Patent value determination method and device, electronic equipment and storage medium

Abstract

The invention provides a patent value determination method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a patent to be evaluated; determining the quoted frequency of the to-be-evaluated patent based on the Ziff's law, and determining the patent citation score of the to-be-evaluated patent according to the quoted frequency through a PageRank algorithm; determining a technical field score, a legal status score, a historical transformation score, a patentee score and a score increase item score of the to-be-evaluated patent; and obtaining a target value score of the patent to be evaluated according to the patent citation score, the technical field score, the legal status score, the historical transformation score, the patentee score and the score increase item score. Therefore, according to the patent citation score, the technical field score, the legal status score, the historical transformation score, the patentee score and the score increase item score, the obtained target value score of the patent to be evaluated is more comprehensive and accurate.

Description

Background Art

[0002] The evaluation of patent value is a complex and multi - dimensional process, involving considerations in multiple aspects such as law, technology, and economy. However, most current patent value evaluations are relatively subjective, relying on the empirical analysis of experts for artificial classification, and there are problems with inaccurate patent value evaluations.

[0003] In view of this, how to more accurately evaluate the value of patents has become a technical problem to be urgently solved. Summary of the Invention

[0004] In view of this, the purpose of the present disclosure is to propose a method, device, electronic device, and storage medium for determining patent value to solve or partially solve the above - mentioned technical problems.

[0005] Based on the above purpose, the first aspect of the present disclosure proposes a method for determining patent value, and the method includes:

[0006] Obtain the patent to be evaluated;

[0007] Determine the citation frequency of the patent to be evaluated based on Zipf's law, and determine the patent citation score of the patent to be evaluated according to the citation frequency through the PageRank algorithm;

[0008] Determine the technical field score, legal status score, historical transformation score, patentee score, and bonus item score of the patent to be evaluated;

[0009] Obtain the target value score of the patent to be evaluated according to the patent citation score, the technical field score, the legal status score, the historical transformation score, the patentee score, and the bonus item score.

[0010] Based on the same inventive concept, the second aspect of the present disclosure proposes a device for determining patent value, including:

[0011] An acquisition module, configured to obtain the patent to be evaluated;

[0012] A patent citation score determination module, configured to determine the citation frequency of the patent to be evaluated based on Zipf's law, and determine the patent citation score of the patent to be evaluated according to the citation frequency through the PageRank algorithm;

[0013] Multiple score determination modules, configured to determine the technical field score, legal status score, historical transformation score, patentee score, and bonus item score of the patent to be evaluated;

[0014] A target value scoring determination module, configured to obtain the target value score of the patent to be evaluated according to the patent citation score, the technical field score, the legal status score, the historical transformation score, the patentee score, and the score for additional items.

[0015] Based on the same inventive concept, a third aspect of the present disclosure provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable by the processor. When the processor executes the computer program, the above-described method is implemented.

[0016] Based on the same inventive concept, a fourth aspect of the present disclosure provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the above-described method.

[0017] As can be seen from the above, the present disclosure provides a method, apparatus, electronic device, and storage medium for determining patent value. Obtain a patent to be evaluated. Determine the citation frequency of the patent to be evaluated based on Zipf's law, and determine the patent citation score of the patent to be evaluated according to the citation frequency through the PageRank algorithm. Determine the technical field score, legal status score, historical transformation score, patentee score, and score for additional items of the patent to be evaluated. Obtain the target value score of the patent to be evaluated according to the patent citation score, technical field score, legal status score, historical transformation score, patentee score, and score for additional items. In this way, the patent citation score of the patent to be evaluated can be accurately determined through Zipf's law and the PageRank algorithm, and by comprehensively considering the patent citation score, technical field score, legal status score, historical transformation score, patentee score, and score for additional items of the patent to be evaluated, the obtained target value score of the patent to be evaluated is more comprehensive and accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] To more clearly illustrate the technical solutions in the present disclosure or related technologies, the following will briefly introduce the drawings required for use in the embodiments or related technology descriptions. Obviously, the drawings in the following description are only embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1 It is a flowchart of the method for determining patent value according to an embodiment of the present disclosure;

[0020] Figure 2 It is a schematic structural diagram of the SG Score model for patent value evaluation according to an embodiment of the present disclosure;

[0021] Figure 3Schematic structural diagram of the patent value determination device according to an embodiment of the present disclosure;

[0022] Figure 4 Schematic structural diagram of an electronic device according to an embodiment of the present disclosure. Detailed implementation manners

[0023] To make the objectives, technical solutions, and advantages of the present disclosure more clear and understandable, the present disclosure will be further described in detail below with reference to specific embodiments and the accompanying drawings.

[0024] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present disclosure should have the ordinary meanings understood by those of ordinary skill in the art to which the present disclosure belongs. The "first", "second", and similar terms used in the embodiments of the present disclosure do not denote any order, quantity, or importance, but are only used to distinguish different components. The terms such as "include" or "comprise" mean that the elements or objects appearing before this term cover the elements or objects listed after this term and their equivalents, without excluding other elements or objects. The terms such as "connect" or "couple" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left", and "right" are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0025] As described above, how to more accurately evaluate the value of a patent has become an important research issue.

[0026] Based on the above description, as Figure 1 shown, the patent value determination method proposed in this embodiment includes:

[0027] Step 101: Obtain the patent to be evaluated.

[0028] Specifically, when implemented, the patent to be evaluated is the patent that needs to be evaluated for value.

[0029] Step 102: Determine the citation frequency of the patent to be evaluated based on Zipf's law, and determine the patent citation score of the patent to be evaluated according to the citation frequency through the PageRank algorithm.

[0030] Specifically, when implemented, Zipf's law describes that in a natural language corpus, the frequency of occurrence of a word is inversely proportional to the rank of the word in the frequency table. Specifically, the word with the highest frequency appears approximately twice as often as the word with the second highest frequency, and the word in the third place is one-fourth of the second place, and so on.

[0031] The PageRank algorithm is an algorithm used to evaluate the importance of web pages. The PageRank algorithm calculates the importance of each web page by analyzing the link relationships between web pages, thereby optimizing the search results of search engines. The basic idea of the PageRank algorithm is based on two important assumptions: the quantity assumption and the quality assumption. Among them, the quantity assumption is that the more in-links a web page receives from other web pages, the more important the web page is. The quality assumption is that the quality of the links pointing to a web page is different, and high-quality web pages will transfer more weight to other web pages through links. Therefore, the web pages pointed to by high-quality web pages are more important.

[0032] Step 103, determine the technical field score, legal status score, historical transformation score, patentee score, and additional score item score of the patent to be evaluated.

