CN113128198A

CN113128198A - Feedback information processing method and device, computer equipment and storage medium

Info

Publication number: CN113128198A
Application number: CN202110443834.XA
Authority: CN
Inventors: 李焕雄; 常明
Original assignee: Guangzhou Kugou Computer Technology Co Ltd
Current assignee: Guangzhou Kugou Computer Technology Co Ltd
Priority date: 2021-04-23
Filing date: 2021-04-23
Publication date: 2021-07-16

Abstract

The application provides a feedback information processing method and device, computer equipment and a storage medium, and belongs to the technical field of computers. The method comprises the following steps: acquiring a plurality of feedback information of a target object and feedback parameters of the plurality of feedback information, wherein the feedback parameters are used for expressing the preference degree of a user who issues the feedback information to the target object; extracting a first target word from the plurality of feedback information, wherein the average value of the feedback parameters of the feedback information including the first target word is different from the average value of the feedback parameters of the feedback information not including the first target word; determining a first weight of the first target word based on the feedback parameters of the plurality of feedback information, the first weight of the first target word being used for representing the influence degree of the first target word on the feedback parameters of the feedback information including the first target word. According to the method and the device, the target words which enable the feedback parameters of the feedback information to generate differences are extracted, and the influence degree of the target words on the feedback parameters is determined according to the corresponding weights, so that the analysis efficiency is improved.

Description

Feedback information processing method and device, computer equipment and storage medium

Technical Field

The present application relates to the field of computer technologies, and in particular, to a feedback information processing method and apparatus, a computer device, and a storage medium.

Background

With the development of computer technology, more and more clients provide various services for users, for example, music clients provide services such as music playing and music sharing for users. The client-side developers need to know the main reason of the corresponding preference degree of the user to the client-side, and can improve the client-side in a targeted manner, attract more users to apply the client-side and improve the viscosity of the user to the client-side.

Currently, a worker usually browses feedback information of a user to a client one by one, and manually finds out a main reason of generating a corresponding preference degree of the user to the client, and the manual analysis efficiency is very low under the condition that the client has massive feedback information.

Disclosure of Invention

The embodiment of the application provides a feedback information processing method and device, computer equipment and a storage medium, and analysis efficiency can be improved. The technical scheme is as follows:

in one aspect, a feedback information processing method is provided, where the method includes:

acquiring a plurality of pieces of feedback information of a target object and feedback parameters of the plurality of pieces of feedback information, wherein the feedback parameters of the feedback information are used for expressing the preference degree of a user who releases the feedback information to the target object;

extracting a first target word from the plurality of feedback information, wherein a feedback parameter mean value of the feedback information including the first target word is different from a feedback parameter mean value of the feedback information not including the first target word;

determining a first weight of the first target word based on the feedback parameters of the plurality of feedback information, wherein the first weight of the first target word is used for representing the influence degree of the first target word on the feedback parameters of the feedback information comprising the first target word.

In an optional implementation manner, the extracting, from the plurality of feedback information, a first target word includes:

for any word included in the plurality of feedback information, determining a first number of first feedback information from a plurality of feedback information including the word, and determining the first number of second feedback information from a plurality of feedback information not including the word;

determining a difference indicating parameter corresponding to the word based on the feedback parameters of the first number of first feedback information and the feedback parameters of the first number of second feedback information, wherein the difference indicating parameter is used for representing the difference condition of the average value of the feedback parameters of the feedback information including the word and the average value of the feedback parameters of the feedback information not including the word;

determining the word as the first target word in response to the difference indication parameter being greater than a threshold value.

In another optional implementation manner, the determining, based on the feedback parameters of the first number of first feedback information and the feedback parameters of the first number of second feedback information, a difference indication parameter corresponding to the word includes:

determining a first average value of the feedback parameters of the first quantity of first feedback information, and determining a second average value of the feedback parameters of the first quantity of second feedback information;

determining a combined standard deviation based on the first mean, the second mean, the feedback parameters of the first quantity of first feedback information, and the feedback parameters of the first quantity of second feedback information;

determining a difference indication parameter corresponding to the word based on the first mean, the second mean, the combined standard deviation, and the first quantity.

In another optional implementation manner, the extracting the first target word from the plurality of feedback information includes:

for any word included in the plurality of feedback information, determining a third average value of feedback parameters of the plurality of feedback information including the word, and determining a fourth average value of feedback parameters of the plurality of feedback information not including the word;

determining the word as the first target word in response to a difference between the third mean and the fourth mean being greater than a first threshold.

In another optional implementation manner, the determining a first weight of the first target word based on the feedback parameters of the plurality of feedback information includes:

selecting a plurality of third feedback information from the plurality of feedback information, and determining a fifth average value of feedback parameters of the plurality of third feedback information;

determining a first weight of the plurality of first target words based on the fifth mean value and the extracted first occurrence indication parameters of the plurality of first target words, and enabling a difference value between a sum value of the first influence parameters of the plurality of first target words and the fifth mean value to be smaller than a second threshold value;

wherein, for any first target word in the plurality of first target words, the first occurrence indication parameter of the first target word is used for representing the occurrence of the first target word in the plurality of third feedback information, and the first influence parameter of the first target word is the product of the first occurrence indication parameter of the first target word and the first weight of the first target word.

In another optional implementation, the method further includes:

selecting a plurality of fourth feedback information from the plurality of feedback information, and determining a sixth average value of feedback parameters of the plurality of fourth feedback information;

updating the first weights of the plurality of first target words based on the sixth mean and the second occurrence indication parameters of the plurality of first target words such that a difference between a sum of the second impact parameters of the plurality of first target words and the fifth mean is less than the second threshold and a difference between a sum of the third impact parameters of the plurality of first target words and the sixth mean is less than the second threshold;

wherein, for any first target word in the plurality of first target words, the second occurrence indication parameter of the first target word is used to represent the occurrence of the first target word in the plurality of fourth feedback information, the second influence parameter of the first target word is the product of the first occurrence indication parameter of the first target word and the updated first weight of the first target word, and the third influence parameter of the target word is the product of the occurrence indication parameter of the first target word and the updated first weight of the first target word.

selecting fifth feedback information from the plurality of feedback information, and acquiring a feedback parameter of the fifth feedback information;

determining a first weight of the plurality of first target words based on the feedback parameter of the fifth feedback information and the extracted third occurrence indication parameter of the plurality of first target words, so that a difference value between a sum of fourth influence parameters of the plurality of first target words and the feedback parameter of the fifth feedback information is smaller than a third threshold value;

wherein, for any first target word in the plurality of first target words, the third occurrence indication parameter of the first target word is used to represent the occurrence of the first target word in the fifth feedback information, and the fourth influence parameter of the first target word is the product of the third occurrence indication parameter of the first target word and the first weight of the first target word.

In another optional implementation, the method further includes:

selecting sixth feedback information from the plurality of feedback information, and acquiring a feedback parameter of the sixth feedback information;

updating the first weights of the plurality of first target words based on the feedback parameters of the sixth feedback information and the fourth occurrence indication parameters of the plurality of first target words, so that the difference between the sum of the fifth influence parameters of the plurality of first target words and the feedback parameters of the fifth feedback information is smaller than the third threshold, and the difference between the sum of the sixth influence parameters of the plurality of first target words and the feedback parameters of the sixth feedback information is smaller than the third threshold;

wherein, for any first target word in the plurality of first target words, the fourth occurrence indication parameter of the first target word is used to represent the occurrence of the first target word in the sixth feedback information, the fifth influence parameter of the first target word is the product of the third occurrence indication parameter of the first target word and the updated first weight of the first target word, and the sixth influence parameter of the first target word is the product of the fourth occurrence indication parameter of the first target word and the updated first weight of the first target word.

In another optional implementation, the method further includes:

extracting a second target word from a plurality of feedback information including the first target word, wherein a feedback parameter mean value of the feedback information including the second target word is different from a feedback parameter mean value of the feedback information not including the second target word;

determining a second weight for the second target term based on a feedback parameter comprising a plurality of feedback information for the first target term;

wherein the second weight of the second target word is used to represent the degree of influence of the second target word on a feedback parameter of feedback information including the second target word.

extracting a plurality of words with the occurrence frequency meeting the occurrence frequency condition from the plurality of feedback information;

selecting the first target word from the plurality of words.

In another optional implementation manner, the extracting, from the plurality of feedback information, a plurality of words whose occurrence frequency satisfies an occurrence frequency condition includes:

extracting words with the occurrence frequency meeting the occurrence frequency condition from a plurality of pieces of feedback information with the feedback parameters larger than a fourth threshold;

and extracting words with the occurrence frequency meeting the occurrence frequency condition from a plurality of pieces of feedback information with the feedback parameters smaller than the fourth threshold.

and extracting a plurality of words with parts of speech as target parts of speech and occurrence frequency meeting the occurrence frequency condition from the plurality of feedback information.

and extracting a plurality of words, of which the occurrence frequency meets the occurrence frequency condition and is used for describing the function of the target object, from the plurality of feedback information.

and sequencing the words included in the feedback information according to the sequence of the occurrence frequency from large to small, and determining the words with the sequencing second number as a plurality of words with the occurrence frequency meeting the occurrence frequency condition.

In another aspect, there is provided a feedback information processing apparatus, the apparatus including:

the information acquisition module is used for acquiring a plurality of pieces of feedback information of a target object and feedback parameters of the plurality of pieces of feedback information, wherein the feedback parameters of the feedback information are used for expressing the preference degree of a user who releases the feedback information to the target object;

the first word extraction module is used for extracting a first target word from the plurality of feedback information, wherein the feedback parameter mean value of the feedback information comprising the first target word is different from the feedback parameter mean value of the feedback information not comprising the first target word;

a first weight determination module, configured to determine a first weight of the first target word based on a feedback parameter of the plurality of feedback information, where the first weight of the first target word is used to indicate a degree of influence of the first target word on the feedback parameter of the feedback information including the first target word.

