CN112256852A - Scenic spot comment data processing method and device, electronic equipment and storage medium - Google Patents
Scenic spot comment data processing method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112256852A CN112256852A CN202011176089.9A CN202011176089A CN112256852A CN 112256852 A CN112256852 A CN 112256852A CN 202011176089 A CN202011176089 A CN 202011176089A CN 112256852 A CN112256852 A CN 112256852A
- Authority
- CN
- China
- Prior art keywords
- comment
- keyword
- current
- determining
- historical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 21
- 238000000034 method Methods 0.000 claims abstract description 16
- 238000012552 review Methods 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 11
- 230000011218 segmentation Effects 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 2
- 238000011156 evaluation Methods 0.000 abstract description 8
- 230000000694 effects Effects 0.000 abstract description 4
- 230000008859 change Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 2
- 230000007935 neutral effect Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3334—Selection or weighting of terms from queries, including natural language queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0282—Rating or review of business operators or products
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/14—Travel agencies
Abstract
The embodiment of the invention discloses a scenic spot comment data processing method and device, electronic equipment and a storage medium. The method comprises the following steps: determining a current comment keyword in current user comment data; determining a current keyword type to which the current comment keyword belongs from at least two candidate keyword types; determining reply information to the user comment data according to the current user comment data and the overall comment result of the current keyword type; and determining the overall comment result of the current keyword type according to historical user comment data. By operating the technical scheme provided by the embodiment of the invention, the problem that the scenic spot information can be acquired in a one-sidedness and ambiguity manner because the tourists cannot actively know the information corresponding to the scenic spot mainly by acquiring the evaluation of other tourists on the scenic spot from the evaluation area corresponding to the scenic spot can be solved, and the effect of improving the accuracy and pertinence of the acquisition of the scenic spot information is realized.
Description
Technical Field
The embodiment of the invention relates to computer technology, in particular to a scenic spot comment data processing method and device, electronic equipment and a storage medium.
Background
With the development of vehicles and the improvement of living standard, more and more people take tourism as a travel choice, and the public praise of scenic spots becomes an important reference for tourists to select a tourist destination.
In the prior art, visitors cannot actively know information corresponding to scenic spots mainly by obtaining evaluations of other visitors on the scenic spots from evaluation areas corresponding to the scenic spots, so that the scenic spot information is obtained in a one-sidedness and ambiguity manner.
Disclosure of Invention
The embodiment of the invention provides a scenic spot comment data processing method and device, electronic equipment and a storage medium, and aims to improve accuracy and pertinence of scenic spot information acquisition.
In a first aspect, an embodiment of the present invention provides a scenic spot review data processing method, where the method includes:
determining a current comment keyword in current user comment data;
determining a current keyword type to which the current comment keyword belongs from at least two candidate keyword types;
determining reply information to the user comment data according to the current user comment data and the overall comment result of the current keyword type; and determining the overall comment result of the current keyword type according to historical user comment data.
In a second aspect, an embodiment of the present invention further provides a scenic spot comment data processing apparatus, where the apparatus includes:
the current comment keyword determining module is used for determining a current comment keyword in the current user comment data;
the current keyword type determining module is used for determining a current keyword type to which the current comment keyword belongs from at least two candidate keyword types;
the reply information determining module is used for determining reply information of the user comment data according to the current user comment data and the overall comment result of the current keyword type; and determining the overall comment result of the current keyword type according to historical user comment data.
In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the scenic comment data processing method as described above.
In a fourth aspect, the embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the scenic spot comment data processing method as described above.
The embodiment of the invention determines the current comment keywords in the current user comment data; determining a current keyword type to which the current comment keyword belongs from at least two candidate keyword types; determining reply information to the user comment data according to the current user comment data and the overall comment result of the current keyword type; and determining the overall comment result of the current keyword type according to historical user comment data. The problem that visitors cannot actively know information corresponding to scenic spots by mainly obtaining evaluations of other visitors on the scenic spots from the appraisal areas corresponding to the scenic spots is solved, so that the scenic spot information is obtained in a one-sided and fuzzy manner, and the effect of improving the accuracy and pertinence of obtaining the scenic spot information is achieved.
Drawings
Fig. 1 is a flowchart of a scenic spot review data processing method according to an embodiment of the present invention;
fig. 2 is a flowchart of a scenic spot review data processing method according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a scenic spot review data processing apparatus according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a scenic spot comment data processing method according to an embodiment of the present invention, where the method is applicable to a case where a user replies to a comment of a scenic spot, and the method may be executed by a scenic spot comment data processing apparatus provided in an embodiment of the present invention, and the apparatus may be implemented by software and/or hardware. Referring to fig. 1, the scenic spot review data processing method provided by this embodiment includes:
and step 110, determining the current comment keywords in the current user comment data.
