A method and device for detecting application of a sub-technology in a target industry

Abstract

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

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of patent analysis, in particular, relates to a method and device for detecting application of a sub-technology in a target industry. BACKGROUND

[0002] Patents are an important indicator of high-tech and knowledge-intensive industrial technology innovation activities. Patent information mining has special significance for exploring and guiding industrial innovation. If only through expert seminars, brainstorming and other expert qualitative selection methods to measure the role of a technology in the development of industrial technology, but such methods are highly subjective, easily affected by the operation process, and lack objectivity in the technical evaluation of a certain technology.

[0003] Therefore, the present application is proposed. SUMMARY

[0004] The technical problem to be solved by the present application is to overcome the shortcomings of the prior art, and to provide a method and device for detecting the application of a sub-technology in a target industry, to solve the problem that the prior art cannot evaluate a technology from multiple angles, and the information selected according to the sub-technology is inaccurate and the technical evaluation is not objective.

[0005] To solve the above technical problems, the basic idea of the technical solution of the present application is:

[0006] In a first aspect, the present application provides a method, comprising:

[0007] obtaining a target patent data set of a target industry;

[0008] labeling each patent data in the target patent data set using a pre-set patent classification system to obtain a corresponding patent technology field for each patent data; the patent technology field comprises at least one sub-technology;

[0009] clustering each patent technology field to obtain a plurality of industrial sub-fields;

[0010] For each industrial sub-field, calculate a comprehensive application score of each sub-technology in the target industrial technology.

[0011] Optionally, the target patent data set of the target industry is obtained, comprising:

[0012] obtaining a patent data set of the target industry according to each technical keyword in the industrial technology decomposition table of the target industry;

[0013] filtering first patent data of the current technology life cycle stage from the patent data set, and taking the first patent data as the target patent data set.

[0014] Optionally, the preset patent classification system is a technical list with a hierarchical structure generated according to technical terms extracted from scientific and technical texts.

[0015] Optionally, the method further comprises:

[0016] The preset patent classification system is any one of the following patent classification systems: the International Patent Classification system, the Joint Patent Classification system, the Japanese Patent Classification system, and the Derwent Patent Classification system.

[0017] Optionally, the calculation of the comprehensive application score of each sub-technology in the target industrial technology for each industrial sub-field comprises:

[0018] For each industrial sub-field, the score of each sub-technology in the industrial sub-field under each evaluation index is calculated.

[0019] For each sub-technology, the comprehensive application score of the sub-technology is obtained according to the sum of the scores of the sub-technology under each evaluation index.

[0020] Optionally, the evaluation indexes include the usage frequency of the sub-technology, the universality of the sub-technology, the connection degree of the sub-technology with other technologies, and the probability of the sub-technology being a core technology. The calculation of the score of each sub-technology in the industrial sub-field under each evaluation index comprises:

[0021] For each sub-technology, the frequency of the sub-technology in the industrial sub-field is normalized to obtain the score of the sub-technology under the usage frequency.

[0022] For each sub-technology, the total number of other sub-technologies that appear simultaneously with the sub-technology in the industrial sub-field is normalized to obtain the score of the sub-technology under the universality.

[0023] For each sub-technology, the connection degree of the sub-technology with other sub-technologies in the industrial sub-field is normalized to obtain the score of the sub-technology under the universality.

[0024] For each sub-technology, the number of paths passing through the sub-technology in the industrial sub-field is normalized to obtain the probability of the sub-technology being a core technology.

[0025] Optionally, the calculation of the comprehensive application score of each sub-technology in the target industrial technology for each industrial sub-field comprises:

[0026] For each sub-technology, the comprehensive application score is obtained according to the sum of the product of the score of the sub-technology under each evaluation index and the calculation weight of the evaluation index.

[0027] In a second aspect, the present application provides a device for detecting application of sub-technologies in a target industry, comprising:

[0028] an acquisition module configured to acquire a target patent data set of the target industry;

[0029] a classification module configured to label a patent technology field of each patent data in the target patent data set by using a preset patent classification system, to obtain a corresponding patent technology field of each patent data; the patent technology field comprises at least one sub-technology;

[0030] a clustering module configured to cluster each patent technology field to obtain a plurality of industrial sub-fields;

[0031] a calculation module configured to calculate a comprehensive application score of the sub-technology in the target industry technology for each patent technology field.

