Intellectual property big data-based customer group recommendation method and device, and storage medium

Abstract

The invention relates to the technical field of intellectual property push services, in particular to a customer group recommendation method and device based on intellectual property big data and a storage medium. On the basis of enterprise intellectual property change data in a public website on the Internet obtained by an enterprise information query platform, a double-helix label system combining a static registration label and a user dynamic behavior weight is adopted, and in a static dimension, the platform establishes a registration enterprise label based on industrial and commercial record information during enterprise registration; mapping the image to a subordinate employee or an individual user as a basic image; in a dynamic dimension, behavior data of a user in a platform is collected in real time, a behavior weight is calculated through a multi-dimensional interest model, and a user tag is updated, so that the data is pushed to the user based on the obtained enterprise intellectual property change data in a period to assist the user in obtaining customers, and the user experience is improved. The defect that most existing enterprise information query platforms are passive information display and do not actively push information is made up.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intellectual property pushing service, in particular to a customer group recommendation method and device based on intellectual property big data and a storage medium. BACKGROUND

[0002] Current enterprise information query platforms such as Tianyancha, Qichaicha, etc. mainly aggregate public intellectual property change data including patents, trademarks, copyrights, etc. to perform basic classification and arrangement, and users need to manually select preset labels to filter target information.

[0003] Such systems generally have three major core defects: first, the label system is static and fixed, and users need to manually select the specified intellectual property labels in the platform enterprise during operation, and view the trademark, patent, copyright change data under this label, and cannot dynamically adjust the push content according to the actual business of the platform user; Second, the data utilization efficiency is low, the platform only provides basic search function, and does not establish a user behavior and label association mechanism, which cannot capture potential demand, for example, the enterprise frequently browses foreign patent application cases but does not trigger related service recommendation; Finally, the service response is lagging, the data update delay is 24-72 hours, and there is no active push strategy, or only simple data display, based on historical data rather than real-time behavior, missing the business opportunity window period. These problems result in less than 30% accuracy of platform push, users need to spend a lot of time manually screening, and the conversion rate is not high. SUMMARY

[0004] The purpose of the present application is to provide a customer group recommendation method based on intellectual property big data to solve the above problems.

[0005] The technical solution adopted by the present application is as follows: a customer group recommendation method based on intellectual property big data, comprising the following steps: Collecting intellectual property change data, collecting enterprise intellectual property change data on the Internet through API interface at fixed frequency, and summarizing as enterprise intellectual property change data set; Data set cleaning, using regular expression to correct the data format in the enterprise intellectual property change data set, filtering invalid fields, and obtaining the change label of the enterprise intellectual property change data; User label generation, after the registered enterprise explicitly authorizes, parsing the business registration information of the registered enterprise of the enterprise information query platform, extracting the main business keywords, generating the registered enterprise label, and mapping the registered enterprise label to the individual user under the jurisdiction of the registered enterprise, and generating the user label; User dynamic behavior update label, after user explicit authorization, establish enterprise information query platform user behavior matrix, record user dynamic behavior in enterprise information query platform according to fixed frequency, generate updated user label based on behavior matrix; Customer group push, match enterprise intellectual property change data change label and user label or updated user label, push enterprise intellectual property change data to user.

[0006] Further, the enterprise intellectual property change data includes patent change data, trademark change data and copyright change data; The patent change data includes patent subject information change data and patent right status change data. The trademark change data includes trademark subject information change data, trademark use change data and trademark ownership relationship change data. The copyright change data includes copyright right subject change data, copyright work information change data and copyright right content change data.

[0007] Further, in the data set cleaning, first, regular expression is used to correct the data format in the enterprise intellectual property change data set, filter invalid fields, and then type shunt is used to classify the enterprise intellectual property change data set based on type identification rules.

[0008] Further, the type identification rule is to extract the character segment of the application number or certificate number in the enterprise intellectual property change data set, and mark the character segment containing "CN", "EP" and "US" as a patent change label. Mark the character segment containing "TM" as a trademark change label. Mark the character segment containing "Guozuo Dianzi" as a copyright change label.

