Urban innovation mode identification method, system and device and storage medium

Abstract

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

Description

Technical Field

[0001] The present invention relates to the technical field of urban innovation assessment, and in particular to an urban innovation pattern recognition method, system, device and storage medium. Background Art

[0002] Technological innovation and progress are closely linked to the innovative potential of the modern economy and are crucial for sustainable economic development. Patent application data, as an important vehicle for encoding knowledge and technological innovation, can effectively measure innovation standards and assess regional technological dynamics. It is often used to measure technological capabilities and identify innovation patterns. Related technologies typically identify innovation patterns at a micro-technical level, determining whether patents belonging to a specific technology category are incremental or breakthrough by determining the frequency of occurrence of a patent classification standard code in patent application data. These indicators rely on single indicators such as patent citations or novelty. However, research on regional-scale innovation pattern identification and its correlation with knowledge evolution is insufficient. Summary of the Invention

[0003] The purpose of the present invention is to solve one of the technical problems existing in the prior art to at least a certain extent.

[0004] To this end, the purpose of the present invention is to provide a highly accurate urban innovation pattern recognition method, system, device and storage medium.

[0005] In order to achieve the above technical objectives, one aspect of an embodiment of the present invention provides a method for identifying urban innovation patterns, comprising the following steps: obtaining patent data of all cities and preprocessing the patent data; evaluating the knowledge changes and knowledge types of the patent data based on patent classification standard codes, and determining a new knowledge entry capability index; wherein the knowledge types include new knowledge and old knowledge; combining patent classification standard codes, and determining the knowledge reorganization type of each combination based on the two knowledge types of new knowledge and old knowledge, and then determining a knowledge reorganization capability index; and determining the innovation pattern of the target city based on the new knowledge entry capability index and the knowledge reorganization capability index. This application achieves accurate identification and evaluation of urban innovation patterns, and enhances the depth of urban innovation pattern evaluation.

[0006] In some embodiments, based on the patent classification standard code, the knowledge change and knowledge type of the patent data are evaluated to determine the new knowledge entry capability index, including:

[0007] According to the patent classification standard code of each patent, determining the share of each city based on the patent classification standard code;

[0008] Conducting comparative analysis of the shares by city to determine the comparative advantages of the target city based on each of the patent classification standard codes;

[0009] determining the knowledge type of each of the patent classification standard codes according to the comparative advantages of the cities within a continuous time window;

[0010] According to the knowledge types of all patent classification standard codes, the new knowledge entry capability index is determined.

[0011] In some embodiments, the comparative analysis of the share by city to determine the comparative advantage of the target city based on each patent classification standard code includes:

[0012] Determine the first share of the first patent classification standard code in the target city;

[0013] Determine the second share of the first patent classification standard code in all cities;

[0014] According to the first share and the second share, the comparative advantage of the target city based on the first patent classification standard code is determined.

[0015] In some embodiments, determining the knowledge type of each patent classification standard code based on the city's comparative advantage within a continuous time window includes:

[0016] If the city comparative advantage in the first time window is 0 and the city comparative advantage in the second time window is 1, the knowledge change is determined to be knowledge expansion; the time of the first time window is earlier than the time of the second time window;

[0017] If the city comparative advantage in the first time window is zero and the city comparative advantage in the second time window is not zero, the knowledge change is determined to be knowledge introduction; the city comparative advantage being zero is used to indicate that the corresponding patent classification standard code does not exist for the city in the corresponding time window;

[0018] If the comparative advantage of the city in the first time window is the same as the comparative advantage of the city in the second time window, the knowledge change is determined to be knowledge persistence;

[0019] If the city comparative advantage in the first time window is 1 and the city comparative advantage in the second time window is 0, the knowledge change is determined to be partial knowledge decay;

[0020] If the city comparative advantage in the first time window is not zero and the city comparative advantage in the second time window is zero, the knowledge change is determined to be complete knowledge withdrawal;

[0021] Determine that the knowledge type corresponding to the patent classification standard code for the knowledge change is new knowledge, i.e., the knowledge introduction and the knowledge expansion;

[0022] The knowledge type corresponding to the patent classification standard code that determines the knowledge change as knowledge continuation, partial knowledge decline and complete knowledge withdrawal is old knowledge.

[0023] In some embodiments, determining a new knowledge entry capability indicator based on the knowledge types of all patent classification standard codes includes:

[0024] Determine the third share of patent classification standard codes in which knowledge change is knowledge introduction in the target city;

[0025] Determine the fourth share of patent classification standard codes whose knowledge change is knowledge expansion in the target city;

[0026] Determining a first number of patent classification standard codes in which the knowledge changes in the target city are knowledge expansion and knowledge introduction;

[0027] A new knowledge entry capability indicator is determined based on the third share, the fourth share, and the first quantity.

[0028] In some embodiments, the patent classification standard codes are combined, and based on the two knowledge types of new knowledge and old knowledge, the knowledge reorganization type of each combination is determined, and then the knowledge reorganization capability index is determined, including:

[0029] Taking the patent classification standard code of each patent in the patent data as a node, constructing a node co-occurrence network;

[0030] Determining a knowledge reorganization type of each edge according to the knowledge type corresponding to the node of each edge in the co-occurrence network;

[0031] According to the knowledge reorganization type, a knowledge reorganization capability indicator is determined.

