Public Opinion Association Method, Device, Readable Storage Medium and Electronic Device

Abstract

The present invention provides a public opinion association method, apparatus, readable storage medium, and electronic device thereof. The public opinion association method includes: obtaining public opinion text, obtaining a plurality of entities in the public opinion text, determining information tags corresponding to each entity in the plurality of entities for the public opinion text, and associating the public opinion text with the entity corresponding to the determined information tag, so that a user can obtain public opinion information through the information tag corresponding to the entity. By using this method, the relevant entities in the public opinion can be accurately determined, and the public opinion is associated with the entity and the information tag corresponding to the entity, avoiding the occurrence of the association event between some insignificant public opinion news and entities that have little relationship with it, so that the user can obtain the associated public opinion corresponding to the entity through the information tag and obtain key information through the public opinion.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a public opinion correlation method, device, readable storage medium and electronic device thereof. Background Art

[0002] In the public opinion section of the enterprise details page, users hope to learn about recent events and news about a company through this public opinion section. In order to enable users to timely understand the key information in the public opinion news corresponding to the enterprise, it is necessary to correspond the public opinion with key information to the enterprise, so that users can intuitively understand the positive information and risk information of the enterprise. However, in the Internet era, there are a large number of public opinion news, including positive and negative public opinion. The existing technology does not screen the key information of public opinion news, but simply identifies the entities in the public opinion through the model. In this way, not only there are errors in the correspondence between enterprises and public opinions, but also some irrelevant public opinion news will be associated with entities that have little relationship with them; in addition, when there are multiple entities in the public opinion news, the existing technology cannot accurately determine which of the multiple entities the semantic tendency expressed by the public opinion news corresponds to, so it cannot be accurately associated with the corresponding entity, resulting in low credibility of risk information and bringing many inconveniences to users. It can be seen that how to accurately associate public opinion with entities has become a technical problem that needs to be solved urgently. Summary of the invention

[0003] The present invention provides a public opinion correlation method, device, readable storage medium and electronic device thereof, which are used to overcome or alleviate the above-mentioned technical problems existing in the prior art.

[0004] According to one aspect of the present invention, a method for associating public opinion is provided, the method comprising:

[0005] Obtain public opinion text;

[0006] Obtain multiple entities in the public opinion text;

[0007] Determine the information tag corresponding to the public opinion text and each entity in the multiple entities;

[0008] Based on the determined information tag, the public opinion text is associated with the entity corresponding to the information tag, so that the user can obtain the public opinion information through the information tag corresponding to the entity.

[0009] Optionally, the obtaining of multiple entities in the public opinion text specifically includes:

[0010] Segment the public opinion text according to a preset method to obtain multiple sentences;

[0011] Tokenize each of the multiple statements according to the sentence composition method;

[0012] Determine the enterprise entities that appear in each statement based on the predicate verb of each statement in the tokenization result;

[0013] Take all the determined enterprise entities as the multiple entities in the public opinion text.

[0014] Optionally, the clause splitting the public opinion text into multiple statements according to the preset method specifically includes:

[0015] In response to the public opinion text being a Chinese text, clause split the public opinion text into multiple statements according to the final identifier;

[0016] In response to the public opinion text being an English text, clause split the public opinion text into multiple statements according to the combined method of preset labels and capital letters.

[0017] Optionally, after taking all the determined enterprise entities as the multiple entities in the public opinion text, it further includes:

[0018] Determine the frequency of each entity in the multiple entities appearing in the public opinion text from the first-person perspective;

[0019] Based on the frequency of each entity appearing in the public opinion text from the first-person perspective, determine the final entity related to the public opinion.

[0020] Optionally, the method further includes:

[0021] Use the collection of garbage corpus words to judge the quality of the public opinion text;

[0022] If it is determined that the public opinion text is garbage public opinion according to the quality of the public opinion text, perform filtering processing on the public opinion text;

[0023] If it is determined that the public opinion text is valid public opinion according to the quality of the public opinion text, perform the step of obtaining the multiple entities in the public opinion text.

