Technical cooperation correlation degree analysis method, device, equipment, medium and product

Abstract

The embodiment of the invention provides a correlation degree analysis method and device for technology cooperation, equipment, a medium and a product, and the method comprises the steps: determining two to-be-analyzed regions, obtaining cooperation patents of the two regions, determining target patents from the cooperation patents of the two regions, obtaining the importance degree of each target patent, and obtaining the correlation degree of each target patent; obtaining a target importance degree according to the importance degrees of all target patents and the distribution condition of the number of cooperative patents in the two regions, obtaining a similarity degree between the two technical field sets according to the technical field sets of the two regions, and obtaining a cooperative patent number of the two regions according to the target importance degree and the similarity degree. The correlation degree of the technical cooperation between the two areas is obtained, and the correlation degree and the cooperation depth of the cooperative areas in the technical level can be accurately reflected through the correlation degree of the technical cooperation between the two areas.

Description

Technical Field

[0001] The present disclosure relates to the field of data mining technology, and in particular, to a method, device, equipment, medium and product for analyzing the relevance of technical cooperation. Background Art

[0002] Through the analysis of the correlation degree of technical cooperation, we can understand the synergy effect of different regions, organizations or countries in scientific and technological innovation. At present, the existing technology mainly evaluates the intensity of cooperation by counting the number of cooperative patents. This method is simple and intuitive, but it ignores the technical details and depth of patents.

[0003] Some technical solutions attempt to enhance the assessment of cooperation intensity by analyzing patent citation relationships, cooperation network structures, etc. These methods can reveal the connection patterns between cooperative entities, but they often require a lot of data cleaning and complex network analysis, and do not take into account the technical content of the patents, and cannot accurately reflect the technical correlation between the two parties and the depth of cooperation. Summary of the invention

[0004] The embodiments of the present disclosure provide a method, device, equipment, medium and product for analyzing the relevance of technical cooperation, which are used to solve the technical problem that the method for analyzing the relevance of technical cooperation in the prior art does not take the technical content of the patent into consideration and the relevance analysis results are inaccurate.

[0005] According to one aspect of an embodiment of the present disclosure, a method for analyzing the relevance of technical cooperation is provided, comprising: Determine two regions to be analyzed, obtain cooperative patents in the two regions respectively, and determine target patents from the cooperative patents in the two regions. The cooperative patents are patents with multiple patent holders and at least one patent holder is located in the corresponding region. The target patents include at least one first patent holder and at least one second patent holder. The first patent holder is located in one of the two regions, and the second patent holder is located in the other of the two regions. Obtain the importance of each target patent. According to the importance of all target patents and the distribution of the number of cooperative patents in the two regions, obtain the target importance. The importance is used to measure the importance of the characteristic information of the target patent in the characteristic information of all cooperative patents. The target importance is used to indicate the common importance of all target patents in the two regions. According to the technical field sets of the two regions, the similarity between the two technical field sets is obtained, and the technical field set of each region includes the technical fields of each cooperative patent in the corresponding region; Based on the importance and similarity of the goals, the relevance of technical cooperation between the two regions is obtained.

[0006] According to another aspect of an embodiment of the present disclosure, a device for analyzing the relevance of technical cooperation is provided, comprising: A target patent determination module is used to determine two regions to be analyzed, obtain cooperative patents in the two regions respectively, and determine a target patent from the cooperative patents in the two regions. The cooperative patent is a patent with multiple patent holders and at least one patent holder is located in the corresponding region. The target patent includes at least one first patent holder and at least one second patent holder. The first patent holder is located in one of the two regions, and the second patent holder is located in the other of the two regions. The importance determination module is used to obtain the importance of each target patent. The target importance is obtained based on the importance of all target patents and the distribution of the number of cooperative patents in the two regions. The importance is used to measure the importance of the characteristic information of the target patent in the characteristic information of all cooperative patents. The target importance is used to indicate the common importance of all target patents in the two regions. A similarity determination module, for obtaining the similarity between two technical field sets according to the technical field sets of the two regions, wherein the technical field set of each region includes the technical fields of each cooperative patent in the corresponding region; The technical cooperation analysis module is used to obtain the relevance of technical cooperation between two regions based on the importance and similarity of the targets.

[0007] According to another aspect of an embodiment of the present disclosure, an electronic device is provided. The electronic device includes a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement the steps of the method provided in any of the above embodiments.

[0008] According to another aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method provided in any of the above embodiments are implemented.

[0009] According to one aspect of an embodiment of the present disclosure, a computer program product is provided, including a computer program, and the computer program is executed by a processor to perform the steps of the method provided in any of the above embodiments.

[0010] The technical solution provided by the embodiments of the present disclosure has the following beneficial effects: Through the relevant data of cooperative patents in the area to be analyzed, the number and distribution of cooperative patents in the two areas to be analyzed and the target patents with cooperative relations between the two areas, the importance of the characteristic information of the target patent in the characteristic information of all cooperative patents is deeply analyzed, the importance of the target patent is determined, and the similarity between the corresponding technical field sets of the two areas is determined to measure the technical agglomeration effect of cooperative patents in the area. The correlation degree of the technical cooperation between the two areas is jointly determined from the two granularities of the characteristic information of a single patent and the technical field of the region as a whole. This can capture the technical details more comprehensively, accurately reflect the correlation degree and the depth of cooperation between the cooperating areas at the technical level, and enable the correlation degree of the technical cooperation to more directly and accurately quantify the intensity of cooperation between the two areas, thereby improving the accuracy of the correlation analysis results. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for describing the embodiments of the present disclosure are briefly introduced below.

[0012] Figure 1 A flowchart of a method for analyzing the relevance of technical cooperation provided by an embodiment of the present disclosure; Figure 2 A schematic diagram of a method for obtaining first regional information provided by an embodiment of the present disclosure; Figure 3 A schematic diagram of a method for obtaining second regional information provided by an embodiment of the present disclosure; Figure 4 A schematic diagram of the structure of a device for analyzing the relevance of technical cooperation provided by an embodiment of the present disclosure; Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0013] The embodiments of the present disclosure are described below in conjunction with the drawings in the present disclosure. It should be understood that the implementation methods described below in conjunction with the drawings are exemplary descriptions for explaining the technical solutions of the embodiments of the present disclosure and do not constitute a limitation on the technical solutions of the embodiments of the present disclosure.

[0014] It will be understood by those skilled in the art that, unless specifically stated, the singular forms "one", "an", "said" and "the" used herein may also include plural forms. It should be further understood that the terms "including" and "comprising" used in the embodiments of the present disclosure refer to that the corresponding features can be implemented as the presented features, information, data, steps, operations, elements and / or components, but do not exclude the implementation as other features, information, data, steps, operations, elements, components and / or combinations thereof supported by the technical field. It should be understood that when we say that an element is "connected" or "coupled" to another element, the one element may be directly connected or coupled to the other element, or it may refer to that the one element and the other element establish a connection relationship through an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein indicates at least one of the items defined by the term, for example, "A and / or B" may be implemented as "A", or as "B", or as "A and B".

