WO2020177463A1

WO2020177463A1 - Information processing method and apparatus, storage medium, and electronic device

Info

Publication number: WO2020177463A1
Application number: PCT/CN2019/129063
Authority: WO
Inventors: 徐凯姮
Original assignee: 拉扎斯网络科技（上海）有限公司
Priority date: 2019-03-04
Filing date: 2019-12-27
Publication date: 2020-09-10
Also published as: CN109902304A

Abstract

Disclosed are an information processing method and apparatus, a storage medium, and an electronic device. The method comprises: acquiring comment information of a user, wherein the comment information comprises text information and comment level information; analyzing the text information according to a predetermined rule, so as to determine first level information; and determining second level information of the comment information according to the comment level information and the first level information. By means of the present invention, relative precise comments on a merchant can be obtained.

Description

Information processing method, device, storage medium and electronic equipment

This application claims the priority of the Chinese patent application filed on March 4, 2019, with the application number 2019101602650 and the title of the invention "information processing methods, devices, storage media and electronic equipment", the entire contents of which are incorporated herein by reference Applying.

Technical field

The disclosure of the present invention relates to the field of information processing, in particular to an information processing method, device, storage medium and electronic equipment.

Background technique

At present, users’ reviews of merchants’ products include an objective score (for example, 0-5 points) and a text review part. The overall rating of the merchant is usually obtained comprehensively based on the user's objective scoring in the product reviews. Specifically, firstly, whether the user review is valid or not is judged based on whether the number of review words is greater than a threshold, whether the review type corresponds to the product, etc., and then based on the scores in the valid reviews, the average value is taken to obtain the overall merchant score.

However, the platform often provides incentives to increase user activity to encourage users to submit reviews. Some merchants also provide activities such as "Praise Rebate" in order to improve their own ratings, causing some users to submit invalid reviews in order to get rewards. For example, pictures are often irrelevant pictures, and text comments are often irrelevant text copied and pasted at random, and then scored with a full score of 5 points. Even though users are dissatisfied with the service in the text comments, they still get high scores. .

These circumstances have caused the overall rating of the merchant to be inaccurate or even falsely high, resulting in other users unable to effectively make decisions or evaluate the merchant based on the merchant's rating.

Summary of the invention

In view of this, embodiments of the present invention provide an information processing method, device, storage medium, and electronic equipment to solve the problem of inaccurate evaluation of merchants based on user review information in the prior art.

According to a first aspect of the embodiments of the present invention, an information processing method is provided, the method includes: acquiring user comment information, the comment information including text information and comment rating information; and analyzing the text information according to predetermined rules to determine the first Level information; the second level information of the review information is determined according to the review level information and the first level information.

According to a second aspect of the embodiments of the present invention, there is provided an information processing device, which includes: an information acquisition unit for acquiring user comment information, the comment information including text information and comment rating information; and a first rating information determining unit, It is used to analyze the text information according to predetermined rules to determine the first level information; the second level information determining unit is used to determine the second level information of the review information according to the review level information and the first level information.

According to a third aspect of the embodiments of the present invention, there is provided a computer-readable storage medium on which computer program instructions are stored, wherein the computer program instructions implement the method as described in the first aspect when executed by a processor.

According to a fourth aspect of the embodiments of the present invention, there is provided an electronic device, including a memory and a processor, wherein the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are The processor executes to implement the method as described in the first aspect.

The embodiment of the present invention analyzes the text information in the obtained user comment information according to a predetermined rule to obtain the first level information, and then determines the second level of the comment information according to the comment level information and the first level information in the obtained user comment information According to the second-level information, a more accurate merchant evaluation can be obtained. Because the embodiment of the present invention introduces predetermined rules, it can overcome the inaccurate evaluation of merchants caused by only evaluating merchants based on user review information in the prior art. problem.