[0024] Optionally, determining the information label corresponding to each entity in the multiple entities and the public opinion text specifically includes:

[0025] Determine the preset keywords corresponding to the multiple entities in the public opinion text respectively;

[0026] Determine the information label corresponding to each entity in the multiple entities and the public opinion text according to the preset keywords corresponding to the multiple entities respectively.

[0027] Optionally, determining the preset keywords corresponding to the multiple entities in the public opinion text specifically includes:

[0028] Determining the preset keywords corresponding to the multiple entities in the public opinion text according to the predicate verb and sentence semantics corresponding to each entity in the multiple entities.

[0029] According to another aspect of the present invention, there is provided a public opinion association device, and the device includes:

[0030] A first acquisition module, configured to acquire public opinion text;

[0031] A second acquisition module, configured to acquire multiple entities in the public opinion text;

[0032] A first determination module, configured to determine the information tags corresponding to each entity in the public opinion text and the multiple entities;

[0033] The association module is configured to associate the public opinion text with the entity corresponding to the information tag based on the determined information tag, so that a user can obtain public opinion information through the information tag corresponding to the entity.

[0034] According to still another aspect of the present invention, there is provided a computer-readable storage medium, on which a computer-executable program is stored, and the computer-executable program is run to implement any one of the public opinion association methods of the embodiments of the present invention.

[0035] According to still another aspect of the present invention, there is provided an electronic device, the electronic device includes a memory and a processor, the memory is used to store a computer-executable program, and the processor is used to run the computer-executable program to implement any one of the public opinion association methods of the embodiments of the present invention.

[0036] The present invention provides a public opinion association method. By using this method, relevant entities in the public opinion can be accurately determined, and the public opinion is associated with the entity and the information tag corresponding to the entity, avoiding the occurrence of events in which some irrelevant public opinion news is associated with entities that have little to do with it, so that a user can obtain the associated public opinion corresponding to the entity through the information tag and obtain key information through the public opinion. Description of the Drawings

[0037] Figure 1 It is a schematic flowchart of a public opinion association method according to an embodiment of the present invention;

[0038] Figure 2 It is a schematic flowchart of a public opinion association method according to an embodiment of the present invention;

[0039] Figure 3Schematic flowchart of a method for associating public opinions according to an embodiment of the present invention;

[0040] Figure 4 Schematic structural diagram of a device for associating public opinions according to an embodiment of the present invention;

[0041] Figure 5 Schematic structural diagram of an electronic device in an embodiment of the present invention. Detailed implementation manners

[0042] Next, exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments of the present invention. It should be understood that the present invention is not limited by the exemplary embodiments described herein.

[0043] It should be noted that: Unless otherwise specifically stated, the relative arrangements of components and steps, numerical expressions and values set forth in these embodiments do not limit the scope of the present invention.

[0044] Those skilled in the art can understand that terms such as "first", "second", etc. in the embodiments of the present invention are only used to distinguish different steps, devices or modules, etc., and neither represent any specific technical meaning nor indicate an inevitable logical order between them.

[0045] It should also be understood that in the embodiments of the present invention, "a plurality of" may refer to two or more, and "at least one" may refer to one, two or more.

[0046] It should also be understood that for any component, data or structure mentioned in the embodiments of the present invention, without clear limitation or contrary indication in the context, it can generally be understood as one or more.

[0047] In addition, the term "and / or" in the present invention is only a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in the present invention generally represents an "or" relationship between the associated objects before and after.

[0048] It should also be understood that the present invention emphasizes the differences between the embodiments, and the same or similar parts can be referred to each other. For the sake of brevity, they will not be described in detail one by one.

[0049] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0050] The following description of at least one exemplary embodiment is merely illustrative and in no way restrictive of the present invention and its application or use.

[0051] Techniques, methods, and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the techniques, methods, and devices should be considered as part of the specification.

[0052] It should be noted that like reference numerals and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.