[0032] Optionally, the acquisition module comprises:

[0033] an acquisition unit configured to acquire the patent data set of the target industry according to each technology keyword in an industrial technology decomposition table of the target industry;

[0034] a screening unit configured to screen first patent data of a current technology life cycle stage from the patent data set, and take the first patent data as the target patent data set.

[0035] Optionally, the calculation module comprises:

[0036] a first calculation unit configured to calculate a score of each sub-technology in each evaluation index for each industrial sub-field;

[0037] a second calculation unit configured to calculate a comprehensive application score of each sub-technology according to a sum of scores of the sub-technology in each evaluation index.

[0038] In a third aspect, the present application further provides a computer device, comprising a processor, a memory and a bus, the memory stores machine readable instructions executable by the processor, when the computer device is running, the processor and the memory communicate through the bus, and the processor executes the machine readable instructions to realize steps of the method for detecting application of sub-technologies in a target industry according to any one of the first aspect.

[0039] In a fourth aspect, the present application further provides a computer storage medium, the computer storage medium stores computer executable instructions, when the computer executable instructions are executed by a processor, steps of the method for detecting application of sub-technologies in a target industry according to any one of the first aspect are realized.

[0040] The present application has the following beneficial effects relative to the prior art:

[0041] The present application evaluates and measures the keyness of the sub-technology in the industry by using the frequency of use of the sub-technology, the universality of the sub-technology, the degree of contact of the sub-technology with other technologies, and the probability of the sub-technology becoming a core technology, thereby avoiding the subjectivity and lack of objectivity of expert evaluation.

[0042] The specific embodiments of the present application will be further described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0043] The accompanying drawings, which are part of the present application, serve to provide a further understanding of the present application, and the schematic embodiments of the present application and the descriptions thereof serve to explain the present application, but do not constitute an improper limitation on the present application. Obviously, the accompanying drawings described below are only some embodiments, and other drawings can be obtained by those skilled in the art without creative labor on the basis of the drawings. In the drawings:

[0044] Figure 1 is a flowchart of a method for detecting the application of a sub-technology in a target industry provided by the present application;

[0045] Figure 2 is a structural schematic diagram of a device for detecting the application of a sub-technology in a target industry provided by the present application;

[0046] Figure 3 is a structural schematic diagram of a computer device provided by the present application.

[0047] It should be noted that these drawings and written descriptions are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments will be described clearly and completely below with reference to the drawings in the embodiments of the present application. The following embodiments are used to illustrate the present application, but are not used to limit the scope of the present application.

[0049] In the description of the present application, it should be noted that the terms "upper", "lower", "front", "back", "left", "right", "vertical", "inner", "outer" and the like indicate the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application.

[0050] In the description of the present application, it should be noted that unless otherwise explicitly specified and limited, the terms "mounting", "connecting", "connecting" should be understood broadly, for example, it can be fixedly connected, or it can be detachably connected, or integrally connected; it can be mechanically connected, or it can be electrically connected; it can be directly connected, or it can be indirectly connected through an intermediate medium. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0051] As Figure 1 shown, a method for detecting the application of a sub-technology in a target industry provided by the present application comprises:

[0052] S101, obtaining a target patent data set of a target industry;

[0053] S102, labeling each patent data in the target patent data set using a predetermined patent classification system to obtain a corresponding patent technology field for each patent data; the patent technology field comprises at least one sub-technology;

[0054] S103, clustering each patent technology field to obtain a plurality of industrial sub-fields;

[0055] S104, for each industrial sub-field, calculating a comprehensive application score of each sub-technology in the target industry technology.

[0056] In the above step S101, the target industry is the technology industry to be detected. The target patent data set is a patent data set used to describe the technologies of the target industry.

[0057] Specifically, obtaining a target patent data set of a target industry, step S101 comprises the following steps:

[0058] Step 1011, obtaining a patent data set of the target industry according to each technical keyword in the industrial technology decomposition table of the target industry;

[0059] Step 1012, filtering first patent data of the current technology life cycle stage from the patent data set, and taking the first patent data as the target patent data set.