In an optional implementation manner, the first word extraction module includes:

an information determining unit configured to determine, for any word included in the plurality of feedback information, a first number of first feedback information from the plurality of feedback information including the word, and determine the first number of second feedback information from the plurality of feedback information not including the word;

a parameter determining unit, configured to determine a difference indication parameter corresponding to the word based on the feedback parameters of the first number of first feedback information and the feedback parameters of the first number of second feedback information, where the difference indication parameter is used to indicate a difference between a feedback parameter average value of the feedback information including the word and a feedback parameter average value of the feedback information not including the word;

a word determination unit, configured to determine the word as the first target word in response to the difference indication parameter being greater than a threshold value.

In another optional implementation manner, the parameter determining unit is configured to:

In another optional implementation manner, the first term extraction module is configured to:

In another optional implementation manner, the first weight determining module is configured to:

In another optional implementation manner, the apparatus further includes:

the average value determining module is used for selecting a plurality of fourth feedback information from the plurality of feedback information and determining a sixth average value of the feedback parameters of the plurality of fourth feedback information;

a first weight updating module, configured to update the first weights of the plurality of first target terms based on the sixth average and the second occurrence indication parameters of the plurality of first target terms, so that a difference between a sum of the second influence parameters of the plurality of first target terms and the fifth average is smaller than the second threshold, and a difference between a sum of the third influence parameters of the plurality of first target terms and the sixth average is smaller than the second threshold;

In another optional implementation manner, the apparatus further includes:

the parameter obtaining module is used for selecting sixth feedback information from the plurality of feedback information and obtaining the feedback parameter of the sixth feedback information;

a second weight updating module, configured to update the first weights of the plurality of first target words based on the feedback parameter of the sixth feedback information and the fourth occurrence indication parameter of the plurality of first target words, so that a difference between a sum of fifth influence parameters of the plurality of first target words and the feedback parameter of the fifth feedback information is smaller than the third threshold, and a difference between a sum of sixth influence parameters of the plurality of first target words and the feedback parameter of the sixth feedback information is smaller than the third threshold;

In another optional implementation manner, the apparatus further includes:

a second word extraction module, configured to extract a second target word from a plurality of feedback information including the first target word, where a feedback parameter mean value of the feedback information including the second target word is different from a feedback parameter mean value of the feedback information not including the second target word;

a second weight determination module, configured to determine a second weight of the second target word based on a feedback parameter of a plurality of feedback information including the first target word;

In another optional implementation manner, the first term extraction module includes:

the word extraction unit is used for extracting a plurality of words with the occurrence frequency meeting the occurrence frequency condition from the plurality of feedback information;

and the target word selecting unit is used for selecting the first target word from the plurality of words.

In another optional implementation manner, the word extraction unit is configured to:

In another aspect, a computer device is provided, where the computer device includes a processor and a memory, where the memory stores at least one program code, and the at least one program code is loaded and executed by the processor to implement the feedback information processing method in any one of the above-mentioned optional implementation manners.

In another aspect, a computer-readable storage medium is provided, where at least one program code is stored, and the at least one program code is loaded and executed by a processor to implement the feedback information processing method in any one of the above-mentioned optional implementation manners.

In another aspect, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer program code, the computer program code being stored in a computer-readable storage medium, the computer program code being read by a processor of a computer device from the computer-readable storage medium, the computer program code being executed by the processor to cause the computer device to perform the feedback information processing method described in any one of the above-mentioned alternative implementations.

According to the technical scheme provided by the embodiment of the application, the target words capable of enabling the feedback parameters of the feedback information to generate differences are extracted from the multiple feedback information of the target object, the target words are used for representing the reason enabling the user to generate the corresponding preference degree on the target object, the influence degree of the target words on the feedback parameters is represented by the first weight, the importance degree of the reason represented by the target words on the target object is reflected, the target object is analyzed, the target words are automatically extracted from the multiple feedback information, the first weight of the target words is automatically determined based on the feedback parameters, workers do not need to browse and analyze the feedback information one by one, the analysis efficiency of the target object is improved, and the efficiency can be remarkably improved under the condition that the target object has massive feedback information.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

FIG. 1 is a schematic illustration of an implementation environment provided by an embodiment of the present application;

fig. 2 is a flowchart of a feedback information processing method provided in an embodiment of the present application;

fig. 3 is a flowchart of a feedback information processing method provided in an embodiment of the present application;

FIG. 4 is a schematic diagram of a word cloud provided by an embodiment of the present application;

FIG. 5 is a schematic diagram of a word cloud provided by an embodiment of the present application;

FIG. 6 is a schematic diagram of further mining points of interest provided by an embodiment of the present application;

fig. 7 is a block diagram of a feedback information processing apparatus according to an embodiment of the present application;

fig. 8 is a block diagram of a terminal according to an embodiment of the present application;

fig. 9 is a block diagram of a server according to an embodiment of the present application.

Detailed Description

To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.

The terms "first," "second," "third," and "fourth," etc. in the description and claims of this application and the accompanying drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "comprising" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.

Fig. 1 is a schematic diagram of an implementation environment provided by an embodiment of the present application. Referring to fig. 1, the implementation environment includes a terminal 101 and a computer device 102.

Optionally, the terminal 101 is a smart phone, a tablet computer, a notebook computer, a desktop computer, or a smart tv, but is not limited thereto. The terminal 101 and the computer device 102 are connected directly or indirectly through a wireless or wired network. The computer device 102 has a function of processing feedback information provided by the terminal 101. In some embodiments, the computer device 102 is a server, which is a server, a plurality of servers, a cloud server, a cloud computing platform, or a virtualization center, etc. In some embodiments, the computer device 102 is a desktop computer, a notebook computer, or a tablet computer, and the device type of the computer device 102 is not limited in the embodiments of the present application.

The terminal 101 refers to one of a plurality of terminals, and the computer device 102 is connected to the plurality of terminals and processes feedback information provided by the plurality of terminals.

The feedback information processing method provided by the embodiment of the application can be applied to a scene for analyzing any object.

For example, in a scenario of analyzing a music client, a user downloads the music client through an application download client, and after experiencing the music client, publishes feedback information and feedback parameters for the music client through the application download client, and a terminal sends the feedback information and the feedback parameters to a computer device. The computer device processes the feedback information of the music client by adopting the feedback information processing method provided by the embodiment of the application to obtain the target words to represent the reason for enabling the user to generate the corresponding preference degree on the music client, and determines the weight of the target words to represent the influence degree of the target words on the feedback parameters based on the feedback parameters of the feedback information, so that a developer of the music client can improve the music client in a targeted manner.

For another example, in a scenario of analyzing a commodity, a user purchases the commodity through a shopping client, and after experiencing the commodity, the user issues feedback information and feedback parameters for the commodity through the shopping client, and the terminal sends the feedback information and the feedback parameters to the computer device. The computer device processes the feedback information of the commodity by adopting the feedback information processing method provided by the embodiment of the application to obtain the target word to represent the reason for enabling the user to generate the corresponding preference degree on the commodity, and determines the weight of the target word based on the feedback parameter of the feedback information to represent the influence degree of the target word on the feedback parameter, so that a producer of the commodity can improve the commodity in a targeted manner.

Fig. 2 is a flowchart of a feedback information processing method according to an embodiment of the present application. Referring to fig. 2, the feedback information processing method will be briefly described with reference to fig. 2, and the feedback information processing method includes the following steps:

201. the computer equipment acquires a plurality of pieces of feedback information of the target object and feedback parameters of the plurality of pieces of feedback information, wherein the feedback parameters of the feedback information are used for expressing the preference degree of a user who releases the feedback information on the target object.

Wherein the target object is an object for which the user experiences and publishes feedback information. In some embodiments, the target object is a virtual product. For example, the target object is any one of a music client, a video client, a game client, a social client, a shopping client and the like; alternatively, the target object is any song. In some embodiments, the target object is a physical product, for example, the target object is any one of electronic devices such as a mobile phone, a computer, a television, a smart speaker, and a robot; alternatively, the target object is any one of articles such as clothes and accessories. In some embodiments, the target object is an object that provides a service for the user, e.g., the target object is a hotel that provides a residential service for the user; alternatively, the target object is a restaurant that provides a food service for the user, and the type of the target object is not limited in the embodiment of the present application.

The feedback information is text information for describing user's feeling of the target object. For example, the feedback information is comment information for the target object. The plurality of pieces of feedback information refer to pieces of feedback information issued by a plurality of users. One feedback information corresponds to one feedback parameter, and when the user edits the feedback information of the target object, the user also selects the feedback parameter to express the preference degree of the target object more intuitively. In some embodiments, the feedback parameter is a numerical value representing the user's preference for the target object, e.g., the feedback parameter is 1, 2, 3, 4, or 5, which in turn represents poor, general, good, or good.

202. The computer equipment extracts a first target word from the plurality of feedback information, wherein the average value of the feedback parameters of the feedback information including the first target word is different from the average value of the feedback parameters of the feedback information not including the first target word.

The feedback parameter average value of the feedback information including the first target word is different from the feedback parameter average value of the feedback information not including the first target word, that is, the first target word causes the feedback parameter of the feedback information including the first target word to be different from the feedback parameter of the feedback information not including the first target word, and since the feedback parameter is used for representing the preference degree of the user to the target object, whether the first target word is included or not expresses different preference degrees of the user to the target object, that is, the first target word can reflect the preference degree of the user to the target object, that is, can represent the reason that the user prefers or does not like the target object, and reflect the advantages and disadvantages of the target object.