Description of the drawings

Through the following description of the embodiments of the present invention with reference to the accompanying drawings, the above and other objectives, features and advantages of the present invention will be clearer, in the accompanying drawings:

Fig. 1 is a flowchart of an information processing method according to an embodiment of the present invention;

Fig. 2 is an example flowchart of an information processing method according to an embodiment of the present invention;

Fig. 3 is a structural block diagram of an information processing device according to an embodiment of the present invention;

Fig. 4 is a specific structural block diagram of an information processing device according to an embodiment of the present invention;

FIG. 5 is a structural block diagram of the first level information determining unit 302 according to an embodiment of the present invention;

6 is a structural block diagram of the second level information determining unit 303 according to an embodiment of the present invention;

Fig. 7 is an application scenario diagram of an information processing device according to an embodiment of the present invention;

Fig. 8 is a schematic diagram of an electronic device according to an embodiment of the present invention.

detailed description

The present invention is described below based on examples, but the present invention is not limited to these examples. In the following detailed description of the present invention, some specific details are described in detail. Those skilled in the art can fully understand the present invention without the description of these details. In order to avoid obscuring the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

In addition, those of ordinary skill in the art should understand that the drawings provided herein are for illustrative purposes, and the drawings are not necessarily drawn to scale.

Unless the context clearly requires, the words "including", "including" and other similar words in the entire specification and claims should be interpreted as inclusive rather than exclusive or exhaustive meanings; in other words, "including but not limited to" Meaning.

In the description of the present invention, it should be understood that the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, "plurality" means two or more.

An embodiment of the present invention provides an information processing method. FIG. 1 is a flowchart of the information processing method. As shown in FIG. 1, the method includes:

Step 101: Obtain user comment information, the comment information includes text information and comment rating information;

Step 102: Analyze the text information according to predetermined rules to determine the first level information;

Step 103: Determine the second level information of the review information according to the review level information and the first level information.

The embodiment of the present invention analyzes the text information in the obtained user comment information according to predetermined rules, ranks the text information according to the analysis result to obtain the first grade information, and then according to the comment grade information and the second grade information in the obtained user comment information. The first-level information determines the second-level information of the review information. According to the second-level information, a more accurate merchant evaluation can be obtained. The embodiment of the present invention introduces a predetermined rule (the predetermined rule is mainly used to analyze text information, so the following can be It is called a predetermined analysis rule), which can overcome the problem of inaccurate evaluation of merchants caused by only evaluating merchants based on user review information in the prior art.

In actual operation, it is necessary to construct predetermined analysis rules first, which specifically include: obtaining multiple pieces of historical comment information; obtaining high-frequency words from multiple pieces of historical comment information according to predetermined rules (for example, industry characteristics) to construct predetermined analysis rules; Set the level of multiple high frequency words obtained. The high-frequency words here can include: high-frequency nouns, high-frequency adjectives, and high-frequency adverbs.

For example, for the catering industry, obtain multiple historical review information of each restaurant, perform word segmentation and other processing on each review information, obtain multiple words, and select nouns with higher occurrence frequency as high-frequency nouns, such as "dish quantity", " "Taste", "rice", "service", "attitude", etc., select adjectives that appear more frequently as high-frequency adjectives, for example, "good", "stick", "bad", etc., and use higher-frequency adverbs as adverbs High-frequency adverbs, for example, "very", "general", etc., and then construct predetermined analysis rules based on the selected high-frequency words, and set a level for each high-frequency word.

In the embodiment of the present invention, the grade can be first-level (representing particularly satisfactory), second-level (representing satisfaction), third-level (representing general), etc., or it can be represented by scores, for example, 0-5 Grade is based on points, such as 5 points for particularly satisfactory, 0 points for particularly unsatisfactory.

In step 102, analyzing the text information according to a predetermined analysis rule includes: obtaining keywords in the text information according to a predetermined analysis rule. That is, according to the high-frequency words in the predetermined analysis rule, the keywords corresponding to the high-frequency words in the text information are obtained.

Afterwards, the acquired keywords are classified according to the level information of the high-frequency words in the predetermined analysis rule to obtain the first level information.

After that, in step 103, the second level information of the review information is determined according to the review level information obtained in step 101 and the first level information obtained in step 102. Specifically, when the difference between the comment rating information and the first rating information is less than a predetermined range, it is determined that the comment information is valid; then the second rating information is determined according to the comment rating information and the first rating information. When the difference between the comment level information and the first level information is greater than the predetermined range, it is determined that the review information is invalid, and the review information is not considered at this time.