[0015] In order to make the objectives, technical solutions and advantages of the present disclosure more clear, the embodiments of the present disclosure will be further described in detail below with reference to the accompanying drawings.

[0016] The following describes several exemplary embodiments to illustrate the technical solutions of the embodiments of the present disclosure and the technical effects produced by the technical solutions of the present disclosure. It should be noted that the following embodiments can refer to, draw on or combine with each other, and the same terms, similar features and similar implementation steps in different embodiments will not be described repeatedly.

[0017] The following is a description of the related technologies involved in this application: Related technology 1: Currently, the main cooperation analysis method used is based on the number of patents. The cooperation intensity is evaluated by counting the number of cooperative patents. This single-dimensional analysis method is simple and intuitive, but it does not involve the technical details and in-depth analysis of cooperative patents. It ignores the importance and relevance of cooperative patents in technical content, which can easily lead to a one-sided understanding of the relevance of technical cooperation and cannot fully reflect the actual value of the cooperative relationship.

[0018] For example, patent holders in two regions may jointly hold multiple collaborative patents, but if the technical content of these collaborative patents is not closely related to the overall technological direction of the region, then the actual significance and influence of these collaborations will be relatively limited.

[0019] Related technology 2: Using cooperation network analysis methods to evaluate cooperation intensity by analyzing patent citation relationships, building cooperation networks, and analyzing network structures, but these methods often require a lot of data cleaning and complex network analysis, and it is difficult to quantify the specific importance of a single patent in cooperation. In addition, related technologies rarely consider the technical content and classification information of patents, and thus cannot accurately reflect the technical relevance and depth of cooperation between the two parties.

[0020] Based on the deficiencies in the above related technologies in analyzing the relevance of technical cooperation, the embodiments of the present disclosure provide a more comprehensive and accurate method for analyzing the relevance of technical cooperation, so as to solve or partially solve the above problems.

[0021] It can be understood that in the method for analyzing the degree of relevance of technical cooperation provided by the embodiment of the present disclosure, any method step can be executed by the terminal and / or the server, and all the steps in the method can be executed independently by the terminal or the server, or jointly by the terminal and the server.

[0022] The server may be an independent physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides cloud computing services. The terminal may be a smart phone, tablet computer, laptop computer, desktop computer, intelligent voice interaction device (such as smart speaker), wearable electronic device (such as smart watch), vehicle-mounted terminal, smart home appliance (such as smart TV), AR / VR device, etc., but is not limited thereto.

[0023] The following describes the embodiments of the present disclosure using a server as an execution subject; however, this does not constitute a limitation to the embodiments of the present disclosure.

[0024] Figure 1 A flowchart of a method for analyzing the relevance of technical cooperation provided by an embodiment of the present disclosure is shown in FIG. Figure 1 As shown, the technical solution provided by the embodiment of the present disclosure includes the following steps: Step S101, determining two regions to be analyzed, obtaining cooperative patents in the two regions respectively, and determining a target patent from the cooperative patents in the two regions.

[0025] Among them, a collaborative patent is a patent with multiple patent owners and at least one patent owner is located in the corresponding region. The target patent includes at least one first patent owner and at least one second patent owner. The first patent owner is located in one of the two regions, and the second patent owner is located in the other of the two regions.

[0026] Specifically, the embodiments of the present disclosure provide a technical solution for analyzing the degree of relevance of regional technical cooperation, wherein a region refers to a unit with clear geographical, administrative, economic or socio-cultural boundaries, and the rules for dividing the region and the selection of the region to be analyzed can be determined according to actual needs.

[0027] For example, if divided based on natural geographical features, the regions can be divided into Europe, Asia, the Yangtze River Delta, the Pearl River Delta, etc.; if divided based on administrative regions, the regions can be divided into different countries, provinces, cities and smaller administrative units; if divided based on economic characteristics, the regions can be divided into special economic zones or economic associations, etc.; if divided based on social and cultural characteristics, the regions can be divided into different organizations, and the organizations can be composed of multiple administrative regions, enterprises, universities, research institutions or individuals.

[0028] In the embodiment of the present disclosure, the two regions to be analyzed may be the same or different regions. When the two regions are the same, the correlation degree of technical cooperation within the region can be analyzed. When the two regions are different, the correlation degree of technical cooperation between the two regions can be analyzed.

[0029] In step S101, two regions to be analyzed are determined and the two regions are respectively denoted as and ,area and Can be the same or different.

[0030] For Region and , respectively, obtain cooperative patents in the corresponding regions. A cooperative patent is a patent with multiple patentees and at least one patentee is located in the corresponding region. The cooperative patent is denoted as p, and the corresponding region The cooperative patent is recorded as p1, and the set of cooperative patents P1 is obtained. The cooperative patent is denoted as p2, and the set of cooperative patents P2 is obtained.

[0031] Determine the target patent from the cooperative patents of the two regions and record the target patent as , target patent It includes at least one first patent owner and at least one second patent owner, the first patent owner is located in one of the two regions, and the second patent owner is located in the other of the two regions.

[0032] It is understood that when two regions are the same, the target patent means that there are at least two patent holders located in the region. and If different, the target patent refers to two patent holders located in the region and .

[0033] In addition, it should be noted that when analyzing the relevance of technical cooperation between regions, it is possible to conduct a comprehensive analysis of technical cooperation between regions in all technical fields, or to analyze technical cooperation between regions corresponding to specific technical fields.

[0034] When determining cooperative patents, you can screen the technical fields to which the cooperative patents belong, such as selecting only cooperative patents related to the field of communication technology, or selecting smaller technical fields such as the field of wireless communication technology, etc. Whether it is necessary to select a technical field and the specific type of the selected technical field can be determined according to actual needs.

[0035] Step S102, obtaining the importance of each target patent, and obtaining the target importance according to the importance of all target patents and the distribution of the number of cooperative patents in the two regions.

[0036] Among them, the importance is used to measure the importance of the characteristic information of the target patent in the characteristic information of all cooperative patents, and the target importance is used to indicate the common importance of all target patents in two regions.

[0037] Specifically, after determining the target patents with a cooperative relationship between the two regions, in step S102, the importance of each target patent is obtained. The importance is used to measure the importance of the characteristic information of the target patent in the characteristic information of all cooperative patents, that is, the importance is used to reflect the extent to which the target patent represents the technical cooperation between the two regions, and quantitatively measure the relative importance or influence of a single target patent on the technical cooperation between the two regions.

[0038] Among them, characteristic information refers to information that can be extracted from the patent text and can represent certain attributes or characteristics of the patent, including but not limited to keywords, classification numbers, citation relationships, patent family size, application year, etc., which can be determined according to actual needs.

[0039] For example, it can be considered that the more keyword frequencies, classification number occurrences, citations, and patent families, and the closer the application year is to the current patent, the higher the importance of the patent. The specific type of characteristic information used to measure the importance and the method of calculating the importance can be determined according to actual needs.