[0053] Embodiments of the present invention can be applied to electronic devices such as terminal devices, computer systems, servers, etc., which can operate with many other general or special computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments, and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, servers, etc. include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, minicomputer systems, mainframe computer systems, and distributed cloud computing technology environments including any of the above systems, and so on.

[0054] Terminal devices, computer systems, servers, and other electronic devices can be described in the general context of computer system-executable instructions, such as program modules, executed by a computer system. Generally, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. The computer system / server can be implemented in a distributed cloud computing environment where tasks are performed by remote processing devices linked through a communication network. In a distributed cloud computing environment, program modules can be located on local or remote computing system storage media including storage devices.

[0055] Exemplary method

[0056] Figure 1 is a schematic flowchart of a public opinion association method provided by an exemplary embodiment of the present invention; as Figure 1 shown, the public opinion association method includes the following steps:

[0057] Step 101, obtain public opinion text;

[0058] In this embodiment, the public opinion text can be obtained from channels that generate public opinion such as various news media, for example, events or news issued by major news websites and news media accounts. It can be understood that the above description is only exemplary, and this embodiment does not make any limitations thereto.

[0059] In some alternative embodiments, after obtaining the public opinion text, the following further includes:

[0060] Use the set of garbage corpus words to judge the quality of public opinion texts;

[0061] If it is determined that the public opinion text is garbage public opinion according to the quality of the public opinion text, filter the public opinion text;

[0062] If it is determined that the public opinion text is valid public opinion according to the quality of the public opinion text, perform the step of obtaining multiple entities in the public opinion text.

[0063] When it is determined that the public opinion text is garbage public opinion, filtering the public opinion text can effectively ensure the quality of the public opinion text. It can be understood that the above description is only exemplary, and this embodiment does not make any limitation thereto.

[0064] In a specific example, the set of garbage corpus words can be pre-configured. If a garbage corpus word in the set of garbage corpus words appears in the title or abstract of the public opinion text, it is determined that the quality of the public opinion text is low quality, and the public opinion text is determined to be garbage public opinion, and then the public opinion text is filtered. For example, if a garbage word such as "giving out red envelopes" appears in the title of the public opinion text, the public opinion text is not processed. If no garbage corpus word in the set of garbage corpus words appears in the title or abstract of the public opinion text, it is determined that the quality of the public opinion text is high quality, and the public opinion text is determined to be valid public opinion, and then step 102 is performed on the public opinion text. It can be understood that the above description is only exemplary, and this embodiment does not make any limitation thereto.

[0065] In a specific example, the public opinion text can specifically be of the infringement litigation type. For example, "Plaintiff Company A is the patentee of a utility model patent. The plaintiff found that Product X manufactured by Defendant Company B unauthorizedly used its patent and sold the infringing products to customers such as Defendant Company C, infringing its patent rights. Court trial conclusion: Plaintiff Company A won the lawsuit, and Company B and Company C were ordered to pay 5 million in damages for infringement..."

[0066] Step 102: Obtain multiple entities in the public opinion text;

[0067] In this embodiment, before step 102, it also includes setting a keyword library and screening public opinion texts according to keywords. Specifically, the keywords included in the keyword library are: credit, finance, management, operation, litigation, monopoly, infringement, environmental protection, contract disputes, customer complaints, rights protection, supervision, public criticism, market entry ban, products, recalls, false propaganda, project notifications, terminations, accidents, illegal and irregularities, case investigations, decline in market valuation, margin calls, explosions, acquisitions, pledges, investment and financing, bidding, patents, blockchain, etc.;

[0068] In some alternative embodiments, such as Figure 2As shown, the obtaining of multiple entities in the public opinion text specifically includes:

[0069] Step 201: Segment the public opinion text according to a preset method to obtain a plurality of sentences;

[0070] Step 202: segment each of the multiple sentences according to the sentence formation method;

[0071] Step 203: determining the enterprise entity appearing in each sentence according to the predicate verb of each sentence in the word segmentation result;

[0072] Step 204: All determined corporate entities are taken as multiple entities in the public opinion text.