[0009] Further, the user label includes patent agent label, trademark agent label and copyright agent label.

[0010] Further, in the user label generation, the registered business scope of the registered enterprise is obtained through the national enterprise credit information public system, and the registered enterprise label is generated. After the registered enterprise registers in the enterprise information query platform, it is subject to multiple individual users, and the registered enterprise label is mapped to the individual users under the registered enterprise, and the user label is generated.

[0011] Further, the user dynamic behavior in the enterprise information query platform includes intellectual property page browsing or click frequency, intellectual property page average stay time and intellectual property page interaction frequency. The user interest degree is generated based on the intellectual property page browsing or click frequency, the intellectual property page average stay time and the intellectual property page interaction frequency, and a first weight is given respectively; The updated user label is generated based on the user interest degree and the label, and a second weight is given respectively.

[0012] Further, the customer group pushing includes an enterprise intellectual property change data main content pushing area and an enterprise intellectual property change data expansion area, the enterprise intellectual property change data main content pushing area contains enterprise intellectual property change data matched with the updated user label, and the enterprise intellectual property change data expansion area folds and displays other data in the enterprise intellectual property change data.

[0013] The application further provides a customer group recommendation device based on intellectual property big data, which comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, and the processor implements the customer group recommendation method based on intellectual property big data when executing the computer program.

[0014] The application further provides a computer readable storage medium comprising a stored computer program, wherein the computer readable storage medium controls the device where the computer readable storage medium is located to execute the customer group recommendation method based on intellectual property big data when the computer program runs.

[0015] The application has at least one of the following beneficial effects; 1. The enterprise intellectual property change data in the public website on the Internet obtained by relying on the enterprise information query platform adopts a double helix label system combining static registration label and user dynamic behavior weight, in the static dimension, the platform establishes a registered enterprise label based on the business registration information during enterprise registration, and maps it to the employees or individual users under jurisdiction as a basic portrait; in the dynamic dimension, the behavior data of the user in the platform is collected in real time, the behavior weight is calculated through a multi-dimensional interest model, and the user label is updated, so that the user is pushed based on the obtained enterprise intellectual property change data in a cycle, and the customer acquisition is assisted.

[0016] 2. The double intellectual property service pushing mechanism adopting static label underpinning combined with dynamic behavior correction, on the one hand, makes up for the lack of passive information display without active pushing of the existing enterprise information query platform, and on the other hand, greatly improves the matching degree of the pushing content and the user demand, greatly shortens the delay of data updating to pushing, and realizes the paradigm shift of the enterprise information query platform from 'passive search' to 'active business opportunity mining'. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 It is a customer group recommendation method flowchart based on intellectual property big data. Figure 2 The logic diagram of the customer group recommendation method based on intellectual property big data is shown in the following figure: Figure 3 The schematic diagram for generating user labels is shown in the following figure: Figure 4 The schematic diagram for cleaning data sets is shown in the following figure: Figure 5 The flowchart of the customer group pushing process is shown in the following figure: Figure 6 The logic diagram of the dynamic behavior and static label pushing is shown in the following figure. DETAILED DESCRIPTION

[0018] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described in the drawings herein can be arranged and designed in various different configurations.

[0019] Therefore, the detailed description of the embodiments of the present application provided in the drawings below is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative labor are within the scope of protection of the present application.

[0020] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0021] It should be noted that: similar reference numerals and letters represent similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0022] As shown in the following figure, the customer group recommendation method based on intellectual property big data includes the following steps: Figure 1 Collecting intellectual property change data, collecting enterprise intellectual property change data on the Internet through API interface at fixed frequency, and summarizing the data into an enterprise intellectual property change data set; Cleaning data sets, correcting the data format in the enterprise intellectual property change data set by using regular expressions, filtering invalid fields, and obtaining the change label of the enterprise intellectual property change data; ​User tag generation, after the explicit authorization of the registered enterprise, the business information query platform parses the business information of the registered enterprise, extracts the main business keywords, generates the registered enterprise tag, and maps the registered enterprise tag to the individual users under the jurisdiction of the registered enterprise, and generates user tags; User dynamic behavior update tag, after the explicit authorization of the user, the enterprise information query platform establishes a user behavior matrix, records the user's dynamic behavior in the enterprise information query platform at a fixed frequency, and generates an updated user tag based on the behavior matrix; Customer group push, matching the change tags of enterprise intellectual property change data and user tags or updated user tags, pushing enterprise intellectual property change data to users.