[0040] The target importance is obtained based on the importance of all target patents and the distribution of the number of cooperative patents in the two regions. The target importance is used to indicate the common importance of all target patents in the two regions, that is, to measure the degree of correlation between all target patents and the overall technical direction of the two regions with a cooperative relationship. The target importance can be used to evaluate the relative importance or influence of all target patents in the cooperation between regions among all cooperative patents in the two regions to obtain an overall measurement.

[0041] It is understandable that the number of cooperative patents corresponding to different regions may be different, that is, the proportion of target patents in different regions may be different. The embodiment of the present disclosure takes into account the distribution of the number of cooperative patents in two regions, summarizes or averages the importance of all target patents, and obtains the target importance to measure the overall importance of all target patents, which can effectively avoid the impact of too many or too few regional cooperative patents on the target importance.

[0042] The calculation method of the target importance can be determined according to actual needs, and the calculation method of the target importance includes but is not limited to weighted summation, arithmetic mean or harmonic mean, etc.

[0043] For example, the ratio of the target patent to the number of cooperative patents corresponding to the region can be used as the weight, and the importance of each target patent can be weighted summed to obtain the target importance; or, the arithmetic mean of the number of cooperative patents corresponding to the two regions can be obtained, and the sum of the importance of each target patent can be divided by the arithmetic mean to obtain the target importance; or, the harmonic mean of the number of cooperative patents corresponding to the two regions can be obtained, and the sum of the importance of each target patent can be divided by the harmonic mean to obtain the target importance.

[0044] It is understandable that if the harmonic mean is used to calculate the target importance , all target patents The set formed is denoted as P o , target patent The importance of ), referred to as ,area The number of corresponding cooperative patents is recorded as .

[0045] When two regions are the same, the region is recorded as , the harmonic mean is equal to the area The number of corresponding collaborative patents .

[0046] Target importance Calculated by the following formula:

[0047] When the area and Different regions and The number of cooperative patents is recorded as and , the harmonic mean is denoted as .

[0048] Harmonic mean Calculated by the following formula:

[0049] Target importance Calculated by the following formula:

[0050] Step S103: obtaining the similarity between the two technical field sets according to the technical field sets of the two regions.

[0051] The technical field set of each region includes the technical fields of each cooperative patent in the corresponding region.

[0052] Specifically, considering the characteristics of regional cooperation, patent holders in a region may be concentrated in a specific technical field, forming a technology clustering effect; there may be cross-regional technical cooperation between patent holders in different regions, and such cooperation may involve multiple technical fields; regional cooperation may include joint research and development, technology transfer, technology licensing and other forms of cooperation. Based on the above characteristics, the embodiment of the present disclosure considers the technology clustering effect within a region, and measures the technical relevance and importance of cooperation between regions by the degree of similarity between two sets of technical fields.

[0053] It can be understood that each collaborative patent corresponds to a technical field, which can be determined based on information such as the collaborative patent's classification number, keywords, and patent text semantics. The specific method of obtaining the technical field can be determined based on actual needs.

[0054] In addition, the division granularity and division rules of technical fields can be determined according to actual needs. For example, when conducting a comprehensive analysis of the technical cooperation between regions in all technical fields, the technical fields can be divided into coarse-grained ones. When analyzing the technical cooperation between regions corresponding to specific technical fields, more fine-grained technical fields can be divided in specific technical fields.

[0055] For example, the classification number of a patent can be determined based on classification methods such as the International Patent Classification (IPC), the Chinese Library Classification (CLC), and the Classification of Instructional Programs (CIP).

[0056] Taking the IPC classification as an example, the IPC classification divides all technical contents related to invention patents into multiple levels such as parts, sub-parts, major categories, minor categories, main groups and sub-groups, forming a complete hierarchical classification system. According to each level, technical field divisions of different granularities can be determined. For example, the IPC sub-category can be used as the classification granularity of the technical field, and each IPC sub-category can be regarded as a technical field dimension.

[0057] After determining the technical field corresponding to each cooperative patent, the technical field sets of the two technical fields are obtained respectively. It can be understood that the technical fields of the cooperative patents corresponding to the regions may be the same or different, and the technical field set of each region includes the technical fields of the cooperative patents of the corresponding region.

[0058] Considering that the patent owners and related cooperative patents in the region may be concentrated in one or some technical fields, forming a technology agglomeration effect, in step S103, the similarity between the two technical field sets is obtained based on the technical field sets of the two regions. The similarity between the two technical field sets is the technology concentration (Technology Concentration), which is used to measure the technology agglomeration effect of cooperative patents in the region, reflect the degree of aggregation of cooperative patents in the two regions in the distribution of technical fields, and more comprehensively reflect the agglomeration effect of regional technical cooperation and inter-regional technical exchanges.

[0059] It is understandable that the specific measurement calculation method of the similarity between two sets of technical fields includes but is not limited to using Jaccard similarity coefficient, cosine similarity, Wasserstein distance, edit distance, etc., or using corresponding variants.

[0060] For example, the Wasserstein distance is used to measure the similarity of the distribution of technical fields in two regions to calculate the similarity between the two technical field sets. and The similarity between the technical field sets is denoted as .

[0061] Similarity Calculated by the following formula:

[0062] In the formula, and Respectively represent the area and The distribution vector of the technical field; the distribution vector of the technical field By statistical area The distribution vector of the IPC classification codes of all patents in the patent database is obtained. Each IPC subclass is regarded as a technical field dimension, and the corresponding regional technical field distribution vector is obtained through multi-hot vector encoding. Represents Wasserstein Distance, which is used to measure the similarity of technology field distribution between two regions.

[0063] It is understood that when two regions are the same, the region is recorded as , the similarity within the region is recorded as , Take 1.

[0064] Step S104, obtaining the correlation degree of the technical cooperation between the two regions according to the target importance and similarity.

[0065] Specifically, after obtaining the target importance and similarity, in step S104, the correlation degree of the technical cooperation between the two regions is obtained according to the target importance and similarity.

[0066] It can be understood that when two regions are the same, the degree of correlation (i.e., cooperation intensity) measures the technical relevance and importance of cooperation within the region; when two regions are different, the degree of correlation (i.e., cooperation intensity) measures the technical relevance and importance of cooperation between the two regions. The specific calculation method of the degree of correlation can be determined according to actual needs, including but not limited to weighted summation and multiplication.

[0067] For example, the product of the target importance and the similarity is taken as the relevance, and the relevance is recorded as , referred to as .

[0068] Degree of relevance Calculated by the following formula:

[0069] It is understood that when two regions are the same, the region is recorded as , the similarity within the region Take 1, the correlation The importance of the target .

[0070] After obtaining the degree of correlation of technical cooperation between two regions, the degree of correlation can be compared with a preset correlation threshold. If it is determined that the degree of correlation is not less than the correlation threshold, it indicates that the technical cooperation between the regions is close. If it is determined that the degree of correlation is less than the correlation threshold, it indicates that the technical cooperation between the regions is distant, there is a lack of effective communication and resource sharing, and technical exchanges and cooperation are at a low level.

