between the technical field to which the patent text belongs and the market response demand; x i Indicates i The characteristic value of the technical field to which the patent text belongs; y i Indicates i The characteristic value of the market response demand; Indicates the average feature value of the technical field to which the patent text belongs; The average characteristic value representing the average market response demand.

7. The patent commercialization value evaluation system according to claim 6, characterized in that: The market demand forecasting module includes: establishing a multivariate time series model and using the multivariate time series model to forecast the market response demand in the future time period; Convert the market demand data into market time series and perform a stationarity test on the market time series. If the market time series is not stationary, perform a differential analysis on the market time series. Test the truncation characteristics of the autocorrelation function and partial autocorrelation function of the market time series after differential analysis, and determine the value range of the multivariate time series model parameters based on the truncation characteristics; The seasonal characteristics of inter-market sequences are analyzed to establish a multivariate time series model, which takes the market demand data model as input and predicts the market response demand in future time periods through the multivariate time series model.

8. The patent commercialization value evaluation system according to claim 7, characterized in that: The comprehensive value assessment unit includes an assessment index construction module, a comprehensive value assessment module and a result generation module, wherein: Evaluation indicator construction module, which is used to convert the technical features of patent texts and market response requirements into quantitative evaluation indicators; The comprehensive value evaluation module is used to assign weights to evaluation indicators, establish a comprehensive evaluation model based on the weights and contributions of the evaluation indicators, and calculate the value of the target patent using the comprehensive evaluation model; The result generation module is used to generate an evaluation report on the value of the target patent and to visualize the evaluation report.

9. The patent commercialization value evaluation system according to claim 8, characterized in that: The comprehensive value evaluation module allocates weights to evaluation indicators, establishes a comprehensive evaluation model based on the weights and contributions of the evaluation indicators, and calculates the value of the target patent using the comprehensive evaluation model, including: The hierarchical analysis method is used to construct a comparison matrix of evaluation indicators, and the contribution of evaluation indicators is calculated after consistency test of the comparison matrix; Assign weights to the evaluation indicators, integrate the evaluation indicators according to their contribution and weight values ​​to obtain a comprehensive evaluation model, calculate the stability index of the comprehensive evaluation model, and grade the comprehensive evaluation model based on the stability index of the comprehensive evaluation model; The graded comprehensive evaluation model is converted into a tree structure, and the tree structure is traversed to obtain a multi-branch sub-level model of the comprehensive evaluation model, and the multi-branch sub-level model is used to calculate the value of the target patent.

10. A method for evaluating the commercialization value of a patent, characterized in that: The method includes: Acquire target patent information from a patent database, wherein the target patent information includes patent text; Extract keyword features from patent texts, compare the keyword features with relevant literature for similarity, and analyze the technical features of patent texts based on the similarity comparison results; Analyze the technical fields in patent texts and use time series analysis techniques to predict market response needs that match the technical fields; A comprehensive evaluation model is established by taking the technical features of the patent text and the market response needs as evaluation indicators, and the comprehensive evaluation model is used to evaluate the value of the target patent.

Images