The current user comment data is comment data issued by a user aiming at a scenic spot, and can be text data or voice or picture data; the acquisition mode may be obtained from the scenic region review area, which is not limited in this embodiment. The current comment keyword is a word having practical meaning in the current comment, for example, the comment is "the price of the scenic spot is very substantial", and then "scenic spot", "price of the ticket" and "substantial" may be keywords.
The keyword may be obtained by performing data cleaning and filtering on the current user comment data through a button tool, and then performing word segmentation, which is not limited in this embodiment.
In this embodiment, optionally, determining the current comment keyword in the current user comment data includes:
filtering the current user comment data according to a pre-constructed stop word list;
and determining the current comment keywords by performing word segmentation processing on the filtered current user comment data.
The stop word list is a list formed by some characters or words which are automatically filtered when the text data is processed, and can be summarized and generalized aiming at commonly used irregular characters and nonsense words in advance to form the stop word list.
Filtering the current user comment data in a text form through a stop word list, segmenting words of the filtered current user comment data, and taking the words obtained after segmentation as keywords. The word segmentation mode may be a jieba word segmentation, which is not limited in this embodiment. The current comment data are filtered by stopping the word list, so that the efficiency and the accuracy of obtaining the current comment keywords are improved.
And step 120, determining a current keyword type to which the current comment keyword belongs from at least two candidate keyword types.
The candidate keyword type is a type to which the keyword may belong, such as price, service, environment, security, transportation, toilet, facility, dining, informatization, item, and the like. Illustratively, when the current keyword is "offer", "cost performance", "loss", or the like, the current keyword type to which the current comment keyword belongs is "price".
According to the identification of the current comment keyword, the current comment keyword can be stored into a file corresponding to the type of the current keyword according to the category of the keyword.
The overall comment result of the current keyword type is an overall comment result of the current keyword type, and the comment result may be presented in a manner of score or evaluation, which is not limited in this embodiment. Illustratively, for each keyword type, a corresponding overall comment result is obtained, for example, the overall comment result of the price is 95 points, the overall comment result of the service is 90 points, and the like. And the overall comment result of the current keyword type is determined according to the comment data of the historical user on the keyword type.
According to the current user comment data and the overall comment result of the current keyword type, determining reply information of the user comment data together, wherein the reply information is reply to the user comment data. For example, if the current comment data of the user is 'how a restaurant is in a scenic spot', and the corresponding current keyword type is determined to be the restaurant according to the current comment data of the user, the reply information to the comment data of the user can be determined by combining the overall comment result of the restaurant type and the specific content of the current keyword. For example, the reply message is "the restaurant score in this scenic spot is 95 points", and the like.
The reply information may be obtained by constructing a question-and-answer knowledge graph in advance in a scenic spot unit and storing the question-and-answer knowledge graph in a database, such as a neo4j database, converting a question of a user into an inquiry statement when the user makes a comment, so as to access the database to inquire the constructed knowledge graph in advance, and obtaining the reply information by combining an overall comment result of a current keyword type, thereby improving the efficiency and accuracy of obtaining the question-and-answer information.
In this embodiment, optionally, determining reply information to the user comment data according to the current user comment data and the overall comment result of the current keyword type includes:
acquiring a keyword code of the current comment keyword;
inputting the keyword codes into a question-answering model constructed in advance;
determining reply information to the user comment data according to the output result of the question-answer model; wherein the question-answering model is trained based on a sequence2sequence network structure.
The keyword codes are codes associated with the keywords in advance, the specific coding mode may be to collect common comments in advance, and then the comment keywords are coded through an embedding layer, the specific coding mode may be to sort according to the frequency of occurrence of the keywords, and the higher the frequency of occurrence, the earlier the sequence is, the coding mode is sequentially coded according to the sort, which is not limited in this embodiment.
And determining corresponding answers aiming at the comments, and training the comments and the answers through an encoder and a decoder based on a sequence2sequence model to generate a question-answer model. The encoder is used for understanding the comments and converting the comments into content vectors, and the decoder is used for decoding the vectors of the understood comments to obtain output.
After the current user comment data is obtained, the keywords in the current user comment are correspondingly coded and input to the question and answer model to obtain the reply information, so that the obtaining efficiency and accuracy of the question and answer information are improved.