By comparing the difference between the comment level information and the first level information, it can be concluded whether the user comment information is valid. If the difference between the comment level information and the first level information is large, it can be considered that the text information in the user comment information is different from the comment level information. The information reflected is inconsistent. For example, for the "Commercial Rebate" campaign, the text information is an irrelevant paragraph that is freely copied and pasted, and the review grade information is 5 points full score. For this type of review, the first grade information (may be 0 points or 0 points) obtained by introducing predetermined analysis rules 1 point), there will be a big difference from the level information (5 points) in the user comments. It can be considered that the first level information obtained through the predetermined analysis rules is more accurate objective level information. In this way, invalid user comments can be filtered out, and the accuracy and reliability of the evaluation of businesses can be improved.

When the difference between the comment rating information and the first rating information is less than a predetermined range (for example, the difference does not exceed 1 point), the user comment information can be considered valid, and then the second rating information is determined based on the comment rating information and the first rating information. Specifically, the weights of the comment level information and the first level information are respectively set first; then the weights and the corresponding level information are weighted and summed to determine the second level information.

For example, according to a predetermined rule (for example, an industry rule), the weight of the review grade information is set to a, and the weight of the first grade information is set to b, and the second grade information is determined by the following formula:

Second level information=aⅹlevel information+bⅹfirst level information, where a and b are real numbers between 0 and 1, and a+b=1.

The predetermined rules here can be based on industry characteristics, or can be based on industry experience. Preferably, a can be 0.5 and b can be 0.5.

Fig. 2 is an example flowchart of an information processing method according to an embodiment of the present invention. As shown in Fig. 2, the example includes the following processes:

Step 201: Construct a public opinion analysis dictionary, which may be the aforementioned predetermined analysis rule.

Construct a public opinion analysis dictionary based on keywords in various industry scenarios, and update the dictionary regularly for different scenarios, such as adding keywords, such as adding new dish names and store names in the catering industry, and adding industries such as "Xiang Nuo" and "Crispy" Unique adjectives, etc. to improve the accuracy of word segmentation and optimize subsequent analysis results.

Specifically, obtain multiple pieces of historical user comment information, use word segmentation and part-of-speech tagging for the text in the comment information, convert the text into a thesaurus, sort out the word frequency of these words, and select the higher occurrence frequency (for example, sort by frequency The top 20) nouns, adjectives, adverbs, etc., are scored on a scale of 0-5 and added to the dictionary to form a public opinion analysis dictionary.

For example, a piece of historical comment information is obtained: The rice tastes super good, the amount of dishes is sufficient, and in short, I am very satisfied!

The result of word segmentation is: rice/taste/super/good/,/amount of dishes/very sufficient/, /in short/very/satisfied/!

The part-of-speech tagging is: (rice, n) (taste, n) (super, b) (good, a) (,, x) (vegetable quantity, n) (very sufficient, a) (,, x) (in short, c ) (Very, d) (satisfied, v) (!, x), where n is the name and b is the distinguishing word (for example, "女" in "woman driver", part of speech is marked as b, and in "head office" "Total", part of speech is marked as b), a means adjective, x means punctuation, c means conjunction (for example, and), d means adverb (for example, "further" in "further development", part of speech is marked as d) , V means verb.

The high-frequency nouns here are "rice", "taste", and "vegetable quantity", which can be put into the dictionary to help improve the accuracy of word segmentation; set a level of 4 for adjectives such as "very enough" and add them to the public opinion dictionary.

Step 202: Obtain and parse user comment information.

Specifically, the user comment information is obtained, and then the text part and the grade part (0-5 points) of the comment are obtained respectively, which is convenient for subsequent processing and statistics.

Step 203: Analyze user comment information, and perform level analysis on the text part;

For example, the obtained user review information is: the rice tastes super good, the dishes are very large, and in short, I am very satisfied!

"Good" in the first clause "The taste of rice is super good" is rated 3.5 points in the public opinion dictionary, and the level of "super good" under "super" modification is 5 points, and the first clause is rated 5 points;

In the second clause "very enough dishes", "very enough" is 4 points, and the second clause has 4 points;

In the third clause “very satisfied in general”, “satisfied” is 4.5 points, and under the modification of “very” is 5 points, the third clause is 5 points.

If the three clauses are juxtaposed, the overall grade of the text part is 4.67 points average of the three clauses.

Step 204: Calculate the comprehensive level of the user review information (ie, the above-mentioned second level information), specifically, according to the level score obtained in step 203 according to the public opinion dictionary (public opinion score) and the level score in the user comment information obtained in step 202 (User points) difference value to calculate the comprehensive level of user comment information.

|Public opinion points-user points|>Threshold value means that the user comment is invalid and this comment is discarded. In this case, the user’s score may not correspond to the text. For example, the user’s text description is dissatisfied with the business, but the actual evaluation is a good score for the business. The threshold here can be determined according to the actual situation.

|Public opinion score-user score|<=threshold, it means that the user evaluation is valid, and the average of the two is taken as the comprehensive score for the merchant.

By identifying and screening user reviews based on the public opinion dictionary, and recalculating the grade score, the accuracy and reliability of the merchant’s score can be effectively improved.

An embodiment of the present invention also provides an information processing device. FIG. 3 is a structural block diagram of the device. As shown in FIG. 3, the device includes: an information acquisition unit 301, a first level information determination unit 302, and a second level information determination unit 303, of which:

The information obtaining unit 301 is configured to obtain user comment information, the comment information including text information and comment rating information;

The first-level information determining unit 302 is configured to analyze text information according to predetermined rules to determine the first-level information;

The second level information determining unit 303 is configured to determine the second level information of the review information according to the review level information and the first level information.

The first level information determining unit 302 in the embodiment of the present invention analyzes the text information in the user comment information obtained by the information acquiring unit 301 according to predetermined rules to determine the first level information, and then the second level information determining unit 303 according to the comment level information The second-level information of the review information is determined with the first-level information. According to the second-level information, a more accurate merchant evaluation can be obtained. The embodiment of the present invention introduces predetermined rules (hereinafter may be referred to as predetermined analysis rules), which can overcome In the prior art, the problem of insufficient accuracy in evaluating merchants caused by evaluating merchants only based on user review information.

In actual operation, as shown in FIG. 4, the above-mentioned device further includes: a valid information determining unit 304 and a valid information determining unit 305, wherein:

The valid information judging unit 304 is configured to judge whether the review information is valid according to the review level information and the first level information;

The valid information determining unit 305 is configured to determine that the review information is valid in response to the difference between the review level information and the first level information being less than a predetermined range, otherwise, determine that the review information is invalid.

The valid information determining unit 304 can determine whether the review information is valid according to the difference between the review rating information and the first level information. When the difference between the review rating information and the first level information is less than a predetermined range, the valid information determining unit 305 determines The comment information is valid. When the difference between the comment level information and the first level information is large, it can be considered that the text information in the user’s comment information does not match the information reflected in the comment level, and the valid information determining unit 305 determines that the comment information is invalid , The comment information is not considered at this time. In this way, invalid user comments can be filtered out, and the accuracy and reliability of the evaluation of businesses can be improved.

As shown in FIG. 5, the first level information determining unit 302 includes: a text information analysis module 3021 and a first level information determining module 3022, wherein:

The text information analysis module 3021 is used to analyze text information according to predetermined analysis rules;

The first level information determining module 3022 is configured to classify the text information according to the analysis result to determine the first level information.

Specifically, the text information analysis module 3021 obtains keywords in the text information according to a predetermined analysis rule, and then the first level information determination module 3022 ranks the obtained keywords according to the predetermined analysis rule to determine the first level information.

As shown in FIG. 6, the second level information determining unit 303 includes: a weight setting module 3031 and a second level information determining module 3032, wherein:

The weight setting module 3031 is used to set the weights of the comment level information and the first level information respectively;

The second level information determining module 3032 is configured to perform a weighted sum operation on the weight and corresponding level information to determine the second level information.

Specifically, the weight setting module 3031 may set the weight of the review rank information to a and the weight of the first rank information to b according to predetermined rules (for example, industry rules); then the second rank information determination module 3032 may pass the following The formula determines the second level information: second level information=aⅹcomment level information+bⅹfirst level information, where a, b are real numbers between 0 and 1, and a+b=1.

The predetermined rule may be based on industry characteristics, or may be based on industry experience. Preferably, a can be 0.5 and b can be 0.5.

Fig. 7 is an application scenario diagram of an information processing device according to an embodiment of the present invention. As shown in Fig. 7, the information obtaining unit 301 obtains multiple user comments (Comment 1, Comment 2, ..., Comment N) of a certain merchant. The first-level information determining unit 302 analyzes the text information in each user review according to predetermined analysis rules to determine the first-level information, and the effective information determining unit 304 determines the comment based on the review level information and the first-level information in each user review Whether it is valid or not, when the difference between the review rank information and the first rank information is less than the predetermined range, the valid information determining unit 305 determines that the review is valid (comments a,..., f), otherwise it is an invalid comment (as shown in the figure) (Not shown in ), then the second level information determining unit 303 determines the second level information of the valid review according to the review level information and the first level information in the valid review, and can obtain the second level information of the valid review according to the second level information of multiple valid reviews. More accurate merchant evaluation.

Fig. 8 is a schematic diagram of an electronic device according to an embodiment of the present invention. The electronic device shown in FIG. 8 is a general data processing apparatus, which includes a general computer hardware structure, and includes at least a processor 801 and a memory 802. The processor 801 and the memory 802 are connected through a bus 803. The memory 802 is suitable for storing one or more instructions or programs executable by the processor 801. The one or more instructions or programs are executed by the processor 801 to implement the following steps:

Obtaining user comment information, the comment information including text information and comment rating information;

Analyzing the text information according to predetermined rules to determine the first level information;

The second level information of the review information is determined according to the review level information and the first level information.

Analyzing the text information according to a predetermined rule to determine the first level information includes: analyzing the text information according to the predetermined rule; classifying the text information according to the analysis result to determine the first level information .

Analyzing the text information according to the predetermined rule includes: acquiring keywords in the text information according to the predetermined rule.

Performing level division on the text information according to the analysis result to determine the first level information includes: performing level division on the acquired keywords according to the predetermined rule to determine the first level information.

Determining the second level information according to the review level information and the first level information includes: setting the weights of the review level information and the first level information respectively; and performing a weighted summation between the weights and the corresponding level information Operate to determine the second level information.

Before determining the second level information of the review information, the above steps further include: judging whether the review information is valid according to the review level information and the first level information; responding to the review level information and the first level information; If the difference of a level information is less than a predetermined range, it is determined that the comment information is valid; otherwise, it is determined that the comment information is invalid.

The aforementioned processor 801 may be an independent microprocessor, or a collection of one or more microprocessors. As a result, the processor 801 executes the command stored in the memory 802 to execute the method flow of the embodiment of the present invention as described above to realize data processing and control of other devices. The bus 803 connects the above-mentioned multiple components together, and at the same time connects the above-mentioned components to the display controller 804 and the display device and the input/output (I/O) device 805. The input/output (I/O) device 805 can be a mouse, a keyboard, a modem, a network interface, a touch input device, a motion sensing input device, a printer, and other devices known in the art. Typically, an input/output (I/O) device 805 is connected to the system through an input/output (I/O) controller 806.

Among them, the memory 802 may store software components, such as an operating system, a communication module, an interaction module, and an application program. Each module and application program described above corresponds to a set of executable program instructions that complete one or more functions and methods described in the embodiments of the invention.

To sum up, since the current evaluation of merchants is usually directly based on the rating information in the user reviews, because there are meaningless comments and comments that do not match the rating in the user reviews, the evaluation of the merchants directly based on the user reviews is If it is not accurate enough, the embodiment of the present invention analyzes the text part of the user review according to predetermined analysis rules to obtain the analyzed level information, and comprehensively considers the level information in the user review to evaluate the merchant, which can exclude meaningless reviews As well as comments that do not match the rating, more accurate merchant evaluations can be obtained.

The above-mentioned flowcharts and/or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present invention describe various aspects of the present invention. It should be understood that each block of the flowchart illustrations and/or block diagrams and combinations of blocks in the flowchart illustrations and/or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to generate a machine, so that the instructions (executed by the processor of the computer or other programmable data processing device) are created for implementation Flow chart and/or block diagram block or means of function/action specified in the block.

At the same time, as those skilled in the art will realize, various aspects of the embodiments of the present invention may be implemented as a system, a method, or a computer program product. Therefore, various aspects of the embodiments of the present invention can take the following forms: a complete hardware implementation, a complete software implementation (including firmware, resident software, microcode, etc.), or can be generally referred to as "circuits" and "modules" in this document. "Or "system" is a way of combining software and hardware. In addition, aspects of the present invention may take the following form: a computer program product implemented in one or more computer-readable media, the computer-readable medium having computer-readable program codes implemented thereon.