[0060] In the step 1011, the industry technology decomposition table is used to divide the target industry into units according to the vertical upstream and downstream relationship of the industry chain of the target industry and the horizontal parallel industry of the target industry, such as setting a first technology branch, and decomposing the first technology branch into a second technology branch, and so on, to generate the industry technology decomposition table.

[0061] Specifically, according to each technology keyword in the industry technology decomposition table of the target industry, the patent text related to the technology keyword is searched, and finally the patent data set of the target industry is obtained.

[0062] For example, if the target industry is the ICT industry, i.e., the information and communication technology industry, the first technology in the industry technology decomposition table is a generalization, such as communication network, Internet of Things, cloud computing, etc. Each first technology branch has multiple second technologies. For example, the communication network includes network equipment manufacturing, terminal manufacturing, and application software development. The patent text data is searched according to the first technology keywords such as communication network and cloud computing, and the patent text data is searched according to the second technology keywords such as terminal manufacturing and application software development, and the patent data set of the target industry is generated.

[0063] For example, if the target industry is the medical and health industry, the first technology branch in the industry technology decomposition table includes the pharmaceutical manufacturing industry and the special equipment manufacturing industry. Each first technology branch has multiple second technology branches. For example, the pharmaceutical manufacturing industry includes chemical drug raw material manufacturing, chemical drug preparation manufacturing, and biological drug product manufacturing. Each second technology branch has multiple third technologies. For example, the biological drug product manufacturing includes biological drug manufacturing, genetic engineering drug and vaccine manufacturing, etc. The patent text data is searched according to the IPC number corresponding to the national economic industry classification code of the third technology, such as A61K38, A61K41, A61K45, A61K49, A61K9, etc. The patent data set of the target industry is generated.

[0064] In the step 1012, the technology development stage of the target industry is divided into different development stages such as the budding stage, the growth stage, the mature stage, and the decline stage based on the S-curve according to the cumulative number of patent applications in the present application. According to the cumulative number of patent applications, it is determined which development stage the target industry is in. The patent data obtained in the step 1011 is distributed in multiple development stages. In order to reduce the calculation and statistics, the first patent text of the current technology life cycle stage is selected as the target patent data set of the target industry according to the patent application time from the patent data set.

[0065] Wherein the S curve is mainly divided into symmetric Logistic model curve and asymmetric Gompertz model curve, the Logistic model curve is proposed by Verhulst, and the formula is as follows, Wherein, y represents the cumulative number of patent applications, ɑ represents the slope of the S curve, that is, the growth rate of the S curve, β represents the time point of the turning point (Midpoint) in the growth curve, l is the saturation level of growth, that is, the saturation point (Saturation), and T is the time, the present application uses the Loglet Lab software to fit the Logistic curve of the target industry technology, and carries out life cycle analysis.

[0066] In the above step S102, a preset patent classification system is used to classify and mark each patent data in the target patent data set of the target industry, which represents the technical field, technical features and other contents involved in each patent data.

[0067] Wherein the preset patent classification system can be a technology noun extracted from a science and technology text in a man-machine combined manner, and a hierarchical technology list generated according to the extracted technology noun, wherein the hierarchical technology list is a technology list with a superior-inferior relationship, for example, at least containing a patent technology field in the superior position and a sub-technology contained in the patent technology field in the inferior position. Further, each patent data in the target patent data set is labeled according to the patent technology field in the superior position and the sub-technology contained in the patent technology field in the technology list.

[0068] Secondly, the preset patent classification system can also directly use the existing patent classification system, which includes but is not limited to: International Patent Classification (IPC), Cooperative Patent Classification (CPC), Japanese Patent Classification (FI / FTerm), Derwent Patent Classification (DWPI manual code).

[0069] For example, the preset patent classification system takes the Derwent patent classification system as an example, the Derwent patent classification system is a technology classification code labeled by technical experts, has a hierarchical tree structure, and can be used for hierarchical management of patent technology concepts.