According to the technical scheme provided by the embodiment, the current comment keywords in the current user comment data are determined; determining a current keyword type to which the current comment keyword belongs from at least two candidate keyword types; determining reply information to the user comment data according to the current user comment data and the overall comment result of the current keyword type; and determining the overall comment result of the current keyword type according to historical user comment data. The problem that visitors cannot actively know information corresponding to scenic spots by mainly obtaining evaluations of other visitors on the scenic spots from the appraisal areas corresponding to the scenic spots is solved, so that the scenic spot information is obtained in a one-sided and fuzzy manner, and the effect of improving the accuracy and pertinence of obtaining the scenic spot information is achieved.
Example two
Fig. 2 is a flowchart of a scenic spot review data processing method according to a second embodiment of the present invention, and the present technical solution is supplementary explained with respect to a process of determining a whole review result of a current keyword type. Compared with the scheme, the scheme is specifically optimized in that the step of determining the overall comment result of the current keyword type comprises the following steps:
determining historical comment keywords in historical user comment data;
determining a history keyword type to which the history comment keyword belongs from at least two candidate keyword types;
and determining the overall comment result of the current keyword type according to the part of speech of the historical keywords and the type of the historical keywords of the historical comment keywords. Specifically, a flowchart of the user scenic spot comment data processing method is shown in fig. 2:
and step 210, determining historical comment keywords in the historical user comment data.
The historical user comment data maintains historical comment data issued by a user aiming at scenic spots, and can be text data or voice or picture data; the obtaining mode may be obtained from the scenic spot review area, and the obtaining mode may be all the historical reviews, or may also be obtained from the historical reviews at a specific time as required, for example, the historical reviews in 2019, and the like, which is not limited in this embodiment.
The candidate keyword type is a type to which the history keyword may belong, such as price, service, environment, security, transportation, toilet, facility, dining, informatization, item, and the like.
The parts of speech of the historical keywords can comprise positive, negative and neutral, under a single historical comment keyword type, the overall comment result of the historical keyword type is determined according to the parts of speech of all the historical keywords, and the overall comment result of the historical keyword type is used as the overall comment result of the current keyword type. Illustratively, all historical comment keywords of the restaurant type are obtained from historical user comment data, the overall comment result of the restaurant type is determined according to the parts of speech of the historical comment keywords of the restaurant type, and if the number of the overall comment results is 95, the overall comment result of the current keyword type is 95 when the current keyword type is the restaurant.
The occurrence frequency of the historical comment keywords in each historical keyword type and the word parts of the historical comment keywords can be counted, and a positive and negative high-frequency keyword set of each keyword type in each scenic spot is generated for displaying.
In this embodiment, optionally, determining the overall comment result of the current keyword type according to the keyword part of speech of the historical comment keyword and the historical keyword type includes:
determining a historical comment score of the historical comment keyword according to the part of speech of the historical keyword;
and determining the overall comment score of the historical keyword type according to the historical comment score and a historical keyword set corresponding to the historical keyword type, and taking the overall comment score as the overall comment result of the current keyword type.
The historical comment score is a score corresponding to the historical comment keyword, and illustratively, the score of the positive keyword is 1, the score of the neutral keyword is 0, and the score of the negative keyword is-1, which is not limited in this embodiment. The historical keyword set is all historical keywords corresponding to a single historical keyword type in the historical user comment data.
And determining the overall comment score of the historical keyword type, and taking the overall comment score as the overall comment result of the current keyword type. Illustratively, if there are 100 keywords in the facility type after identifying the historical user comment data, adding the scores corresponding to all the keywords to obtain a total score as an overall comment result. The integral comment score is used as the integral comment result of the current keyword type, so that the intuitiveness of the display of the integral comment result is improved.
Optionally, the overall comment results corresponding to all the keyword types may be presented in the form of a radar map, so as to improve the intuitiveness of result presentation.
In this embodiment, optionally, after determining the overall comment result of the current keyword type, the method further includes:
and determining the variation trend of the overall comment result according to the historical overall comment result of the current keyword type.
The historical overall comment results of the current keyword type are the comment results corresponding to the keyword type before the current time point, illustratively, the overall comment results are obtained in a month unit, then the overall change trend can be generated according to the overall comment results of each month in the past, the overall comment results can be presented in a line graph form, the intuitiveness of the change display of the overall comment results corresponding to each keyword type is improved, and therefore the accuracy and pertinence of the scenic spot information obtaining of the user are improved.