Any combination of one or more computer readable media can be utilized. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any appropriate combination of the foregoing. More specific examples (non-exhaustive list) of computer-readable storage media would include the following: electrical connections with one or more wires, portable computer floppy disks, hard disks, random access memory (RAM), read-only memory ( ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any appropriate combination of the foregoing. In the context of the embodiments of the present invention, a computer-readable storage medium may be any tangible medium that can contain or store a program used by an instruction execution system, device, or device or a program used in conjunction with an instruction execution system, device, or device.

The computer-readable signal medium may include a propagated data signal having computer-readable program code implemented therein as in baseband or as part of a carrier wave. Such a propagated signal can take any of a variety of forms, including but not limited to: electromagnetic, optical, or any suitable combination. The computer-readable signal medium may be any of the following computer-readable media: it is not a computer-readable storage medium, and it can communicate and propagate the program used by the instruction execution system, device or device or used in conjunction with the instruction execution system, device or device Or transmission.

The computer program code used to perform operations directed to various aspects of the present invention can be written in any combination of one or more programming languages, including: object-oriented programming languages such as Java, Smalltalk, C++, PHP, Python Etc.; and conventional process programming languages such as "C" programming language or similar programming languages. The program code can be executed as an independent software package entirely on the user's computer, partly on the user's computer; partly on the user's computer and partly on a remote computer; or entirely on the remote computer or server. In the latter case, the remote computer can be connected to the user computer through any type of network including a local area network (LAN) or a wide area network (WAN), or can be connected with an external computer (for example, by using the Internet of an Internet service provider) .

The above descriptions are only preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

An information processing method, characterized in that the method includes:

Obtaining user comment information, the comment information including text information and comment rating information;

Analyzing the text information according to predetermined rules to determine the first level information;

The second level information of the review information is determined according to the review level information and the first level information.
The information processing method according to claim 1, wherein analyzing the text information according to a predetermined rule to determine the first level information comprises:

Analyze the text information according to the predetermined rule;

The text information is classified according to the analysis result to determine the first level information.
The information processing method according to claim 2, wherein analyzing the text information according to the predetermined rule comprises:

Acquire keywords in the text information according to the predetermined rule.
The information processing method according to claim 3, wherein the classification of the text information according to the analysis result to determine the first level information comprises:

The acquired keywords are classified according to the predetermined rules to determine the first level information.
The information processing method according to claim 1, wherein determining the second level information according to the review level information and the first level information comprises:

Respectively setting the weights of the comment level information and the first level information;

Perform a weighted sum operation on the weight and the corresponding level information to determine the second level information.
The information processing method according to claim 1, wherein before determining the second level information of the review information, the method further comprises:

Judging whether the comment information is valid according to the comment rating information and the first rating information;

In response to the difference between the comment rating information and the first rating information being less than a predetermined range, it is determined that the comment information is valid; otherwise, it is determined that the comment information is invalid.
An information processing device, characterized in that the device includes:

An information acquisition unit for acquiring user comment information, the comment information including text information and comment rating information;

The first level information determining unit is configured to analyze the text information according to predetermined rules to determine the first level information;

The second level information determining unit is configured to determine the second level information of the review information according to the review level information and the first level information.
The information processing device according to claim 7, wherein the first level information determining unit comprises:

A text information analysis module, configured to analyze the text information according to the predetermined rule;

The first level information determining module is used to classify the text information according to the analysis result to determine the first level information.
The information processing device according to claim 8, wherein the text information analysis module is specifically configured to:

Acquire keywords in the text information according to the predetermined rule.
The information processing device according to claim 9, wherein the first level information determining module is specifically configured to:

The acquired keywords are classified according to the predetermined rules to determine the first level information.
The information processing device according to claim 7, wherein the second level information determining unit comprises:

A weight setting module for setting the weights of the comment level information and the first level information respectively;

The second level information determining module is configured to perform a weighted sum operation on the weight and corresponding level information to determine the second level information.
The information processing device according to claim 7, wherein the device further comprises:

A valid information judging unit, configured to judge whether the comment information is valid according to the comment level information and the first level information;

The valid information determining unit is configured to determine that the review information is valid in response to the difference between the review level information and the first level information being less than a predetermined range; otherwise, determine that the review information is invalid.
A computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement the method according to any one of claims 1-6.
An electronic device comprising a memory and a processor, wherein the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to realize The method of any one of claims 1-6.