[0070] If the target industry is the ICT industry, i.e., the target patent data set is the information and communication technology industry, according to the Derwent patent classification system, each patent document data in the above target patent data set is labeled, and each patent document data is labeled at least one patent technology field and at least one sub-technology contained in the patent technology field. The final labeling result shows that it involves 277 patent technology fields, including: T01 digital computer patent technology field, which involves T01-C01 disk, drive, card reader, cache, etc. recording carrier, T01-J10 image processing data processing system, T01-N03 Internet software, etc. 228 sub-technologies; T04 computer peripheral device patent technology field, which involves T04-D07 character, pattern, biological feature recognition technology, T04-K03 smart card, memory stick, etc. 114 sub-technologies; U11 semiconductor material and process patent technology field, which involves U11-C05 multilayer semiconductor device preparation method, U11-F01 semiconductor material, device, packaging, etc. 98 sub-technologies.

[0071] In the above step 103, the labeled patent technology field is divided into communities based on the clustering method of graph theory, and finally a plurality of industry sub-fields are clustered.

[0072] Specifically, based on the labeling result of each patent technology in the target patent technology set in the above step 102, i.e., according to the patent technology field labeled by each patent data, a patent technology field co-occurrence network is constructed, and a plurality of industry sub-fields are clustered according to the community division algorithm. The patent technology field co-occurrence network model is G=(V,E), G represents the set of mutual co-occurrence relationships of patent technology fields in this period, V represents the set of patent technology fields in this period, V={v1,v2,v3,...}, v i ∈V, E represents the set of connections between patent technology fields in this period, E={e1,e2,e3,...}, e i ∈E. The adjacency matrix of the network is A, A=(a ij ) N*N , which is a symmetric matrix. If v i and v j are directly connected, it means that v i and v j have a co-occurrence relationship, then e ij =1 and a ij =w ij , otherwise e ij =0 and a ij =0, where w ij represents v i and v jThe weight of the connected edges is the co-occurrence frequency.

[0073] In the co-occurrence network of patent technology fields, some technology fields are densely connected, while the connections with other patent technology fields are relatively sparse. These closely connected technology fields combine to form a whole, which is regarded as an industry subfield. According to the patent technology classification system, industry technology is divided into several industry subfields, and each industry subfield contains several sub-technologies.

[0074] Modularity, as a criterion for identifying online communities, is calculated using the following formula: in, Indicates v i Point intensity, G represents the sum of the weights of all edges. i Indicates v i The community ID, if v i With v j If they belong to the same association, then δ(g) i ,g j ) = 1, otherwise δ(g) i ,g j ) = 0.

[0075] For example, taking the target patent data set of the ICT industry, namely the information and communication technology industry, as an example, a patent field co-occurrence network is constructed based on the patent field technology marked by each patent data and the sub-technology contained in each patent field technology. According to the community partitioning algorithm, 8 communities are obtained, which are 8 industry sub-fields, namely: (aviation, navigation) remote control signal industry sub-field, integrated circuit materials and devices industry sub-field, electronic medical device industry sub-field, etc.

[0076] In step 104 above, for each industry sub-sector, based on graph theory node analysis, the comprehensive application score of each sub-technology in the target industry technology is calculated.

[0077] In step S104 above, the comprehensive application of sub-technology in the target industry is not a technology for a specific enterprise, but a technology that serves one or more industries. When a technology can be widely applied in a sub-field of an industry, or appears together with other sub-technology, it can be judged that the sub-technology is an important technology in the industrial technology innovation chain. The comprehensive application score is used to represent the frequency of the sub-technology in the target industry and its relationship with other sub-technology, reflecting the comprehensive application of the sub-technology.

[0078] Specifically, for each industry sub-field, based on the results of marking the patent technology set of the target patent technology, that is, according to the sub-technology contained in the patent technology field marked by each patent data in the industry sub-field, a sub-technology co-occurrence network is constructed, and the network model is G=(V, E), G represents the set of mutual co-occurrence relationships of sub-technologies in the industry sub-field in this period, V represents the set of sub-technologies in the industry sub-field in this period, V={v1, v2, v3,...}, v i ∈V, E represents the set of connections between sub-technologies in the industry sub-field in this period, E={e1, e2, e3,...}, e i ∈E. The adjacency matrix of the network is A, A=(a ij ) N*N , which is a symmetric matrix. If v i and v j are directly connected, it represents that there is a co-occurrence relationship between v i and v j , then e ij =1 and a ij =w ij , otherwise e ij =0 and a ij =0, where w ij represents the weight of the edge between v i and v j , that is, the co-occurrence frequency.

[0079] Among them, the characteristics of the knowledge network include: the degree and degree distribution of the node, the point weight and unit weight of the node, the betweenness of the node and its distribution characteristics, the distance distribution and the average distance. The degree calculation formula is: The point weight calculation formula is: The unit weight calculation formula is: U i =S i / k i , and the distance calculation formula between any two nodes is: The betweenness calculation formula is: Where n st (i) represents the number of paths passing through v i , and g st represents the number of shortest paths connecting v s and v t .

[0080] In order to reduce the size of the network, a threshold a zero can be set, and the threshold a zero represents the minimum value of the edge weight in the network. When the co-occurrence frequency of v i and v j is less than a zero , v i and v jEdge a connected between v ij = 0; threshold value e can be set zero , represents the minimum frequency of the occurrence of a node, when the occurrence frequency of v i is less than e zero , v i cannot be a node of network G; threshold value v max can be set, representing the number of nodes contained in the network, ranked in descending order of the occurrence frequency of v i , and the first v max nodes are taken to construct the network; threshold value e min can be set, representing the minimum number of edges connected to a node, when the number of edges connected to v i is less than e min , v i cannot be a node of network G.

[0081] For each sub-technology, the frequency of occurrence of the sub-technology in the target industry, the correlation with other sub-technologies, etc. are calculated to obtain a comprehensive application score.

[0082] For a more detailed understanding, for each industry sub-field, the comprehensive application score of each sub-technology in the target industry is calculated, step S104, including:

[0083] Step 1041, for each industry sub-field, the score of each sub-technology in the industry sub-field under each evaluation index is calculated;

[0084] Step 1042, for each sub-technology, the sum of the scores of the sub-technology under each evaluation index is obtained to obtain the comprehensive application score of the sub-technology.

[0085] In the above step 1041, the evaluation index is used to evaluate the actual application of a sub-technology from different dimensions. The evaluation index can be the number of occurrences of a sub-technology, which is used to reflect the importance of the sub-technology; the evaluation index can be the number of direct contacts of the sub-technology with other sub-technologies, which is used to judge the universality of the sub-technology; the evaluation index can be the degree of association of the sub-technology with other sub-technologies, which is used to reflect the influence or action of the sub-technology on other sub-technologies; the evaluation index can be the probability of the sub-technology becoming a core technology, which is used to judge the role or influence of the sub-technology in the knowledge network.

[0086] In the above step 1041, for each industry sub-field, the comprehensive application score of each sub-technology under different dimensions is calculated based on the co-occurrence network of the sub-technologies.

[0087] Further, in order to understand in more detail, the evaluation index includes the frequency of use of the sub-technology, the general degree of the sub-technology, the connection degree of the sub-technology and other technologies, and the probability that the sub-technology is a core technology. Based on the node features of the sub-technology co-occurrence network, the score of each sub-technology under each evaluation index is calculated, step 1041, including:

[0088] Step 10411, for each sub-technology, the frequency of the sub-technology appearing in the industry sub-field is normalized to obtain the score of the sub-technology under the frequency of use;

[0089] Step 10412, for each sub-technology, the total number of other sub-technologies appearing simultaneously with the sub-technology in the industry sub-field is normalized to obtain the score of the sub-technology under the general degree;

[0090] Step 10413, for each sub-technology, the connection degree of the sub-technology with other sub-technologies in the industry sub-field is normalized to obtain the score of the sub-technology under the general degree;

[0091] Step 10414, for each sub-technology, the number of paths passing through the sub-technology in the industry sub-field is normalized to obtain the probability that the sub-technology is a core technology.

[0092] In the above step 10411, for each sub-technology, the frequency of the sub-technology appearing in the sub-technology co-occurrence network is counted.

[0093] For example, taking sub-technology v i as an example, the frequency of the sub-technology appearing in a certain sub-field P of the target industry is counted v i is normalized to obtain the score of v i under the frequency of use

[0094] In the above step 10412, for each sub-technology, the number of other sub-technologies connected to the sub-technology in the sub-technology co-occurrence network is counted.

[0095] For example, taking sub-technology v i as an example, the total number of other sub-technologies appearing simultaneously with the sub-technology in a certain sub-field P of the target industry is counted where V represents the set of sub-technologies of the industry sub-field P at the present stage, v i , v j represent each sub-technology in the sub-technology co-occurrence network, e ij represents the connection between v i and v j , and

[0096] In the above step 10413, for each sub-technology, the degree of association of the sub-technology with other sub-technologies in the sub-technology co-occurrence network is counted.

[0097] For example, for sub-technology v i , the degree of association of the sub-technology with other sub-technologies in the target industry sub-field P is counted Wherein Wherein, S i represents the point intensity of v i , that is, the sum of edge weights associated with v i , k i represents the degree of v i , that is, the sum of edges associated with v i , and the normalized processing is performed on

[0098] In the above step 10414, for each sub-technology, the probability of the sub-technology becoming a core technology in the sub-technology co-occurrence network is counted.

[0099] For example, for sub-technology v i , the probability of the sub-technology becoming a core technology in the target industry sub-field P is counted Wherein Wherein, represents the number of paths passing through v i , and g st represents the number of shortest paths connecting v s and v t , and the normalized processing is performed on

[0100] Wherein, in the normalization processing step, taking the frequency of occurrence in the industry sub-field P as an example, assuming that there are four nodes v i , v j , v m , v n in the sub-technology co-occurrence network, and the occurrence frequencies are Determine the maximum value x max and the minimum value x mix , assuming that the maximum value is and the minimum value is The calculation formula of the normalization processing is Then

[0101] ​​​In step 1042, for each sub-technology, the scores of the sub-technology under each evaluation index are added to obtain the comprehensive application score of the sub-technology, and specifically, the comprehensive application score of the sub-technology is obtained by adding the scores of the sub-technology under each evaluation index.

[0102] In step 10421, for each industrial sub-field, the calculation weight of each evaluation index is set.

[0103] The calculation weight of the use frequency in the industrial sub-field P is set as The calculation weight of the generalization degree in the industrial sub-field P is set as The calculation weight of the association degree in the industrial sub-field P is set as The calculation weight of the core technology in the industrial sub-field P is set as The calculation weight of the use frequency in the industrial sub-field B is set as The calculation weight of the generalization degree in the industrial sub-field B is set as The calculation weight of the association degree in the industrial sub-field B is set as The calculation weight of the core technology in the industrial sub-field B is set as The calculation weight of the core technology in the industrial sub-field B is set as

[0104] In step 10422, for each sub-technology, the comprehensive application score is obtained according to the sum of the products of the scores of the sub-technology under each evaluation index and the calculation weight of the evaluation index.

[0105] Specifically, the comprehensive application score of the sub-technology is equal to the sum of the products of the scores of the sub-technology under each evaluation index in each industrial sub-field and the calculation weight, and the formula is represented as:

[0106]

[0107] In the present application, when obtaining the target patent data set of the target industry, according to the technical development of the target industry, the target patent data set of the current technical life cycle is first selected from all patent data related to the target industry, which can cover the current situation of industrial technology innovation and avoid irrelevant data from participating in the calculation. From the two aspects of patent literature content and industrial technology development law, the rationality and reliability of the selection of target patent data are ensured. Then, the patent data in the target patent data set is labeled using the preset patent classification system, and the patent technology field co-occurrence network and the sub-technology co-occurrence network are constructed according to the labeling results. The potential association between the industrial sub-fields and the sub-technologies is revealed through the structural characteristics of the above two co-occurrence networks, which more comprehensively, objectively and accurately reflects the application status of the sub-technologies.

[0108] The application measures the application of the sub-technologies in the target industry from four dimensions, i.e., the use frequency of the sub-technologies, the generality of the sub-technologies, the degree of association of the sub-technologies with other sub-technologies, and the probability of the sub-technologies becoming core technologies, so that the evaluation is more accurate and comprehensive.

[0109] As shown in Figure 2 The application further provides a device for detecting the application of the sub-technologies in the target industry, which comprises an acquisition module 201, a classification module 202, a clustering module 203, and a calculation module 204, and specifically comprises:

[0110] The acquisition module 201 is configured to acquire a target patent data set of the target industry.