[0071] After determining that the degree of relevance is less than the relevance threshold, preset measures may be taken to strengthen technical cooperation between regions, where the preset measures include but are not limited to regularly or irregularly pushing relevant patents of patent owners in the same technical field in the other region of the two regions to patent owners in one of the two regions (or for the same region, pushing relevant patents of other patent owners to patent owners in the same technical field), and carrying out regional development projects, such as joint scientific research between regions, and jointly developing industrial parks.

[0072] The technical solution provided by the disclosed embodiment uses the relevant data of cooperative patents in the area to be analyzed, the cooperative patents of the two areas to be analyzed, and the number and distribution of target patents with cooperative relations between the two areas to be analyzed, to deeply analyze the importance of the characteristic information of the target patent in the characteristic information of all cooperative patents, determine the importance of the target patent, and determine the similarity between the corresponding technical field sets of the two areas to measure the technical agglomeration effect of the cooperative patents in the area, and jointly determine the correlation of the technical cooperation between the two areas from the two granularities of the characteristic information of a single patent and the technical field of the region as a whole, so as to capture the technical details more comprehensively, accurately reflect the correlation between the cooperating areas at the technical level and the depth of cooperation, so that the correlation of the technical cooperation can more directly and accurately quantify the intensity of cooperation between the two areas, thereby improving the accuracy of the correlation analysis results.

[0073] Compared with the related technologies that only use relevant information such as the number of cooperation to analyze the intensity of cooperation, the technical solution provided by the embodiment of the present disclosure can quantify the intensity of cooperation of each cooperation relationship between regions from a fine-grained level with the importance of each target patent, providing a more substantial measurement of cooperation intensity. In addition, not only the number of all target patents and cooperative patents, but also the distribution of the number of cooperative patents and target patents in each region are considered, and the importance of each target patent is used to jointly determine the target cooperation intensity, making the target importance more direct and accurate, which can better reflect the intensity and depth of cooperation and reveal the complexity and distribution characteristics of technical cooperation.

[0074] In a possible implementation, the characteristic information of the target patent includes keywords and classification numbers; Accordingly, obtain the importance of each target patent, including: For each target patent, the first information and the second information of the target patent are obtained, wherein the first information is used to measure the importance of the keywords of the target patent among the keywords of all the cooperative patents, and the second information is used to measure the importance of the classification number of the target patent among the classification numbers of all the cooperative patents; For each target patent, the first information and the second information of the target patent are weighted and summed to obtain the importance of the target patent.

[0075] Specifically, the characteristic information of the target patent in the embodiment of the present disclosure includes keywords and classification numbers. Keywords can be used to measure the similarity of patents in technical themes and research fields, and classification numbers can be used to measure the similarity of patents in technical classifications. Through comprehensive consideration of the two dimensions of keywords and classification numbers, the importance of the target patent can be measured more comprehensively and accurately.

[0076] Considering the keyword dimension, for each target patent , obtain the first information of the target patent. The first information is used to measure the importance of the target patent's keywords among the keywords of all cooperative patents. The similarity and importance of the target patent's keywords and the keywords of all cooperative patents are positively correlated. The first information can be determined by the frequency or frequency of the target patent's keywords appearing in all cooperative patents. The specific method can be determined according to actual needs.

[0077] Considering the classification number, for each target patent , obtain the second information of the target patent. The second information is used to measure the importance of the classification number of the target patent in the classification numbers of all cooperative patents. The similarity between the classification number of the target patent and the classification numbers of all cooperative patents is positively correlated with the importance. The second information can be determined by the structural similarity between the classification number of the target patent and the classification numbers of all cooperative patents. The specific method can be determined according to actual needs.

[0078] It can be understood that the classification number is a numbering system. The classification number of a patent can directly reflect the technical classification and application scenarios of the patent. The higher the structural similarity of the classification numbers of two patents, the closer the technical classification of the patents.

[0079] For each target patent, after obtaining the first information and the second information of the target patent, the first information and the second information are weighted and summed to obtain the importance of the target patent.

[0080] Target Patent Importance Calculated by the following formula:

[0081] In the formula, The target patent First information; The target patent The second information; and The weight parameters of the first information and the second information are respectively used to balance the contributions of the two dimensions of keywords and classification numbers. The specific values ​​of the weight parameters can be determined according to actual needs. For example, the weight parameters can be determined through artificial experience setting, cross-validation or principal component analysis.

[0082] The characteristic information of the cooperative patents (including the target patents) in the technical solution provided by the embodiments of the present disclosure includes keywords and classification numbers. The similarity of the patents in technical description can be directly reflected from the keyword dimension, and the proximity of the patents in technical classification can be reflected from the classification number dimension. By comprehensively considering the importance of the keywords and classification numbers of each target patent in all cooperative patents and jointly determining the importance of the target patent, it is possible to more comprehensively capture the technical details and the depth of cooperation, and comprehensively evaluate the technical relevance between the target patent and the cooperative patents of each region.

[0083] In a possible implementation, the first information of the target patent is obtained in the following manner: Extract keywords from target patents; For each region, according to the regional keyword weight of each keyword in the region, the average value of the regional keyword weight of each keyword in the target patent in the region is calculated as the regional first information of the target patent in the region; The sum of the first regional information of the target patent in the two regions is taken as the first information of the target patent; Among them, for each region, the regional keyword weight of the keyword in the region is positively correlated with the number of first patents in the region, and the first patent is a cooperative patent with the corresponding keyword.

[0084] Specifically, in order to more accurately reflect the importance of the target patent in the regional cooperative relationship, in the keyword dimension, the embodiment of the present disclosure not only considers whether the keywords existing in the corresponding cooperative patents of the region exist in the target patent, but also considers the importance of each keyword of the target patent in each cooperative patent of the region, and proposes an extended calculation method based on the basic idea of ​​Jaccard similarity, which more accurately reflects the similarity in technical descriptions between patents by introducing regional keyword weights.

[0085] Jaccard similarity is a statistical method for comparing the similarity of two sets, especially suitable for comparing binary features (presence / absence). Its calculation formula is:

[0086] In the formula, A ∩ B Representing a collection A and collection B The size of the intersection of the two sets (that is, the number of elements that exist in both sets), A ∪ B Representing a collection A and collection B The Jaccard similarity value range is [0,1], where 0 means that the two sets have no common elements at all and 1 means that the two sets are exactly the same.

[0087] By introducing regional keyword weights, the importance of keywords within the region is taken into account. For each target patent, the keywords in the target patent and the corresponding regional keyword weights are used. For each region, the regional first information of the target patent in the region needs to be obtained, and the first information of the target patent is determined by the regional first information of the two regions.

[0088] Figure 2 A schematic diagram of a method for obtaining first regional information provided by an embodiment of the present disclosure is shown in FIG. Figure 2 As shown, for the target patent , extract target patent Keyword k in target patent At least one keyword k is included in the target patent All the keywords in , the total number of keywords is recorded as ,The method and quantity of keyword extraction are determined according to actual needs.