[0032] In some embodiments, determining the knowledge reorganization type of each edge according to the knowledge types corresponding to the two nodes of each edge in the co-occurrence network includes:

[0033] If the knowledge type corresponding to at least one node of the first edge is new knowledge, determining that the knowledge reorganization type of the first edge is reorganization creation;

[0034] If the knowledge types corresponding to the nodes of the first edge are all old knowledge and the first edge does not exist in the previous adjacent time window, determining that the knowledge reorganization type of the first edge is reorganization creation;

[0035] If the knowledge types corresponding to the nodes of the first edge are all old knowledge and the first edge exists in the previous adjacent time window, it is determined that the knowledge reorganization type of the first edge is reorganization and reuse.

[0036] On the other hand, an embodiment of the present invention provides a method system for identifying urban innovation patterns, including:

[0037] The first module is used to obtain patent data of all cities and pre-process the patent data;

[0038] The second module is used to evaluate the knowledge changes and knowledge types of the patent data based on the patent classification standard code and determine the new knowledge entry capability index; wherein the knowledge types include new knowledge and old knowledge;

[0039] The third module is used to combine the patent classification standard codes, determine the knowledge reorganization type of each combination based on the two knowledge types of new knowledge and old knowledge, and then determine the knowledge reorganization capability index;

[0040] The fourth module is used to determine the innovation model of the target city based on the new knowledge entry capability index and the knowledge reorganization capability index.

[0041] In another aspect, an embodiment of the present invention provides a method and apparatus for identifying an urban innovation pattern, comprising:

[0042] at least one processor;

[0043] at least one memory for storing at least one program;

[0044] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned urban innovation pattern recognition method.

[0045] On the other hand, an embodiment of the present invention provides a storage medium storing a program executable by a processor. When the program is executed by the processor, it is used to implement the above-mentioned urban innovation pattern recognition method.

[0046] The embodiments of the present application include at least the following beneficial effects: The method provided by the present application includes: obtaining patent data for all cities and preprocessing the patent data; evaluating the knowledge changes and knowledge types of the patent data based on patent classification standard codes, and determining a new knowledge entry capability index; wherein the knowledge types include new knowledge and old knowledge; combining patent classification standard codes, and determining the knowledge reorganization type of each combination based on the new knowledge and the old knowledge, thereby determining a knowledge reorganization capability index; and determining the innovation model of the target city based on the new knowledge entry capability index and the knowledge reorganization capability index. The present application achieves accurate identification and evaluation of urban innovation models, enhancing the depth of urban innovation model evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following introduction is made to the drawings of the embodiments of the present invention or the related technical solutions in the prior art. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative work.

[0048] Figure 1 A schematic diagram of a flow chart of an embodiment of the urban innovation pattern recognition method provided by the present invention;

[0049] Figure 2 A schematic flow chart of another embodiment of the urban innovation pattern recognition method provided by the present invention;

[0050] Figure 3 A schematic flow chart of an embodiment of a process for determining two indicators provided by the present invention;

[0051] Figure 4 A scatter diagram of the dual innovation model of multiple cities in different time windows provided by the present invention;

[0052] Figure 5 A schematic diagram of the structure of an embodiment of the urban innovation pattern recognition method system provided by the present invention;

[0053] Figure 6 This is a structural diagram of an embodiment of the urban innovation pattern recognition method and device provided by the present invention. DETAILED DESCRIPTION

[0054] The embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention and are not to be construed as limiting the present invention. The step numbers in the following embodiments are provided for ease of explanation only and do not limit the order of the steps. The order of execution of the steps in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.

[0055] Technological innovation and progress are closely linked to the innovative potential of the modern economy and are crucial for sustainable economic development. Patent application data, as an important vehicle for encoding knowledge and technological innovation, can effectively measure innovation standards and assess regional technological dynamics. It is often used to gauge technological capabilities and identify innovation patterns. However, existing approaches often identify innovation patterns at a micro-technical level, determining whether patents belonging to a specific patent classification standard code are incremental or breakthrough by determining its frequency of occurrence in patent application data. However, research on innovation patterns within a specific field remains insufficient.

[0056] Specifically, the following deficiencies are included:

[0057] There is insufficient analysis of the dynamic changes in urban innovation. Traditional research has mostly focused on the evolution of regional innovation from the perspectives of enterprise entry and exit, industrial upgrading, etc., and the perspective has mainly focused on spatial characteristics. There is insufficient analysis of the characteristics of the knowledge types contained in patents themselves and their temporal changes.

[0058] The innovation pattern recognition methods are mainly aimed at micro-innovation entities such as enterprises, and the indicators rely on single indicators such as the degree of patent citations or novelty. However, there is still insufficient research on the characteristics of innovation pattern recognition at the regional scale and its correlation with knowledge evolution.

[0059] The present invention aims to make up for the shortcomings of the existing technology and proposes a complete working plan for defining and identifying urban innovation models based on ultra-large-scale patent application data at a national scale. It proposes two indicators: new knowledge entry capability and knowledge reorganization capability. Then, it identifies the knowledge type based on the applicant's address, technology code and other information in the patent application data, measures the knowledge change process, and thus identifies the changes in urban innovation models based on different combinations of the two indicators.

[0060] The urban innovation pattern recognition method and system proposed by the present invention are described in detail below with reference to the accompanying drawings.

[0061] On the one hand, referring to Figure 1 , an embodiment of the present invention provides an urban innovation pattern recognition method. The urban innovation pattern recognition method in the embodiment of the present invention can be applied to a terminal, can be applied to a server, or can be software running in a terminal or a server. The terminal can be a tablet computer, a laptop computer, a desktop computer, etc., but is not limited to this. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The urban innovation pattern recognition method in the embodiment of the present invention mainly includes the following steps:

[0062] S100: Obtain patent data of all cities and pre-process the patent data;

[0063] S200: Based on the patent classification standard code, evaluating the knowledge change and knowledge type of the patent data to determine the new knowledge entry capability index; wherein the knowledge type includes new knowledge and old knowledge;

[0064] S300: combining the patent classification standard codes, and determining the knowledge reorganization type of each combination based on the two knowledge types of new knowledge and old knowledge, and then determining the knowledge reorganization capability index;

[0065] S400: Determine the innovation model of the target city based on the new knowledge entry capability index and the knowledge reorganization capability index.

[0066] The patent classification standard code in this application can be any technical standard code for classifying patents, for example, an IPC code. The knowledge type is a classification of knowledge based on the knowledge changes in the target city. Based on the new knowledge entry capability index and the knowledge reorganization capability index, the innovation model of the target city can be determined through table query, curve mapping, function calculation, etc., which is not specifically limited in this application.

[0067] In some embodiments, based on the patent classification standard code, the knowledge change and knowledge type of the patent data are evaluated to determine the new knowledge entry capability index, including:

[0068] According to the patent classification standard code of each patent, determining the share of each city based on the patent classification standard code;

[0069] Conducting comparative analysis of the shares by city to determine the comparative advantages of the target city based on each of the patent classification standard codes;

[0070] determining the knowledge type of each of the patent classification standard codes according to the comparative advantages of the cities within a continuous time window;

[0071] According to the knowledge types of all patent classification standard codes, the new knowledge entry capability index is determined.

[0072] Specifically, this application determines the new knowledge entry capability index of the target city based on the knowledge types of all patent classification standard codes in the target city.

[0073] In some embodiments, the comparative analysis of the share by city to determine the comparative advantage of the target city based on each patent classification standard code includes:

[0074] Determine the first share of the first patent classification standard code in the target city;

[0075] Determine the second share of the first patent classification standard code in all cities;

[0076] According to the first share and the second share, the comparative advantage of the target city based on the first patent classification standard code is determined.

[0077] The first patent classification standard code is any patent classification standard code. The first in the first patent classification standard code is only used to distinguish it from the above-mentioned patent classification standard code, and does not limit the number of patent classification standard codes and the selection of specific patent classification standard codes in the calculation process of urban comparative advantages.

[0078] In some embodiments, determining the knowledge type of each patent classification standard code based on the city's comparative advantage within a continuous time window includes:

[0079] Analyze the changes in the comparative advantages of the cities in successive time windows to determine knowledge changes;

[0080] Determine the type of knowledge based on knowledge changes.

[0081] The knowledge changes in this application can be set as knowledge persistence, knowledge exit, and knowledge entry. Specifically, knowledge exit includes partial knowledge decay and complete knowledge exit, and knowledge entry includes knowledge introduction and knowledge expansion.

[0082] In some embodiments, determining the knowledge type of each patent classification standard code based on the city's comparative advantage within a continuous time window includes:

[0083] If the city comparative advantage in the first time window is 0 and the city comparative advantage in the second time window is 1, the knowledge change is determined to be knowledge expansion; the time of the first time window is earlier than the time of the second time window;

[0084] If the city comparative advantage in the first time window is zero and the city comparative advantage in the second time window is not zero, the knowledge change is determined to be knowledge introduction; the city comparative advantage being zero is used to indicate that the corresponding patent classification standard code does not exist for the city in the corresponding time window;

[0085] If the comparative advantage of the city in the first time window is the same as the comparative advantage of the city in the second time window, the knowledge change is determined to be knowledge persistence;

[0086] If the city comparative advantage in the first time window is 1 and the city comparative advantage in the second time window is 0, the knowledge change is determined to be partial knowledge decay;

[0087] If the city comparative advantage in the first time window is not zero and the city comparative advantage in the second time window is zero, the knowledge change is determined to be complete knowledge withdrawal;

[0088] Determine that the knowledge type corresponding to the patent classification standard code for the knowledge change is new knowledge, i.e., the knowledge introduction and the knowledge expansion;

[0089] The knowledge type corresponding to the patent classification standard code that determines the knowledge change as knowledge continuation, partial knowledge decline and complete knowledge withdrawal is old knowledge.

[0090] This application makes a knowledge change judgment based on the comparative advantage of cities determined by each patent classification standard code, and then determines the knowledge type of each patent classification standard code.

[0091] In some embodiments, determining a new knowledge entry capability indicator based on the knowledge types of all patent classification standard codes includes:

[0092] Determine the third share of patent classification standard codes in which knowledge change is knowledge introduction in the target city;

[0093] Determine the fourth share of patent classification standard codes whose knowledge change is knowledge expansion in the target city;

[0094] Determining a first number of patent classification standard codes in which the knowledge changes in the target city are knowledge expansion and knowledge introduction;

[0095] A new knowledge entry capability indicator is determined based on the third share, the fourth share, and the first quantity.

[0096] In some embodiments, the patent classification standard codes are combined, and based on the two knowledge types of new knowledge and old knowledge, the knowledge reorganization type of each combination is determined, and then the knowledge reorganization capability index is determined, including:

[0097] Taking the patent classification standard code of each patent in the patent data as a node, constructing a node co-occurrence network;

[0098] Determining a knowledge reorganization type of each edge according to the knowledge types corresponding to the two nodes of each edge in the co-occurrence network;

[0099] According to the knowledge reorganization type, a knowledge reorganization capability indicator is determined.

[0100] This application constructs a co-occurrence network for each city.

[0101] In some embodiments, determining the knowledge reorganization type of each edge according to the knowledge type corresponding to the node of each edge in the co-occurrence network includes:

[0102] If the knowledge type corresponding to at least one node of the first edge is new knowledge, determining that the knowledge reorganization type of the first edge is reorganization creation;

[0103] If the knowledge types corresponding to the nodes of the first edge are all old knowledge and the first edge does not exist in the previous adjacent time window, determining that the knowledge reorganization type of the first edge is reorganization creation;

[0104] If the knowledge types corresponding to the nodes of the first edge are all old knowledge and the first edge exists in the previous adjacent time window, it is determined that the knowledge reorganization type of the first edge is reorganization and reuse.

[0105] The type of knowledge recombination in this application can be determined based on the number of reorganizations and recombinant reuses in the target city.

[0106] The method provided by this application is described in detail below with a specific embodiment:

[0107] The purpose of this invention is to provide a solution for defining and identifying urban innovation models based on patent application data. Specifically, based on large-scale patent application data at a national scale, this invention proposes a complete workflow for defining and identifying urban innovation models: S1. Patent application data preprocessing; S2. Knowledge change assessment; S3. Knowledge combination classification; S4. Urban innovation model identification (see Figure 2 shown).

[0108] The basic steps of the present invention are as follows:

[0109] S1. Patent application data preprocessing: Obtain nationwide patent application data from relevant databases, and then perform the following preprocessing operations on the data:

[0110] S11. Data Acquisition and Cleaning: After obtaining a large-scale national patent application dataset from relevant databases (Table 1), we first remove duplicates based on patent publication number. Then, we traverse fields such as patent address, classification number, and publication date, removing all data with empty records in these fields.

[0111] S12. Screening patent types: Select the required patent types based on the identified focus. In some embodiments, to identify innovation models, innovation assessment is performed based on invention patents. Therefore, invention patents are retained through screening in this step.

[0112] S13. Determine the patent location: Determine the city information of all invention patents selected in the previous step based on the address of the patent applicant and keep a record;

[0113] S14. Patent technology code type extraction: Technology codes can be used to identify different technical capabilities, measure technical complexity, and provide an empirical basis for technological change research. According to different patent classification standards, each patent is assigned a technology code representing a different technology category. These codes can reflect the technical characteristics of the underlying knowledge base they embody. According to the characteristics of the evaluation area, the corresponding patent technology code is selected. For example, in some countries / regions, the International Patent Classification (IPC) standard is widely used. The IPC classification system decomposes the technology code of each patent into five levels: section, class, subclass, main group, and subgroup. The 4-digit IPC code (4-digit IPC Codes) includes section, class, and subclass. According to the latest IPC classification standard, it includes 8 sections, including A, B,...H. It is generally believed that the 4-digit IPC code is sufficient to fully express the technical or knowledge characteristics of a patent. Therefore, the present invention uses 4-digit IPC codes to represent the technical category of knowledge elements. By extracting and deleting duplicate 4-digit IPC codes, each patent can be classified into one or more 4-digit IPC codes;

[0114] S15. Time Window Division: National-scale patent application data generally spans a long timeframe, and the number of patent applications filed in different cities varies significantly over the same timeframe. Some small cities experience minimal change in patent applications over two or three consecutive years, which can affect the measurement of subsequent knowledge change. Therefore, this paper proposes dividing the data into five-year intervals, forming multiple time windows, each covering five consecutive years of patent application information.

[0115]

[0116]

[0117] Table 1

[0118] S2. Knowledge change assessment: Evaluate the knowledge types and change characteristics in the pre-processed patent application data, and measure the new knowledge entry capability index.

[0119] S21. Determine IPC shares: For patents with only one type of IPC code, the IPC share is allocated as 1. For patents with multiple types of IPC codes, the IPC share needs to be allocated proportionally. For example, if a patent has IPC codes A01B, A01B, A01C, and H01B, the IPC share of the patent is allocated 1 / 2 to A01B, 1 / 4 to A01C, and 1 / 4 to H01B.

[0120] S22. Count IPC shares by city: Based on the share of different types of IPC in each patent calculated in the previous step, summarize them by city to form a data set of different IPC shares corresponding to each city. For example, refer to

[0121] As shown in Table 2.

[0122] City A01B A01C A01D A01F *** H10K H10N A 80.235 181.572 92.564 16.533 *** 0 0 B 8.433 30.101 19.034 4.683 *** 0 0 *** *** *** *** *** *** *** ***

[0123] Table 2

[0124] S23. Calculate the city's comparative advantage (RCA): RCA is also known as the location quotient. The calculation method in this invention is to divide the share of a certain IPC in a city by the total share of that IPC in all cities. The specific formula is:

[0125]

[0126] Where r represents the city, p represents the IPC type, and F p,r Represents the number of corresponding IPC types of type p in city r. Convert the RCA result to binary, with values ​​greater than 1 recorded as 1 and values ​​less than 1 as 0. Note that in order to accurately identify knowledge changes in subsequent steps, IPC types with a corresponding share of 0 calculated in the previous step are not included in the RCA calculation and their RCA values ​​are directly recorded as "None", that is, the city's comparative advantage in this application is "None".

[0127] S24. Identify knowledge changes and knowledge types: By comparing the changes in RCA between two consecutive time windows (from t-1 to t), identify knowledge changes and knowledge types (new knowledge and old knowledge) (Table 3), specifically:

[0128] S241. Identify knowledge changes: By comparing the RCA changes of different types of IPC codes in a city within two consecutive time windows, we can identify changes in knowledge to varying degrees, such as entry, persistence, or exit. It should be noted that in two different time windows, there may be a situation where a city does not have a certain type of IPC. To facilitate comparison, the IPCs are first unified, and the RCA values ​​corresponding to the non-existent IPCs are recorded as None (including IPC types with a corresponding share of 0). Then, the RCAs of the two consecutive time windows are compared. The identification results include the following three major types:

[0129] (1) Knowledge entry: emphasizes the use of new knowledge to promote local innovation and development. This new knowledge may be developed on the basis of existing local knowledge, or it may be new knowledge that already exists elsewhere but does not exist locally and is directly introduced. Therefore, knowledge entry includes two types: partial expansion of existing knowledge and introduction of new knowledge. Specifically, from t-1 to t, if the RCA corresponding to the city changes from 0 to 1, the corresponding knowledge type is identified as the expansion of existing knowledge, recorded as Expansion (i.e., knowledge expansion of this application); if RCA changes from None to 0 or 1, it is identified as the introduction of new external knowledge, recorded as Emergence (i.e., knowledge introduction of this application);

[0130] (2) Knowledge persistence: reflects the continuation and accumulation of local existing knowledge resources, with little change or unchanged degree. Specifically, from t-1 to t, if the change of RCA is 0 to 0 or 1 to 1, it means that its comparative advantage has not changed significantly in two consecutive periods, which is considered as the persistence of existing knowledge and recorded as Incumbent (i.e., the knowledge persistence of this application);

[0131] (3) Knowledge Exit: This includes two types: partial decay of knowledge and complete exit of knowledge. If RCA changes from 1 to 0 from t-1 to t, it is considered as partial decay of knowledge and is recorded as Decline (i.e., partial decay of knowledge in this application); if it changes from 0 or 1 to None, it is considered as complete exit of knowledge and is recorded as Extinction (i.e., complete exit of knowledge in this application);

[0132] S242. Identify knowledge types: Knowledge types include existing local knowledge and newly introduced or added knowledge. The specific identification rules are as follows:

[0133] (1) Old knowledge: The knowledge retention and knowledge exit identified in S231 are considered old knowledge;

[0134] New knowledge: The knowledge entry portion identified in S231 is considered new knowledge.

[0135]

[0136] Table 3

[0137] S25. Measuring the ability to enter new knowledge: The ability to enter new knowledge represents the level of introduction, transformation and application of new knowledge in different cities. It includes both the creation and production of unprecedented types of knowledge and the expansion and innovation of existing knowledge fields. Taking into account that megacities with rich knowledge bases have a larger total amount of knowledge than cities with scarce knowledge resources, when measuring the ability to enter new knowledge, we cannot simply seek the direct ratio of new knowledge to existing knowledge, but need to comprehensively consider the new knowledge expanded on the basis of the original knowledge and the new knowledge directly introduced from the outside. In summary, the present invention proposes a measurement index for the ability to enter new knowledge, and defines it as the ratio of the sum of the shares of IPCs recorded as Emergence and Expansion in the same city (IPC Share, IS) to the number of IPC types recorded as Emergence and Expansion (the first number), respectively. The specific formula is:

[0138]

[0139] In the formula, rKE represents the new knowledge entry capacity of a city; a represents the IPC code recorded as Emergence in the city; b represents the IPC code recorded as Expansion; IS a and IS b Represents the share of IPC recorded as Emergency and Expansion (third share and fourth share) respectively; n represents the total number of IPC types recorded as Emergency and Expansion in the calculated city. Taking City A in the time window of 2016-2020 as an example, the specific calculation steps are as follows:

[0140] In S251.S22, the share of each category of IPC in each city was calculated. In S24, the specific knowledge change to which each IPC belongs was identified. On this basis, the total share of IPCs with knowledge changes of Emergence and Expansion in each city was first summarized and counted, which were recorded as Σ a∈Emergence IS a and Σ b∈Expansion IS b Taking City A as an example, the results are Σ a∈Emergence IS a =98.607,Σ b∈Expansion IS b =7102.499;

[0141] S252. Continue to count the total number of IPCs recorded as Emergency and Expansion in each city, denoted as n. Taking City A as an example, there are 11 categories of IPCs recorded as Emergency and 35 categories of IPCs recorded as Expansion, so n = 11 + 35 = 46;

[0142] S253. Calculate the new knowledge entry capability for each city, denoted as rNKE. Taking City A as an example, rNKE = (98.607 + 7102.499) / 46 = 156.546.

[0143] S3. Knowledge combination classification: Based on the new and old knowledge types identified in S2, identify the knowledge combination types according to different combinations of the two and measure the knowledge recombination ability index;

[0144] S31. Constructing a city IPC co-occurrence network: The patent "IPC co-occurrence" describes the different classification numbers that appear simultaneously in the same patent application data. For example, each patent application data corresponds to one or more patent classification numbers, namely IPCs. When a patent application data has two or more IPCs, it is determined that these IPCs can be connected to form edges, and the IPCs themselves constitute nodes, together forming a technology co-occurrence network. For each city, the IPC co-occurrence relationship in all patent application data in the corresponding city is counted to construct a city IPC co-occurrence network;

[0145] S32. Identify the types of knowledge recombination: including recombination creation and recombination reuse ( Figure 3 ), the specific identification rules are:

[0146] S321. Determine the knowledge type of the IPC node corresponding to each edge: For the city IPC co-occurrence network constructed in the previous step, based on the knowledge type assigned to each IPC in S2, determine whether the knowledge type of the two IPC nodes corresponding to each edge in the network is new knowledge or old knowledge. If any node is new knowledge, the knowledge reorganization type corresponding to the edge is identified as recombinant creation;

[0147] S322. Determine whether the edge is repeated relative to the previous time window: If both IPC nodes are old knowledge, it is necessary to further determine whether the corresponding edge exists in the adjacent previous time window. If so, it proves that the edge formed by the two IPC nodes is repeated and should be considered as knowledge reorganization and reuse. Otherwise, it is considered as knowledge reorganization and creation.

[0148] S33. Measuring knowledge recombination capability: Regional knowledge recombination capability reflects the ability to recombine different types of knowledge within the knowledge space. The stronger the recombination capability of a city, the more likely it is to generate innovation based on the combination of new knowledge and existing knowledge bases, and the higher the utilization rate of new knowledge. Compared with recombination and reuse, knowledge recombination creation is more likely to generate new knowledge and technology, and is more conducive to the generation of breakthrough innovations. However, since recombination and reuse continue to cooperate between old knowledge with a deep foundation, in order to fully tap the innovation potential, it is necessary to screen and combine the original knowledge elements. Therefore, it is also an indispensable type of knowledge combination for regional breakthrough innovations, but its scope is more limited than recombination creation. In summary, the present invention proposes a knowledge recombination capability index, and defines it as the weighted sum of the number of technology co-occurrences of recombination creation and the number of technology co-occurrences of recombination and reuse in the same city. The specific formula is:

[0149] rKC=α×New Combinations r,t +β×Repeated Combinations r,t

[0150] (r∈R,t={t1,...,t n})

[0151] In the formula, New Combinations r,t Repeated Combinations represents the number of new knowledge combinations that appear in city r in the tth time window; r,t represents the number of repeated knowledge combinations that occur in city r during the tth time window; α and β represent the weights of recombination creation and recombination reuse, respectively, and can be adjusted based on actual needs. For example, α = 3 / 4 and β = 1 / 4 can be set. Similarly, taking City A for the 2016-2020 time window as an example, in the constructed IPC co-occurrence network for City A, 16,711 edges were identified as recombination creation and 318,935 edges were identified as recombination reuse. Therefore, its knowledge recombination capacity is rKC = 3 / 4 × 16,711 + 1 / 4 × 318,935 = 92,267.

[0152] S4. Identification of Urban Innovation Models: Based on different combinations of the two indicators of new knowledge access capability and knowledge reorganization capability, we identify four types of urban innovation models (Table 4).

[0153] (1) Innovation generation: Cities at this stage have low levels of knowledge combination and new knowledge entry capabilities, lack motivation for innovation activities, and stagnate in overall innovation levels. Such cities may face problems such as lack of resources, insufficient policy support, or a poor innovation environment.

[0154] (2) Imitative innovation: This type of innovation mainly achieves creative imitation by introducing and applying existing innovative achievements from other places. This type of innovation is characterized by strong new knowledge entry capabilities but weak knowledge reorganization capabilities. Such cities are often in the technological catching-up stage and focus on absorbing and imitating external advanced technologies.

[0155] (3) Incremental innovation: This reflects that cities mainly rely on the recombination of existing knowledge, while the introduction of new knowledge is relatively rare. Innovation is mainly achieved through the improvement and optimization of existing technologies and knowledge. Such cities usually have a stable innovation environment and the innovation process is relatively gradual.

[0156] (4) Breakthrough innovation: It shows high activity in knowledge reorganization and the introduction of new knowledge. The key lies in creativity. It requires breaking the original connection between knowledge elements and generating new creative ideas by finding new knowledge combinations. The innovation process is often accompanied by high risks and uncertainties, but once new technologies are successfully introduced or technological breakthroughs are achieved, it will generate higher returns on investment than incremental innovation.

[0157] It should be noted that in order to eliminate extreme values ​​and extreme data skewness as much as possible, it is necessary to standardize the two indicators rNKE and rKC before combining them. The specific method is to take the logarithm and normalize them to the same unit interval, and uniformly map the corresponding values ​​to between 0 and 1, so as to facilitate comparison on the same scale. Figure 4 As shown, the innovation model of a city is evaluated using the method provided in this application, and the evaluation results of multiple cities are compared.

[0158]

[0159] Table 4

[0160] This application combines the theory of comparative advantage to analyze the patent classification numbers (i.e., IPC) of large-scale urban patent application data, thereby accurately identifying and evaluating urban knowledge types and knowledge changes; based on the knowledge base and knowledge combination theory, this application designs two major indicators, knowledge entry capability and knowledge reorganization capability, to identify urban dual innovation models.

[0161] In the identification of urban dual innovation models, most existing research is based on micro-innovation entities such as enterprises, and relies on single indicators such as patent citations or novelty. However, there is still insufficient research on the identification of innovation models at the regional scale and the correlation characteristics between them and knowledge evolution. Therefore, this solution is innovative and scientific in terms of identification methods and content. In combination with large-scale patent application data, this invention proposes a complete workflow for accurately identifying and evaluating urban knowledge types and knowledge changes, as well as identifying dual innovation models at the urban scale, thereby scientifically analyzing the long-term dynamic changes in urban knowledge and innovation models.

[0162] This application accurately identifies the knowledge types of cities and the changing patterns of knowledge entry, exit and survival by setting the comparative advantage change rules of a certain IPC in different cities in different time windows; this application proposes a new innovation pattern identification method by integrating the two major driving force indicators of urban innovation, new knowledge entry and knowledge reorganization, and effectively identifies the changes in innovation patterns at the urban scale.

[0163] The method provided in the embodiment of this application includes: obtaining patent data for all cities and preprocessing the patent data; evaluating the knowledge changes and knowledge types of the patent data based on patent classification standard codes, and determining a new knowledge entry capability index; wherein the knowledge types include new knowledge and old knowledge; combining the patent classification standard codes, and based on the two knowledge types of new knowledge and old knowledge, determining the knowledge reorganization type of each combination, and then determining a knowledge reorganization capability index; and determining the innovation model of the target city based on the new knowledge entry capability index and the knowledge reorganization capability index. This application achieves the precise identification and evaluation of urban innovation models, and enhances the depth of urban innovation model evaluation.

[0164] On the other hand, refer to the attached Figure 5 A method system for identifying urban innovation patterns according to an embodiment of the present invention is described. The system specifically includes:

[0165] The first module 510 is used to obtain patent data of all cities and pre-process the patent data;

[0166] The second module 520 is configured to evaluate the knowledge changes and knowledge types of the patent data based on the patent classification standard code, and determine the new knowledge entry capability index; wherein the knowledge types include new knowledge and old knowledge;

[0167] The third module 530 is used to combine the patent classification standard codes, determine the knowledge recombination type of each combination based on the two knowledge types of new knowledge and old knowledge, and then determine the knowledge recombination capability index;

[0168] The fourth module 540 is used to determine the innovation model of the target city based on the new knowledge entry capability index and the knowledge reorganization capability index.

[0169] It can be seen that the contents of the above method embodiments are all applicable to the present system embodiments. The functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0170] Reference Figure 6 , an embodiment of the present invention provides a method and apparatus for identifying an urban innovation pattern, comprising:

[0171] at least one processor 610;

[0172] at least one memory 620, for storing at least one program;

[0173] When the at least one program is executed by the at least one processor 610, the at least one processor 610 implements the urban innovation pattern recognition method.

[0174] Similarly, the contents of the above method embodiments are applicable to the present device embodiments. The functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0175] An embodiment of the present invention further provides a computer-readable storage medium storing a program executable by a processor. The program executable by the processor is used to execute the above-mentioned urban innovation pattern recognition method when executed by the processor.

[0176] Similarly, the contents of the above method embodiments are applicable to the present storage medium embodiment. The functions specifically implemented by the present storage medium embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0177] In some optional embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided in an exemplary manner for the purpose of providing a more comprehensive understanding of the technology. The disclosed method is not limited to the operation and logic flow presented herein. Optional embodiments are contemplated in which the order of the various operations is changed and the sub-operations described as a part of a larger operation are performed independently.

[0178] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It is also understood that a detailed discussion of the actual implementation of each module is not necessary for understanding the present invention. More specifically, given the properties, functions, and internal relationships of the various functional modules in the devices disclosed herein, the actual implementation of the module will be understood within the ordinary skill of an engineer. Therefore, a person skilled in the art will be able to implement the present invention set forth in the claims using ordinary skill without undue experimentation. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0179] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several programs for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0180] The logic and / or steps represented in a flowchart or otherwise described herein, for example, may be considered as an ordered list of executable programs for implementing the logical functions, and may be embodied in any computer-readable medium for use by, or in conjunction with, a program execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can retrieve and execute a program from a program execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" may be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, a program execution system, apparatus, or device.

[0181] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0182] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable program execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0183] In the above description of this specification, reference to the terms "one embodiment / example," "another embodiment / example," or "certain embodiments / examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0184] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the claims and their equivalents.

[0185] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the embodiments. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. A method for identifying urban innovation patterns, characterized in that: The method comprises the following steps: Obtaining patent data of all cities and preprocessing the patent data; Based on the patent classification standard code, the knowledge change and knowledge type of the patent data are evaluated to determine the new knowledge entry capability index; wherein the knowledge type includes new knowledge and old knowledge; Combining the patent classification standard codes, and determining the knowledge reorganization type of each combination based on the two knowledge types of new knowledge and old knowledge, and then determining the knowledge reorganization capability index; The innovation model of the target city is determined based on the new knowledge entry capability index and the knowledge reorganization capability index.