According to the embodiment of the invention, the overall comment result of the current keyword type is determined according to the part of speech of the historical keyword and the type of the historical keyword of the historical comment keyword, so that the accuracy of determining the overall comment result is improved.
EXAMPLE III
Fig. 3 is a schematic structural diagram of a scenic spot review data processing apparatus according to a third embodiment of the present invention. The device can be realized in a hardware and/or software mode, can execute the scenic spot comment data processing method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method. As shown in fig. 3, the apparatus includes:
a current comment keyword determination module 310, configured to determine a current comment keyword in current user comment data;
a current keyword type determining module 320, configured to determine, from at least two candidate keyword types, a current keyword type to which the current comment keyword belongs;
a reply information determining module 330, configured to determine reply information for the user comment data according to the current user comment data and the overall comment result of the current keyword type; and determining the overall comment result of the current keyword type according to historical user comment data.
According to the technical scheme provided by the embodiment, the current comment keywords in the current user comment data are determined; determining a current keyword type to which the current comment keyword belongs from at least two candidate keyword types; determining reply information to the user comment data according to the current user comment data and the overall comment result of the current keyword type; and determining the overall comment result of the current keyword type according to historical user comment data. The problem that visitors cannot actively know information corresponding to scenic spots by mainly obtaining evaluations of other visitors on the scenic spots from the appraisal areas corresponding to the scenic spots is solved, so that the scenic spot information is obtained in a one-sided and fuzzy manner, and the effect of improving the accuracy and pertinence of obtaining the scenic spot information is achieved.
On the basis of the above technical solutions, optionally, the reply information determining module includes:
a keyword code acquiring unit for acquiring a keyword code of the comment keyword;
the question-answer model input unit is used for inputting the keyword codes into a question-answer model which is constructed in advance; wherein the question-answering model is trained based on a sequence2sequence network structure
And the reply information determining unit is used for determining reply information to the user comment data according to the output result of the question-answer model.
On the basis of the above technical solutions, optionally, the overall comment result module includes:
the history comment keyword unit is used for determining history comment keywords in the history user comment data;
the history keyword type determining unit is used for determining a history keyword type to which the history comment keyword belongs from at least two candidate keyword types;
and the overall comment result determining unit is used for determining the overall comment result of the current keyword type according to the part of speech of the historical keywords and the historical keyword type of the historical comment keywords.
On the basis of the above technical solutions, optionally, the overall comment result determining unit includes:
the historical comment score determining subunit is used for determining the historical comment scores of the historical comment keywords according to the parts of speech of the historical keywords;
and the overall comment score determining subunit is used for determining the overall comment score of the historical keyword type according to the historical comment score and the historical keyword set corresponding to the historical keyword type, and taking the overall comment score as the overall comment result of the current keyword type.
On the basis of the above technical solutions, optionally, the apparatus further includes:
and the result change trend determining unit is used for determining the change trend of the overall comment result according to the historical overall comment result of the current keyword type after the overall comment result determining unit.
On the basis of the above technical solutions, optionally, the current comment keyword determining module includes:
the current user comment data filtering unit is used for filtering the current user comment data according to a pre-constructed stop word list;
and the current comment keyword determining unit is used for determining the current comment keyword by performing word segmentation processing on the filtered current user comment data.
Example four
Fig. 4 is a schematic structural diagram of an electronic apparatus according to a fourth embodiment of the present invention, as shown in fig. 4, the electronic apparatus includes a processor 40, a memory 41, an input device 42, and an output device 43; the number of the processors 40 in the electronic device may be one or more, and one processor 40 is taken as an example in fig. 4; the processor 40, the memory 41, the input device 42 and the output device 43 in the electronic apparatus may be connected by a bus or other means, and the bus connection is exemplified in fig. 4.
The memory 41 is a computer-readable storage medium, and can be used for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the scenic spot review data processing method in the embodiment of the present invention. The processor 40 executes various functional applications and data processing of the electronic device by running software programs, instructions and modules stored in the memory 41, that is, implements the above-described scenic comment data processing method.
The memory 41 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 41 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, memory 41 may further include memory located remotely from processor 40, which may be connected to the electronic device through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
EXAMPLE five
An embodiment of the present invention further provides a storage medium containing computer-executable instructions, where the computer-executable instructions are executed by a computer processor to perform a method for processing scenic spot review data, where the method includes:
determining a current comment keyword in current user comment data;
determining a current keyword type to which the current comment keyword belongs from at least two candidate keyword types;
determining reply information to the user comment data according to the current user comment data and the overall comment result of the current keyword type; and determining the overall comment result of the current keyword type according to historical user comment data.