203. The computer device determines a first weight of the first target word based on a feedback parameter of the plurality of feedback information, wherein the first weight of the first target word is used for representing the influence degree of the first target word on the feedback parameter of the feedback information comprising the first target word.

The occurrence of the first target word affects a feedback parameter of the feedback information, and therefore, the computer device determines a first weight of the first target word based on the feedback parameters of the plurality of feedback information, the first weight representing a degree of influence of the first target word on the feedback parameter.

The first weight is a positive number or a negative number, and under the condition that the first weight of the first target word is a positive number, the first weight indicates that the first target word has a positive influence on the feedback parameter, the first weight includes that the first target word is one of reasons for enabling the feedback parameter of the feedback information to be higher. Under the condition that the first weight of the first target word is negative, the first weight indicates that the first target word has a negative influence on the feedback parameter, the first target word is one of reasons for making the feedback parameter of the feedback information lower, correspondingly, the content of the first target word indicates a reason for making the user have a lower recognition degree on the target object, namely the disadvantage of the target object, and related personnel of the target object can know the disadvantage of the target object by looking at the first target word.

The absolute value of the first weight is positively correlated with the degree of influence of the first target word on the feedback parameter. Under the condition that the first weight is positive, the larger the first weight is, the larger the positive influence degree of the first target word on the feedback parameter is, the more the first target word can reflect the advantage of the target object, the more important the content representation reason of the first target word is to the target object, the more the advantage of the target object is maintained based on the first target word, and the more the user can improve the recognition degree of the target object; when the first weight is negative, the smaller the first weight is, the greater the degree of negative influence of the first target word on the feedback parameter is, the more the first target word reflects the disadvantage of the target object, the more important the cause of the content representation of the first target word is to the target object, and the more the user can improve the recognition degree of the target object based on the disadvantage of the first target word.

Fig. 3 is a flowchart of a feedback information processing method according to an embodiment of the present application. The feedback information processing method is described in detail below with reference to fig. 3, and referring to fig. 3, the feedback information processing method includes the following steps:

301. the computer device obtains a plurality of pieces of feedback information of the target object and feedback parameters of the plurality of pieces of feedback information.

In some embodiments, the computer device obtains a plurality of feedback information of the target object whose publication time is within the reference time period and feedback parameters of the plurality of feedback information. Wherein the reference time period is flexibly configurable. For example, the ending time of the reference time period is the current time, and the duration of the reference time period is one year, three months, one month, one week, or the like, which is not limited in the embodiment of the present application. In some embodiments, the computer device obtains the reference number of feedback information of the target object and the feedback parameters of the reference number of feedback information in the order from the near to the far of the publication time compared with the current time. The reference number can be flexibly configured, for example, the reference number is 10 ten thousand, 50 ten thousand, or 100 ten thousand, and the like, which is not limited in the embodiments of the present application. In some embodiments, the plurality of feedback information acquired by the computer device is all feedback information of the target object.

In some embodiments, the computer device locally stores the feedback information of the target object and the feedback parameters of the feedback information, and the computer device obtains the plurality of pieces of feedback information of the target object and the feedback parameters of the plurality of pieces of feedback information from the local storage. In some embodiments, the feedback information of the target object and the feedback parameters of the feedback information stored locally by the computer device are sent by the terminal. The storage process of the feedback information of the target object and the feedback parameters of the feedback information comprises the following steps: the terminal displays a feedback information editing interface; the terminal responds to the releasing operation of the feedback information and acquires the feedback information and the feedback parameters which are input in the feedback information editing interface; the terminal sends the feedback information and the feedback parameters to the computer equipment; the computer device, in response to receiving the feedback information and the feedback parameter, stores the feedback information and the feedback parameter in association.

In some embodiments, the feedback information of the target object is stored on an information storage server from which the computer device obtains a plurality of feedback information of the target object. In some embodiments, in a case that the target object is a certain client, the user downloads the client through the application download client, and issues feedback information to the client through the application download client, the information storage server is a background server of the application download client, and the information storage server is configured to receive and store the feedback information and the feedback parameters sent by the terminal. In some embodiments, different users download the client through different application download clients and issue feedback information to the client, and accordingly, the feedback information of the target object is stored in information storage servers corresponding to the different application download clients, and the computer device obtains the feedback information of the target object from the information storage servers. For example, manufacturers of different terminals provide different application downloading clients, the information storage servers are background servers of different manufacturers, and the computer device obtains feedback information from the background servers of different manufacturers, that is, obtains feedback information from each channel.

302. The computer equipment extracts a plurality of words with the occurrence frequency meeting the occurrence frequency condition from the plurality of feedback information.

In some embodiments, the frequency of occurrence refers to the number of occurrences of the word in the plurality of feedback information. In some embodiments, the frequency of occurrence condition is a second number of names arranged in descending order of frequency of occurrence, and step 302 includes: and the computer equipment sequences the words included in the plurality of feedback information according to the sequence of the occurrence frequency from large to small, and determines the words with the sequence in the second number as a plurality of words with parts of speech as the target parts of speech and the occurrence frequency meeting the occurrence frequency condition.

The second number can be flexibly configured, for example, the second number is 30, 50, or 100, and the like, which is not limited in the embodiments of the present application. The computer device determines the second number of words in the sequence as a plurality of words with the frequency of occurrence meeting the frequency of occurrence condition, that is, sequentially obtains the second number of words from the first word in the sequence, thereby obtaining a plurality of words with the frequency of occurrence meeting the frequency of occurrence condition. For example, the second number is 50, and the computer device determines the top 50 words as a plurality of words whose frequency of occurrence satisfies the frequency of occurrence condition.

According to the technical scheme, words with the most advanced current frequency sequence are selected from the plurality of feedback information, namely high-frequency words are selected, so that key points expressed by the feedback information published by the user group are reflected more accurately, and the accuracy of word extraction is improved.

In some embodiments, the frequency of occurrence condition is that the frequency of occurrence is greater than a frequency of occurrence threshold, and accordingly, the step 302 includes: the computer device determines a plurality of words with the occurrence frequency larger than the occurrence frequency threshold from the words included in the plurality of feedback information. The occurrence frequency threshold may be flexibly configured, for example, the occurrence frequency threshold is 500, 1000, or 2000, and the like, which is not limited in this embodiment of the application.

In some embodiments, the computer device obtains words included in the plurality of feedback information by performing word segmentation processing on the plurality of feedback information, and then extracts a plurality of words whose occurrence frequency satisfies the occurrence frequency condition from the words included in the plurality of feedback information, and accordingly, the step 302 includes: the computer equipment carries out word segmentation processing on the feedback information to obtain a plurality of words after word segmentation; and extracting a plurality of words with the occurrence frequency meeting the occurrence frequency condition from the plurality of words after word segmentation.

In some embodiments, the computer device extracts, from the plurality of feedback information, a plurality of words whose part-of-speech is the target part-of-speech and whose frequency of occurrence satisfies the frequency-of-occurrence condition. The target part of speech is a part of speech having a substantial meaning, and the target part of speech is flexibly configurable, for example, the target part of speech includes at least one of a noun, a verb, an adjective, and a vernoun, which is not limited in this embodiment of the application.

In some embodiments, the step of extracting, by the computer device, from the plurality of feedback information, a plurality of words whose part of speech is the target part of speech and whose frequency of occurrence satisfies the frequency of occurrence condition includes: the computer equipment carries out word segmentation processing and part-of-speech tagging processing on the plurality of feedback information to obtain a plurality of words after word segmentation and the part-of-speech of each word; extracting words with parts of speech as target parts of speech from the words after word segmentation; and extracting a plurality of words with the occurrence frequency meeting the occurrence frequency condition from the words with the part of speech as the target part of speech. The process of extracting the words with the occurrence frequency meeting the occurrence frequency condition from the words with the part of speech as the target part of speech by the computer device is the same as the process of extracting the words with the occurrence frequency meeting the occurrence frequency condition from the feedback information by the computer device, and the description is omitted here.

According to the technical scheme, the plurality of words with the parts of speech as the target parts of speech and the occurrence frequency meeting the occurrence frequency condition are extracted, so that the extracted plurality of words can reflect the substantial problem concerned by the user group, and the accuracy of word extraction is improved.

In some embodiments, the computer device extracts, from the plurality of feedback information, a plurality of words whose frequency of occurrence satisfies the frequency of occurrence condition and which are used to describe a function of the target object. In some embodiments, the step of extracting, by the computer device, from the plurality of feedback information, the frequency of occurrence satisfies the frequency of occurrence condition, and the plurality of words describing the function of the target object includes: the computer equipment extracts a plurality of words with the occurrence frequency meeting the occurrence frequency condition from the plurality of feedback information; from the extracted plurality of words, a plurality of words for describing a function of the target object is determined.

In some embodiments, the computer device determines, from the extracted plurality of words, a plurality of words for describing a function of the target object through a word recognition model. The computer equipment inputs the extracted words into a word recognition model to obtain a function identifier of each word output by the word recognition model; the word identifying the function as the target function identification is determined as a word for describing the function of the target object.

The function identification comprises a first function identification or a second function identification, the first function identification represents that the corresponding words are used for describing the functions of the target object, the second function identification represents that the corresponding words are not the words used for describing the functions of the target object, and the target function identification is the first function identification. For example, the first function identifier is 1, the second function identifier is 0, the target function identifier is 1, and the computer device determines the word with function identifier 1 as the word for describing the function of the target object.

The word recognition model is used for recognizing whether the words are used for describing the functions of the target object, and is obtained through training by a machine learning method. The training process of the word recognition model comprises the following steps: acquiring a training sample, wherein the training sample comprises words and function identifiers, and the function identifiers in the training sample are used for identifying whether the words in the training sample are used for describing the functions of the target object; based on the training samples, a word recognition model is trained. The training samples based on the word recognition model training are multiple in number, and the training samples respectively comprise different words and different function identifications. The plurality of training samples may be divided into positive samples and negative samples, the positive samples including words describing the function of the target object and a first function identification, and the negative samples including words not describing the function of the target object and a second function identification.

In some embodiments, in the training process of the word recognition model, for any training sample in a plurality of training samples, inputting the training sample into the word recognition model to obtain a training function identifier output by the word recognition model; updating model parameters of the word recognition model in response to the fact that the training function identification is inconsistent with the function identification included in the training sample; and under the condition that the training function identification output by the word recognition model for n times continuously is consistent with the function identification included by the corresponding training sample, stopping training and outputting the word recognition model after training. Where n is a positive integer, for example, n is 3, 5, or 10, and the like, which is not limited in the present application.

According to the technical scheme, the plurality of words with the occurrence frequency meeting the occurrence frequency condition and used for describing the functions of the target object are extracted, so that the extracted words can reflect the substantial problem concerned by a user group, and the accuracy of word extraction is improved.

In some embodiments, to ensure reliability of word selection, a plurality of words describing the function of the target object are selected with assistance of a worker. Under the condition that the computer equipment has a display function, after extracting a plurality of words with the occurrence frequency meeting the occurrence frequency condition from a plurality of feedback information, the computer equipment displays a word selection interface, wherein the word selection interface comprises a plurality of words with the occurrence frequency meeting the occurrence frequency condition and a selection control corresponding to each word; the computer device determines the word for which the selection control is selected as a plurality of words for describing the functionality of the target object. Under the condition that the computer equipment does not have a display function, the computer equipment extracts a plurality of words with the occurrence frequency meeting the occurrence frequency condition from the plurality of feedback information, and then sends the extracted words to a terminal with a display function connected with the computer equipment; the terminal displays a word selection interface, wherein the word selection interface comprises a plurality of words with the occurrence frequency meeting the occurrence frequency condition and a selection control corresponding to each word; the terminal obtains the selected words of the selection control; sending the selected words of the selection control to the computer equipment; the computer equipment receives the words sent by the terminal, so that a plurality of words for describing the functions of the target object are obtained.

In some embodiments, the computer device divides the obtained plurality of feedback information into two groups according to the magnitude relation between the feedback parameter and the fourth threshold, and extracts a plurality of words whose occurrence frequency meets the occurrence frequency condition from the two groups of feedback information respectively. Correspondingly, the step of extracting, by the computer device, the words whose occurrence frequencies satisfy the occurrence frequency condition from the plurality of feedback information includes: extracting, by the computer device, words of which the occurrence frequency meets the occurrence frequency condition from the plurality of feedback information of which the feedback parameters are greater than the fourth threshold; and extracting the words with the occurrence frequency meeting the occurrence frequency condition from the plurality of feedback information with the feedback parameters smaller than the fourth threshold value by the computer equipment.

In some embodiments, the larger the feedback parameter is, the more the user likes the target object, the fourth threshold is used to indicate that the preference degree of the user for the target object is the medium preference degree, and the feedback information of which the feedback parameter is greater than the fourth threshold is used to indicate that the user likes the target object; the feedback information with the feedback parameter smaller than the fourth threshold is used for indicating that the user dislikes the target object. In some embodiments, feedback information with a feedback parameter greater than a fourth threshold is also referred to as good scores, and feedback information with a feedback parameter less than the fourth threshold is also referred to as bad scores. The fourth threshold may be flexibly configured according to the distribution of the feedback parameters, and in some embodiments, the fourth threshold is an intermediate value in the distribution of the feedback parameters. For example, if the feedback parameter is 1, 2, 3, 4 or 5, the fourth threshold is 3.

According to the technical scheme, words are extracted from the feedback information with higher feedback parameters and the feedback information with lower feedback parameters respectively, so that the advantages of the target object expressed by the user group with higher feedback parameters through the feedback information and the disadvantages of the target object expressed by the user group with lower feedback parameters through the feedback information are obtained, the pertinence of word extraction is improved, a maintainer of the target object can maintain the advantages of the target object in a targeted mode according to the extracted extraction, and the disadvantages of the target object are improved.

It should be noted that, the technical solution provided by the above embodiments to extract a plurality of words from a plurality of feedback information may be combined in any manner to form other alternative embodiments. For example, the step of extracting, by the computer device, from the plurality of feedback information, the plurality of words whose occurrence frequencies satisfy the occurrence frequency condition includes: performing word segmentation processing and part-of-speech tagging processing on a plurality of pieces of feedback information with the feedback parameters larger than a fourth threshold value to obtain a plurality of first words after word segmentation and part-of-speech of each first word; determining a first word with part of speech as a target part of speech from a plurality of first words; sequencing first words with parts of speech as target parts of speech according to the sequence of the occurrence frequency from large to small, and determining the first number of words with the sequence as a plurality of second words with parts of speech as target parts of speech and occurrence frequency meeting the occurrence frequency condition; determining a plurality of third words for describing the function of the target object from the plurality of second words; performing word segmentation processing and part-of-speech tagging processing on a plurality of pieces of feedback information with the feedback parameters smaller than a fourth threshold value to obtain a plurality of fourth words after word segmentation and part-of-speech of each fourth word; determining a fourth word with the part of speech as the target part of speech from the plurality of fourth words; according to the sequence of the occurrence frequency from big to small, ordering the fourth words with the part of speech as the target part of speech, and determining the words with the second number in the top order as a plurality of fifth words with the part of speech as the target part of speech and the occurrence frequency meeting the occurrence frequency condition; from the plurality of fifth words, a plurality of sixth words for describing a function of the target object is determined. The third words and the sixth words are words extracted from the feedback information.

In some embodiments, the target object is a music client, the second words whose parts of speech are target parts of speech and whose occurrence frequency satisfies the occurrence frequency condition may be drawn as a word cloud graph as shown in fig. 4, the word cloud graph shown in fig. 4 may also be referred to as a good term cloud, the fifth words whose parts of speech are target parts of speech and whose occurrence frequency satisfies the occurrence frequency condition may be drawn as a word cloud graph as shown in fig. 5, and the word cloud graph shown in fig. 5 may also be referred to as a bad term cloud.

303. The computer device selects a first target word from the extracted plurality of words.

And the feedback parameter average value of the feedback information comprising the first target word is different from the feedback parameter average value of the feedback information not comprising the first target word. In some embodiments, the amount of the multiple feedback information of the target object is huge, and the computer device selects a small amount of feedback information to reflect the difference situation of the multiple feedback information in total. Accordingly, the step 303 includes the following steps 3031 to 3033:

3031. for any word included in the extracted plurality of words, the computer device determines a first number of first feedback information from the plurality of feedback information including the word, and determines a first number of second feedback information from the plurality of feedback information not including the word.

The first number may be flexibly configured, for example, the first number is 30, 50, 100, or 200, and the like, which is not limited in this embodiment of the application.

3032. The computer device determines a difference indication parameter corresponding to the word based on the feedback parameters of the first number of first feedback information and the feedback parameters of the first number of second feedback information.

Wherein the difference indication parameter is used for indicating the difference between the average value of the feedback parameters of the feedback information including the word and the average value of the feedback parameters of the feedback information not including the word. The step 3032 includes: the computer equipment determines a first average value of the feedback parameters of the first quantity of first feedback information and determines a second average value of the feedback parameters of the first quantity of second feedback information; determining a combined standard deviation based on the first mean value, the second mean value, the feedback parameters of the first amount of first feedback information and the feedback parameters of the first amount of second feedback information; and determining a difference indication parameter corresponding to the word based on the first mean value, the second mean value, the combined standard deviation and the first quantity.

The step of determining, by the computer device, a combined standard deviation based on the first mean value, the second mean value, the feedback parameters of the first number of pieces of first feedback information, and the feedback parameters of the first number of pieces of second feedback information includes: the computer equipment determines a first square difference based on the first mean value and the feedback parameters of the first feedback information of the first quantity; the computer equipment determines a second variance based on the second mean value and the feedback parameters of the first quantity of second feedback information; a combined standard deviation is determined based on the first variance, the second variance, and the first quantity. Wherein the computer device determines the combined standard deviation by the following formula one.

The formula I is as follows:

wherein s is_pRepresents the combined standard deviation; n is₁Denotes a first number, n₁Is a positive integer;

which represents the first variance of the first signal,

is a positive number; n is₂Denotes a first number, n₂Is a positive integer;

the second variance is represented as a function of,

is a positive number.

The first variance is an average of squared values of differences between the feedback parameter of each first feedback information and the first mean value, and the computer device determines the first variance by the following formula two.

The formula II is as follows:

wherein the content of the first and second substances,

representing a first variance; x_iA feedback parameter representing the ith first feedback information, i being greater than 0 and less than or equal to n₁A positive integer of (d); n is₁Denotes a first number, n₁Is a positive integer;

representing the first mean value.

The second variance is an average of squared values of differences between the feedback parameter of each second feedback information and the second mean value, and the computer device determines the second variance according to the following formula three.

The formula III is as follows:

wherein the content of the first and second substances,

representing a second variance; x_iA feedback parameter representing the ith second feedback information, i is greater than 0 and less than or equal to n₂A positive integer of (d); n is₂Denotes a first number, n₂Is a positive integer;

representing the second mean.

In some embodiments, the feedback information including the first target word is also referred to as a first group of feedback information, the feedback information not including the first target word is also referred to as a second group of feedback information, the computer device determines a difference indicating parameter corresponding to the word by a method of t-test based on the first mean value, the second mean value, the combined standard deviation and the first quantity, and determines whether the difference between the mean values of the feedback parameters of the two groups of feedback information is significant or not based on the difference indicating parameter. The step of determining the difference indication parameter corresponding to the word by the computer device through a t-test method based on the first mean value, the second mean value, the combined standard deviation and the first quantity comprises the following steps: the computer equipment determines the difference value of the first mean value and the second mean value; determining a square root of twice the inverse of the first quantity; determining the product of said combined standard deviation and said square root; determining a ratio of said difference to said product; the absolute value of the above ratio is determined as the difference indicating parameter. That is, the computer device determines the difference indicating parameter by the following formula four.

The formula four is as follows:

wherein t represents a differenceAn indication parameter, also referred to as a t statistic in some embodiments;

represents a first mean value;

represents a second mean value; s_pRepresents the combined standard deviation; n is₁Representing a first quantity; n is₂A first number is indicated.

According to the technical scheme, based on the feedback parameters of the first quantity of first feedback information and the feedback parameters of the first quantity of second feedback information, the mean value and the merging standard deviation corresponding to the feedback parameters are determined, and then the statistic quantity reflecting the difference condition of the feedback parameter mean value of the feedback information including a certain word and the feedback parameter mean value of the feedback information not including the word is determined, so that the accuracy of the difference indication parameter on the difference condition expression is improved.

3033. The computer device determines the word as the first target word in response to the difference indicating parameter being greater than the threshold value.

In some embodiments, the computer device establishes an original hypothesis that a feedback parameter mean value of the first group of feedback information is equal to a feedback parameter mean value of the second group of feedback information by a t-test method, and establishes an alternative hypothesis that the feedback parameter mean value of the first group of feedback information is different from the feedback parameter mean value of the second group of feedback information; in the case of significance level alpha, look-up t alpha/2, n from the t distribution critical value table₁-1 as a critical value, wherein t α/2, n₁-1 is n₁-1 and a/2. α represents a probability of falsely rejecting the original hypothesis, that is, a probability of rejecting the original hypothesis when the original hypothesis is established, and α is flexibly configurable, for example, α is 0.05 or 0.01, and the embodiment of the present application does not limit this.

The more the difference indicating parameter is greater than the critical value, the lower the probability of falsely rejecting the original hypothesis is, the higher the probability of correctly rejecting the original hypothesis is, that is, the higher the probability that the feedback parameter mean of the first group of feedback information is different from the feedback parameter mean of the second group of feedback information is, the more significant the difference between the feedback parameter mean of the first group of feedback information and the feedback parameter mean of the second group of feedback information is, and therefore, the computer device determines the word as the first target word in response to the difference indicating parameter being greater than the critical value. In addition, the computer device continues to select a first target word from the remaining plurality of words in response to the difference indicating parameter not being greater than the threshold value, without performing the step of determining the word as the first target word.

According to the technical scheme provided by the embodiment of the application, a small amount of feedback parameters of the feedback information are selected from massive feedback information to serve as sample data, the difference indication parameters are determined according to the sample data, the difference condition of the average value of the feedback parameters of the massive feedback information is reflected by the difference indication parameters, and the target words which enable the feedback parameters of the feedback information to generate differences are determined. In the process, the target words can be determined according to the feedback parameters of a small amount of feedback information, the determination efficiency of the target words is improved, the calculation resources consumed by determining the target words are reduced, and the utilization rate of the calculation resources is improved.

In some embodiments, the computer device determines a third average value of the feedback parameters of all feedback information including a certain word and a fourth average value of the feedback parameters of all feedback information not including the word, respectively, and determines the word as the first target word if the third average value and the fourth average value are different greatly. Correspondingly, the step of selecting the first target word from the extracted plurality of words by the computer device comprises the following steps: for any word of the extracted plurality of words, the computer device determines a third mean value of feedback parameters of the plurality of feedback information that includes the word, and determines a fourth mean value of feedback parameters of the plurality of feedback information that does not include the word; the computer device determines the word as the first target word in response to a difference between the third mean and the fourth mean being greater than a first threshold. The first threshold may be flexibly configured according to a value range of the feedback parameter, where the first threshold is smaller than a difference between an upper limit and a lower limit of the value range of the feedback parameter, for example, the feedback parameter is 1, 2, 3, 4, or 5, and the first threshold is 3, 3.5, or 4, and the like, which is not limited in this embodiment of the application. In addition, the computer device continues to select a first target word from the remaining plurality of words in response to the difference between the third average and the fourth average not being greater than the first threshold, without performing the step of determining the word as the first target word.

According to the technical scheme, whether the word is the target word or not is determined by comparing the average value of the feedback information including a certain word with the average value of the feedback information not including the word, and the accuracy of determining the target word is improved.

According to the technical scheme provided by the steps 302 to 303, the plurality of words are extracted from the plurality of feedback information according to the occurrence frequency condition, so that the extracted plurality of words can more accurately represent key points expressed by the feedback information published by the user group, and further, the target words are selected from the extracted plurality of words, so that the target words can represent key reasons causing the user to generate different preference degrees on the target object, and the accuracy of target word selection is improved.

In some embodiments, the computer device extracts the first target word from the plurality of words included in the plurality of feedback information after acquiring the plurality of feedback information. In some embodiments, the step 302 to the step 303 may be replaced by the following steps: for any word included in the plurality of feedback information, the computer device determines a first number of first feedback information from the plurality of feedback information including the word, and determines a first number of second feedback information from the plurality of feedback information not including the word; determining a difference indicating parameter corresponding to the word based on the feedback parameters of the first number of first feedback information and the feedback parameters of the first number of second feedback information, wherein the difference indicating parameter is used for indicating the difference condition of the average value of the feedback parameters of the feedback information including the word and the average value of the feedback parameters of the feedback information not including the word; in response to the difference indication parameter being greater than a threshold, the word is determined to be a first target word.

In some embodiments, the above steps 302 to 303 can be replaced by the following steps: for any word included in the plurality of feedback information, the computer device determines a third average of the feedback parameters of the plurality of feedback information that includes the word, and determines a fourth average of the feedback parameters of the plurality of feedback information that does not include the word; in response to a difference between the third average and the fourth average being greater than a first threshold, the word is determined to be the first target word.

304. The computer device determines a first weight for the first target word based on a feedback parameter of the plurality of feedback information.

Wherein the first weight of the first target word is used for representing the influence degree of the first target word on the feedback parameter of the feedback information comprising the first target word. In some embodiments, the computer device determines a plurality of first target words through the above steps 302 to 303. For example, referring to table 1, in the case where the target object is a music client, the plurality of first target words include copyrights, VIP (members) and members, payment and charge, sound effects, play, interface, song list, live broadcast, advertisement, lyrics, collection, and experience, and the amount of feedback information including each of the first target words is different.

TABLE 1

First target word	Number of feedback information including first target word
		Copyright rights	30055
VIP and member	19386
		Payment and charging	7054
Sound effect	5633
		Play back	3110
Interface (I)	2420
		Singing sheet	1984
Live broadcast	1781
		Advertising	1717
Lyric of a song	1706
		Collection method	1339
Experience (experience)	1242

Wherein, the VIP and the member are words with the same meaning, and the computer device determines the feedback information including the VIP and the feedback information including the member as the feedback information including the VIP, or determines the feedback information including the VIP and the feedback information including the member as the feedback information including the member. The payment and the charge are words of the same sense, and the computer device determines both the feedback information including the payment and the feedback information including the charge as feedback information including the payment, or the computer device determines both the feedback information including the payment and the feedback information including the charge as feedback information including the charge.

In the case that one piece of feedback information comprises a plurality of first target words, each first target word influences a feedback parameter of the piece of feedback information, so that the computer device determines first weights of the plurality of first target words respectively based on the feedback parameters of the plurality of pieces of feedback information, and the influence degree of the first target words on the feedback parameter is reflected more clearly and definitely.

In some embodiments, the computer device selects multiple sets of feedback information from multiple sets of feedback information of the target object, and iteratively updates the first weight of the first target word based on a mean value of feedback parameters of the multiple sets of feedback information and an occurrence of the first target word in each set of feedback information, so that the first weight more accurately represents an influence degree of the first target word on the feedback parameters.

In an iterative process, the step of determining, by the computer device, a first weight of the first target word based on the feedback parameters of the plurality of feedback information includes: the computer equipment selects a plurality of third feedback information from the plurality of feedback information and determines a fifth average value of the feedback parameters of the plurality of third feedback information; the computer equipment determines a first weight of the plurality of first target words based on the fifth mean value and the extracted first occurrence indication parameters of the plurality of first target words, and the difference value of the sum value of the first influence parameters of the plurality of first target words and the fifth mean value is smaller than a second threshold value; and for any first target word in the plurality of first target words, the first occurrence indication parameter of the first target word is used for representing the occurrence condition of the first target word in the plurality of third feedback information, and the first influence parameter of the first target word is the product of the first occurrence indication parameter of the first target word and the first weight of the first target word.

The plurality of third feedback information is any plurality of feedback information in the plurality of feedback information, the computer device randomly selects the plurality of feedback information from the plurality of feedback information, and the selected plurality of feedback information is the plurality of third feedback information. It should be noted that, in the embodiment of the present application, the number of the plurality of third feedback information selected by the computer device is not limited, for example, the number of the plurality of third feedback information is 1000, 5000, or 10000. The second threshold may be flexibly configured, for example, the second threshold is 0.1, 0.2, or 0.5, and the like, which is not limited in this embodiment of the application.

In some embodiments, the computer device establishes a regression model representing the association of the feedback parameter with the first target word, the dependent variable in the regression model being the feedback parameter and the independent variable being the occurrence of the first target word. For example, if the first target words determined by the computer device include sound effects, payment, and collection, the regression model is represented as v ═ ax + by + cz, where v represents the feedback parameter, a represents the first weight of "sound effects", x represents the occurrence of "sound effects" in the feedback information, b represents the first weight of "payment", y represents the occurrence of "payment" in the feedback information, c represents the first weight of "collection", and z represents the occurrence of "collection" in the feedback information. The computer device determines a first weight for the first target word, i.e., a first weight to fit the regression model.

In some embodiments, the first occurrence indication parameter is used to indicate whether the first target word occurs in the plurality of third feedback information, the first occurrence indication parameter is 0 or 1, 0 indicates that the first target word does not occur in the plurality of third feedback information, and 1 indicates that the first target word occurs in the plurality of third feedback information. For example, referring to table 2, in the case where the target object is a music client, the dependent variable is a feedback parameter, and the plurality of first target words include sound effect, payment, collection, copyright, member, interface, lyric, play, experience, advertisement, live broadcast, and song list. For any first target word, under the condition that the first target word appears in the feedback information, the first appearance indication parameter of the first target word is 1; in the case that the first target word does not appear in the feedback information, the first appearance indication parameter of the first target word is 0.

TABLE 2

For example, the plurality of first target words includes sound effects, payment and collection, the plurality of third feedback information includes 200 sound effects, 100 payment and 90 collection, and the average value of the feedback parameters of the plurality of third feedback information is 4, the computer device determines a, b and c, so that the difference between 4 and a + b + c is less than a second threshold, wherein a represents a first weight of sound effects, b represents a first weight of payment, and c represents a first weight of collection.

In some embodiments, the first occurrence indication parameter is used to indicate a number of occurrences of the first target word in the plurality of third feedback information. For example, the plurality of first target words includes sound effects, payment and collection, the plurality of third feedback information includes 200 "sound effects", 100 "payment" and 90 "collection", and the average value of the feedback parameters of the plurality of third feedback information is 4, the computer device determines a, b and c such that the difference between 4 and 200a +100b +90c is less than the second threshold.

According to the technical scheme, the weight of the target word and the feedback parameter represented by the occurrence condition of the target word in the selected part of feedback information are close to the average value of the feedback parameters of the part of feedback information as much as possible, so that the accuracy of determining the weight of the target word and the universality of the weight of the target word on the feedback information of the target object are improved.

In some embodiments, the computer device further selects a plurality of fourth feedback information from the plurality of feedback information after determining the first weight of the plurality of first target words based on the plurality of third feedback information, to update the first weight of the plurality of first target words based on the plurality of third feedback information and the plurality of fourth feedback information, such that the updated first weight approximates both the feedback parameter corresponding to the plurality of third feedback information determined based on the updated weight and the average of the feedback parameters of the plurality of third feedback information and the feedback parameter corresponding to the plurality of fourth feedback information determined based on the updated weight and the average of the feedback parameters of the plurality of fourth feedback information.

Correspondingly, after the computer device determines the first weight of the plurality of first target words and makes the difference value between the sum of the first influence parameters of the plurality of first target words and the fifth mean value smaller than the second threshold value, the following steps are further performed: the computer equipment selects a plurality of fourth feedback information from the plurality of feedback information and determines a sixth average value of the feedback parameters of the plurality of fourth feedback information; the computer equipment updates the first weights of the first target words based on the sixth average value and the second occurrence indication parameters of the first target words, so that the difference value between the sum value of the second influence parameters of the first target words and the fifth average value is smaller than a second threshold value, and the difference value between the sum value of the third influence parameters of the first target words and the sixth average value is smaller than the second threshold value; for any first target word in the plurality of first target words, the second occurrence indication parameter of the first target word is used for representing the occurrence condition of the first target word in the plurality of fourth feedback information, the second influence parameter of the first target word is the product of the first occurrence indication parameter of the first target word and the first weight after the first target word is updated, and the third influence parameter of the target word is the product of the occurrence indication parameter of the first target word and the first weight after the first target word is updated. The plurality of fourth feedback information is any plurality of feedback information except the plurality of third feedback information in the plurality of feedback information, the computer device randomly selects a plurality of feedback information different from the plurality of third feedback information from the plurality of feedback information, and the plurality of selected feedback information is the plurality of fourth feedback information. The number of the plurality of fourth feedback information is not limited in the embodiment of the present application, for example, the number of the plurality of fourth feedback information is 1000, 5000, 10000, or the like.

For example, the first occurrence indication parameter is used to indicate the number of occurrences of the first target word in the third feedback information, the second occurrence indication parameter is used to indicate the number of occurrences of the first target word in the fourth feedback information, the first target words include sound effects, payment and collection, the third feedback information includes 200 sound effects, 100 payment and 90 collection, the average value of the feedback parameters of the third feedback information is 4, the fourth feedback information includes 100 sound effects, 10 payment and 20 collection, the average value of the feedback parameters of the fourth feedback information is 3.5, the computer device updates a, b and c so that the difference between 4 and 200a +100b +90c is smaller than the second threshold, and the difference between 3.5 and 100a +10b +20c is smaller than the second threshold, wherein a represents the first weight of the updated sound effects, b represents the first weight of the updated "pay", and c represents the first weight of the updated "favorites".

In some embodiments, the computer device may update the first weight multiple times based on the multiple different pieces of feedback information selected multiple times, respectively, through a process similar to the process of updating the first weight of the first target word based on the multiple pieces of fourth feedback information. In some embodiments, the computer device updates the first weight multiple times according to the reference times, wherein the reference times can be flexibly configured, for example, the reference times are 10, 50, or 100, and the like, which is not limited in this application. In some embodiments, after updating the first weight, the computer device selects multiple sets of verification feedback information from the multiple sets of feedback information, for any set of verification feedback information, the computer device determines a verification feedback parameter corresponding to the set of feedback information based on the updated first weight and the occurrence of the first target word in the set of verification feedback information, determines a difference between the verification feedback parameter and a mean value of the feedback parameters of the set of verification feedback information, and compares the difference with a second threshold to obtain a verification result; and under the condition that the verification result is that the proportion of the group number of the target verification result is greater than the proportion threshold value, ending the updating of the first weight, wherein the updated first weight before the verification is the finally determined first weight. The target verification result is that the difference is smaller than the second threshold, and the verification result is the proportion of the number of groups of the target verification result, that is, the verification result is the proportion of the number of groups of the target verification result and the number of groups of the multiple groups of verification feedback information.

According to the technical scheme, the weight of the target word is updated in an iterative mode, so that the feedback parameters expressed by the weight of the target word and the occurrence condition of the target word in the plurality of feedback information are as close as possible to the average value of the feedback parameters of the plurality of feedback information, and the accuracy of determining the weight of the target word is improved.

In some embodiments, the target object is a music client, the plurality of first target words includes members, pay, copyright, play, song list, lyrics, interface, live broadcast, favorite, advertisement and sound effect, and the computer device finally determines a first weight of each first target word as shown in table 3.

TABLE 3

The first weight of the first target word is a positive number or a negative number, and under the condition that the first weight is the positive number, the first weight indicates that the effect of the first target word on the feedback parameter of the feedback information is positive, namely the effect of enabling the feedback parameter to be larger; in the case where the first weight is a negative number, the first weight indicates that the effect of the first target word on the feedback parameter of the feedback information is a negative effect, that is, an effect of making the feedback parameter smaller. The larger the absolute value of the first weight is, the larger the degree of influence of the first target word on the feedback parameter of the feedback information is represented. For example, the first weight of "member" is-19.525, which means that the feedback information including "member" is strongly negatively correlated with the feedback parameter, and most of the feedback parameters including the feedback information of "member" are low.

The corresponding p-value and significance of the first target word are also shown in table 3. Where the p value is accurate to three decimal places. The p value represents a probability of making a mistake in determining that the mean value of the feedback parameters of the feedback information including the first target word is different from the mean value of the feedback parameters of the feedback information not including the first target word, that is, in the case that there is no difference between the mean value of the feedback parameters of the feedback information including the first target word and the mean value of the feedback parameters of the feedback information not including the first target word, the probability of erroneously determining that the mean value of the feedback parameters of the feedback information including the first target word is different from the mean value of the feedback parameters of the feedback information not including the first target word. The larger the p value is, the less the difference indicated by the selected sample data can reflect the difference of the feedback information as a whole. The smaller the p value is, the more accurately the difference represented by the selected sample data can reflect the difference of the feedback information population, and the more significant the difference between the feedback parameter average of the feedback information including the first target word and the feedback parameter average of the feedback information not including the first target word is. The significance represents the significance degree of the difference between the feedback parameter average value of the feedback information of the first target word and the feedback parameter average value of the feedback information not including the first target word, the significance is positively correlated with the p value, and the smaller the p value is, the higher the significance degree is; the larger the p-value, the lower the significance.

In some embodiments, the computer device iteratively updates the first weight for the first target term based on the feedback parameters of the plurality of feedback information and the occurrence of the first target term in each feedback information, respectively. In an iterative process, the step of determining, by the computer device, a first weight of the first target word based on the feedback parameters of the plurality of feedback information includes: the computer equipment selects fifth feedback information from the plurality of feedback information and obtains a feedback parameter of the fifth feedback information; the computer equipment determines a first weight of the first target words based on the feedback parameters of the fifth feedback information and the extracted third occurrence indication parameters of the first target words, and the difference value between the sum of the fourth influence parameters of the first target words and the feedback parameters of the fifth feedback information is smaller than a third threshold value; and for any first target word in the plurality of first target words, the third occurrence indication parameter of the first target word is used for representing the occurrence condition of the first target word in the fifth feedback information, and the fourth influence parameter of the first target word is the product of the third occurrence indication parameter of the first target word and the first weight of the first target word.

The fifth feedback information is any one of the plurality of feedback information, the computer device randomly selects one feedback information from the plurality of feedback information, and the selected feedback information is the fifth feedback information. The third threshold may be flexibly configured, for example, the third threshold is 0.2, 0.3, or 0.5, and the like, which is not limited in the embodiment of the present application.

In some embodiments, the third occurrence indication parameter is used to indicate whether the first target word is present in the fifth feedback information. In some embodiments, the third occurrence indication parameter is used to indicate a number of occurrences of the first target word in the fifth feedback information. For example, the plurality of first target words includes sound effects, payment and collection, the fifth feedback information includes 2 "sound effects", 1 "payment" and 0 "collection", the feedback parameter of the fifth feedback information is 4, and in the case that the third occurrence indication parameter is used to indicate the number of occurrences of the first target words in the fifth feedback information, the computer device determines a, b and c such that the difference between 4 and 2a + b is less than the third threshold value.

According to the technical scheme, the weight of the target word and the feedback parameter represented by the occurrence condition of the target word in certain feedback information are close to the feedback parameter of the feedback information as much as possible, and the accuracy of determining the weight of the target word is improved.

In some embodiments, the computer device further selects new feedback information from the plurality of feedback information after determining the first weights of the plurality of first target words based on the fifth feedback information, to update the first weights of the plurality of first target words based on the fifth feedback information and the new feedback information, such that the updated first weights both approximate the feedback parameters corresponding to the fifth feedback information determined based on the updated weights to the feedback parameters of the fifth feedback information and approximate the feedback parameters corresponding to the new feedback information determined based on the updated weights to the feedback parameters of the new feedback information.

Correspondingly, after determining the first weights of the plurality of first target words and making the difference value between the sum value of the fourth influence parameters of the plurality of first target words and the feedback parameter of the fifth feedback information smaller than the third threshold value, the computer device further performs the following steps: the computer equipment selects sixth feedback information from the plurality of feedback information and obtains a feedback parameter of the sixth feedback information; the computer equipment updates the first weights of the first target words based on the feedback parameters of the sixth feedback information and the fourth appearance indication parameters of the first target words, so that the difference value between the sum value of the fifth influence parameters of the first target words and the feedback parameters of the fifth feedback information is smaller than a third threshold value, and the difference value between the sum value of the sixth influence parameters of the first target words and the feedback parameters of the sixth feedback information is smaller than the third threshold value; for any first target word in the plurality of first target words, the fourth occurrence indication parameter of the first target word is used for representing the occurrence condition of the first target word in the sixth feedback information, the fifth influence parameter of the first target word is the product of the third occurrence indication parameter of the first target word and the first weight after the first target word is updated, and the sixth influence parameter of the first target word is the product of the fourth occurrence indication parameter of the first target word and the first weight after the first target word is updated. The sixth feedback information is any one of the plurality of feedback information different from the fifth feedback information, the computer equipment randomly selects one of the plurality of feedback information which is different from the fifth feedback information, and the selected feedback information is the sixth feedback information.

In some embodiments, the computer device may update the first weight a plurality of times based on the plurality of feedback information, respectively, through a process that is the same as updating the first weight of the first target word based on the sixth feedback information. In some embodiments, the computer device updates the first weight multiple times according to the reference times, wherein the reference times can be flexibly configured, for example, the reference times are 10, 50, or 100, and the like, which is not limited in this application. In some embodiments, after updating the first weight, the computer device selects multiple pieces of verification feedback information from the multiple pieces of feedback information, and for any piece of verification feedback information, the computer device determines a verification feedback parameter corresponding to the feedback information based on the updated first weight and the occurrence of the first target word in the verification feedback information, determines a difference between the verification feedback parameter and the feedback parameter of the verification feedback information, and compares the difference with a third threshold to obtain a verification result; and under the condition that the proportion of the number of the verification feedback information with the verification result being the target verification result is greater than a proportion threshold value, ending the updating of the first weight, wherein the updated first weight before the verification is the finally determined first weight. The target verification result is the ratio of the number of groups of the target verification result, that is, the ratio of the number of the verification feedback information with the verification result being the target verification result to the number of the verification feedback information with the verification result being the target verification result.

According to the technical scheme, the weights of the target words are updated in an iterative mode, so that the weights of the target words and the feedback parameters expressed by the occurrence conditions of the target words in the feedback information are as close as possible to the feedback parameters of the feedback information, and the accuracy of determining the weights of the target words is improved.

In some embodiments, after determining the first target word and the first weight of the first target word, the computer device outputs the first target word and the first weight of the first target word, so that the relevant people of the target object can view the first target word and the first weight of the first target word and visually know the advantages and disadvantages of the target object. In some embodiments, after determining the first target word and the first weight of the first target word, the computer device further mines the feedback information including the first target word to obtain a second weight of the second target word and the second target word, and the advantages and disadvantages of the target object are more intuitively represented by the first target word, the first weight of the first target word, the second weight of the second target word and the second weight of the second target word.

305. The computer device extracts a second target word from the plurality of feedback information including the first target word.

And the feedback parameter average value of the feedback information comprising the second target word is different from the feedback parameter average value of the feedback information not comprising the second target word. Step 305 is similar to the process of extracting the first target word from the plurality of feedback information of the target object by the computer device. In some embodiments, referring to fig. 6, the computer device extracts a plurality of feedback information including the first target word from the plurality of feedback information of the target object; extracting words with the occurrence frequency meeting the occurrence frequency condition from a plurality of feedback information including the first target words, namely finding out high-frequency words in the plurality of feedback information including the first target words; and selecting a second target word from the words with the occurrence frequency meeting the occurrence frequency condition, namely, inducing the main concern from the high-frequency words.

306. The computer device determines a second weight for the second target word based on a feedback parameter of the plurality of feedback information including the first target word.

Wherein the second weight of the second target word is used for representing the influence degree of the second target word on the feedback parameter of the feedback information comprising the second target word. Step 306 is the same as the process of determining, by the computer device, the first weight of the first target word based on the feedback parameters of the plurality of feedback information of the target object. With continued reference to FIG. 6, the computer device determines a second weight for the second target term, i.e., explores the positive and negative effects of each point of interest.

It should be noted that, the above steps 305 to 306 are described by taking an example in which the computer device extracts the second target word from the plurality of feedback information including the first target word, and determines the second weight of the second target word. Under the condition that the number of the first target words is multiple, the processes of extracting the second target words from the multiple feedback information including each first target word and determining the second weight of the second target words by the computer device are the same, and are not described herein again.

According to the technical scheme, after the plurality of first target words are extracted from the plurality of feedback information of the target object, the second target words are further continuously mined from the feedback information comprising the first target words, the influence degree of the second target words on the feedback parameters of the feedback information is determined, the attention points related to the first target words are explored, the attention points of the user on the target object are reflected more intuitively and accurately through the first target words and the second target words, and the accuracy of analyzing the advantages and disadvantages of the target object is improved.

In some embodiments, after determining the first target word and the second target word, the computer device further determines a number of feedback information including the feedback information of the first target word and a seventh mean value of feedback parameters including the feedback information of the first target word; and determining an eighth average value of the feedback parameters of the feedback information comprising the first target words and the second target words, and outputting a table shown in table 4.

TABLE 4

The number of the plurality of pieces of feedback information of the target object is about 70 ten thousand, the average value of the feedback parameters of the plurality of pieces of feedback information is 4.72, and the "↓" in the column corresponding to the seventh average value indicates that the seventh average value is smaller than 4.72. "↓" in the column corresponding to the seventh mean value means larger than 4.72. "↓" in the column corresponding to the eighth mean value represents that the mean value of the feedback parameters of the plurality of feedback information including the first target word and the second target word is smaller than the overall mean value of the plurality of feedback information including the first target word. "×" in the column corresponding to the eighth mean value indicates that the mean value of the feedback parameters of the plurality of feedback information including the first target word and the second target word is larger than the overall mean value of the plurality of feedback information including the first target word.

In some embodiments, the computer device further determines a number of feedback information including the first target word and the second target word, outputs the analysis result based on the first target word and the second target word and the number of feedback information including the first target word and the second target word. For example, the analysis results include: 2386 charges are charged for the song to be put in the groove, wherein 872 charges are charged for the song to be put in the groove; if the downloaded charged songs are distributed in the slot, the member cannot listen to 1328 songs continuously after expiration; 314 advertisements in the spitting groove, wherein 56 advertisements in the spitting groove are broadcast directly; dislike live function 223 pieces; 133 grooves are easy to be touched by mistake by the groove flashing advertisements, wherein 82 grooves are touched by mistake by the groove direct broadcast advertisements; members should not have 108 advertisements; the format of paid songs downloaded by the members who tell the groove is 86 pieces of encrypted; no copyright exists for 67 song pieces in the groove-spitting song list, 36 song pieces can be listened by the member, and 21 song pieces are lost in collection.

All the above optional technical solutions may be combined arbitrarily to form optional embodiments of the present application, and are not described herein again.

Fig. 7 is a block diagram of a feedback information processing apparatus according to an embodiment of the present application. Referring to fig. 7, the apparatus includes:

an information obtaining module 701, configured to obtain multiple pieces of feedback information of a target object and feedback parameters of the multiple pieces of feedback information, where the feedback parameters of the feedback information are used to indicate a preference degree of a user who issues the feedback information for the target object;

a first word extracting module 702, configured to extract a first target word from the multiple pieces of feedback information, where a feedback parameter mean value of the feedback information including the first target word is different from a feedback parameter mean value of the feedback information not including the first target word;

a first weight determining module 703, configured to determine a first weight of the first target word based on the feedback parameters of the plurality of feedback information, where the first weight of the first target word is used to indicate a degree of influence of the first target word on the feedback parameters of the feedback information including the first target word.