[0023] The purpose of such design is to obtain enterprise intellectual property change data in public websites on the Internet relying on the enterprise information query platform, and to adopt a double helix tag system combining static registration tags and user dynamic behavior weights. In the static dimension, the platform establishes registered enterprise tags based on business information during enterprise registration, and maps them to the employees or individual users under its jurisdiction as the basic portrait. In the dynamic dimension, the behavior data of users in the platform is collected in real time, the behavior weight is calculated through a multi-dimensional interest model, and the user tag is updated, so as to push the users based on the obtained enterprise intellectual property change data in a cycle, assist them in obtaining customers, and solve the problem that the existing enterprise information query platform tag system is static and fixed, and the user needs to manually select the specified intellectual property tags in the platform during operation., and based on the change data of trademarks, patents, copyrights and other labels under this label, the user can view it by himself, and cannot adjust the push content according to the actual business dynamics of the platform users.

[0024] It should be pointed out that the public websites on the Internet referred to in the present embodiment include the website of the State Intellectual Property Office, China Trademark Network, Trademark Review Documents Inquiry Network, State Copyright Bureau website, China Copyright Protection Center, etc. which can obtain official certification of enterprise intellectual property change data.

[0025] It should be pointed out that in actual use, since it involves more accurate customer group push based on user data and behavior, when implementing the method, the user needs to be informed that the function can only be carried out after the user's explicit authorization.

[0026] Meanwhile, it also needs to be pointed out that in the enterprise information query platform provided by the embodiment, in order to facilitate the pushing of intellectual property data, all are enterprise users, and the system does not support independent registration. The opening process provides enterprise users with mobile phone numbers and business license information for login, and then opens an account in the enterprise information query platform, sends a login password to the enterprise user, and the enterprise user can log in and use it. Of course, as a user, the same enterprise user can contain multiple individual users, and these individual users carry out corresponding work on the basis of the enterprise.

[0027] In the embodiment, the enterprise intellectual property change data includes patent change data, trademark change data and copyright change data; The patent change data includes patent subject information change data and patent right status change data. The trademark change data includes trademark subject information change data, trademark use change data and trademark ownership relationship change data. The copyright change data includes copyright right subject change data, copyright work information change data and copyright right content change data.

[0028] Meanwhile, in the data set cleaning, the regular expression is used to correct the data format in the enterprise intellectual property change data set, filter invalid fields, and then the type shunt is used to classify the enterprise intellectual property change data set based on type identification rules.

[0029] And the type identification rule is to extract the character segment of the application number or certificate number in the enterprise intellectual property change data set, and mark the character segment containing "CN", "EP" and "US" as a patent change label. Mark the character segment containing "TM" as a trademark change label. Mark the character segment containing "national work registration" as a copyright change label.

[0030] As shown in Figure 4 Take patent as an example, batch obtain patent change data from the website of the State Intellectual Property Office. Since these patent change data all contain a patent number, based on the combination of its country code and number, generate unique patent change data matched with the enterprise.

[0031] Meanwhile, in the classification, only the intellectual property change types are distinguished, such as patents, trademarks and copyrights, and after the three categories are distinguished, the corresponding enterprise name, change time, registration number and other metadata are retained, and the display is classified according to the secondary type patent subject information change data, patent right state change data, trademark subject information change data, trademark use change data, trademark ownership relationship change data, copyright right subject change data, copyright work information change data and copyright right content change data.

[0032] In the embodiment, the business scope registered by the enterprise is obtained through the national enterprise credit information public system in the user tag generation, and the registered enterprise tag is generated; After the registered enterprise registers on the enterprise information query platform, a plurality of individual users are subordinate to the registered enterprise as the main body, and the registered enterprise tag is mapped to the individual users subordinate to the registered enterprise, and the user tag is generated; The user tag includes a patent agency tag, a trademark agency tag and a copyright agency tag.