Of course, the storage medium provided by the embodiment of the present invention contains computer-executable instructions, and the computer-executable instructions are not limited to the method operations described above, and may also perform related operations in the scenic spot comment data processing method provided by any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the above embodiment of the scenic spot review data processing apparatus, the included units and modules are only divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A scenic spot comment data processing method is characterized by comprising the following steps:
determining a current comment keyword in current user comment data;
determining a current keyword type to which the current comment keyword belongs from at least two candidate keyword types;
determining reply information to the user comment data according to the current user comment data and the overall comment result of the current keyword type; and determining the overall comment result of the current keyword type according to historical user comment data.
2. The method of claim 1, wherein determining reply information to the user comment data based on the current user comment data and the global comment result for the current keyword type comprises:
acquiring a keyword code of the current comment keyword;
inputting the keyword codes into a question-answering model constructed in advance;
determining reply information to the user comment data according to the output result of the question-answer model; wherein the question-answering model is trained based on a sequence2sequence network structure.
3. The method of claim 1, wherein determining the global comment result for the current keyword type comprises:
determining historical comment keywords in historical user comment data;
determining a history keyword type to which the history comment keyword belongs from at least two candidate keyword types;
and determining the overall comment result of the current keyword type according to the part of speech of the historical keywords and the type of the historical keywords of the historical comment keywords.
4. The method of claim 3, wherein determining the global comment result for the current keyword type based on the keyword part-of-speech of the historical comment keyword and the historical keyword type comprises:
determining a historical comment score of the historical comment keyword according to the part of speech of the historical keyword;
and determining the overall comment score of the historical keyword type according to the historical comment score and a historical keyword set corresponding to the historical keyword type, and taking the overall comment score as the overall comment result of the current keyword type.
5. The method of claim 3, after determining the global comment result for the current keyword type, further comprising:
and determining the variation trend of the overall comment result according to the historical overall comment result of the current keyword type.
6. The method of claim 1, wherein determining a current comment keyword in current user comment data comprises:
filtering the current user comment data according to a pre-constructed stop word list;
and determining the current comment keywords by performing word segmentation processing on the filtered current user comment data.
7. A scenic spot review data processing apparatus characterized by comprising:
the current comment keyword determining module is used for determining a current comment keyword in the current user comment data;
the current keyword type determining module is used for determining a current keyword type to which the current comment keyword belongs from at least two candidate keyword types;
the reply information determining module is used for determining reply information of the user comment data according to the current user comment data and the overall comment result of the current keyword type; and determining the overall comment result of the current keyword type according to historical user comment data.
8. The apparatus of claim 7, wherein the reply information determining module comprises:
a keyword code acquiring unit for acquiring a keyword code of the comment keyword;
the question-answer model input unit is used for inputting the keyword codes into a question-answer model which is constructed in advance; wherein the question-answering model is trained based on a sequence2sequence network structure
And the reply information determining unit is used for determining reply information to the user comment data according to the output result of the question-answer model.
9. An electronic device, characterized in that the electronic device comprises:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the scenic review data processing method of any of claims 1-6.