[0033] In specific implementation, in addition to scoring the patent citation dimension of the patent to be evaluated to obtain the patent citation score, it is also necessary to score multiple dimensions of the patent to be evaluated. Among them, the multiple dimensions include at least one of the following: technical field dimension, legal status dimension, historical transformation dimension, patentee dimension, and additional score item dimension.

[0034] Specifically, score the technical field dimension of the patent to be evaluated to obtain the technical field score. Score the legal status dimension of the patent to be evaluated to obtain the legal status score. Score the historical transformation dimension of the patent to be evaluated to obtain the historical transformation score. Score the patentee dimension of the patent to be evaluated to obtain the patentee score. Score the additional score item dimension of the patent to be evaluated to obtain the additional score item score.

[0035] Step 104, obtain the target value score of the patent to be evaluated according to the patent citation score, the technical field score, the legal status score, the historical transformation score, the patentee score, and the additional score item score.

[0036] In specific implementation, sum up the patent citation score, technical field score, legal status score, historical transformation score, patentee score, and additional score item score to obtain the target value score of the patent to be evaluated. In this way, the patent value of the patent to be evaluated can be quickly and accurately judged according to the target value score.

[0037] Perform visualization processing on the patent citation score, technical field score, legal status score, historical transformation score, patentee score, and additional score item score to obtain the target value score of the patent to be evaluated. In this way, the patent value of the patent to be evaluated in each dimension can be clearly and intuitively judged according to the target value score.

[0038] Through the above embodiments, the patent to be evaluated is obtained. The citation frequency of the patent to be evaluated is determined based on Zipf's law, and the patent citation score of the patent to be evaluated is determined according to the citation frequency through the PageRank algorithm. The technical field score, legal status score, historical transformation score, patentee score, and score for additional points of the patent to be evaluated are determined. According to the patent citation score, technical field score, legal status score, historical transformation score, patentee score, and score for additional points, the target value score of the patent to be evaluated is obtained. In this way, through Zipf's law and the PageRank algorithm, the patent citation score of the patent to be evaluated can be accurately determined, and by comprehensively considering the patent citation score, technical field score, legal status score, historical transformation score, patentee score, and score for additional points of the patent to be evaluated, the obtained target value score of the patent to be evaluated is more comprehensive and accurate.

[0039] The hierarchical classification management of patents is the basis of patent operation and poses great challenges. The reason is that the hierarchical management of patents involves specialized tasks such as the analysis, evaluation, and assessment of patent value. It is particularly important to establish a refined patent value analysis model. On this basis, the SGScore model for patent hierarchical classification management is proposed.

[0040] Figure 2 It is a schematic structural diagram of the SG Score model for patent value evaluation according to an embodiment of the present disclosure. As Figure 2 shown, the SGScore model for multi-dimensional patent value evaluation realizes "4 + 1 + N" comprehensive evaluation from four major dimensions of patent attributes (technical field, legal status, historical transformation, patent citation) + enterprise attribute dimension (advantage of the patentee) + multiple patent score-increasing rules, so as to achieve refined patent value analysis and hierarchical classification management.

[0041] In some embodiments, step 102 includes:

[0042] Step 1021, obtaining a plurality of cited patents that cite the patent to be evaluated.

[0043] Step 1022, based on Zipf's law, determining the citation frequency of the patent to be evaluated according to the plurality of cited patents,

[0044]

[0045] wherein, is the citation frequency of the patent to be evaluated, C is a citation constant, and r α is the sorting order of the plurality of cited patents.

[0046] Step 1023, determining a citation coefficient according to the citation frequency,

[0047]

[0048] Among them, σ zipf is the citation coefficient, is the sharing coefficient of the i-th cited patent, and σ share = 10%σ, where σ is the directed graph of the patent pool constructed based on the citation relationship between the patent to be evaluated and the multiple cited patents.

[0049] Step 1024, through the PageRank algorithm, determine the patent citation score of the patent to be evaluated according to the citation coefficient,

[0050]

[0051] Among them, SG reference (p i ) is the patent citation score of the patent to be evaluated p i , d is the damping factor, N is the number of high-value patents in the directed graph of the patent pool, p i is the patent to be evaluated, M(p i ) is the set of the multiple cited patents, p j is the j-th cited patent, SG referencd (p j ) is the patent citation score of the j-th cited patent, and L(p j ) is the number of multiple cited patents cited by the patent to be evaluated p i .

[0052] Specifically, when implemented, the patent citation score set by the patent citation dimension is represented by SG reference . Considering two main aspects, that is, the patent cited by high-value patents also has a relatively high value; the patent cited by many patents generally has a relatively high value. In addition, a frequency-importance evaluation algorithm - Zipf's law is added to this part of the design. The effectiveness of Zipf's law was first verified in the field of natural language processing. Natural language can also be regarded as a generalized time series with obvious context connections. In a natural corpus, the frequency of occurrence of a word is inversely proportional to its descending order ranking in the frequency table, described as follows: (where r α is the word frequency sorting order, is the word frequency)

[0053]

[0054] Among them, C is a constant, and it is verified by the law of large numbers that α≈0.993.

[0055] The patent pool of the patent to be evaluated and multiple cited patents is regarded as a huge directed graph, where each patent is a node, and patent citation is a one-way edge pointing from one node to some other nodes. Among these nodes, low-value patents are considered "dormant nodes", and high-value patents after evaluation are considered "activated nodes". An activated node can share 10% of its comprehensive score with the patents it cites according to the Hough model. Referring to the PageRank algorithm and the Zipf's law based on the importance of natural language word frequency statistics, for a node:

[0056]

[0057] In the formula, SG reference (p j ) represents the citation situation score of the i-th patent, (p j ) is the number of patents cited by p i , p i represents the patent to be evaluated, M(p i ) is the set of patents citing p i , L(p i ) is the number of patents cited by p i , N is the number of high-value patents in the patent pool, and d is the damping factor, mainly to solve rank leakage and rank sink (generally, d = 0.85 is taken). It can be proved that the final SG reference patent citation value model can converge, that is, a stable and normal SG reference value can be obtained. Among them,

[0058] Through the above solution, based on Zipf's law, the citation frequency of the patent to be evaluated can be accurately determined according to multiple cited patents, and the citation coefficient can be accurately determined according to the citation frequency of the patent to be evaluated. Through the PageRank algorithm, the patent citation score of the patent to be evaluated can be accurately determined according to the citation coefficient.

[0059] In some embodiments, the determination process of the technical field score includes:

[0060] Step 1031, obtain the technical field label of the patent to be evaluated.

[0061] Step 1032, determine the first-level label in the preset first-level field from the technical field label, and determine the first-level technical coefficient according to the total number of preset first-level fields and the number of first-level labels.

[0062]

[0063] Among them, α is the first-level technical coefficient, the total number of preset first-level fields is 10, and n is the number of first-level tags.

[0064] Step 1033: Determine the first-level tag weight according to the first-level tag and the preset first-level field.

[0065]

[0066] Among them, A i is the weight of the i-th first-level tag. is the quantity of the i-th first-level tag. is the quantity of the j-th preset first-level field.

[0067] Step 1034: Determine the second-level tags in the preset second-level fields from the technical field tags, and determine the second-level technical coefficient according to the total number of preset second-level fields and the number of second-level tags.

[0068]

[0069] Among them, β is the second-level technical coefficient, the total number of preset second-level fields is 50, and m is the number of second-level tags.

[0070] Step 1035: Determine the second-level tag weight according to the second-level tag and the preset second-level field.

[0071]

[0072] Among them, B i is the weight of the i-th second-level tag. is the quantity of the i-th second-level tag. is the quantity of the j-th preset second-level field.

[0073] Step 1036: Determine the core value tags in the preset core value fields from the technical field tags, and determine the core value technical coefficient according to the total number of preset core value fields and the number of core value tags.

[0074]

[0075] Among them, θ is the core value technical coefficient, the total number of preset core value fields is 14, and t is the number of core value tags.

[0076] Step 1037: Determine the core value tag weight according to the core value tag and the preset core value field.

[0077]

[0078] Among them, C iis the weight of the i-th core value label, is the quantity of the i-th core value label, is the quantity of the j-th preset core value field.

[0079] Step 1038: Determine the technical field score of the patent to be evaluated according to the first-level technical coefficient, the first-level label weight, the second-level technical coefficient, the second-level label weight, the core value technical coefficient, and the core value label weight.

[0080]

[0081] where SG technology is the technical field score, and M is the total number of first-level label weights.

[0082] In specific implementation, from the perspective of technical field classification, the technical field of a patent reflects the most core innovation direction and application value orientation of the patent, and the technical field classification is also refined with the times.

[0083] The patent to be evaluated is scored according to different technical field dimensions. The full score of the technical field dimension is 10 points. If the patent to be evaluated exceeds the full score, the technical field score of the patent to be evaluated is 1SG point; the patent to be evaluated is analyzed through a clustering algorithm and keywords are extracted. The preliminary label setting is two-level:

[0084] Among the 10 first-level labels, if the patent corresponds to n first-level labels, the first-level technical coefficient α of the patent is set as:

[0085]

[0086] Among the 50 second-level labels, if the patent corresponds to m second-level labels, the second-level technical coefficient β of the patent is set as:

[0087]

[0088] At the same time, each first-level and second-level label divides different internal weights according to the frequency-Zipf law, that is, the comprehensive weight A of the technical advancement and superiority of the i-th first-level field i is linearly allocated according to the word frequency of the patent during clustering, where N represents the total number of patents attached to this label:

[0089]

[0090] In addition, based on expert experience, key business layouts, and existing technical advantages, evaluations of innovation, reliability, irreplaceability, and technical maturity in the technical classification field are carried out. 14 core high-value technical fields are also divided. If the patent to be evaluated hits t of the core high-value labels, the high-value technical coefficient θ is set as:

[0091]

[0092] In summary, the calculation method of the technical field score SG of the patent to be evaluated is as follows: technology is:

[0093]

[0094] Through the above solution, the first-level labels in the preset first-level fields are determined from the technical field labels, and the first-level technical coefficients can be accurately determined according to the total number of preset first-level fields and the number of first-level labels. The second-level labels in the preset second-level fields are determined from the technical field labels, and the second-level technical coefficients can be accurately determined according to the total number of preset second-level fields and the number of second-level labels. The core value labels in the preset core value fields are determined from the technical field labels, and the core value technical coefficients can be accurately determined according to the total number of preset core value fields and the number of core value labels. In this way, the technical field score of the patent to be evaluated can be comprehensively and accurately judged based on the three technical fields of the preset first-level fields, preset second-level fields, and preset core value fields.

[0095] In some embodiments, the process of determining the legal status score includes:

[0096] Step 103A, obtaining the current legal status of the patent to be evaluated.

[0097] Step 103B, in response to determining that the current legal status is an authorized and valid status, obtaining the legal status score of the patent to be evaluated by determining whether the patent to be evaluated has undergone a litigation act and whether it has won.

[0098] Step 103C, comparing the legal status score with a preset score threshold.

[0099] Step 103D, in response to determining that the legal status score is greater than or equal to the preset score threshold, determining that the legal status score of the patent to be evaluated is the first value.

[0100] Step 103E, in response to determining that the legal status score is less than the preset score threshold, determining that the legal status score of the patent to be evaluated is the second value.

[0101] In specific implementation, analyze the current legal status of the patent to be evaluated. If the patent to be evaluated is in an authorized and valid state, score it according to different other legal evaluation dimensions, with a full score of 10 points. If the patent to be evaluated exceeds the full score, the legal status score of the patent to be evaluated is 1 SG point; if the patent to be evaluated is in a litigation state, the existing SG points are temporarily invalid; if the patent to be evaluated wins the lawsuit, the legal status points of the patent to be evaluated +1, and the existing SG points are valid; if the patent to be evaluated is in a state of patent invalidation, losing a patent lawsuit, or the patent has expired, the legal status score of the evaluated patent is 0 SG points. If the patent to be evaluated is in an authorized and valid state, determine the legal status points of the patent to be evaluated according to the legal dimension score standard in Table 1 below.

[0102] Table 1 Legal Status Dimension Score Standard

[0103] Evaluation Dimensions integral Patents are stable and not easily invalidated or revoked +3 The scope of protection of the claim is greater than 8 items +2 No litigation occurred +1 A lawsuit has occurred and the case has been won +3, +1 for each additional win There are many patents in the same family, and the stability is good +1 No pledge security occurred +1 During the application process, no rejection review occurred +1 No invalidation application has been made +1

[0104] Among them, the preset score threshold is 10 points. If the legal status score is greater than or equal to 10 points, the legal status score of the patent to be evaluated is 1 SG point. If the legal status score is less than 10 points, the legal status score of the patent to be evaluated is 0 SG points.

[0105] Through the above solution, when the current legal status of the patent to be evaluated is an authorized and valid state, by judging whether the patent to be evaluated has had a litigation behavior and whether it has won, the legal status points of the patent to be evaluated are obtained, so as to accurately determine the legal status score of the patent to be evaluated according to the legal status points. At the same time, the legal status points of the patent to be evaluated can also be determined according to multiple legal status dimensions, so as to accurately and comprehensively determine the legal status score of the patent to be evaluated.

[0106] In some embodiments, the process of determining the historical conversion score includes:

[0107] Step 103a, obtain the historical conversion data of the patent to be evaluated.

[0108] Step 103b, in response to determining that there is an exclusive license in the historical conversion data, obtain the exclusive license points of the patent to be evaluated.

[0109] Step 103c, in response to determining that there is an exclusive license in the historical conversion data and the patent to be evaluated is in the execution period of the exclusive license at the current moment, obtain the exclusive license points of the patent to be evaluated.

[0110] Step 103d, in response to determining that the historical conversion data has an exclusive license and the patent to be evaluated is not in the execution period of the exclusive license at the current moment, determine the exclusive license score based on the maintenance years, the number of exclusive licenses, and the exclusive license years of the patent to be evaluated.

[0111]

[0112] where SG permission is the exclusive license score, X is the maintenance years of the patent to be evaluated, N i is the number of exclusive licenses of the patent to be evaluated, m is the exclusive license years of the patent to be evaluated, is the exclusive license execution period coefficient,

[0113] Step 103e, in response to determining that the historical conversion data has a non-exclusive license, determine the non-exclusive license score based on the maintenance years and the number of non-exclusive licenses of the patent to be evaluated.

[0114]

[0115] where SG permission is the non-exclusive license score, a 0 is a preset harmonic coefficient, X is the maintenance years of the patent to be evaluated, N i is the number of non-exclusive licenses of the patent to be evaluated, is the non-exclusive license execution period coefficient,

[0116] Step 103f, in response to determining that the historical conversion data has a sub-license, determine the sub-license score of the patent to be evaluated based on the number of sub-licenses.

[0117] Step 103g, in response to determining that the historical conversion data has a cross-license, determine the cross-license score of the patent to be evaluated based on the number of cross-licenses.

[0118] Step 103h, obtain the historical conversion score of the patent to be evaluated according to the exclusive license score, the exclusive license score, the non-exclusive license score, the sub-license score, and the cross-license score.

[0119] Step 103i, compare the historical conversion score with a preset score threshold.

[0120] Step 103j, in response to determining that the historical conversion score is greater than or equal to the preset score threshold, determine that the historical conversion score of the patent to be evaluated is the first value.

[0121] Step 103k, in response to determining that the historical conversion score is less than a preset score threshold, determine that the historical conversion score of the patent to be evaluated is the second value.

[0122] In specific implementation, if a license occurs for the patent to be evaluated, calculate the historical conversion score of the patent to be evaluated in the historical conversion dimension according to different license methods. The full score of the integral in the historical conversion dimension is 10 points. If the historical conversion score of the patent to be evaluated exceeds the full score, determine that the historical conversion score of the patent to be evaluated is 1SG score.

[0123] (1) Exclusive license. In this way, the licensee not only obtains the right to implement a certain patented technology within the specified time and territory, but also has the right to reject any third party, including the licensor and all other people, from implementing the technology within the specified time and territory. If the patent to be evaluated has obtained an exclusive license historically, 10 points can be directly obtained.

[0124] (2) Sole license, that is, in a certain territory, the licensor only allows the licensee to implement its patent and no longer allows others to implement it in this territory, but the licensor still has the right to implement it in this territory. If the patent to be evaluated has obtained a sole license historically and is still in the execution period of the sole license during the value evaluation inspection period, 10 points can be directly obtained; if the patent to be evaluated has obtained a sole license historically but is not in the execution period of the sole license during the value evaluation inspection period, calculate from the date of publication of the authorization announcement. If the maintenance period of the patent to be evaluated is X years, if the patent to be evaluated has the i-th sole license in the Nth i year, and the duration of this sole license is m years, the obtained score is:

[0125]

[0126] In the formula, the coefficient for judging whether it is in the execution period

[0127] (3) Non-exclusive license. The licensor allows the licensee to use a certain patent within the specified time and territory. At the same time, the licensor itself still retains the right to use the technology in this territory and the right to sign a license contract with a third party for the same technology. Calculate from the date of publication of the authorization announcement. The maintenance period of the patent to be evaluated is X years. The patent to be evaluated has the i-th non-exclusive license in the Nth i year, then the obtained score is:

[0128]

[0129] (4) Sub-license. With the consent of the licensor, the licensee can license a third party to implement its patent in its own name. The score for this item is +1 for each sub-license occurrence.

[0130] (5) Cross-license. It refers to a transaction in which two or more patent holders grant each other the right to implement their respective patents under certain conditions. Cross-licensing is often a necessary reference condition for the birth of a new invention patent. For each occurrence of cross-licensing, the score is increased by 1.

[0131] Through the above solution, when there is an exclusive license for the patent to be evaluated, the exclusive license score of the patent to be evaluated is determined. When there is an exclusive license for the patent to be evaluated, the exclusive license score of the patent to be evaluated is determined by judging whether the patent to be evaluated is in the execution period of the exclusive license at the current moment. When there is a non-exclusive license for the patent to be evaluated, the non-exclusive license score is determined based on the maintenance period and the number of non-exclusive licenses of the patent to be evaluated. When there is a sub-license for the patent to be evaluated, the sub-license score of the patent to be evaluated is determined based on the number of sub-licenses. When there is a cross-license for the patent to be evaluated, the cross-license score of the patent to be evaluated is determined based on the number of cross-licenses. In this way, according to the exclusive license score, exclusive license score, non-exclusive license score, sub-license score and cross-license score, the historical conversion score of the patent to be evaluated is made more comprehensive and accurate, so as to accurately and comprehensively determine the historical conversion score of the patent to be evaluated.

[0132] In some embodiments, the process of determining the score of the patent holder includes:

[0133] Step 103M, obtain the information of the patent holder of the patent to be evaluated.

[0134] Step 103N, judge whether the patent to be evaluated is relevant to the main business of the patent holder's unit according to the information of the patent holder, and obtain the patent holder score of the patent to be evaluated.

[0135] Step 103O, compare and process the patent holder score with a preset score threshold.

[0136] Step 103P, in response to determining that the patent holder score is greater than or equal to the preset score threshold, determine that the patent holder score of the patent to be evaluated is the first value.

[0137] Step 103Q, in response to determining that the patent holder score is less than the preset score threshold, determine that the patent holder score of the patent to be evaluated is the second value.

[0138] In specific implementation, the patentee dimension is also a key factor affecting the patent value. For example, some groups are major providers of information and communication technologies, products, and services in the energy industry, with a wide range of main business scopes covering multiple industrial fields such as the Internet of Things, cloud computing, big data, artificial intelligence, blockchain, and security. They have strong technical strength and have built a complete industrial business system of "cloud-network-edge-terminal-chip-intelligence-chain", providing a complete information and communication industry chain covering upstream technical services, midstream industry applications, and downstream basic hardware. Most of the patents of the group in the fields of chips and the Internet of Things, artificial intelligence, big data and cloud services, communication, management informatization, operation and maintenance services, Beidou and geographic information services have relatively high theoretical research and practical application values.

[0139] The patentee and their affiliated unit represent the scientific research strength for applying for this patent. If the unit where the inventor of the patent to be evaluated is located has strong scientific research strength, and the patent to be evaluated is related to the main business, advantageous fields, and strategic layout of the patentee's unit at the same time, then the patent to be evaluated often has relatively high scientific research value. According to the patentee score standard in Table 2 below, determine the patentee score of the patent to be evaluated.

[0140] Table 2 Patentee Dimension Score Standard

[0141]

[0142]

[0143] Among them, the preset score threshold is 10 points. If the patentee score is greater than or equal to 10 points, then the patentee score of the patent to be evaluated is 1SG score. If the patentee score is less than 10 points, then the patentee score of the patent to be evaluated is 0SG score.

[0144] Through the above solution, judge whether the patent to be evaluated is related to the main business of the patentee's unit according to the patentee information of the patent to be evaluated, obtain the patentee score of the patent to be evaluated, and thus accurately determine the patentee score of the patent to be evaluated according to the patentee score. At the same time, the patentee score of the patent to be evaluated can also be determined according to multiple patentee dimensions, so as to accurately and comprehensively determine the patentee score of the patent to be evaluated.

[0145] In some embodiments, the process of determining the score of the score increase item includes:

[0146] Step 103I, obtain the score of the score increase item of the patent to be evaluated by judging whether the patent to be evaluated has practical value and theoretical research value.

[0147] Step 103II, compare and process the score of the score increase item with the preset score threshold.

[0148] Step 103III, in response to determining that the score of the incremental item is greater than or equal to the preset score threshold, determine that the score of the incremental item of the patent to be evaluated is the first value.

[0149] Step 103IV, in response to determining that the score of the incremental item is less than the preset score threshold, determine that the score of the incremental item of the patent to be evaluated is the second value.

[0150] In specific implementation, the setting of the incremental item dimension is mainly to avoid the situation that some patents that have been verified to have high value are not selected because they have a small but refined technical field coverage, the time difference between the authorization time and the evaluation value time is short, and there is no historical transformation for theoretical research patents, etc., and they are calculated with relatively low scores in the objective model scoring. Specifically, the following conditions can be used as the incremental items of the patent, and at the same time, users can also customize the incremental items according to the actual situation:

[0151] (1) The patent has been implemented, a contract has been signed, or economic benefits have been generated;

[0152] (2) The patent has won an award or received an award;

[0153] (3) The patent has been verified to have extremely high practical value or is recognized by experts as having extremely high theoretical research value;

[0154] (4) The patent has generated interactions with other scientific research results (for example, national, industry, or enterprise standards have been generated based on the patent, and core journals or above papers have been generated based on the patent, etc.);

[0155] (5) When the scientific and technological project is delivered and accepted, the scientific and technological project relied on by the patent has obtained an evaluation result of "excellent";

[0156] (6) The patent relies on the core technology team and is publicized as the core achievement of the team (core technology research team, core technology key laboratory, etc.);

[0157] (7) The patent belongs to fields such as the photovoltaic industry, the chip industry, and AI high-tech, which have great potential market prospects and the company has significant advantages and hopes to carry out patent layout;

[0158] (8) In the "4+1" dimension of the SG Score model, the SG score of the patent is 2 points or more.

[0159] Among them, the preset score threshold is 10 points. If the score of the incremental item is greater than or equal to 10 points, the score of the incremental item of the patent to be evaluated is 1 SG score. If the score of the incremental item is less than 10 points, the score of the incremental item of the patent to be evaluated is 0 SG score.

[0160] Through the above solution, by judging whether the patent to be evaluated has practical value and theoretical research value, the integral of the score-increasing items of the patent to be evaluated is obtained, so as to accurately determine the score of the score-increasing items of the patent to be evaluated according to the integral of the score-increasing items. At the same time, the integral of the score-increasing items of the patent to be evaluated can also be determined according to multiple score-increasing item dimensions, so as to accurately and comprehensively determine the score of the score-increasing items of the patent to be evaluated.

[0161] Through the above embodiments, the patent to be evaluated is obtained. The citation frequency of the patent to be evaluated is determined based on Zipf's law, and the patent citation score of the patent to be evaluated is determined according to the citation frequency through the PageRank algorithm. The technical field score, legal status score, historical transformation score, patentee score, and score of the score-increasing items of the patent to be evaluated are determined. According to the patent citation score, technical field score, legal status score, historical transformation score, patentee score, and score of the score-increasing items, the target value score of the patent to be evaluated is obtained. In this way, the patent citation score of the patent to be evaluated can be accurately determined through Zipf's law and the PageRank algorithm. By comprehensively considering the patent citation score, technical field score, legal status score, historical transformation score, patentee score, and score of the score-increasing items of the patent to be evaluated, the obtained target value score of the patent to be evaluated is more comprehensive and accurate.

[0162] It should be noted that the method of the embodiments of the present disclosure can be executed by a single device, such as a computer or a server. The method of this embodiment can also be applied to a distributed scenario, and completed by multiple devices cooperating with each other. In this case of a distributed scenario, one of the multiple devices can only execute one or more steps of the method of the embodiments of the present disclosure, and these multiple devices will interact with each other to complete the described method.

[0163] It should be noted that some embodiments of the present disclosure have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the above embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require the particular order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0164] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present disclosure also provides a patent value determination device.

[0165] Refer to Figure 3 , the patent value determination device includes:

[0166] An acquisition module 301, configured to acquire the patent to be evaluated;

[0167] The patent citation score determination module 302 is configured to determine the citation frequency of the patent to be evaluated based on Zipf's law, and determine the patent citation score of the patent to be evaluated according to the citation frequency through the PageRank algorithm;

[0168] A plurality of score determination modules 303 are configured to determine the technical field score, legal status score, historical transformation score, patentee score, and score for additional points of the patent to be evaluated;

[0169] The target value score determination module 304 is configured to obtain the target value score of the patent to be evaluated according to the patent citation score, the technical field score, the legal status score, the historical transformation score, the patentee score, and the score for additional points.

[0170] In some embodiments, the patent citation score determination module 302 includes:

[0171] A plurality of cited patent acquisition units are configured to acquire a plurality of cited patents that cite the patent to be evaluated;

[0172] The cited frequency determination unit is configured to determine the cited frequency of the patent to be evaluated based on Zipf's law according to the plurality of cited patents,

[0173]

[0174] wherein, is the cited frequency of the patent to be evaluated, C is a citation constant, and r α is the sorting order of the plurality of cited patents;

[0175] The citation coefficient determination unit is configured to determine the citation coefficient according to the cited frequency,

[0176]

[0177] wherein, σ zipf is the citation coefficient, is the sharing coefficient of the i-th cited patent, and σ share = 10%σ, and σ is the directed graph of the patent pool constructed based on the citation relationship between the patent to be evaluated and the plurality of cited patents;

[0178] The patent citation score determination unit is configured to determine the patent citation score of the patent to be evaluated according to the citation coefficient through the PageRank algorithm,

[0179]

[0180] wherein, SG reference(p i ) is the patent citation score for the patent p to be evaluated, d is the damping factor, N is the number of high-value patents in the patent pool directed graph, p i is the patent to be evaluated, M(p i ) is the set of the multiple cited patents, p i is the j-th cited patent, SG j (p reference ) is the patent citation score of the j-th cited patent, L(p j ) is the number of the multiple cited patents cited by the patent p to be evaluated. j is the patent p to be evaluated i

[0181] In some embodiments, the multiple score determination modules 303 include a technical field score determination module; the technical field score determination module includes:

[0182] A technical field label acquisition unit configured to acquire the technical field label of the patent to be evaluated;

[0183] A primary technical coefficient determination unit configured to determine a primary label in a preset primary field from the technical field label and determine a primary technical coefficient according to the total number of preset primary fields and the number of primary labels,

[0184]

[0185] where α is the primary technical coefficient, the total number of preset primary fields is 10, and n is the number of primary labels;

[0186] A primary label weight determination unit configured to determine a primary label weight according to the primary label and the preset primary field,

[0187]

[0188] where A i is the weight of the i-th primary label, is the number of the i-th primary label, is the number of the j-th preset primary field;

[0189] A secondary technical coefficient determination unit configured to determine a secondary label in a preset secondary field from the technical field label and determine a secondary technical coefficient according to the total number of preset secondary fields and the number of secondary labels,

[0190]

[0191] where β is the secondary technical coefficient, the total number of preset secondary fields is 50, and m is the number of secondary labels;

[0192] The secondary label weight determination unit is configured to determine the secondary label weight according to the secondary label and the preset secondary field,

[0193]

[0194] where B i is the weight of the i-th secondary label, is the quantity of the i-th secondary label, is the quantity of the j-th preset secondary field;

[0195] The core value technology coefficient determination unit is configured to determine the core value labels in the preset core value fields from the technology field labels, and determine the core value technology coefficient according to the total number of preset core value fields and the number of core value labels,

[0196]

[0197] where θ is the core value technology coefficient, the total number of preset core value fields is 14, and t is the number of core value labels;

[0198] The core value label weight determination unit is configured to determine the core value label weight according to the core value label and the preset core value field,

[0199]

[0200] where C i is the weight of the i-th core value label, is the quantity of the i-th core value label, is the quantity of the j-th preset core value field;

[0201] The technology field score determination unit is configured to determine the technology field score of the patent to be evaluated according to the primary technology coefficient, the primary label weight, the secondary technology coefficient, the secondary label weight, the core value technology coefficient, and the core value label weight,

[0202]

[0203] where SG technology is the technology field score, and M is the total number of primary label weights.

[0204] In some embodiments, the multiple score determination modules 303 include a legal status score determination module; the legal status score determination module includes:

[0205] The legal status acquisition unit is configured to acquire the current legal status of the patent to be evaluated;

[0206] A legal status score determination unit, configured to, in response to determining that the current legal status is an authorized and valid status, obtain the legal status score of the patent to be evaluated by determining whether the patent to be evaluated has undergone a litigation act and whether it has won the lawsuit;

[0207] A comparison processing unit, configured to perform a comparison process on the legal status score and a preset score threshold;

[0208] A first legal status score determination unit, configured to, in response to determining that the legal status score is greater than or equal to the preset score threshold, determine that the legal status score of the patent to be evaluated is a first value;

[0209] A second legal status score determination unit, configured to, in response to determining that the legal status score is less than the preset score threshold, determine that the legal status score of the patent to be evaluated is a second value.

[0210] In some embodiments, the multiple score determination modules 303 include a historical conversion score determination module; the historical conversion score determination module includes:

[0211] A historical conversion data acquisition unit, configured to acquire the historical conversion data of the patent to be evaluated;

[0212] An exclusive license score determination unit, configured to, in response to determining that there is an exclusive license in the historical conversion data, obtain the exclusive license score of the patent to be evaluated;

[0213] A sole license score determination unit, configured to, in response to determining that there is a sole license in the historical conversion data and the patent to be evaluated is in the execution period of the sole license at the current moment, obtain the sole license score of the patent to be evaluated;

[0214] A sole license score determination unit, configured to, in response to determining that there is a sole license in the historical conversion data and the patent to be evaluated is not in the execution period of the sole license at the current moment, determine the sole license score based on the maintenance years, the number of sole licenses, and the sole license years of the patent to be evaluated,

[0215]

[0216] wherein, SG permission is the sole license score, X is the maintenance years of the patent to be evaluated, N i is the number of sole licenses of the patent to be evaluated, m is the sole license years of the patent to be evaluated, is the sole license execution period coefficient,

[0217] A non-exclusive license score determination unit, configured to determine a non-exclusive license score based on the maintenance years of the patent to be evaluated and the number of non-exclusive licenses in response to determining that there is a non-exclusive license in the historical conversion data,

[0218]

[0219] wherein, SG permission is the non-exclusive license score, a 0 is a preset harmonic coefficient, X is the maintenance years of the patent to be evaluated, N i is the number of non-exclusive licenses of the patent to be evaluated, is the non-exclusive license execution period coefficient,

[0220] A sub-license score determination unit, configured to determine the sub-license score of the patent to be evaluated based on the number of sub-licenses in response to determining that there is a sub-license in the historical conversion data;

[0221] A cross-license score determination unit, configured to determine the cross-license score of the patent to be evaluated based on the number of cross-licenses in response to determining that there is a cross-license in the historical conversion data;

[0222] A historical conversion score determination unit, configured to obtain the historical conversion score of the patent to be evaluated according to the exclusive license score, the sole license score, the non-exclusive license score, the sub-license score and the cross-license score;

[0223] A comparison processing unit, configured to compare and process the historical conversion score with a preset score threshold;

[0224] A first historical conversion score determination unit, configured to determine that the historical conversion score of the patent to be evaluated is a first value in response to determining that the historical conversion score is greater than or equal to the preset score threshold;

[0225] A second historical conversion score determination unit, configured to determine that the historical conversion score of the patent to be evaluated is a second value in response to determining that the historical conversion score is less than the preset score threshold.

[0226] In some embodiments, the multiple score determination modules 303 include a patentee score determination module; the patentee score determination module includes:

[0227] A patentee information acquisition unit, configured to acquire the patentee information of the patent to be evaluated;

[0228] The patentee score determination unit is configured to determine whether the patent to be evaluated is relevant to the main business of the patentee's unit based on the patentee information, and obtain the patentee score of the patent to be evaluated;

[0229] The comparison processing unit is configured to perform a comparison process between the patentee score and a preset score threshold;

[0230] The first patentee score determination unit is configured to, in response to determining that the patentee score is greater than or equal to the preset score threshold, determine that the patentee score of the patent to be evaluated is a first value;

[0231] The second patentee score determination unit is configured to, in response to determining that the patentee score is less than the preset score threshold, determine that the patentee score of the patent to be evaluated is a second value.

[0232] In some embodiments, the multiple score determination modules 303 include a score increase item score determination module; the score increase item score determination module includes:

[0233] The score increase item score determination unit is configured to obtain the score increase item score of the patent to be evaluated by determining whether the patent to be evaluated has practical value and theoretical research value;

[0234] The comparison processing unit is configured to perform a comparison process between the score increase item score and a preset score threshold;

[0235] The first score increase item score determination unit is configured to, in response to determining that the score increase item score is greater than or equal to the preset score threshold, determine that the score increase item score of the patent to be evaluated is a first value;

[0236] The second score increase item score determination unit is configured to, in response to determining that the score increase item score is less than the preset score threshold, determine that the score increase item score of the patent to be evaluated is a second value.

[0237] For the convenience of description, when describing the above device, it is divided into various modules according to functions for separate description. Of course, when implementing the present disclosure, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0238] The device in the above embodiments is used to implement the corresponding patent value determination method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0239] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present disclosure also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the method for determining the patent value described in any one of the above embodiments is implemented.

[0240] Figure 4 FIG. shows a more specific schematic diagram of the hardware structure of the electronic device provided in this embodiment. The device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. Among them, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are communicatively connected to each other inside the device through the bus 1050.

[0241] The processor 1010 may be implemented in a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0242] The memory 1020 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0243] The input / output interface 1030 is used to connect to an input / output module to implement information input and output. The input / output module may be configured as a component in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Among them, the input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0244] The communication interface 1040 is used to connect to a communication module (not shown in the figure) to enable communication and interaction between this device and other devices. The communication module can achieve communication through a wired method (such as USB (Universal Serial Bus), network cable, etc.) or through a wireless method (such as mobile network, WIFI (Wireless Fidelity), Bluetooth, etc.).

[0245] The bus 1050 includes a path for transmitting information between various components of the device (such as the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0246] It should be noted that although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040, and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device may also only include the components necessary to implement the solution of the embodiments of this specification, and does not necessarily include all the components shown in the figure.

[0247] The electronic device in the above embodiment is used to implement the corresponding patent value determination method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0248] Based on the same inventive concept, corresponding to the method in any of the above embodiments, the present disclosure also provides a non-transitory computer-readable storage medium. The non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to cause the computer to execute the patent value determination method described in any of the foregoing embodiments.

[0249] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory, or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassette tapes, magnetic disk storage, or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device.

[0250] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to execute the patent value determination method described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0251] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present application further provides a computer program product, including computer program instructions. When the computer program instructions run on a computer, the computer is caused to execute the patent value determination method described in any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0252] It can be understood that before using the technical solutions of the various embodiments in the present disclosure, the types, usage scopes, usage scenarios, etc. of the personal information involved will be informed to the user in an appropriate manner, and the user's authorization will be obtained.

[0253] For example, when responding to receiving an active request from the user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be executed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, an application program, a server, or a storage medium that executes the operation of the technical solution of the present disclosure according to the prompt message.

[0254] As an optional but non-limiting implementation manner, the manner of sending a prompt message to the user in response to receiving an active request from the user may be, for example, in the form of a pop-up window, and the prompt message may be presented in text in the pop-up window. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0255] It can be understood that the above process of notifying and obtaining the user's authorization is only illustrative and does not limit the implementation manner of the present disclosure. Other manners that meet relevant laws and regulations can also be applied to the implementation manner of the present disclosure.

[0256] Those of ordinary skill in the art should understand that the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the present disclosure is limited to these examples; under the idea of the present disclosure, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations in different aspects of the embodiments of the present disclosure as described above, which are not provided in detail for the sake of brevity.

[0257] In addition, for simplicity of explanation and discussion, and so as not to make the embodiments of the present disclosure difficult to understand, well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Further, the devices may be shown in block diagram form in order to avoid making the embodiments of the present disclosure difficult to understand, and this also takes into account the fact that details regarding the implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the present disclosure are to be implemented (i.e., these details should be fully within the understanding of those skilled in the art). In cases where specific details (such as circuits) are set forth to describe exemplary embodiments of the present disclosure, it will be apparent to those skilled in the art that the embodiments of the present disclosure may be practiced without these specific details or with variations of these specific details. Accordingly, these descriptions should be considered illustrative rather than restrictive.

[0258] Although the present disclosure has been described in connection with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art based on the foregoing description. For example, other memory architectures (such as dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0259] Embodiments of the present disclosure are intended to cover all such alternatives, modifications, and variations that fall within the broad scope of the present disclosure. Accordingly, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of the present disclosure shall be included within the protection scope of the present disclosure.

Claims

1. A method for determining patent value, characterized in that: The method comprises: Obtain patents to be evaluated; Determine the citation frequency of the patent to be evaluated based on Zipf's law, and determine the patent citation score of the patent to be evaluated according to the citation frequency through the PageRank algorithm; Determine the technical field score, legal status score, historical transformation score, patentee score and additional score score of the patent to be evaluated; The target value score of the patent to be evaluated is obtained based on the patent citation score, the technical field score, the legal status score, the historical transformation score, the patentee score and the score of the added score item.

2. The method according to claim 1, characterized in that The determining of the citation frequency of the patent to be evaluated based on Zipf's law, and determining the patent citation score of the patent to be evaluated according to the citation frequency by using the PageRank algorithm, includes: Obtain multiple cited patents that cite the patent to be evaluated; Based on Zipf's law, the citation frequency of the patent to be evaluated is determined according to the multiple cited patents. in, is the citation frequency of the patent to be evaluated, C is the citation constant, r α is the ranking order of the multiple cited patents; Determine the citation coefficient based on the cited frequency, Among them, σ zipf is the citation coefficient, is the sharing coefficient of the i-th cited patent, σ share =10%σ, where σ is a directed graph of a patent pool constructed based on the citation relationship between the patent to be evaluated and the multiple cited patents; The patent citation score of the patent to be evaluated is determined according to the citation coefficient by using the PageRank algorithm. Among them, SG reference (p i ) is the patent to be evaluated i The patent citation score, d is the damping factor, N is the number of high-value patents in the patent pool directed graph, and p i is the patent to be evaluated, M(p i ) is the collection of the multiple cited patents, p j is the jth cited patent, SG referencd (p j ) is the patent citation score of the j-th citing patent, L(p j ) is the patent to be evaluated i The number of cited multiple citing patents.