[0033] As Figure 3 shown, although the embodiment is described in terms of methods, the functions need to rely on corresponding functional modules and functional layers, such as the label management module and the label application layer used in the user tag generation, and this part of the content can be realized by means of the existing layer structure.

[0034] In the specific execution, due to the limitation of the enterprise information query platform in the embodiment, individual registration cannot be performed, so the enterprise responsible person or the enterprise entrustor needs to provide the mobile phone number for login and the enterprise information such as business license to complete the enterprise registration. At this time, the enterprise information query platform obtains the registered enterprise business registration information, analyzes the business scope to obtain the core field related to intellectual property, and simultaneously, since the method mainly involves the customer push under the intellectual property change, the other non-intellectual property related content is not described. After the above steps are completed, the registered enterprise obtains the registered enterprise tag, which includes one or more of the patent agency tag, the trademark agency tag and the copyright agency tag. Since the employees under the registered enterprise develop the business in the subsequent actual business activities, not the enterprise itself, the registered enterprise tag is mapped to the individual users subordinate thereto, and the user tag is generated as the initial tag of the person. The user tag is updated with the individual user behavior, and the user tag result is stored after the above steps are completed.

[0035] In the embodiment, the dynamic behavior of the user in the enterprise information query platform includes intellectual property page browsing or click frequency, intellectual property page average stay time and intellectual property page interaction frequency. Based on the intellectual property page browsing or click frequency, the intellectual property page average stay time and the intellectual property page interaction frequency, and respectively giving the first weight to generate the user interest degree; Based on the user interest degree and the label, and respectively giving the second weight to generate the updated user label.

[0036] In the specific implementation, as shown in Figure 6 The patent agency label, the trademark agency label and the copyright agency label are defined first, since this part is originally obtained, and is the most basic data in the whole method execution process, therefore, it is defined as a static label, and has the following formula: L static ={P patent , P trademark , P copyright}; Wherein, L static Indicates the static label; P patent Indicates the patent agency label; P trademark Indicates the trademark agency label; P copyright Indicates the copyright agency label; The user interest degree obtained by the dynamic behavior has the following formula: ; The updated user label is obtained by the following formula: ; Wherein, alpha and B respectively indicate the static label weight coefficient and the dynamic behavior weight coefficient, and the second weight is composed of alpha and B; Lambda is a time decay factor; T is the number of days from the last label update time to the current time.

[0037] As shown in Figure 5 In the specific execution, taking the patent as an example, the user first browses the patent page in daily use, and the browsing time is 150 seconds. This behavior as an initial interaction triggers the subsequent data collection and processing process.

[0038] Then the user browsing behavior is captured by the front-end system, and the front-end system reports the user behavior events to the behavior collection module in real time, and completes the preliminary record of the user behavior.

[0039] Then the behavior collection module is responsible for summarizing the user behavior events, and sends the data to the computing center according to the fixed frequency, to ensure the orderly processing of massive behavior data.

[0040] At the same time, after the computing center receives the behavior data, two core tasks are executed: Real-time interest calculation: Based on the user's current and historical behavior data, real-time analysis of the user's interest in patents, such as through browsing time, click frequency, and other indicators.

[0041] Update label weight: According to the real-time calculation of interest, dynamically adjust the label weight of the user or the patent, such as strengthening the user's preferred patent label, weakening the low correlation label, and providing data basis for accurate push.

[0042] In this way, the push service pushes the patent content highly matched with the user's interest to the user based on the label weight updated by the computing center, forming a closed loop of "user behavior → data processing → intelligent recommendation".

[0043] In addition, after the user receives the pushed patent, new browsing behavior may be generated, triggering the reporting and subsequent processing process of the front-end system again, realizing the continuous optimization of the recommendation system and the iteration of personalized experience.

[0044] In this way, the whole process starts with user behavior, and through the link of "data collection → real-time calculation → label optimization → accurate push", realizes dynamic recommendation based on user interest, and balances data processing efficiency and real-time recommendation through the combination of minute-level batch transmission and real-time calculation.

[0045] In specific implementation, large model machine learning can also be introduced in this step, taking user browsing time, click / collection / download interaction behavior, historical browsing sequence, and time interval features as raw behavior data, and then taking technical field labels, text abstracts, IPC classification numbers, reference relationships, and update times in patent category label as structured / unstructured features. Meta data, then based on the fusion of behavior frequency, preference intensity, and sequence pattern, build a patent feature vector, extract text keywords using TF-IDF, generate technical semantic vectors using pre-trained models such as BERT, aggregate label weights to build a patent feature vector, and generate interaction features based on the two feature vectors. Calculate user-patent matching degree and behavior decay factor, and then through model selection and training, upgrade traditional rules to model prediction value: through model output user's interest probability of patent, directly mapped to label weight, instead of artificial experience setting, realize multi-objective sorting fusion machine learning model interest score, patent timeliness, diversity (avoiding repeated recommendation of similar technology) and other multi-dimensional indicators, through sorting model to generate personalized recommendation list, in this way, through model regular iteration, automatically adapt to user interest migration.

[0046] In the specific implementation of the customer group pushing, the enterprise intellectual property change data is pushed to the user based on the matching of the change label and the user label or the updated user label, and the enterprise intellectual property change data includes an enterprise intellectual property change data main content pushing area and an enterprise intellectual property change data expansion area. The enterprise intellectual property change data main content pushing area contains the enterprise intellectual property change data matched with the updated user label, and the enterprise intellectual property change data expansion area folds and displays other data in the enterprise intellectual property change data.

[0047] Taking a patent as an example, if the main attribute of the updated user label of the user is a patent agent, the main content pushing area displays the patent change data of the selected enterprise when the customer group is pushed, and other intellectual property change data is also pushed, but in the folding area. The user selects whether to display according to the needs, and if the user selects to display other intellectual property change data, the enterprise information query platform will record the behavior and affect the subsequent dynamic behavior.

[0048] It should be noted that the customer group pushing in the actual operation process can be divided into two categories, one is the pushing of the intellectual property change data of the registered enterprise, and the other is the pushing of the intellectual property change data of the individual user under the jurisdiction of the registered enterprise. This can be set according to the actual needs and user selection.

[0049] The electronic device provided in the embodiment of the present application includes a memory and a processor. The memory is used to store computer readable instructions, and the processor is used to execute the computer readable instructions stored in the memory to realize the customer group recommendation method based on intellectual property big data in any of the above embodiments.

[0050] In an embodiment of the present application, the electronic device further includes a bus, a computer program stored in the memory and executable on the processor, such as a customer group recommendation program based on intellectual property big data.

[0051] The figure only shows an electronic device with a memory and a processor, and those skilled in the art can understand that the structure shown in the figure does not constitute a limitation on the electronic device, and can include fewer or more components than the figure, or combine certain components, or different component arrangements.

[0052] In combination with the figure, the memory in the electronic device stores a plurality of computer readable instructions to realize a customer group recommendation method based on intellectual property big data, and the processor can execute the plurality of instructions to realize.

[0053] Specifically, the specific implementation method of the processor for the above instructions can refer to the description of the related steps in the corresponding embodiment of the figure, which will not be described here.

[0054] Those skilled in the art can understand that the schematic diagram is only an example of the electronic device, and does not constitute a limitation on the electronic device, the electronic device can be a bus type structure, or a star type structure, and the electronic device can further include more or less other hardware or software, or a different arrangement of components, for example, the electronic device can further include an input / output device, a network access device, etc.

[0055] It should be noted that the electronic device is only an example, and other existing or future electronic products can also be applicable to the present application, and should be included in the protection scope of the present application.

[0056] The memory includes at least one type of readable storage medium, which can be non-volatile or volatile. The readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card type memory (for example, an SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory can be an internal storage unit of the electronic device in some embodiments, for example, a mobile hard disk of the electronic device. The memory can also be an external storage device of the electronic device in other embodiments, for example, a plug-in mobile hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. The memory can be used not only to store application software and various data installed in the electronic device, for example, the code of the customer group recommendation program based on intellectual property big data, but also to temporarily store data that has been output or will be output.

[0057] The processor can be composed of an integrated circuit in some embodiments, for example, can be composed of a single packaged integrated circuit, or can be composed of multiple packaged integrated circuits with the same function or different functions, including a combination of one or more central processing units (CPU), microprocessors, digital processing chips, graphics processors, and various control chips, etc. The processor is the control unit of the electronic device, which connects all components of the electronic device through various interfaces and lines, executes programs or modules stored in the memory (for example, executes the customer group recommendation program based on intellectual property big data, etc.), and calls data stored in the memory, to perform various functions of the electronic device and process data.

[0058] The processor executes an operating system of the electronic device and various installed applications. The processor executes the applications to implement the steps in the various embodiments of the method for recommending a customer group based on big data of intellectual property rights, such as the steps shown in the figures.

[0059] For example, the computer program can be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present application. The one or more modules / units can be a series of computer-readable instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program in the electronic device. For example, the computer program can be divided into a receiving module, a preprocessing module, a projection module, and a determination module.

[0060] The integrated units in the form of software function modules described above can be stored in a computer-readable storage medium. The software function modules described above are stored in a storage medium, including a number of instructions for causing a computer device (which can be a personal computer, a computer device, or a network device, etc.) or a processor (Processor) to execute part of the method for recommending a customer group based on big data of intellectual property rights described in various embodiments of the present application.

[0061] The modules / units integrated in the electronic device, if implemented in the form of software function units and sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above-mentioned embodiments can also be completed by a computer program to instruct related hardware devices, and the computer program can be stored in a computer-readable storage medium. When the processor executes the computer program, the steps of the various method embodiments described above can be implemented.

[0062] The embodiments of the present application provide a method for recommending a customer group based on big data of intellectual property rights, which can be applied to one or more electronic devices. An electronic device is a device that can automatically perform numerical calculation and / or information processing according to pre-set or stored instructions. The hardware thereof includes but is not limited to a microprocessor, an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), an embedded device, etc.

[0063] The electronic device can be any electronic product that can interact with the user, such as a personal computer, a tablet computer, a smart phone, a personal digital assistant (PDA), a game console, an interactive Internet Protocol Television (IPTV), a smart wearable device, etc.

[0064] The electronic device can also include a network device and / or a client device. The network device includes, but is not limited to, a single network server, a server group composed of multiple network servers, or a cloud composed of a large number of hosts or network servers based on cloud computing.

[0065] The network in which the electronic device is located includes, but is not limited to, the Internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (VPN), etc.

[0066] The computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate forms, etc. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory, and other memories, etc.

[0067] Further, the computer readable storage medium can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required by a function, etc.; the data storage area can store data created according to the use of the blockchain node, etc.

[0068] The bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one arrow is used in the figure, but it does not mean that there is only one bus or only one type of bus. The bus is arranged to realize the connection and communication between the memory, the at least one processor, etc.

[0069] The embodiment of the present application further provides a computer readable storage medium (not shown in the figure), which stores computer readable instructions, and the computer readable instructions are executed by a processor in an electronic device to implement the method for recommending a customer group based on intellectual property big data according to any of the foregoing embodiments.

[0070] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other manners. For example, the described device embodiments are merely schematic. Taking the division of the modules as an example, the division can be merely a logical function division, and there can be another division manner in actual implementation.

[0071] The modules illustrated as separated components can or can not be physically separated, and the components illustrated as modules can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. According to actual needs, some or all of the modules can be selected to achieve the purpose of the embodiments.

[0072] In addition, each functional module in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present independently, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware, or in the form of hardware plus software functional modules.

[0073] In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. The plurality of units or devices stated in the specification can also be implemented by one unit or device through software or hardware. The words "first", "second" and the like are used to indicate names, and do not indicate any specific order.