[0073] Specifically, in this embodiment, the public opinion text is divided into sentences according to a preset method to obtain multiple sentences, specifically including:

[0074] In response to the public opinion text being a Chinese text, the public opinion text is divided into sentences according to the final identifier to obtain a plurality of sentences;

[0075] In response to the public opinion text being an English text, the public opinion text is segmented into sentences according to a combination of preset labels and capital letters to obtain a plurality of sentences.

[0076] In a specific example, if the public opinion text is a Chinese text, the public opinion text is divided into sentences according to the end of the sentence, i.e., a period, to obtain multiple sentences; if the public opinion text is an English text, the public opinion text is divided into sentences according to the position of the end of the English sentence, i.e., a period, and the beginning of the next capital letter to obtain multiple sentences.

[0077] Specifically, in this embodiment, after all the determined enterprise entities are taken as multiple entities in the public opinion text, the method further includes:

[0078] Determine the frequency of each entity in the public opinion text appearing in the public opinion text from the first person perspective;

[0079] Based on the frequency with which each entity appears in the public opinion text from the first person's perspective, a final entity related to the public opinion is determined.

[0080] Thus, the relevance between the entity and the public opinion text can be accurately determined by the frequency of the entity appearing in the public opinion text or the frequency of the entity appearing in the public opinion text from the first person perspective. In addition, the final entity can be accurately determined by the relevance between the entity and the public opinion text. It can be understood that the above description is only exemplary and this embodiment does not make any limitation to this.

[0081] In a specific example, the more frequently an entity appears in a public opinion text, the stronger the correlation between the entity and the public opinion text. The more frequently an entity appears in a public opinion text from a first-person perspective, the stronger the correlation between the entity and the public opinion text. Among them, the correlation can be characterized by correlation characterization data. When determining the final entity, the entity with the strongest correlation with the public opinion text is determined as the final entity. For example, the public opinion text is "Tencent and a certain company have a lawsuit about a certain game, and Tencent wins." Tencent is in the first-person perspective and appears twice, so the public opinion text is more correlated with Tencent. It can be understood that the above description is only exemplary, and this embodiment does not impose any limitation on this.

[0082] In some optional embodiments, after obtaining multiple entities in the public opinion text, the method further includes: using regular expressions to perform entity matching on the public opinion text to obtain matching entities in the public opinion text; if the matching entity in the public opinion text is the same as the entity in the obtained public opinion text, then the entity is determined as the final entity of the public opinion text. Thereby, using regular expressions to perform entity matching on the public opinion text can further improve the accuracy of obtaining entities in the public opinion text. It can be understood that the above description is only exemplary and this embodiment does not impose any limitation on this.

[0083] In a specific example, most of the problems can be solved by obtaining entities through word segmentation and sentence segmentation, but for a small number of situations that cannot be handled and are easily missed during word segmentation, these situations can be further processed. For example, when the public opinion text is "According to Tianyancha data display", then Tianyancha's sentiment in the text is neutral, and in most cases it is neutral, but if the public opinion text is "Tianyancha data shows that AA was recently interviewed and the app was removed from the shelves", some extremely negative information appears near Tianyancha, which is likely to have a negative impact on the entity. Using regular expressions, such as *entity*data display / report, etc., the sentiment polarity of such entities can be corrected to improve accuracy. It can be understood that the above description is only exemplary, and this embodiment does not impose any limitation on this.

[0084] In a specific example, the public opinion text is such as "Plaintiff Company A is the patent owner of a utility model patent. The plaintiff discovered that the defendant Company B manufactured product X that used its patent without authorization, and sold the infringing product to the defendant Company C and other customers, infringing its patent rights. The court concluded that the plaintiff Company A won the case, and Company B and Company C were ordered to pay 5 million yuan for infringement..." The entities obtained according to step 102 include: "Company A, Company B, Company C".

[0085] Step 103: determining the information tag corresponding to the public opinion text and each of the multiple entities;

[0086] In this embodiment, as Figure 3 shown, determining the information tags corresponding to each entity in the multiple entities for the public opinion text specifically includes:

[0087] Step 301, determining the preset keywords corresponding to the multiple entities in the public opinion text respectively;

[0088] Step 302, determining the information tags corresponding to each entity in the multiple entities for the public opinion text according to the preset keywords corresponding to the multiple entities respectively.

[0089] In some optional embodiments, determining the preset keywords corresponding to the multiple entities in the public opinion text respectively specifically includes: determining the preset keywords corresponding to the multiple entities in the public opinion text according to the predicate verbs and sentence semantics corresponding to each entity in the multiple entities.

[0090] In a specific example, the preset keywords specifically include: credit, finance, management, operation, litigation, monopoly, infringement, environmental protection, contract disputes, customer complaints, rights protection, supervision, public criticism, market access ban, products, recalls, false propaganda, project notifications, terminations, accidents, illegal and irregular acts, case-filing investigations, decline in market valuation, margin calls, explosions, acquisitions, pledges, investment and financing, bidding, patents, blockchain; among which, the information tags are constructed according to the keywords; for example, the information tags include: credit-related, finance-related, management-related, operation-related, litigation-related, product-related, market-related, intellectual property-related, technology-related, etc.

[0091] In a specific example, the public opinion text is, for example, "Plaintiff Company A is the patentee of a utility model patent. The plaintiff found that Product X manufactured by Defendant Company B used its patent without permission and sold the infringing products to customers such as Defendant Company C, infringing its patent rights. The court's judgment conclusion: Plaintiff Company A won the lawsuit, and Company B and Company C were ordered to pay 5 million yuan in damages for infringement...". According to Step 103, the preset keywords corresponding to the multiple entities (Company A, Company B, Company C) in the public opinion text are determined as: winning the lawsuit, infringement, infringement; according to the preset keywords corresponding to the three entities of Company A, Company B, and Company C respectively, the information tags corresponding to each of the 3 entities for the public opinion text are all determined as intellectual property-related or litigation-related.

[0092] Step 104, associating the public opinion text with the entity corresponding to the information tag based on the determined information tag.

[0093] In this embodiment, in Step 104, the information tag further includes subclass tags; the subclass tags specifically include: positive public opinion, neutral public opinion, negative public opinion;

[0094] Among them, the specific process of associating the public opinion text with the entity corresponding to the information label further includes: determining the information tendency of each entity corresponding to the public opinion text according to the keywords corresponding to each entity among multiple entities, and associating the public opinion text with the subclass label corresponding to the information label according to the determined information tendency.

[0095] In a specific example, the public opinion text is, for example, "Plaintiff Company A is the patentee of a utility model patent. The plaintiff found that Product X manufactured by Defendant Company B unauthorizedly used its patent and sold the infringing products to customers such as Defendant Company C, infringing its patent rights. Court trial conclusion: Plaintiff Company A won the lawsuit, and Company B and Company C were ordered to pay 5 million in damages for infringement..." According to step 103, the preset keywords corresponding to the multiple entities (Company A, Company B, Company C) in the public opinion text are determined as: winning the lawsuit, infringement, infringement; according to the preset keywords corresponding to the three entities of Company A, Company B, and Company C respectively, it is determined that the information labels corresponding to each entity in the public opinion text are all related to intellectual property or litigation; according to the keywords corresponding to the three entities, the information tendency of each entity corresponding to the public opinion text is determined. For example, the keyword corresponding to Company A is winning the lawsuit, so it is determined that the information tendency of this public opinion text towards Company A is positive, and the public opinion text is associated with the positive public opinion corresponding to the information label. The keywords corresponding to Company B and Company C are both infringement, so it is determined that the information tendencies of this public opinion text towards Company B and Company C are both negative, and the public opinion text is associated with the negative public opinion corresponding to the information label.

[0096] By associating the public opinion text with the entity corresponding to the information label, users can obtain public opinion information through the information label corresponding to the entity, and obtain relevant public opinion information through the sub-labels under the information label, and can intuitively understand the current positive or risk information of the enterprise entity.

[0097] Using this method can accurately determine the relevant entities in the public opinion, and associate the public opinion with the entity and the information label corresponding to the entity, avoiding the occurrence of the association of some irrelevant public opinion news with entities that have little to do with it, so that users can obtain the associated public opinion corresponding to the entity through the information label and obtain key information through the public opinion.

[0098] Exemplary device

[0099] Figure 4 This is a schematic structural diagram of a public opinion association device according to an embodiment of the present invention; as Figure 4 shown, the public opinion association device 400 includes:

[0100] A first acquisition module 401, configured to acquire a public opinion text;

[0101] The second acquisition module 402 is configured to acquire multiple entities in the public opinion text;

[0102] The first determination module 403 is configured to determine information tags corresponding to each entity in the public opinion text and the multiple entities;

[0103] The association module 404 is configured to associate the public opinion text with the entity corresponding to the information tag based on the determined information tag, so that the user can obtain public opinion information through the information tag corresponding to the entity.

[0104] Optionally, in this embodiment, the second acquisition module specifically includes a sentence splitting unit, a word segmentation unit, and a first determination unit. Among them, the sentence splitting unit is configured to split the public opinion text into multiple sentences according to a preset method; the word segmentation unit is configured to perform word segmentation on each of the multiple sentences according to the sentence composition method; the first determination unit is configured to determine the enterprise entities appearing in each sentence according to the predicate verb in the word segmentation result of each sentence; and is further configured to use all the determined enterprise entities as the multiple entities in the public opinion text.

[0105] Optionally, in this embodiment, the sentence splitting unit is specifically configured to, in response to the public opinion text being a Chinese text, split the public opinion text into multiple sentences according to the final identifier; and is further specifically configured to, in response to the public opinion text being an English text, split the public opinion text into multiple sentences according to a combination method of a preset label and a capital letter.

[0106] Optionally, in this embodiment, the apparatus further includes a second determination module, configured to determine the frequency of each entity in the multiple entities appearing from the first-person perspective in the public opinion text; and based on the frequency of each entity appearing from the first-person perspective in the public opinion text, determine the final entity related to the public opinion.

[0107] Optionally, in this embodiment, the apparatus further includes a first judgment module, configured to use a garbage corpus word set to judge the quality of the public opinion text; and further configured to, if it is determined that the public opinion text is garbage public opinion according to the quality of the public opinion text, perform filtering processing on the public opinion text; and further configured to, if it is determined that the public opinion text is valid public opinion according to the quality of the public opinion text, perform the step of acquiring multiple entities in the public opinion text.

[0108] Optionally, in this embodiment, the first determination module specifically further includes a second determination unit and a third determination unit. The second determination unit is configured to determine preset keywords corresponding to the multiple entities in the public opinion text; the third determination unit is configured to determine information tags corresponding to each entity in the public opinion text and the multiple entities according to the preset keywords corresponding to the multiple entities respectively.

[0109] Optionally, in this embodiment, the first determination unit is specifically configured to determine the preset keywords corresponding to the multiple entities in the public opinion text according to the predicate verb and sentence semantics corresponding to each entity in the multiple entities.

[0110] Exemplary electronic device

[0111] Figure 5 It is the structure of an electronic device provided by an exemplary embodiment of the present invention. The electronic device may be any one or both of the first device and the second device, or a stand-alone device independent of them, and the stand-alone device may communicate with the first device and the second device to receive the input signals collected from them. Figure 5 The block diagram of the electronic device according to an embodiment of the present invention is illustrated. As Figure 5 shown, the electronic device 500 includes one or more processors 501 and a memory 502.

[0112] The processor 501 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0113] The memory 502 may include one or more computer programs, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory, etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage media, and the processor 501 may run the program instructions to implement the public opinion association method of various embodiments of the present invention described above and / or other desired functions. In one example, the electronic device may further include: an input device 503 and an output device 504, and these components are interconnected through a bus system and / or other forms of connection mechanisms (not shown).

[0114] In addition, the input device 503 may further include, for example, a keyboard, a mouse, and so on.

[0115] The output device 504 may output various information to the outside. The output device 504 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, and so on.

[0116] Of course, for simplicity, Figure 5Only some of the components related to the present invention in the electronic device are shown, and components such as buses, input / output interfaces, etc. are omitted. In addition, according to specific application scenarios, the electronic device may further include any other appropriate components.

[0117] Exemplary computer program product and computer-readable storage medium

[0118] In addition to the above methods and devices, an embodiment of the present invention may also be a computer program product, which includes computer program instructions that, when run by a processor, cause the processor to execute the steps in the public opinion association method according to various embodiments of the present invention described in the above "Exemplary Method" section of this specification.

[0119] The computer program product may be written in any combination of one or more programming languages for programming code to perform the operations of the embodiments of the present invention. The programming languages include object-oriented programming languages such as Java, C++, etc., and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user device, executed as an independent software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0120] In addition, an embodiment of the present invention may also be a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are run by a processor, the processor is caused to execute the steps in the public opinion association method according to various embodiments of the present invention described in the above "Exemplary Method" section of this specification.

[0121] The computer-readable storage medium may adopt any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination of the above. More specific examples (non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0122] The basic principles of the present invention have been described in conjunction with specific embodiments. However, it should be noted that the advantages, benefits, effects, etc. mentioned in the present invention are only examples and not limitations. It cannot be considered that these advantages, benefits, effects, etc. are essential for each embodiment of the present invention. Additionally, the specific details disclosed above are only for illustrative and facilitating understanding purposes, not limitations. These details do not limit the present invention to necessarily implementing with the above specific details.

[0123] Each embodiment in this specification is described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. For the same or similar parts among the embodiments, reference can be made to each other. For system embodiments, since they basically correspond to method embodiments, the description is relatively simple. For related parts, reference can be made to the partial description of the method embodiments.

[0124] The block diagrams of the devices, apparatuses, equipment, and systems involved in the present invention are only illustrative examples and do not intend to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any way. Words such as "including", "comprising", "having", etc. are open-ended terms, meaning "including but not limited to", and can be used interchangeably with each other. The words "or" and "and" used here refer to the word "and / or", and can be used interchangeably with each other, unless the context clearly indicates otherwise. The word "such as" used here refers to the phrase "such as but not limited to", and can be used interchangeably with each other.

[0125] The methods and apparatuses of the present invention can be implemented in many ways. For example, the methods and apparatuses of the present invention can be implemented through software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of the steps for the methods is only for illustration purposes. The steps of the methods of the present invention are not limited to the above specifically described order, unless otherwise specifically stated in other ways. Additionally, in some embodiments, the present invention can also be implemented as a program recorded in a recording medium, and these programs include machine-readable instructions for implementing the methods according to the present invention. Therefore, the present invention also covers the recording medium storing the programs for executing the methods according to the present invention.

[0126] It should also be noted that in the devices, equipment and methods of the present invention, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations shall be regarded as equivalent solutions of the present invention. The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the present invention. Therefore, the present invention is not intended to be limited to the aspects shown herein, but rather to the broadest scope consistent with the principles and novel features disclosed herein.

[0127] The above description has been given for purposes of illustration and description. In addition, this description is not intended to limit the embodiments of the present invention to the forms disclosed herein. Although several example aspects and embodiments have been discussed above, those skilled in the art will recognize some of their variations, modifications, alterations, additions, and subcombinations.

Claims

1. A public opinion association method, characterized in that, The method comprises: Obtain public opinion text; Obtain multiple entities in the public opinion text; Determine the information tag corresponding to the public opinion text and each entity in the multiple entities; Based on the determined information tag, the public opinion text is associated with the entity corresponding to the information tag, so that the user can obtain the public opinion information through the information tag corresponding to the entity; After obtaining the multiple entities in the public opinion text, the method further includes: Using regular expressions, performing entity matching on the public opinion text to obtain matching entities in the public opinion text; If the matched entity in the public opinion text is the same as the entity in the acquired public opinion text, the entity is determined as the final entity of the public opinion text; The information label also includes sub-category labels; the sub-category labels specifically include: positive public opinion, neutral public opinion, and negative public opinion; Wherein, associating the public opinion text with the entity corresponding to the information tag specifically includes: The information tendency corresponding to each entity in the public opinion text is determined according to the keywords corresponding to each entity in the multiple entities, and the public opinion text is associated with the subclass label corresponding to the information label according to the determined information tendency.