[0111] The classification module 202 is configured to label each patent data in the target patent data set by using a preset patent classification system to obtain a corresponding patent technology field of each patent data; and the patent technology field comprises at least one sub-technology.

[0112] The clustering module 203 is configured to cluster the various patent technology fields to obtain a plurality of industrial sub-fields.

[0113] The calculation module 204 is configured to calculate, for each patent technology field, a comprehensive application score of the sub-technologies in the target industrial technology.

[0114] Optionally, the acquisition module comprises:

[0115] The first acquisition unit is configured to acquire a patent data set of the target industry according to each technical keyword in an industrial technology decomposition table of the target industry.

[0116] The screening unit is configured to screen first patent data in a current technology life cycle stage from the patent data set, and take the first patent data as the target patent data set.

[0117] Optionally, the calculation module comprises:

[0118] The first calculation unit is configured to calculate, for each industrial sub-field, a score of each sub-technology in the industrial sub-field under each evaluation index.

[0119] The second calculation unit is configured to calculate, for each sub-technology, a comprehensive application score of the sub-technology according to the sum of the scores of the sub-technology under each evaluation index.

[0120] Optionally, the evaluation index of the first calculation unit comprises the use frequency of the sub-technology, the generality of the sub-technology, the degree of association of the sub-technology with other technologies, and the probability of the sub-technology being a core technology.

[0121] The first processing unit is used to normalize the frequency of occurrence of each sub-technology in the sub-field of the industry for each sub-technology, and obtain a score for the sub-technology based on its frequency of use.

[0122] The second processing unit is used to normalize the total number of other sub-technologies that appear simultaneously with the sub-technology in the industry sub-field for each sub-technology, and obtain the score of the sub-technology in terms of generality.

[0123] The third processing unit is used to normalize the degree of connection between each sub-technology and other sub-technology in the industry sub-field for each sub-technology, and obtain the score of the sub-technology in terms of generality.

[0124] The fourth processing unit is used to normalize the number of paths that pass through the shortest path in the sub-field of the industry for each sub-technology, so as to obtain the probability that the sub-technology is the core technology.

[0125] Optionally, the second computing unit includes:

[0126] The fifth processing unit is used to obtain the comprehensive application score for each sub-technology by summing the products of the sub-technology's score under each evaluation index and the calculated weight of that evaluation index.

[0127] Corresponding to Figure 1 The present invention also provides a computer device 800, such as a detection sub-technology in the target industry. Figure 3 As shown, the device includes a memory 801, a processor 802, and a computer program stored in the memory 801 and executable on the processor 802, wherein the processor 802 executes the computer program to implement the steps of a method for detecting subtechnology in a target industry.

[0128] Specifically, the aforementioned memory 801 and processor 802 can be general-purpose memory and processor, without specific limitations. When the processor 802 runs the computer program stored in the memory 801, it can execute the aforementioned method for detecting the application of sub-technology in the target industry. This solves the problems in the prior art where it is impossible to evaluate a technology from multiple perspectives, and where the selection information based on the sub-technology is inaccurate and the technology evaluation is not objective enough. First, a target patent data set of the target industry is obtained; each patent data in the target patent data set is labeled using a preset patent classification system to obtain the patent technology field corresponding to each patent data; the patent technology field includes at least one sub-technology; the various patent technology fields are clustered to obtain multiple industry sub-fields; for each industry sub-field, the comprehensive application score of each sub-technology in the target industry technology is calculated. This invention evaluates and measures the criticality of a sub-technology in the industry application through four dimensions: the frequency of use of a sub-technology, the universality of the sub-technology, the degree of connection between the sub-technology and other technologies, and the probability of the sub-technology becoming a core technology, avoiding the problems of subjectivity and lack of objectivity in expert evaluation.

[0129] Corresponding to Figure 1 The present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the method for applying the detection sub-technology in the target industry.