3. The method according to claim 1, characterized in that The process for determining the scores for the technical areas includes: Obtain the technical field label of the patent to be evaluated; Determine the first-level labels in the preset first-level fields from the technical field labels, and determine the first-level technical coefficient according to the total number of the preset first-level fields and the number of first-level labels, Wherein, α is the first-level technical coefficient, the total number of the preset first-level fields is 10, and n is the number of the first-level tags; Determine the first-level label weight according to the first-level label and the preset first-level domain, Among them, A i is the weight of the i-th first-level label, is the number of the i-th first-level label, is the number of the jth preset first-level domains; Determine the secondary tags in the preset secondary fields from the technical field tags, and determine the secondary technical coefficient according to the total number of preset secondary fields and the number of secondary tags, Wherein, β is the secondary technical coefficient, the total number of the preset secondary fields is 50, and m is the number of the secondary tags; Determine the secondary tag weight according to the secondary tag and the preset secondary field, Among them, B i is the weight of the i-th secondary label, is the number of the i-th secondary label, is the number of the jth preset secondary domains; Determine the core value labels in the preset core value fields from the technical field labels, and determine the core value technology coefficient according to the total number of preset core value fields and the number of core value labels, Wherein, θ is the core value technology coefficient, the total number of preset core value fields is 14, and t is the number of core value labels; Determine the core value label weight according to the core value label and the preset core value field, Among them, C i is the weight of the i-th core value label, is the number of the i-th core value label, is the number of the jth preset core value areas; Determine the technical field score of the patent to be evaluated based on the first-level technical coefficient, the first-level label weight, the second-level technical coefficient, the second-level label weight, the core value technical coefficient and the core value label weight, Among them, SG technology Score the technical field, and M is the total number of primary label weights.

4. The method according to claim 1, characterized in that: The process of determining the legal status score includes: Obtain the current legal status of the patent to be evaluated; In response to determining that the current legal status is an authorized valid status, obtaining a legal status score of the patent to be evaluated by determining whether the patent to be evaluated has ever been involved in litigation and whether the litigation has been successful; Comparing the legal status score with a preset score threshold; In response to determining that the legal status score is greater than or equal to a preset score threshold, determining that the legal status score of the patent to be evaluated is a first value; In response to determining that the legal status score is less than a preset score threshold, the legal status score of the patent to be evaluated is determined to be a second value.

5. The method according to claim 1, characterized in that The process of determining the historical conversion score includes: Obtaining historical conversion data of the patent to be evaluated; In response to determining that an exclusive license exists for the historical conversion data, obtaining an exclusive license score for the patent to be evaluated; In response to determining that the historical conversion data has an exclusive license, and the patent to be evaluated is currently in the execution period of the exclusive license, obtaining exclusive license points of the patent to be evaluated; In response to determining that the historical conversion data has an exclusive license, and the patent to be evaluated is not in the execution period of the exclusive license at the current moment, determining the exclusive license points based on the maintenance years, the number of exclusive licenses, and the exclusive license years of the patent to be evaluated, Among them, SG permission is the exclusive licensing points, X is the maintenance period of the patent to be evaluated, N i is the number of exclusive licenses of the patent to be evaluated, m is the exclusive license period of the patent to be evaluated, is the coefficient of the exclusive license execution period, In response to determining that the historical conversion data has a non-exclusive license, determining a non-exclusive license point based on the maintenance years and the number of non-exclusive licenses of the patent to be evaluated, Among them, SG permission is the non-exclusive licensing credit, a0 is the preset harmonic coefficient, X is the maintenance period of the patent to be evaluated, N i is the number of non-exclusive licenses of the patent to be evaluated, is the coefficient of the non-exclusive license execution period, In response to determining that there is a sublicense in the historical conversion data, determining a sublicense score of the patent to be evaluated based on the number of sublicenses; In response to determining that there is a cross-licensing in the historical conversion data, determining a cross-licensing score of the patent to be evaluated based on the number of cross-licensings; Obtaining the historical conversion score of the patent to be evaluated according to the exclusive license score, the exclusive license score, the non-exclusive license score, the subordinate license score and the cross-license score; Compare the historical conversion points with a preset point threshold; In response to determining that the historical conversion score is greater than or equal to a preset score threshold, determining the historical conversion score of the patent to be evaluated to be a first value; In response to determining that the historical conversion score is less than a preset score threshold, the historical conversion score of the patent to be evaluated is determined to be a second value.

6. The method according to claim 1, characterized in that The process of determining the patentee score includes: Obtaining the patentee information of the patent to be evaluated; Determine whether the patent to be evaluated is related to the main business of the patent owner's unit based on the patent owner information, and obtain the patent owner points of the patent to be evaluated; Compare the patentee's points with a preset points threshold; In response to determining that the patentee score is greater than or equal to a preset score threshold, determining the patentee score of the patent to be evaluated to be a first value; In response to determining that the patentee score is less than a preset score threshold, the patentee score of the patent to be evaluated is determined to be a second value.

7. The method according to claim 1, characterized in that The process of determining the score of the additional points item includes: By judging whether the patent to be evaluated has practical value and theoretical research value, the points for the additional items of the patent to be evaluated are obtained; Compare the points of the point-enhancing items with a preset point threshold; In response to determining that the score of the score-enhancing item is greater than or equal to a preset score threshold, determining that the score of the score-enhancing item of the patent to be evaluated is a first value; In response to determining that the score of the point-enhancing item is less than a preset score threshold, the score of the point-enhancing item of the patent to be evaluated is determined to be a second value.

8. A patent value determination device, characterized in that: include: an acquisition module, configured to acquire patents to be evaluated; A patent citation score determination module is configured to determine the citation frequency of the patent to be evaluated based on Zipf's law, and determine the patent citation score of the patent to be evaluated according to the citation frequency through a PageRank algorithm; A plurality of score determination modules, configured to determine a technical field score, a legal status score, a historical conversion score, a patentee score, and a score of an additional item of the patent to be evaluated; The target value score determination module is configured to obtain the target value score of the patent to be evaluated based on the patent citation score, the technical field score, the legal status score, the historical conversion score, the patentee score and the score of the added score item.

9. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and running on the processor, wherein when the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to cause a computer to execute the method according to any one of claims 1 to 7.

Images