10. A computer-readable storage medium on which a computer program is stored, characterized in that the program, when executed by a processor, implements the scenic comment data processing method as set forth in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011176089.9A CN112256852A (en) | 2020-10-28 | 2020-10-28 | Scenic spot comment data processing method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011176089.9A CN112256852A (en) | 2020-10-28 | 2020-10-28 | Scenic spot comment data processing method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112256852A true CN112256852A (en) | 2021-01-22 |
Family
ID=74261220
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011176089.9A Pending CN112256852A (en) | 2020-10-28 | 2020-10-28 | Scenic spot comment data processing method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112256852A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150074020A1 (en) * | 2013-09-10 | 2015-03-12 | Facebook, Inc. | Sentiment polarity for users of a social networking system |
| CN109657033A (en) * | 2018-12-13 | 2019-04-19 | 泰康保险集团股份有限公司 | Method, apparatus, storage medium and the electronic equipment of customer problem processing |
| CN110807091A (en) * | 2019-03-01 | 2020-02-18 | 王涵 | Hotel intelligent question-answer recommendation and decision support analysis method and system |
| CN111078894A (en) * | 2019-12-17 | 2020-04-28 | 中国科学院遥感与数字地球研究所 | Scenic spot evaluation knowledge base construction method based on metaphor topic mining |
| CN111143540A (en) * | 2020-04-03 | 2020-05-12 | 腾讯科技（深圳）有限公司 | Intelligent question and answer method, device, equipment and storage medium |
| CN111310466A (en) * | 2020-02-26 | 2020-06-19 | 山东爱城市网信息技术有限公司 | Keyword library-based specific dimension scenic spot satisfaction measuring method and system |
| CN111311295A (en) * | 2018-12-12 | 2020-06-19 | 北京嘀嘀无限科技发展有限公司 | Service mode determining method and device, electronic equipment and storage medium |
| CN111340385A (en) * | 2020-03-10 | 2020-06-26 | 深圳华侨城创新研究院有限公司 | Scientific measuring method for measuring joy index of tourist attraction |
-
2020
- 2020-10-28 CN CN202011176089.9A patent/CN112256852A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150074020A1 (en) * | 2013-09-10 | 2015-03-12 | Facebook, Inc. | Sentiment polarity for users of a social networking system |
| CN111311295A (en) * | 2018-12-12 | 2020-06-19 | 北京嘀嘀无限科技发展有限公司 | Service mode determining method and device, electronic equipment and storage medium |
| CN109657033A (en) * | 2018-12-13 | 2019-04-19 | 泰康保险集团股份有限公司 | Method, apparatus, storage medium and the electronic equipment of customer problem processing |
| CN110807091A (en) * | 2019-03-01 | 2020-02-18 | 王涵 | Hotel intelligent question-answer recommendation and decision support analysis method and system |
| CN111078894A (en) * | 2019-12-17 | 2020-04-28 | 中国科学院遥感与数字地球研究所 | Scenic spot evaluation knowledge base construction method based on metaphor topic mining |
| CN111310466A (en) * | 2020-02-26 | 2020-06-19 | 山东爱城市网信息技术有限公司 | Keyword library-based specific dimension scenic spot satisfaction measuring method and system |
| CN111340385A (en) * | 2020-03-10 | 2020-06-26 | 深圳华侨城创新研究院有限公司 | Scientific measuring method for measuring joy index of tourist attraction |
| CN111143540A (en) * | 2020-04-03 | 2020-05-12 | 腾讯科技（深圳）有限公司 | Intelligent question and answer method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109726274B (en) | Question generation method, device and storage medium | |
| US8862492B1 (en) | Identifying unreliable contributors of user-generated content | |
| US11757807B2 (en) | Interactive chatbot for multi-way communication | |
| CN110275965A (en) | Pseudo event detection method, electronic device and computer readable storage medium | |
| US9552552B1 (en) | Identification of over-clustered map features | |
| CN113312461A (en) | Intelligent question-answering method, device, equipment and medium based on natural language processing | |
| US11868914B2 (en) | Moderation of user-generated content | |
| CN113420229B (en) | Social media information pushing method and system based on big data | |
| CN110688434B (en) | Method, device, equipment and medium for processing interest points | |
| CN114372133A (en) | Query information question answering method, related device and computer program product | |
| CN116070019A (en) | Intelligent recruitment recommendation method and system based on big data and readable storage medium | |
| CN111079428B (en) | Word segmentation and industry dictionary construction method and device and readable storage medium | |
| CN111126422B (en) | Method, device, equipment and medium for establishing industry model and determining industry | |
| Puri et al. | Pragmatics and semantics to connect specific local laws with public reactions | |
| CN109145092B (en) | Database updating and intelligent question and answer management method, device and equipment | |
| CN112966076A (en) | Intelligent question and answer generating method and device, computer equipment and storage medium | |
| CN111538796A (en) | Address normalization processing method, device, equipment and storage medium | |
| CN112256852A (en) | Scenic spot comment data processing method and device, electronic equipment and storage medium | |
| CN115185986A (en) | Method and device for matching provincial and urban area address information, computer equipment and storage medium | |
| CN109344342B (en) | Map data retrieval method, map data retrieval device, map data retrieval server and map data retrieval system | |
| CN113468306A (en) | Voice conversation method, device, electronic equipment and storage medium | |
| CN112148847A (en) | Voice information processing method and device | |
| Lurie et al. | Searching for Representation: A sociotechnical audit of googling for members of US Congress | |
| Tikhonova et al. | Detecting a citizens' activity profile of an urban territory through natural language processing of social media data | |
| CN112800188A (en) | Conversation processing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |