CN112199557A

CN112199557A - Invention content recommendation tool, electronic equipment and computer-readable storage medium

Info

Publication number: CN112199557A
Application number: CN202011104864.XA
Authority: CN
Inventors: 王楠; 蔡月; 王洪宇; 赵宏宇; 蔡洁; 谢炜金; 蔡利亚
Original assignee: Beijing Ruyitang Technology Co ltd
Current assignee: Beijing Ruyitang Technology Co ltd
Priority date: 2020-10-15
Filing date: 2020-10-15
Publication date: 2021-01-08

Abstract

The invention provides an invention content recommendation tool, electronic equipment and a computer readable storage medium. The inventive measure management module controls at least one concept label in function, parameter, object, content and interactive characteristic of each measure. The content recommending module is a technical scheme for recommending specific implementation processes for each measure based on the characteristics or the combined characteristics of the inventive measures. The interaction module is used for recording, mining and feeding back the operation behaviors. The invention provides a tool for providing practical and referable invention content information for TRIZ invention measures.

Description

Invention content recommendation tool, electronic equipment and computer-readable storage medium

Technical Field

The present disclosure relates to the field of artificial intelligence, and more particularly to the field of natural language understanding, knowledge mapping, and intelligent assisted innovation.

Background

The traditional auxiliary innovation method comprises methods of experience investigation, brainstorming and the like, and since 1946, a former Soviet Union team extracts a universal problem solving tool of a cross-industry technical system, namely a classic TRIZ innovation methodology from 40 thousands of patents, and comprises abstract descriptions of system analysis, a contradiction matrix, an object field model and the like, and invention measures of 40 invention principles, four separation methods, 76 object field standard solutions, a scientific effect knowledge base and the like. However, each inventive measure of the classic TRIZ is too abstract, and the semantic relation between contradiction and the inventive principle has no interpretability. Therefore, the innovation of the invention directly using the classical TRIZ method is difficult. For the above problems, the modern TRIZ genre deepens the cognition of the evolution trend, the functions and the attributes, but still cannot be semantically combined with the invention contents such as scientific and technical literature, patents and the like, so that the knowledge matched with the input description is difficult to retrieve for the invention measures, and the semantic disjunction exists between the knowledge and the actual problem processing. At present, there is an urgent need to find a feasible matching scheme that can explicably merge the existing TRIZ inventive measures with the referable inventive content.

Disclosure of Invention

In view of the above problems, the present invention provides an inventive content recommendation tool; the invention content comprises executable examples such as scientific and technical documents, patents, technical documents or available technical schemes. And selecting a reasonable method or an algorithm model through characteristic engineering to recommend invention content for matching various invention measures.

A first aspect of the present invention provides an inventive content recommendation tool, characterized in that:

the system comprises an invention measure management module, a content recommendation module and an interaction module;

the inventive measure management module marks the inventive measure with a characteristic label;

the content recommendation module recommends related invention content for each invention measure by using a similar matching method according to the invention measure characteristic label and the invention content characteristic label;

and the interaction module records, excavates, feeds back, indexes and updates the operation behavior tags.

In some embodiments, the inventive measures include rules of evolution in TRIZ theory, clipping methods, inventive principles, standard solutions, flow improvement measures, scientific effects, and the like;

in some embodiments, the inventive content includes complete examples of patents, technical literature, technical texts;

in some embodiments, the complete example is a technical solution with a specific implementation flow, specifically, organized and stored in a multi-modal form such as text, image, voice, video, and the like.

The inventive measure management module and the feature label comprise functions, attributes and parameters, objects, measure contents, interaction records, and hierarchical concepts, relations, concept examples, explanation texts or combination features of the functions, the attributes and the parameters;

in some embodiments, the functions are abstracted functional operation hierarchical concepts and relationships through inductive abstracted functional operations in combination with system analysis, functional models, and functional analysis. The respective hierarchical conceptual systems and relationships are manipulated through inductive refinement functions.

In some embodiments, the functional operations include, but are not limited to, verbs and their multi-level conceptual structures. Specifically, for example, the concept "increase" is a first-level concept of functional operation, and the example is "increase";

the attributes and parameters comprise the attributes, attribute examples, variables or characteristic parameters of the operation objects recorded in the invention information base and various reference texts, and comprise parameters or parameter combinations related to the innovation texts, and the hierarchical concepts and the relations of the related parameters are induced;

in some embodiments, the attribute concept may be "brightness", and the parameter instance may be "brightness value";

in some embodiments, the parameters further comprise parameters or parameter combinations related to the inventive innovation text, and the hierarchical concepts and relationships of the related parameters are induced. Specifically, for example, the parameter concept "field", the secondary parameter is "physical quantity", and the parameter example may be "body weight";

in some embodiments, the objects include objective entities, substances, energy, and information recorded in the various inventive content;

in some embodiments, the relationship includes "upper and lower", "same position", "same sense", "similar sense", "antisense", and the like, for example, the "physical quantity" is a generic concept of "weight", so that the "physical quantity" includes the example of "weight", and the "physical quantity" and "weight" are "including" relationship, which is equivalent to the "upper and lower" relationship.

The relationship is the concept and the relationship example of the upper and lower positions and the same position relationship among all elements in the concept;

the marking is to extract the knowledge of each feature label through manual editing or by utilizing grammatical features, rule templates or algorithm models;

the labeling also comprises storage, indexing, editing and interactive operation.

The combined feature is a combination of at least two feature tags;

in some embodiments, the combined feature, specifically, for example, the first-level concept of the function operation is "added", the instance is "stacked", the object concept may be "solid", the object instance may be "component", and then "stacked component" becomes an example of the combined feature;

the interactive records comprise records of manual clicking, collection, labeling, addition, deletion, modification and check.

In some embodiments, the interactive features include manual clicking, collection, labeling, deletion-adding and retrieval, and specifically, record labels of various preferences, operations, collection, labeling, deletion-adding and retrieval, and the like, labeled for the inventive measures.

The inventive content features comprise various feature tag knowledge labeled from the inventive content, and also comprise the extension features of concepts, examples and relations related to the inventive content.

In some embodiments, the feature tags further comprise textual feature tags labeled from the description of the inventive measures and inventive content;

in particular, textual features include title, abstract, product, component, patent claims, technical field category, TFIDF value, and the like, and combinations thereof.

In some embodiments, the summary features further include other related labels, specifically, for example, patent, such as applicant, inventor, country, IPC, CPC labels, label relations (such as applicant and inventor relations, IPC context relation, applicant and country relation), such as value of text calculation, text context (associated knowledge).

The content recommending module comprises the steps of searching and recalling the inventive content and also comprises the steps of recommending and sequencing similar matching;

the searching comprises the modes of character index matching, semantic searching and the like;

the sequencing is to configure a weight strategy to screen the invention content;

in some embodiments, the retrieved recalled invention content results are ranked and filtered based on the feature tags;

in some embodiments, the search recall is to search various knowledge by using an extended search mode, to perform deformation and expansion on elements, and to recall the inventive content by using a similar matching method;

optionally, selecting character matching or semantic matching of the upper concept, the parity and the lower instance of the element;

in some embodiments, the weight policy includes different weight rule settings of a higher concept, a same-position example and a lower example of the inventive measure feature tag;

in some embodiments, the weight policy further comprises configuring weights according to relevant resources, systems, component characteristics, and relevant domains of inventive measures, selection preference constraints;

optionally, the preference policy includes interaction records, selection weights, and the like;

in some embodiments, the inventive content screening recommends one or more combinations of the inventive content from the ranking results according to a weighting policy;

and selecting a feature label set of the invention measures and the invention contents by the similarity matching, and realizing by using recommendation algorithms including collaborative filtering, matrix decomposition, factorization, deep neural network learning and the like.

In some embodiments, the recommended content includes multimodal content such as images, voice, text, video, and so on.

The interactive module is responsible for editing operation of various feature labels of the invention measures and the invention contents;

the editing comprises evaluation, indexing and storage;

and the evaluation is to analyze and judge the characteristic labels according to a manual or algorithm model, and to perform the addition, deletion, modification and check of the labels.

In some embodiments, the evaluation is labeling each type of feature label with the correct result;

in some embodiments, for unstructured inventive content, direct labeling is possible; or training the model of the labeled data by a machine learning method, and selecting the optimal model for automatic labeling;

optionally, persistence of offline or real-time data is supported.

Optionally, the structured instance, the instance relationship, and the attribute information are obtained and used as an index basis of the feature tag.

A second aspect of the invention provides an electronic device comprising one or more storage devices and a processor; storage means for storing one or more programs; when executed by the one or more processors, cause the one or more processors to implement any of the methods described above.

In some embodiments, the functions may be implemented by hardware, or by hardware executing corresponding software;

the hardware or software includes one or more modules corresponding to the above-described functions.

A third aspect of the invention provides a computer-readable storage medium having stored thereon computer-executable instructions operable, when executed by a computing device, to perform any of the methods described above.

In some embodiments, the computer instructions are read by a computer to perform the method of any of claims 1-10, the instructions when executed by a computing device being operable to perform any of the methods.

The technical scheme of the invention has the following beneficial technical effects:

the method comprises the steps of providing a set of content recommendation tools for inventive measures, realizing label labeling of the existing inventive measures, guiding the inventive content feature extraction by uniform semantic concept mapping, forming multi-level label feature semantic indexes of the inventive measures and the inventive contents, and facilitating the feature generation of a search recommendation algorithm;

designing a set of content recommendation interactive flow facing the inventive measures, editing and updating the inventive measure labels and the inventive content characteristics through manual intervention, selecting a search or recommendation algorithm, performing characteristic combination screening according to the inventive measure labels, setting a weight strategy, finishing recall sequencing and evaluating the recommended inventive content effect.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings used in the description of the embodiments will be briefly introduced below. Other features, objects, and advantages of the present disclosure will become more apparent from the following detailed description of non-limiting embodiments when taken in conjunction with the accompanying drawings. It is obvious that the drawings in the following description are only some embodiments of the application, and that it is also possible for a person skilled in the art to apply the application to other similar scenarios without inventive effort on the basis of these drawings. Unless otherwise apparent from the context of language or otherwise indicated, like reference numerals in the figures refer to like structures and operations.

The attached drawings are as follows:

FIG. 1 illustrates a block diagram of an inventive content recommendation tool according to an embodiment of the present disclosure;

FIG. 2 illustrates a work flow diagram of module S102 according to the embodiment shown in FIG. 1;

FIG. 3 illustrates a work flow diagram of module S104 according to the embodiment shown in FIG. 1;

FIG. 4 illustrates a work flow diagram of module S106 according to the embodiment shown in FIG. 1;

FIG. 5 shows a block diagram of an electronic device according to an embodiment of the present disclosure;

FIG. 6 illustrates a schematic diagram of a computer storage medium suitable for implementing a recommendation tool in accordance with an embodiment of the present disclosure.

Detailed Description

In the following detailed description, numerous specific details of the present application are set forth by way of examples in order to provide a thorough understanding of the relevant disclosure. It will be apparent, however, to one skilled in the art that the present application may be practiced without these specific details. It should be understood that the use of the terms "system," "apparatus," "unit" and/or "module" herein is a method for distinguishing between different components, elements, portions or assemblies at different levels of sequential arrangement. However, these terms may be replaced by other expressions if they can achieve the same purpose.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of the present application. As used in the specification and claims of this application, the terms "a", "an", and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" are intended to cover only the explicitly identified features, integers, steps, operations, elements, and/or components, but not to constitute an exclusive list of such features, integers, steps, operations, elements, and/or components.

The protection scope of this application is subject to the claims. Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. Also, for the sake of clarity, parts not relevant to the description of the exemplary embodiments are omitted in the drawings.

In the present disclosure, it is to be understood that terms such as "including" or "having," etc., are intended to indicate the presence of the disclosed features, numbers, steps, behaviors, components, parts, or combinations thereof, and are not intended to preclude the possibility that one or more other features, numbers, steps, behaviors, components, parts, or combinations thereof may be present or added. It should be further noted that the embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

The technical scheme of the invention can be applied to the innovation aspects in a plurality of fields of auxiliary industrial design, intelligent manufacturing, product research and development and the like. In particular, the technical scheme of the invention mainly explores the feasible auxiliary innovation method.

A first aspect of the present invention provides an inventive content recommendation tool that may be used to perform method embodiments of the present invention. The method comprises the following steps:

the specific implementation mode is as follows:

fig. 1 shows a block diagram of an inventive content recommendation tool, which may be implemented as part or all of an electronic device through software, hardware or a combination of both, according to an embodiment of the present invention, the tool comprising:

an inventive measure management module S102 configured to manage feature tags of the inventive measures, the feature tags including functions, attributes and parameters, objects, measure contents, interaction records, and their hierarchical concepts, relationships, concept instances, explanatory explanation texts, or combined features;

the combined feature is a combination of at least two feature tags;

The content recommending module S104 is configured to search and recall the inventive content according to the inventive measure label characteristics and the inventive content characteristics, and also comprises similar matching recommendation and sequencing;

the interaction module S106 is configured to be responsible for editing operation of various feature labels;

the editing comprises evaluation, indexing and storage;

The inventive measure management module S102, the concept label is based on functions, attributes and parameters corresponding to each measure, hierarchical concepts, relationships, concept instances, explanatory explanation texts or combination features of the object;

the combined features are the combination of at least two of functions, objects, parameters and other label features;

the management also comprises labeling, storing, indexing and editing the hierarchical labels.

in some embodiments, the term includes objective entities, substances, energy and information recorded in the various inventive concepts;

in some embodiments, the parameters include parameters or combinations of parameters related to the inventive subject matter, generalizing the hierarchical concepts and relationships associated with the parameters. Specifically, for example, the parameter concept "field", the secondary parameter is "physical quantity", and the parameter example may be "body weight";

in some embodiments, the text label is a text feature label extracted or labeled from the descriptive content of the inventive measure;

in particular, the text features include existing fields (title, abstract, product, component, claims, technical field, TFIDF value, etc., and combinations).

The invention content features also include other external tags, specifically, patent as an example, such as applicant, inventor, country, IPC, CPC tags, tag relationships (such as applicant and inventor relationships, IPC context relationships, applicant and country relationships), such as value of text calculation, text context (associated knowledge).

The content recommendation module S104 retrieves the invention content and sorts and screens the recall result based on the label characteristic and the interaction characteristic;

the sorting is to select preference constraint, configure weight strategy and recall sorting according to the label characteristics and interaction characteristics of the measures;

the similarity matching method comprises search recommendation algorithms such as index matching, collaborative filtering, matrix decomposition, factorization, deep neural network learning and the like.

The interaction module S106 is responsible for editing the characteristics of various labels;

the editing comprises marking, indexing, adding, deleting, modifying, checking and storing;

in an optional implementation manner of this embodiment, as shown in fig. 2, the inventive measure management module includes:

in step S202, a feature tag system is established;

in step S204, starting from the content of the inventive measures, labels are labeled for the inventive measures manually or automatically;

in some embodiments, the label for manually labeling the inventive measure is in a hierarchical system, for example, for the inventive measure "segmentation principle", the abstracted functional label is "segmentation", and the label features may have two levels: "split", corresponding to the function instance of the next level, namely "split subdivision into split conversion";

in some embodiments, the labels of the inventive measures are automatically labeled, the label labeling can be regarded as a label classification problem, and a subclass label or a label instance is allocated to each major class label through a classification algorithm or a model;

in some embodiments, the invention measure tags are generated and may be a tag hierarchy, a combination of tag features, a manual interaction feature, and the like. For example, the first-level function of forming the label features is divided, and the second-level function is divided into subdivision, splitting and splitting conversion; the tag feature combination can be a function object combination, a function parameter combination, a function object parameter combination, such as "split" + object "steel plate", "split" + parameter "size", "split +" steel plate "+" size "; the interactive characteristics comprise operation records such as clicking, collecting, adding, deleting, changing and checking and the like, for example, the invention content with the function of 'segmenting' is clicked and selected by the 'segmenting principle';

further, for recommending the inventive content, as shown in fig. 3, the method flow includes:

in step S302, the invention content features are extracted, knowledge is labeled or extracted from the content text based on various concept labels, and the extended search elements perform concept, instance, and top and bottom voxel extension on the input elements based on the semantic ontology and the hierarchical knowledge. For example, the function label labels the function type of the patent abstract, labels the function instance in the abstract by using a machine learning method or a rule template, and finally gives the function label result of each invention content;

optionally, the unstructured invention content data is labeled according to the invention measure labels, and the processed knowledge is further indexed and stored.

Alternatively, the data may be stored indexed by trigram data, characteristic field relationship data, and the like.

Optionally, the indexed reference text knowledge is represented in the form of graph data.

Optionally, the extracting further includes storing, indexing, and editing the above hierarchical knowledge.

In step S304, a search or recommendation algorithm is selected for the invention measure, for example, considering that the label combination features of the "segmentation principle" are less, and basically, the labels are "functional" single labels, and at this time, a semantic search model is directly adopted to directly recommend the index of the functional instance. If the label combination characteristics of the local quality principle are many, such as a great number of functional parameter combinations and functional object combinations, the characteristic selection can be performed by utilizing the factorization, wide & deep models and the like commonly used in the industry so as to recommend the invention content, such as patent and scientific and technical literature;

in step S306, the matched invention content is recommended for the invention measure, for example, if the label combination of the invention measure is "raise brightness", "raise temperature", etc., then a "method for raising brightness of the bulb" patent or a "raise heat-resisting temperature of the tungsten lamp" patent, etc. is recommended;

in some embodiments, a search or recommendation model is selected, the search model may be a direct feature matching model, a rule matching model, etc., and the recommendation model may be a collaborative filtering, factoring, deep neural network matching model, etc. For example, if there is feature matching between the "segmentation principle" and the "local quality principle" of many patents, a certain patent belonging to the "segmentation principle" may be matched by the "local quality principle";

optionally, based on the feature tag, the invention content is retrieved, and the recall result is sorted and screened; the sorting is to select preference constraint, configure weight strategy and recall sorting according to the relevant resources, systems and component characteristics of the problem to be innovated, the relevant fields and relevant users;

optionally, the knowledge in the invention information and the reference text is extracted respectively;

optionally, the similarity matching method includes various search recommendation algorithms such as inverted index, collaborative filtering, matrix decomposition, factorization, deep neural network learning, and the like.

A qualifier is represented and replaced by a series of words. After the substitution, a combination of subject sentence + existing exclusive content is generated. And finally, editing by combining the invention knowledge base to generate a scheme.

Generating the scheme, namely searching, recalling and sequencing and screening a target text from the invention of the hierarchical index and the reference text knowledge;

in some embodiments, the searching is to search various knowledge by using an extended search mode, to perform deformation and extension on elements, and to match one or a combination of the recalled invention information and the reference text;

in some embodiments, the recall ranking is performed by configuring a weight policy according to relevant resources, systems and component characteristics of the problem to be innovated, relevant fields, relevant users and selection preference constraints;

in some embodiments, the weight policy further includes a top concept, parity, and bottom instances of the input elements;

in some embodiments, the screening recommends one or a combination of the invention information, the reference text from the ranking results according to a weight strategy;

the recommended content includes multi-modal content such as images, voice, text, video, and the like.

Further, interactive operation is carried out after the invention content is recommended, and the interactive operation is used for marking, indexing, updating and feeding back the existing invention measures and the invention content; in particular, one alternative is shown in fig. 4, the steps comprising:

in step S402, manually editing the feature tag of the inventive measure, for example, summarizing the content of the inventive measure, and marking or indexing the summary;

optionally, a semantic label can be directly marked aiming at the structured reference text of the invention measure, for example, the karman vortex street effect in the scientific effect can be marked as bridge vibration. Or the label classification is carried out by utilizing a machine learning method;

in step S404, the feature labels of the inventive measures and inventive content are updated. The optional method comprises manual marking and automatic marking.

In some embodiments, a label can be a domain, a function, an object, an attribute, a parameter, a product, a component, and combinations thereof.

In some embodiments, the labeling method includes editing operations such as labeling, indexing, adding, deleting, modifying and checking of various label features;

in some embodiments, for unstructured reference text, it may be directly labeled; training the model of the labeled data by a machine learning method, and selecting an optimal model for automatic labeling of the reference text;

optionally, persistence of offline or real-time data is supported.

Optionally, the labeling result and the corresponding label are extracted, and the structured instance, the instance relationship and the attribute information are obtained and used as an index basis of the reference text.

In step S406, the model is iteratively updated, the input element-related features are referred to, the ranking is performed in combination with the weight policy, and the inventive content is screened.

The search recall is to search various knowledge by using an extended search mode, deform and expand elements, and recall one or a combined text in invention information and a reference text by a similar matching method;

optionally, the similarity matching method may select character matching or semantic matching of the upper concept, the parity, and the lower instance of the element;

in some embodiments, the weight policy includes different weight rule settings of the upper concept, the co-located instance, and the lower instance of the input element;

in some embodiments, the weighting policy further includes configuring weights according to resources, systems, component characteristics related to the problem to be created, and related fields, related users, and selection preference constraints;

optionally, the preference policy includes history, user selection weight, etc.;

in some embodiments, the screening target texts recommend one or more combinations of the invention contents from the sorting results according to a weight strategy;

optionally, the sorting and screening includes text matching or text classification methods, and iterative optimization. The classification method can select various methods such as association rule, matching, clustering, classification and the like;

optionally, the association rule method may select Apriori, FP-growth, graph calculation method; the classification method can select classification methods such as decision trees, naive Bayes, perceptrons, LR, SVM and the like; the clustering method can select K-means, density clustering, hierarchical clustering and other clustering; the matching method may select LDA, search (semantic search), CF model (user (applicant), item (product, component or arbitrary field)), LR model, FM (consider cross-relationship features), GBDT (do automatic feature screening and combination then used for LR model, etc.).

Also disclosed is an electronic device, fig. 5 shows a block diagram 1500 of the electronic device according to an embodiment of the disclosure, the electronic device 1500 comprising a memory 1510 and a processor 1520;

the memory 1510 is used for storing one or more computer instructions, wherein the one or more computer instructions are executed by the processor 1520 to implement the working steps of the inventive content recommendation tool in the above-mentioned embodiments.

As shown in the schematic structural diagram of the electronic apparatus shown in fig. 6, the electronic apparatus 1600 includes a Central Processing Unit (CPU)1601 that can execute various processes in the above-described embodiment shown in fig. 1 according to a program stored in a Read Only Memory (ROM)1602 or a program loaded from a storage section 1610 into a Random Access Memory (RAM) 1603. In the RAM1603, various programs and data necessary for the operation of the electronic apparatus 1600 are also stored. The CPU1601, ROM1602, and RAM1603 are connected to each other via a bus 1604. An input/output (I/O) interface 1605 is also connected to the bus 1604.

The following components are connected to the I/O interface 1605: the drive 1606 is connected to the I/O interface 1605 as necessary; removable media 1607 such as magnetic disks, optical disks, magneto-optical disks, semiconductor memories, and the like; an input portion 1608 including a keyboard, a mouse, and the like, installed on the driver 1606 as needed; an output portion 1609 including a display device such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and a speaker; a storage portion 1610 including a hard disk and the like; a computer program for facilitating reading is installed into the storage portion 1610 as necessary; a communication section 1611 of a network interface card such as a LAN card, modem, or the like. The communication section 1611 performs communication processing via a network such as the internet.

As another aspect, the present disclosure also provides a computer-readable storage medium, which may be the computer-readable storage medium included in the apparatus in the above-described embodiment; or it may be a separate computer readable storage medium not incorporated into the device. The computer readable storage medium stores one or more programs for use by one or more processors in performing the methods described in the present disclosure.

In particular, according to embodiments of the present disclosure, the method described above with reference to fig. 1 may be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program tangibly embodied on a medium readable thereby, the computer program comprising program code for performing the method of fig. 1. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 1611, and/or installed from the removable medium 1607.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowcharts or block diagrams may represent a module, a program segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units or modules described in the embodiments of the present disclosure may be implemented by software or hardware. The units or modules described may also be provided in a processor, and the names of the units or modules do not in some cases constitute a limitation of the units or modules themselves.

Thus, a computer-readable medium may take many forms, including but not limited to, a tangible storage medium, a carrier wave medium, or a physical transmission medium. The stable storage medium comprises: optical or magnetic disks, and other computer or similar devices, capable of implementing the system components described in the figures. Volatile storage media include dynamic memory, such as the main memory of a computer platform. Tangible transmission media include coaxial cables, copper cables, and fiber optics, including the wires that form a bus within a computer system. Carrier wave transmission media may convey electrical, electromagnetic, acoustic, or light wave signals, which may be generated by radio frequency or infrared data communication methods. Common computer-readable media include hard disks, floppy disks, magnetic tape, any other magnetic medium; CD-ROM, DVD-ROM, any other optical medium; punch cards, any other physical storage medium containing a pattern of holes; RAM, PROM, EPROM, FLASH-EPROM, any other memory chip or cartridge; a carrier wave transmitting data or instructions, a cable or connection transmitting a carrier wave, any other program code and/or data which can be read by a computer. These computer-readable media may take many forms, and include any type of program code for causing a processor to perform instructions, communicate one or more results, and/or the like.

Computer program code required for the operation of various portions of the present application may be written in any one or more programming languages for execution as a complete software package on a user's computer, as a stand-alone software package on a user's computer, as a partial software package on a remote computer, or as a complete software package on a remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any network, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service, such as a software as a service (SaaS).

Those skilled in the art will appreciate that various modifications and improvements may be made to the disclosure herein. For example, the different system components described above are implemented by hardware devices, but may also be implemented by software solutions only. For example: the system is installed on an existing server. Further, the location information disclosed herein may be provided via a firmware, firmware/software combination, firmware/hardware combination, or hardware/firmware/software combination.

The foregoing describes the present application and/or some other examples. It is to be understood that the above-described embodiments of the present invention are merely illustrative of or explaining the principles of the invention and are not to be construed as limiting the invention. The subject matter disclosed herein can be implemented in various forms and examples, and the present application can be applied to a wide variety of applications. All applications, modifications and variations that are claimed are within the scope of the application.

Claims

1. An inventive content recommendation tool, comprising: the system comprises a measure management module, a content recommendation module and an interaction module;

2. The inventive content recommendation tool of claim 1, wherein the inventive measures include rules of evolution in TRIZ theory, clipping methods, inventive principles, standard solutions, flow improvement measures, scientific effects, and the like;

the invention content comprises complete examples from patents, scientific and technical literatures and technical texts;

the complete example is a technical scheme with a specific implementation process, and is organized and stored in multi-modal forms such as texts, images, voice, videos and the like.

3. The inventive content recommendation tool as claimed in claim 1, wherein the feature tags comprise functions, attributes and parameters, objects, measure content, interaction records, and their hierarchical concepts, relationships, concept instances, explanatory explanation texts or combined features;

the combined feature is a combination of at least two feature tags;

4. The inventive content recommendation tool of claim 3, wherein said functionality is an abstracted functional operational concept hierarchy;

the objects comprise substances, energy, information concept systems and relations;

the attributes and the parameters are obtained by inducing respective concept systems of refined attributes, attribute parameters, engineering parameters, constraint variables, feature labels and the like;

the concept system comprises a concept hierarchy label, a concept relation, a concept instance, an instance relation and each item description explanation text;

5. The inventive content recommendation tool according to claim 1, wherein the inventive content features comprise various types of feature tag knowledge labeled from the inventive content, and further comprise extensive extension features of concepts, instances and relationships related to the inventive content.

6. The inventive content recommendation tool of claim 1, wherein said content recommendation module comprises ranking inventive content retrieval and recall, and further comprises similarity match recommendation and ranking;

and the sorting and the configuration of a weight strategy are used for screening the invention content.

7. The invention content recommendation tool according to claim 1, wherein the interaction module is responsible for editing various types of feature tags;

the editing comprises evaluation, indexing and storage;

8. The invention content recommendation tool according to claim 1 or 6, wherein the similarity matching, the selection of feature tag sets of the inventive measures and the inventive content, is implemented by using recommendation algorithms including collaborative filtering, matrix decomposition, factorization, deep neural network learning, and the like.

9. An electronic device comprising one or more memory devices and a processor, the memory devices being configured to store one or more programs, execution of the one or more programs by the one or more processors causing the one or more processors to perform the method of any one of claims 1-8.

The method can be realized by hardware, and can also be realized by hardware executing corresponding software;

the hardware or software includes one or more modules corresponding to the above-described methods.

10. A computer readable storage medium storing computer instructions, wherein the computer instructions, when read by a computer, perform the method of any one of claims 1 to 9, the instructions, when executed by a computing device, being operable to perform any one of the methods.