[0089] It is understandable that the number of keywords affects the complexity of calculation. The embodiment of the present disclosure can construct a keyword table based on the high-frequency technical terms in the technical fields involved in the cooperative patents of the two regions to be analyzed, and extract keywords in the target patent based on the keyword table to reduce the number of keywords, reduce the complexity of calculation, and improve calculation efficiency.

[0090] Any area For example, for the target patent For each keyword k in the region Regional keyword weight .

[0091] Among them, for each area , keyword k in the region Regional keyword weight With area The first patent is a cooperative patent with the corresponding keyword k, that is, for the region The more cooperative patents with the corresponding keyword k, the more likely keyword k is in this area. Regional keyword weight in The larger the regional keyword weight is, the The specific value and determination method can be determined according to actual needs.

[0092] For target patents All keywords in , calculate the average value of the corresponding regional keyword weights, and use the average value of the regional keyword weights as the target patent In the area The first information of the region .

[0093] Regional first information Calculated by the following formula:

[0094] Through the above calculation method, for the area , i is 1 or 2, the target patent can be calculated In the area The first information of the region , and target patents In the area The first information of the region .

[0095] The target patent First information in both areas and The sum is used as the first information of the target patent .

[0096] First Information Calculated by the following formula:

[0097] It is understood that when two regions are the same, the region is recorded as , the first information of the target patent Target patent In the area The first information of the region twice as much.

[0098] The technical solution provided by the embodiment of the present disclosure takes into account the importance of keywords within a region by introducing the regional keyword weights of keywords in the region for each region. For each target patent, the average value of the regional keyword weights of each keyword of the target patent in two regions is obtained as the first regional information. The first regional information can reflect the similarity between the target patent and the keyword set of all cooperative patents in the corresponding region, can directly reflect the similarity between the target patent and the cooperative patents in the region in terms of technical description, and can more accurately evaluate the importance of the target patent in the corresponding region from the keyword dimension.

[0099] In a possible implementation, the regional keyword weight of a keyword in a region is obtained in the following manner: Obtain keywords from each cooperative patent in the region and build a regional keyword set; Obtaining a first number of first patents corresponding to each keyword in a regional keyword set; According to the first number of first patents corresponding to each keyword in the regional keyword set, the first number of first patents corresponding to the keyword is normalized to obtain the regional keyword weight of the keyword in the region.

[0100] Specifically, any area For example, the area The collaborative patent is recorded as ,area All cooperative patent construction areas in The collaborative patent collection is recorded as .

[0101] Extract each collaborative patent Keyword k in the collaborative patent set All cooperative patents Keyword k in the , build a regional keyword set , the same keyword is recorded only once in the regional keyword set.

[0102] For regional keyword sets For each keyword k in the table, the cooperative patent with the keyword k is recorded as the first patent, and the number of first patents is recorded as the first number .

[0103] For the first quantity corresponding to each keyword, it can be determined that each keyword is in the regional keyword set The total count in is recorded as , the first number of the first patents corresponding to the keywords Perform normalization to obtain the keyword k in the region Regional keyword weight .

[0104] The regional keyword weight takes into account the importance of keywords within each region. Through normalization processing, it ensures that when there are many keywords, the corresponding regional keyword weight will not be too large, thus ensuring the consistency of the calculation measurement.

[0105] Regional keyword weight Calculated by the following formula:

[0106] Through the above calculation method, for the area , i is 1 or 2, and the keyword k in the region can be calculated Regional keyword weight , keyword k in the region Regional keyword weight It can be understood that when the two regions are the same, the regional keyword weights of keyword k in the two regions are also the same.

[0107] The technical solution provided by the embodiment of the present disclosure can measure the importance of keywords within the corresponding region through regional keyword weights. For each keyword of each target patent, the average value of the regional keyword weights corresponding to each keyword of each target patent is calculated in two regions respectively as the regional first information, which can accurately quantify the importance of the target patent in the corresponding region.

[0108] In a possible implementation, the second information of the target patent is obtained in the following manner: Determine the classification number of the target patent; For each region, obtain the classification code similarity between the classification code of the target patent and the classification codes of each cooperative patent in the region; For each region, according to the regional classification weights of the classifications of the cooperative patents in the region, the classification similarities between the classification of the target patent and the classifications of the cooperative patents in the region are weighted and summed to obtain the regional second information of the target patent in the region; The sum of the second regional information of the target patent in the two regions is used as the second information of the target patent; Among them, the classification number similarity between two classification numbers is positively correlated with the length of the same prefix of the two classification numbers; For each region, the regional classification number weight of the classification number in the region is positively correlated with the number of second patents in the region, where the second patent is a collaborative patent with the corresponding classification number.

[0109] Specifically, in order to more accurately reflect the importance of the target patent in the regional cooperative relationship, in the classification number dimension, the disclosed embodiment not only considers whether the classification number of the target patent is the same as the classification numbers of the corresponding cooperative patents in the region, but also considers the importance of the classification numbers of each cooperative patent in the regional cooperative patents. By introducing regional classification number weights, the similarities between patents in technical classification are more accurately reflected.

[0110] For each target patent, the classification code similarity between the classification code in the target patent and the classification codes of each cooperative patent in the region, as well as the corresponding regional classification code weight, is used. For each region, the regional second information of the target patent in that region needs to be obtained, and the second information of the target patent is jointly determined by the regional second information of the two regions.

[0111] Figure 3 A schematic diagram of a method for obtaining the second regional information provided by an embodiment of the present disclosure is shown in FIG. Figure 3 As shown, for the target patent , determine the target patent Classification code: m.

[0112] Any area For example, the area The collaborative patent is recorded as ,area All cooperative patent construction areas in The collaborative patent collection is recorded as , determine each cooperative patent Classification number c, build regional classification number set , the same classification number is recorded only once in the regional classification number set. The classification number division system used by the embodiment of the present disclosure to determine the classification number of each patent can be determined according to actual needs.

[0113] For regional classification code sets For each classification code c in the target patent The classification code similarity between the classification code m and each classification code c. The classification code similarity refers to the structural similarity between two classification codes, denoted as , referred to as .

[0114] Patents with similar technical classifications may have large differences in text descriptions and keywords. It is difficult to capture such patents by only considering the keyword dimension. The analysis of a single dimension may lead to deviations or information omissions, which may have an adverse impact on the calculation of the importance of the target patent and make the calculation results inaccurate. The structural similarity of the classification number is suitable for measuring patents with similar technical classifications. Combining the two dimensions of keywords and classification numbers can effectively and comprehensively measure the importance of the target patent and improve the accuracy of the importance calculation.

[0115] It can be understood that the similarity of the classification numbers is positively correlated with the length of the same prefix of the two classification numbers, that is, the longer the length of the same prefix of the two classification numbers, the greater the similarity of the classification numbers. The specific value and determination method of the similarity of the classification numbers can be determined according to actual needs.

[0116] Any area For example, for the regional classification code set For each classification number c in the region Weight of regional classification number .

[0117] Among them, for each area , classification number c in the area Classification number weight With area The second patent is a cooperative patent with the corresponding classification number c, that is, for the region The more the number of cooperative patents with the corresponding classification number c is, the more classification number c is in this area. The weight of the regional classification number in The larger the value, the greater the weight of the regional classification number. The specific value and determination method can be determined according to actual needs.