[0074] Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art can modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some of the technical features, and any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A customer recommendation method based on intellectual property big data, applicable to enterprise information query platforms, characterized in that: It includes the following steps: Collecting intellectual property change data, obtaining enterprise intellectual property change data on public websites on the Internet through the API interface at a fixed frequency, and summarizing it into an enterprise intellectual property change data set; Cleaning the data set, using regular expressions to correct the data format in the enterprise intellectual property change data set, filtering invalid fields, and obtaining the change labels of the enterprise intellectual property change data; Generating user labels, after the registered enterprise gives explicit authorization, parsing the industrial and commercial filing information of the registered enterprise on the enterprise information query platform, extracting the keywords of the main business, generating registered enterprise labels, and mapping the registered enterprise labels to the individual users under the registered enterprise to generate user labels; Updating the labels of the user's dynamic behavior, after the user gives explicit authorization, establishing a user behavior matrix on the enterprise information query platform, recording the user's dynamic behavior in the enterprise information query platform at a fixed frequency, and generating updated user labels based on the behavior matrix; Customer group push, matching the change labels of the enterprise intellectual property change data with the user labels or the updated user labels, and pushing the enterprise intellectual property change data to the users.

2. The customer recommendation method based on intellectual property big data according to claim 1, characterized in that, The enterprise intellectual property change data includes patent-related change data, trademark-related change data, and copyright-related change data; The patent-related change data includes patent subject information change data and patent right status change data; The trademark-related change data includes trademark subject information change data, trademark use change data, and trademark ownership relationship change data; 3. The customer recommendation method based on intellectual property big data according to claim 2, characterized in that, The copyright-related change data includes copyright right subject change data, copyright work information change data, and copyright right content change data.

4. The customer recommendation method based on intellectual property big data according to claim 3, characterized in that, In the cleaning of the data set, first use regular expressions to correct the data format in the enterprise intellectual property change data set, filter invalid fields, and then classify the change labels of the enterprise intellectual property change data set through a type splitter based on type recognition rules. The type recognition rule is to extract the character segment of the application number or certificate number in the enterprise intellectual property change data set, and mark the character segment containing "CN", "EP", "US" as the patent-related change label; Mark the character segment containing "TM" as the trademark-related change label; 5. The customer recommendation method based on intellectual property big data according to claim 1, characterized in that, Mark the character segment containing "National Copyright Registration" as the copyright change label.

6. The customer recommendation method based on intellectual property big data according to claim 5, characterized in that, The user labels include patent agency labels, trademark agency labels, and copyright agency labels. In generating user labels, obtain the business scope registered by the registered enterprise through the National Enterprise Credit Information Publicity System and generate registered enterprise labels; 7. The customer recommendation method based on intellectual property big data according to claim 5, characterized in that, After the registered enterprise registers on the enterprise information query platform, it has multiple individual users under it as the main body, and maps the registered enterprise labels to the individual users under the registered enterprise to generate user labels. The user's dynamic behavior in the enterprise information query platform includes the browsing or click frequency of the intellectual property page, the average stay time on the intellectual property page, and the interaction frequency of the intellectual property page; Based on the browsing or click frequency of the intellectual property page, the average stay time on the intellectual property page, and the interaction frequency of the intellectual property page, and respectively assigning the first weight to generate the user interest degree; Based on the user interest degree and the labels, and respectively assigning the second weight to generate the updated user labels.

8. The customer recommendation method based on intellectual property big data according to claim 7, characterized in that, The customer push includes a main content push area for enterprise intellectual property change data and an extended area for enterprise intellectual property change data. The main content push area for enterprise intellectual property change data contains enterprise intellectual property change data that matches the change tags with the updated user tags. The extended area for enterprise intellectual property change data displays other data in the enterprise intellectual property change data in a collapsed manner.

9. A customer recommendation device based on intellectual property big data, characterized in that, The device includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the customer recommendation method based on intellectual property big data as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device on which the computer-readable storage medium is located to perform the customer recommendation method based on intellectual property big data as described in any one of claims 1 to 8.

Images