[0130] Specifically, the storage medium can be a general-purpose storage medium, such as a portable disk or hard drive. When the computer program on this storage medium is run, it can execute the aforementioned method for detecting the application of sub-technology in the target industry. This solves the problems of existing technologies, such as the inability to evaluate a technology from multiple perspectives, inaccurate selection information based on the sub-technology, and insufficient objectivity in technology evaluation. First, a target patent data set for the target industry is obtained; each patent data in the target patent data set is labeled using a preset patent classification system to obtain the patent technology field corresponding to each patent data; the patent technology field includes at least one sub-technology; the various patent technology fields are clustered to obtain multiple industry sub-fields; for each industry sub-field, the comprehensive application score of each sub-technology in the target industry technology is calculated. This invention evaluates and measures the criticality of a sub-technology in industry application through four dimensions: the frequency of use of a sub-technology, the universality of the sub-technology, the degree of connection between the sub-technology and other technologies, and the probability of the sub-technology becoming a core technology. This avoids the problems of subjectivity and insufficient objectivity in expert evaluation.

[0131] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-described technical content to create equivalent embodiments without departing from the scope of the present invention. The implementation schemes in the above embodiments can also be further combined or replaced. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A method of detecting application of a sub-technology in a target industry, characterized by, The method comprises the following steps: obtaining a target patent data set of a target industry; labeling each patent data in the target patent data set by using a preset patent classification system to obtain a corresponding patent technology field of each patent data; the patent technology field comprises at least one sub-technology; clustering the patent technology fields to obtain a plurality of industry sub-fields; for each industry sub-field, calculating a comprehensive application score of each sub-technology in the target industry technology, comprising: for each industry sub-field, calculating the score of each sub-technology in the industry sub-field under each evaluation index, for each sub-technology, obtaining the comprehensive application score of the sub-technology according to the sum of the scores of the sub-technology under each evaluation index; the evaluation index comprises the use frequency of the sub-technology, the universality of the sub-technology, the connection degree of the sub-technology with other technologies, and the probability of the sub-technology being a core technology; wherein, for each industry sub-field, the score of each sub-technology in the industry sub-field under each evaluation index comprises: for each sub-technology, normalizing the frequency of the sub-technology in the industry sub-field to obtain the score of the sub-technology under the use frequency; for each sub-technology, normalizing the total number of other sub-technologies that appear simultaneously with the sub-technology in the industry sub-field to obtain the score of the sub-technology under the universality; for each sub-technology, normalizing the connection degree of the sub-technology with other sub-technologies in the industry sub-field to obtain the score of the sub-technology under the universality; for each sub-technology, normalizing the number of paths passing through the sub-technology in the industry sub-field to obtain the probability of the sub-technology being a core technology.

2. The method of claim 1, wherein the detection sub-technology is applied to the target industry. The method comprises the following steps: obtaining a target patent data set of a target industry; obtaining a target patent data set of a target industry from the patent data set according to the technical keywords in the industry technology decomposition table of the target industry; 3. The method of claim 1, wherein the method is applied to the target industry. filtering out first patent data of the current technology life cycle stage from the patent data set, and taking the first patent data as the target patent data set. The method comprises the following steps:

4. The method of claim 1, wherein the detection sub-technology is applied to the target industry. The preset patent classification system is a technology list with hierarchical structure generated according to technical terms extracted from scientific and technological texts. The method further comprises the following steps:

5. The method of claim 1, wherein the detection sub-technology is applied to the target industry. The preset patent classification system is any one of the following patent classification systems: International Patent Classification System, Joint Patent Classification System, Japanese Patent Classification System, and Derwent Patent Classification System. The method comprises the following steps: for each sub-technology, obtaining the comprehensive application score according to the product of the score of the sub-technology under each evaluation index and the calculation weight of the evaluation index.

6. A device for detecting the application of a sub-technology in a target industry by using the method of any one of claims 1-5, comprising: an obtaining module for obtaining a target patent data set of a target industry; A classification module is configured to label each patent data in the target patent data set by using a preset patent classification system to obtain a corresponding patent technology field of each patent data, wherein the patent technology field comprises at least one sub-technology. A clustering module is configured to cluster each patent technology field to obtain a plurality of industrial sub-fields. A calculation module is configured to calculate a comprehensive application score of each sub-technology in the target industrial technology for each industrial sub-field.

7. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the steps of the method of any one of claims 1-5.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that The computer program is run by the processor to execute the steps of the method of any one of claims 1-5.

Images