[0118] For regional classification code sets All classification codes c in the region Weight of regional classification number , for the target patent The similarity between the classification code m and the classification code c of each cooperative patent in the region Perform weighted summation to obtain the target patent In the area Second information of the area .

[0119] Regional Second Information Calculated by the following formula:

[0120] Through the above calculation method, for the area , i is 1 or 2, the target patent can be calculated In the area Second information of the area ( ), and the target patent In the area Second information of the area ( ).

[0121] The target patent Second information in two areas ( )and The sum is used as the second information of the target patent .

[0122] Second information Calculated by the following formula:

[0123] It is understood that when two regions are the same, the region is recorded as , the regional second information of the target patent Target patent In the area Second information of the area twice as much.

[0124] The technical solution provided by the embodiment of the present disclosure takes into account the importance of the classification number within the region by introducing the regional classification number weight of the classification number in the region for each region. For each target patent, in each region, the classification number similarity between the target classification number and the classification numbers of the corresponding region and the cooperative patent is calculated, and the corresponding regional classification number weight is used to weight the sum of the similarities of each classification number to obtain the regional second information. The regional second information can reflect the similarity between the target patent and the classification number set of all cooperative patents in the corresponding region, can directly reflect the similarity between the target patent and the cooperative patents in the region in terms of technical classification, and can more accurately evaluate the importance of the target patent in the corresponding region from the classification number dimension.

[0125] In a possible implementation, the weight of the regional classification number of the classification number in the region is obtained by: Obtain the classification numbers of each cooperative patent in the region and construct a regional classification number set; Obtain the second quantity of the second patent corresponding to each classification code in the regional classification code set; According to the second number of second patents corresponding to each classification number in the regional classification number set, the second number of second patents corresponding to the classification number is normalized to obtain the regional classification number weight of the classification number in the region.

[0126] Specifically, any area For example, the area The collaborative patent is recorded as ,area All cooperative patent construction areas in The collaborative patent collection is recorded as , determine each cooperative patent Classification number c, build regional classification number set .

[0127] For regional classification code sets For each classification number c in the table, record the cooperative patent with classification number c as the second patent, and record the number of the second patent as the second number .

[0128] For the second quantity corresponding to each classification number, it can be determined that each classification number is in the regional classification number set The total count in is recorded as , the second number of the second patent corresponding to the classification number Perform normalization to obtain the classification number c in the area Weight of regional classification number .

[0129] The regional classification number weight takes into account the importance of the classification number within each region. Through normalization processing, it ensures that when the number of classification numbers is large, the corresponding regional classification number weight will not be too large, thus ensuring the consistency of the calculation measurement.

[0130] Regional classification number weight Calculated by the following formula:

[0131] Through the above calculation method, for the area , i is 1 or 2, and the classification number c in the area can be calculated. Weight of regional classification number , classification number c in the area Weight of regional classification number It can be understood that when two regions are the same, the regional classification number weights of classification number c in the two regions are also the same.

[0132] The technical solution provided by the embodiment of the present disclosure can measure the importance of the classification number within the corresponding region through the regional classification number weight. For each classification number of the target patent, the similarity between the target classification number and the classification numbers of the corresponding region and the cooperative patent is calculated in two regions respectively, and the corresponding regional classification number weight is used to perform the weighted summation of the similarities of each classification number to obtain the second regional information, which can accurately quantify the importance of the classification number of the target patent in the corresponding region.

[0133] In a possible implementation, the classification code similarity between two classification codes is obtained by: Construct a similarity calculation function, which is the reciprocal of an exponential function with a base greater than 1; For any two classification numbers, the length of the difference between the two classification numbers is determined based on the length of the same prefix of the two classification numbers; Substitute the difference length as the independent variable into the similarity calculation function, and use the calculated dependent variable as the classification number similarity.

[0134] Specifically, for classification number c and classification number m, the length of the same prefix of the two classification numbers is recorded as , referred to as , the maximum length of the classification number c and the classification number m is recorded as , referred to as , that is, the difference length of the difference part of the two classification numbers is .

[0135] In the embodiment of the present disclosure, a similarity calculation function is constructed using the reciprocal of an exponential function whose base is greater than 1, and the specific size of the base can be determined according to actual needs.

[0136] Difference in length Substitute it into the similarity calculation function as the independent variable, and use the calculated dependent variable as the classification number similarity .

[0137] For example, the similarity calculation function The calculation formula is:

[0138] Taking the IPC classification system as an example, the IPC code of the classification number is 5 digits, which represent the department, major category, minor category, major group and minor group from front to back, and the granularity of the corresponding technical classification is from coarse to fine.

[0139] When the common prefix length of two classification numbers is 5, each coded bit of the two classification numbers is the same. 1; When the common prefix length of two classification numbers is 4, the two classification numbers are the same up to the large group code and before. ; When the common prefix length of two classification numbers is 3, the two classification numbers are the same up to the subclass code and before. ; When the common prefix length of two classification numbers is 2, the two classification numbers are the same up to the major category code and before. ; When the common prefix length of two classification numbers is 1, the two classification numbers only have some of the same coding bits. .

[0140] The technical solution provided by the disclosed embodiment constructs a similarity calculation formula with an exponential function, so that the longer the length of the common prefix of the classification number is, the higher the similarity of the classification number reflected is. The longer the common prefix is, the closer the calculated similarity value is to 1. For the classification number with a shorter common prefix, the similarity of the classification number will be lower, but will not drop to zero, which is in line with the actual situation. Even if the classification numbers belong to different categories, there may be certain similarities, which can provide good discrimination, so that even classification numbers with slight differences can have obvious differences in similarity.

[0141] Compared with the existing related technologies 1 and 2, the method for analyzing the relevance of technical cooperation provided by the embodiment of the present disclosure has the following advantages: The technical solution provided by the embodiments of the present disclosure comprehensively considers multiple dimensions, such as the number of cooperative patents in each region, the number of target patents with cooperative relations between the two regions, the importance of keywords and classification numbers of each target patent in all cooperative patents, and the degree of similarity between two sets of technical fields (technical concentration). Compared with the traditional method of existing related technologies that requires a large amount of data cleaning and complex network analysis, it provides a more efficient analysis approach and reduces the complexity and time cost of data processing.

[0142] Moreover, compared with existing related technologies, our analysis depth is enhanced, and the correlation degree of technical cooperation between regions is analyzed more deeply and accurately, and the intensity of regional cooperation is quantified, so as to help users obtain a more comprehensive view of cooperative relations. By revealing the mode and intensity of technical cooperation between different entities, our technical solution can promote cross-domain and cross-regional technical cooperation, promote technological innovation and knowledge sharing. It provides users with data-driven insights to help users understand the technical dynamics and trends behind the cooperation, so as to stay ahead in the competition.