2. The method according to claim 1, characterized in that, The obtaining of multiple entities in the public opinion text specifically includes: Segment the public opinion text according to a preset method to obtain multiple sentences; Segmenting each of the plurality of sentences according to a sentence formation method; Determine the enterprise entity appearing in each sentence according to the predicate verb of each sentence in the word segmentation result; All determined corporate entities are regarded as multiple entities in the public opinion text.

3. The method according to claim 2, characterized in that, The step of dividing the public opinion text into sentences according to a preset method to obtain a plurality of sentences specifically includes: In response to the public opinion text being a Chinese text, the public opinion text is divided into sentences according to the final identifier to obtain a plurality of sentences; In response to the public opinion text being an English text, the public opinion text is segmented into sentences according to a combination of preset labels and capital letters to obtain a plurality of sentences.

4. The method according to claim 2, characterized in that, After taking all the determined corporate entities as multiple entities in the public opinion text, the method further includes: Determine the frequency of each entity in the plurality of entities appearing in the public opinion text from a first-person perspective; Based on the frequency of each entity appearing in the public opinion text from a first-person perspective, a final entity related to the public opinion is determined.

5. The method according to claim 1, characterized in that, The method further comprises: Using the junk corpus word set to judge the quality of the public opinion text; If the public opinion text is determined to be junk public opinion based on the quality of the public opinion text, filtering the public opinion text; If the public opinion text is determined to be valid public opinion based on the quality of the public opinion text, the step of obtaining multiple entities in the public opinion text is performed.

6. The method according to claim 2, characterized in that, Determining the information tag corresponding to the public opinion text and each of the multiple entities specifically includes: Determining preset keywords in the public opinion text corresponding to the multiple entities respectively; The public opinion text and information tags corresponding to each of the multiple entities are determined according to preset keywords respectively corresponding to the multiple entities.

7. The method according to claim 6, characterized in that, Determining the preset keywords corresponding to the multiple entities in the public opinion text specifically includes: Determining the preset keywords corresponding to the multiple entities in the public opinion text according to the predicate verb and sentence semantics corresponding to each entity in the multiple entities.

8. A public opinion association device, characterized in that, The device includes: A first acquisition module for acquiring public opinion text; A second acquisition module for acquiring multiple entities in the public opinion text; A first determination module for determining the information tags corresponding to each entity in the public opinion text and the multiple entities; An association module for associating the public opinion text with the entity corresponding to the information tag based on the determined information tag, so that the user can obtain public opinion information through the information tag corresponding to the entity; Wherein, the second acquisition module is further configured to: After acquiring multiple entities in the public opinion text, use a regular expression to perform entity matching on the public opinion text to obtain the matching entities in the public opinion text; If the matching entity in the public opinion text is the same as the entity acquired in the public opinion text, then determine the entity as the final entity of the public opinion text; Wherein, the information tag further includes a subclass tag; the subclass tag specifically includes: positive public opinion, neutral public opinion, negative public opinion; Wherein, associating the public opinion text with the entity corresponding to the information tag specifically further includes: Determining the information tendency corresponding to each entity in the public opinion text according to the keyword corresponding to each entity in the multiple entities, and associating the public opinion text with the subclass tag corresponding to the information tag according to the determined information tendency.

9. A computer-readable storage medium, characterized in that, A computer-readable storage medium stores a computer-executable program, and the computer-executable program is run to implement the method according to any one of claims 1-7.

10. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory is used to store a computer-executable program, and the processor is used to run the computer-executable program to implement the method according to any one of claims 1-7.

Images