2. The urban innovation pattern recognition method according to claim 1, characterized in that: Based on the patent classification standard code, the knowledge changes and knowledge types of the patent data are evaluated to determine the new knowledge entry capability indicators, including: According to the patent classification standard code of each patent, determining the share of each city based on the patent classification standard code; Conducting comparative analysis of the shares by city to determine the comparative advantages of the target city based on each of the patent classification standard codes; determining the knowledge type of each of the patent classification standard codes according to the comparative advantages of the cities within a continuous time window; According to the knowledge types of all patent classification standard codes, the new knowledge entry capability index is determined.

3. The urban innovation pattern recognition method according to claim 2, characterized in that: Conduct a comparative analysis of the share of the patent classification standard code by city to determine the comparative advantage of the target city based on each patent classification standard code, including: Determine the first share of the first patent classification standard code in the target city; Determine the second share of the first patent classification standard code in all cities; According to the first share and the second share, the comparative advantage of the target city based on the first patent classification standard code is determined.

4. The urban innovation pattern recognition method according to claim 2, characterized in that: According to the comparative advantages of the cities within a continuous time window, the knowledge type of each patent classification standard code is determined, including: If the city comparative advantage in the first time window is 0 and the city comparative advantage in the second time window is 1, the knowledge change is determined to be knowledge expansion; the time of the first time window is earlier than the time of the second time window; If the city comparative advantage in the first time window is zero and the city comparative advantage in the second time window is not zero, the knowledge change is determined to be knowledge introduction; the city comparative advantage being zero is used to indicate that the corresponding patent classification standard code does not exist for the city in the corresponding time window; If the comparative advantage of the city in the first time window is the same as the comparative advantage of the city in the second time window, the knowledge change is determined to be knowledge persistence; If the city comparative advantage in the first time window is 1 and the city comparative advantage in the second time window is 0, the knowledge change is determined to be partial knowledge decay; If the city comparative advantage in the first time window is not zero and the city comparative advantage in the second time window is zero, the knowledge change is determined to be complete knowledge withdrawal; Determine that the knowledge type corresponding to the patent classification standard code for the knowledge change is new knowledge, i.e., the knowledge introduction and the knowledge expansion; The knowledge type corresponding to the patent classification standard code that determines the knowledge change as knowledge continuation, partial knowledge decline and complete knowledge withdrawal is old knowledge.

5. The urban innovation pattern recognition method according to claim 4, characterized in that: Based on the knowledge types of all patent classification standard codes, determine the new knowledge entry capability indicators, including: Determine the third share of patent classification standard codes in which knowledge change is knowledge introduction in the target city; Determine the fourth share of patent classification standard codes whose knowledge change is knowledge expansion in the target city; Determining a first number of patent classification standard codes in which the knowledge changes in the target city are knowledge expansion and knowledge introduction; A new knowledge entry capability indicator is determined based on the third share, the fourth share, and the first quantity.

6. The urban innovation pattern recognition method according to claim 1, characterized in that: The patent classification standard codes are combined, and based on the two knowledge types of new knowledge and old knowledge, the knowledge reorganization type of each combination is determined, and then the knowledge reorganization capability index is determined, including: Taking the patent classification standard code of each patent in the patent data as a node, constructing a node co-occurrence network; Determining a knowledge reorganization type of each edge according to the knowledge types corresponding to the two nodes of each edge in the co-occurrence network; According to the knowledge reorganization type, a knowledge reorganization capability indicator is determined.

7. The urban innovation pattern recognition method according to claim 6, characterized in that: According to the knowledge type corresponding to the node of each edge in the co-occurrence network, the knowledge reorganization type of each edge is determined, including: If the knowledge type corresponding to at least one node of the first edge is new knowledge, determining that the knowledge reorganization type of the first edge is reorganization creation; If the knowledge types corresponding to the nodes of the first edge are all old knowledge and the first edge does not exist in the previous adjacent time window, determining that the knowledge reorganization type of the first edge is reorganization creation; If the knowledge types corresponding to the nodes of the first edge are all old knowledge and the first edge exists in the previous adjacent time window, it is determined that the knowledge reorganization type of the first edge is reorganization and reuse.

8. A city innovation pattern recognition method system, characterized by: include: The first module is used to obtain patent data of all cities and pre-process the patent data; The second module is used to evaluate the knowledge changes and knowledge types of the patent data based on the patent classification standard code and determine the new knowledge entry capability index; wherein the knowledge types include new knowledge and old knowledge; The third module is used to combine the patent classification standard codes, determine the knowledge reorganization type of each combination based on the two knowledge types of new knowledge and old knowledge, and then determine the knowledge reorganization capability index; The fourth module is used to determine the innovation model of the target city based on the new knowledge entry capability index and the knowledge reorganization capability index.

9. A method and device for identifying urban innovation patterns, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the urban innovation pattern recognition method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a program executable by a processor, characterized in that: The processor-executable program is used to implement the urban innovation pattern recognition method according to any one of claims 1 to 7 when executed by the processor.

Images