[0143] The technical solution provided by the embodiments of the present disclosure can provide customized analysis services according to different user needs, such as the relevance analysis of technical cooperation in a specific industry (technical field) or region, such as the relevance analysis of technical cooperation between some patent holders, domestic regions, and international cities (cross-border), providing users with greater flexibility and value. It can be applied to products or projects such as patent analysis tools, enterprise cooperation decision support systems, and regional innovation cooperation evaluation platforms, especially in areas that require in-depth analysis of technical cooperation and knowledge flow, and has obvious competitive advantages.

[0144] It can provide more accurate and detailed analysis results of the relevance of technical cooperation, provide scientific basis and decision-making support for policy makers, business managers and research institutions, make more scientific decisions based on data, and improve the quality and efficiency of decision-making. It is helpful to promote the development of technological innovation, promote cross-sector, cross-regional and cross-national technical cooperation, and achieve more efficient resource allocation and more extensive knowledge sharing.

[0145] It should be understood that the embodiments of the present disclosure are only used as a specific example to explain the present invention in detail, and the described embodiments are only intended to facilitate the understanding of the present invention and do not have any limiting effect on the present invention.

[0146] Figure 4 A schematic diagram of a device for analyzing the relevance of technical cooperation provided by an embodiment of the present disclosure is shown in FIG. Figure 4 As shown, the technical cooperation relevance analysis device 400 includes: The target patent determination module 401 is used to determine two regions to be analyzed, obtain cooperative patents in the two regions respectively, and determine the target patent from the cooperative patents in the two regions. The cooperative patent is a patent with multiple patent holders and at least one patent holder is located in the corresponding region. The target patent includes at least one first patent holder and at least one second patent holder. The first patent holder is located in one of the two regions, and the second patent holder is located in the other of the two regions. The importance determination module 402 is used to obtain the importance of each target patent. According to the importance of all target patents and the distribution of the number of cooperative patents in the two regions, the target importance is obtained. The importance is used to measure the importance of the characteristic information of the target patent in the characteristic information of all cooperative patents. The target importance is used to represent the common importance of all target patents in the two regions. A similarity determination module 403 is used to obtain the similarity between two technical field sets according to the technical field sets of the two regions, where the technical field set of each region includes the technical fields of each cooperative patent in the corresponding region; The technical cooperation analysis module 404 is used to obtain the relevance of the technical cooperation between two regions according to the importance and similarity of the targets.

[0147] In a possible implementation, the characteristic information of the target patent includes keywords and classification numbers; Accordingly, obtain the importance of each target patent, including: For each target patent, the first information and the second information of the target patent are obtained, wherein the first information is used to measure the importance of the keywords of the target patent among the keywords of all the cooperative patents, and the second information is used to measure the importance of the classification number of the target patent among the classification numbers of all the cooperative patents; For each target patent, the first information and the second information of the target patent are weighted and summed to obtain the importance of the target patent.

[0148] In a possible implementation, the first information of the target patent is obtained in the following manner: Extract keywords from target patents; For each region, according to the regional keyword weight of each keyword in the region, the average value of the regional keyword weight of each keyword in the target patent in the region is calculated as the regional first information of the target patent in the region; The sum of the first regional information of the target patent in the two regions is taken as the first information of the target patent; Among them, for each region, the regional keyword weight of the keyword in the region is positively correlated with the number of first patents in the region, and the first patent is a cooperative patent with the corresponding keyword.

[0149] In a possible implementation, the regional keyword weight of a keyword in a region is obtained in the following manner: Obtain keywords from each cooperative patent in the region and build a regional keyword set; Obtaining a first number of first patents corresponding to each keyword in a regional keyword set; According to the first number of first patents corresponding to each keyword in the regional keyword set, the first number of first patents corresponding to the keyword is normalized to obtain the regional keyword weight of the keyword in the region.

[0150] In a possible implementation, the second information of the target patent is obtained in the following manner: Determine the classification number of the target patent; For each region, obtain the classification code similarity between the classification code of the target patent and the classification codes of each cooperative patent in the region; For each region, according to the regional classification weights of the classifications of the cooperative patents in the region, the classification similarities between the classification of the target patent and the classifications of the cooperative patents in the region are weighted and summed to obtain the regional second information of the target patent in the region; The sum of the second regional information of the target patent in the two regions is used as the second information of the target patent; Among them, the classification number similarity between two classification numbers is positively correlated with the length of the same prefix of the two classification numbers; For each region, the regional classification number weight of the classification number in the region is positively correlated with the number of second patents in the region, where the second patent is a collaborative patent with the corresponding classification number.

[0151] In a possible implementation, the weight of the regional classification number of the classification number in the region is obtained by: Obtain the classification numbers of each cooperative patent in the region and construct a regional classification number set; Obtain the second quantity of the second patent corresponding to each classification code in the regional classification code set; According to the second number of second patents corresponding to each classification number in the regional classification number set, the second number of second patents corresponding to the classification number is normalized to obtain the regional classification number weight of the classification number in the region.

[0152] In a possible implementation, the classification code similarity between two classification codes is obtained by: Construct a similarity calculation function, which is the reciprocal of an exponential function with a base greater than 1; For any two classification numbers, the length of the difference between the two classification numbers is determined based on the length of the same prefix of the two classification numbers; Substitute the difference length as the independent variable into the similarity calculation function, and use the calculated dependent variable as the classification number similarity.

[0153] The device of the embodiments of the present disclosure can execute the method provided by the embodiments of the present disclosure, and the implementation principles are similar. The actions performed by each module in the device of each embodiment of the present disclosure correspond to the steps in the method of each embodiment of the present disclosure. For the detailed functional description of each module of the device, please refer to the description in the corresponding method shown in the previous text, which will not be repeated here.

[0154] In addition, in the embodiments of the present disclosure, the term "module" or "unit" refers to a computer program or a part of a computer program with a predetermined function, and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories), or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0155] An embodiment of the present disclosure provides an electronic device (computer device / equipment / system), including a memory, a processor, and a computer program stored in the memory, and the processor executes the above-mentioned computer program to implement the steps of the method provided in any optional embodiment of the present disclosure and achieve corresponding technical effects.

[0156] In an optional embodiment, an electronic device is provided. Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure is shown in FIG. Figure 5As shown, the electronic device 500 includes: a processor 501 and a memory 503. The processor 501 and the memory 503 are connected, such as through a bus 502. Optionally, the electronic device 500 may also include a transceiver 504, which may be used for data interaction between the electronic device and other electronic devices, such as data transmission and / or data reception. It should be noted that in actual applications, the transceiver 504 is not limited to one, and the structure of the electronic device 500 does not constitute a limitation on the embodiments of the present disclosure.

[0157] Processor 501 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of the present invention. Processor 501 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0158] The bus 502 may include a path to transmit information between the above components. The bus 502 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 502 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0159] The memory 503 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), magnetic disk storage medium, other magnetic storage devices, or any other medium that can be used to carry or store computer programs and can be read by a computer, without limitation herein.

[0160] The memory 503 is used to store the computer program for executing the embodiment of the present disclosure, and the execution is controlled by the processor 501. The processor 501 is used to execute the computer program stored in the memory 503 to implement the steps shown in the above method embodiment.

[0161] The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), wearable devices, etc., and fixed terminals such as digital TVs, desktop computers, etc.

[0162] An embodiment of the present disclosure provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps and corresponding contents of the aforementioned method embodiment can be implemented.

[0163] The embodiments of the present disclosure also provide a computer program product, including a computer program, which can implement the steps and corresponding contents of the aforementioned method embodiments when executed by a processor.

[0164] It should be noted that the computer-readable storage medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0165] In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0166] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0167] The terms "first", "second", "third", "fourth", "1", "2", etc. (if any) in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than that shown or described in the text.

[0168] It should be understood that, although the flowchart of the embodiment of the present disclosure indicates each operation step by arrows, the implementation order of these steps is not limited to the order indicated by the arrows. Unless clearly stated herein, in some implementation scenarios of the embodiment of the present disclosure, the implementation steps in each flowchart can be executed in other orders according to demand. In addition, some or all of the steps in each flowchart may include multiple sub-steps or multiple stages based on the actual implementation scenario. Some or all of these sub-steps or stages can be executed at the same time, and each sub-step or stage in these sub-steps or stages can also be executed at different times. In scenarios with different execution times, the execution order of these sub-steps or stages can be flexibly configured according to demand, and the embodiment of the present disclosure does not limit this.

[0169] The above is only an optional implementation method for some implementation scenarios of the present disclosure. It should be pointed out that for ordinary technicians in this technical field, without departing from the technical concept of the scheme of the present disclosure, other similar implementation methods based on the technical ideas of the present disclosure are also within the protection scope of the embodiments of the present disclosure.

Claims

1. A method for analyzing the relevance of technical cooperation, characterized in that: include: Determine two regions to be analyzed, obtain cooperative patents in the two regions respectively, and determine a target patent from the cooperative patents in the two regions, wherein the cooperative patent is a patent with multiple patent holders and at least one patent holder is located in the corresponding region, and the target patent includes at least one first patent holder and at least one second patent holder, wherein the first patent holder is located in one of the two regions and the second patent holder is located in the other of the two regions; Obtain the importance of each target patent, and obtain the target importance according to the importance of all target patents and the distribution of the number of cooperative patents in the two regions. The target importance is used to measure the importance of the characteristic information of the target patent in the characteristic information of all cooperative patents. The target importance is used to represent the common importance of all target patents in the two regions; According to the technical field sets of the two regions, the similarity between the two technical field sets is obtained, and the technical field set of each region includes the technical fields of each cooperative patent in the corresponding region; According to the importance of the targets and the similarity, the relevance of the technical cooperation between the two regions is obtained.

2. The method for analyzing the relevance of technical cooperation according to claim 1, characterized in that: The characteristic information of the target patent includes keywords and classification numbers; Accordingly, obtain the importance of each target patent, including: For each target patent, first information and second information of the target patent are obtained, wherein the first information is used to measure the importance of the keywords of the target patent among the keywords of all the cooperative patents, and the second information is used to measure the importance of the classification number of the target patent among the classification numbers of all the cooperative patents; For each target patent, the first information and the second information of the target patent are weighted and summed to obtain the importance of the target patent.

3. The method for analyzing the relevance of technical cooperation according to claim 2, characterized in that: The first information of the target patent is obtained by: Extracting keywords from the target patent; For each region, according to the regional keyword weight of each keyword in the region, the average value of the regional keyword weight of each keyword in the target patent in the region is calculated as the regional first information of the target patent in the region; The sum of the first regional information of the target patent in two regions is used as the first information of the target patent; Among them, for each region, the regional keyword weight of the keyword in the region is positively correlated with the number of first patents in the region, and the first patents are cooperative patents with corresponding keywords.

4. The method for analyzing the relevance of technical cooperation according to claim 3, characterized in that: The regional keyword weight of the keyword in the region is obtained in the following way: Obtain keywords from each cooperative patent in the region and construct a regional keyword set; Obtaining a first number of first patents corresponding to each keyword in the regional keyword set; According to the first number of first patents corresponding to each keyword in the regional keyword set, the first number of first patents corresponding to the keyword is normalized to obtain the regional keyword weight of the keyword in the region.

5. The method for analyzing the relevance of technical cooperation according to any one of claims 2 to 4, characterized in that: The second information of the target patent is obtained by: Determine the classification number of the target patent; For each region, obtaining the classification code similarity between the classification code of the target patent and the classification codes of each cooperative patent in the region; For each region, according to the regional classification number weights of the classification numbers of the respective cooperative patents in the region, weighted sum is performed on the classification number similarities between the classification number of the target patent and the classification numbers of the respective cooperative patents in the region, so as to obtain the regional second information of the target patent in the region; The sum of the second regional information of the target patent in two regions is used as the second information of the target patent; Among them, the classification code similarity between two classification codes is positively correlated with the length of the same prefix of the two classification codes; For each region, the regional classification number weight of the classification number in the region is positively correlated with the number of second patents in the region, where the second patents are cooperative patents with the corresponding classification number.

6. The method for analyzing the relevance of technical cooperation according to claim 5, characterized in that: The regional classification number weight of the classification number in the region is obtained by: Obtain the classification codes of each cooperative patent in the region and construct a regional classification code set; Obtain a second number of second patents corresponding to each classification code in the regional classification code set; According to the second number of second patents corresponding to each classification number in the regional classification number set, the second number of second patents corresponding to the classification number is normalized to obtain the regional classification number weight of the classification number in the region.

7. The method for analyzing the relevance of technical cooperation according to claim 5, characterized in that: The classification code similarity between two classification codes is obtained by the following methods, including: Constructing a similarity calculation function, wherein the similarity calculation function is the reciprocal of an exponential function whose base is greater than 1; For any two classification numbers, the length of the difference between the two classification numbers is determined based on the length of the same prefix of the two classification numbers; Substitute the difference length as an independent variable into the similarity calculation function, and use the calculated dependent variable as the classification number similarity.

8. A device for analyzing the relevance of technical cooperation, characterized in that: include: A target patent determination module is used to determine two regions to be analyzed, obtain cooperative patents in the two regions respectively, and determine a target patent from the cooperative patents in the two regions, wherein the cooperative patent is a patent with multiple patent holders and at least one patent holder is located in the corresponding region, and the target patent includes at least one first patent holder and at least one second patent holder, wherein the first patent holder is located in one of the two regions and the second patent holder is located in the other of the two regions; An importance determination module is used to obtain the importance of each target patent. According to the importance of all target patents and the distribution of the number of cooperative patents in the two regions, the target importance is obtained. The importance is used to measure the importance of the characteristic information of the target patent in the characteristic information of all cooperative patents. The target importance is used to represent the common importance of all target patents in the two regions. A similarity determination module, for obtaining the similarity between two technical field sets according to the technical field sets of the two regions, wherein the technical field set of each region includes the technical fields of each cooperative patent in the corresponding region; The technical cooperation analysis module is used to obtain the relevance of the technical cooperation between two regions according to the importance of the target and the similarity.

9. An electronic device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images