The feedback information processing device provided by the embodiment of the application extracts the target words capable of enabling the feedback parameters of the feedback information to generate differences from the plurality of feedback information of the target object, adopts the target words to represent the reason for enabling the user to generate the corresponding preference degree on the target object, and adopts the first weight to represent the influence degree of the target words on the feedback parameters, so that the importance degree of the reason represented by the target words on the target object is reflected, the analysis on the target object is realized, because the target words are automatically extracted from the plurality of feedback information and the first weight of the target words is automatically determined based on the feedback parameters, a worker does not need to browse and analyze the feedback information one by one, the analysis efficiency on the target object is improved, and the efficiency can be remarkably improved under the condition that the target object has massive feedback information.

In an alternative implementation, the first word extraction module 702 includes:

an information determination unit configured to determine, for any word included in the plurality of feedback information, a first number of first feedback information from the plurality of feedback information including the word, and determine a first number of second feedback information from the plurality of feedback information not including the word;

the parameter determining unit is used for determining a difference indicating parameter corresponding to the word based on the feedback parameters of the first number of first feedback information and the feedback parameters of the first number of second feedback information, and the difference indicating parameter is used for indicating the difference condition of the average value of the feedback parameters of the feedback information including the word and the average value of the feedback parameters of the feedback information not including the word;

and the word determining unit is used for determining the word as the first target word in response to the difference indicating parameter being larger than the critical value.

determining a combined standard deviation based on the first mean value, the second mean value, the feedback parameters of the first amount of first feedback information and the feedback parameters of the first amount of second feedback information;

and determining a difference indication parameter corresponding to the word based on the first mean value, the second mean value, the combined standard deviation and the first quantity.

In another alternative implementation, the first word extraction module 702 is configured to:

in response to a difference between the third average and the fourth average being greater than a first threshold, the word is determined to be the first target word.

In another optional implementation manner, the first weight determining module 703 is configured to:

determining a first weight of the plurality of first target words based on the fifth mean value and the extracted first occurrence indication parameters of the plurality of first target words, and enabling the difference value between the sum value of the first influence parameters of the plurality of first target words and the fifth mean value to be smaller than a second threshold value;

and for any first target word in the plurality of first target words, the first occurrence indication parameter of the first target word is used for representing the occurrence condition of the first target word in the plurality of third feedback information, and the first influence parameter of the first target word is the product of the first occurrence indication parameter of the first target word and the first weight of the first target word.

In another optional implementation manner, the apparatus further includes:

the first weight updating module is used for updating the first weights of the first target words based on the sixth average value and the second occurrence indication parameters of the first target words, so that the difference value between the sum value of the second influence parameters of the first target words and the fifth average value is smaller than a second threshold value, and the difference value between the sum value of the third influence parameters of the first target words and the sixth average value is smaller than the second threshold value;

for any first target word in the plurality of first target words, the second occurrence indication parameter of the first target word is used for representing the occurrence condition of the first target word in the plurality of fourth feedback information, the second influence parameter of the first target word is the product of the first occurrence indication parameter of the first target word and the first weight after the first target word is updated, and the third influence parameter of the target word is the product of the occurrence indication parameter of the first target word and the first weight after the first target word is updated.

determining a first weight of the plurality of first target words based on the feedback parameter of the fifth feedback information and the extracted third occurrence indication parameter of the plurality of first target words, so that a difference value between a sum value of fourth influence parameters of the plurality of first target words and the feedback parameter of the fifth feedback information is smaller than a third threshold value;

and for any first target word in the plurality of first target words, the third occurrence indication parameter of the first target word is used for representing the occurrence condition of the first target word in the fifth feedback information, and the fourth influence parameter of the first target word is the product of the third occurrence indication parameter of the first target word and the first weight of the first target word.

In another optional implementation manner, the apparatus further includes:

the second weight updating module is used for updating the first weights of the first target words based on the feedback parameters of the sixth feedback information and the fourth occurrence indication parameters of the first target words, so that the difference value between the sum value of the fifth influence parameters of the first target words and the feedback parameters of the fifth feedback information is smaller than a third threshold value, and the difference value between the sum value of the sixth influence parameters of the first target words and the feedback parameters of the sixth feedback information is smaller than the third threshold value;

for any first target word in the plurality of first target words, the fourth occurrence indication parameter of the first target word is used for representing the occurrence condition of the first target word in the sixth feedback information, the fifth influence parameter of the first target word is the product of the third occurrence indication parameter of the first target word and the first weight after the first target word is updated, and the sixth influence parameter of the first target word is the product of the fourth occurrence indication parameter of the first target word and the first weight after the first target word is updated.

In another optional implementation manner, the apparatus further includes:

the second word extraction module is used for extracting a second target word from a plurality of feedback information including the first target word, wherein the feedback parameter average value of the feedback information including the second target word is different from the feedback parameter average value of the feedback information not including the second target word;

the second weight determination module is used for determining a second weight of a second target word based on a feedback parameter of a plurality of feedback information including the first target word;

wherein the second weight of the second target word is used for representing the influence degree of the second target word on the feedback parameter of the feedback information comprising the second target word.

In another alternative implementation, the first word extraction module 702 includes:

and the target word selecting unit is used for selecting a first target word from the plurality of words.

In another alternative implementation, the word extraction unit is configured to:

and extracting words with the occurrence frequency meeting the occurrence frequency condition from a plurality of pieces of feedback information with the feedback parameters smaller than a fourth threshold value.

It should be noted that: in the feedback information processing apparatus provided in the above embodiment, when processing the feedback information, only the division of the above functional modules is exemplified, and in practical applications, the above functions may be distributed by different functional modules according to needs, that is, the internal structure of the computer device may be divided into different functional modules to complete all or part of the above described functions. In addition, the feedback information processing apparatus and the feedback information processing method provided in the above embodiments belong to the same concept, and specific implementation processes thereof are described in the method embodiments and are not described herein again.

In some embodiments, the computer device is configured as a terminal. Fig. 8 is a block diagram of a terminal according to an embodiment of the present disclosure. The terminal 800 may be a notebook computer, a desktop computer, or a tablet computer. The terminal 800 may also be referred to by other names such as user equipment, portable terminal, laptop terminal, desktop terminal, etc.

In general, the terminal 800 includes: a processor 801 and a memory 802.

The processor 801 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and so forth. The processor 801 may be implemented in at least one hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array). The processor 801 may also include a main processor and a coprocessor, where the main processor is a processor for Processing data in an awake state, and is also called a Central Processing Unit (CPU); a coprocessor is a low power processor for processing data in a standby state. In some embodiments, the processor 801 may be integrated with a GPU (Graphics Processing Unit) which is responsible for rendering and drawing the content required to be displayed by the display screen. In some embodiments, the processor 801 may further include an AI (Artificial Intelligence) processor for processing computing operations related to machine learning.

Memory 802 may include one or more computer-readable storage media, which may be non-transitory. Memory 802 may also include high speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In some embodiments, a non-transitory computer readable storage medium in the memory 802 is used to store at least one program code for execution by the processor 801 to implement the feedback information processing method provided by the method embodiments of the present application.

In some embodiments, the terminal 800 may further include: a peripheral interface 803 and at least one peripheral. The processor 801, memory 802 and peripheral interface 803 may be connected by bus or signal lines. Various peripheral devices may be connected to peripheral interface 803 by a bus, signal line, or circuit board. Specifically, the peripheral device includes: at least one of a radio frequency circuit 804, a display screen 805, a camera assembly 806, an audio circuit 807, a positioning assembly 808, and a power supply 809.

The peripheral interface 803 may be used to connect at least one peripheral related to I/O (Input/Output) to the processor 801 and the memory 802. In some embodiments, the processor 801, memory 802, and peripheral interface 803 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 801, the memory 802, and the peripheral interface 803 may be implemented on separate chips or circuit boards, which are not limited by this embodiment.

The Radio Frequency circuit 804 is used for receiving and transmitting RF (Radio Frequency) signals, also called electromagnetic signals. The radio frequency circuitry 804 communicates with communication networks and other communication devices via electromagnetic signals. The rf circuit 804 converts an electrical signal into an electromagnetic signal to be transmitted, or converts a received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit 804 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a subscriber identity module card, and so forth. The radio frequency circuit 804 may communicate with other terminals via at least one wireless communication protocol. The wireless communication protocols include, but are not limited to: the world wide web, metropolitan area networks, intranets, generations of mobile communication networks (2G, 3G, 4G, and 5G), Wireless local area networks, and/or WiFi (Wireless Fidelity) networks. In some embodiments, the radio frequency circuit 804 may further include NFC (Near Field Communication) related circuits, which are not limited in this application.

The display screen 805 is used to display a UI (User Interface). The UI may include graphics, text, icons, video, and any combination thereof. When the display 805 is a touch display, the display 805 also has the ability to capture touch signals on or above the surface of the display 805. The touch signal may be input to the processor 801 as a control signal for processing. At this point, the display 805 may also be used to provide virtual buttons and/or a virtual keyboard, also referred to as soft buttons and/or a soft keyboard. In some embodiments, the display 805 may be one, disposed on a front panel of the terminal 800; in other embodiments, the display 805 may be at least two, respectively disposed on different surfaces of the terminal 800 or in a folded design; in other embodiments, the display 805 may be a flexible display disposed on a curved surface or a folded surface of the terminal 800. Even further, the display 805 may be arranged in a non-rectangular irregular pattern, i.e., a shaped screen. The Display 805 can be made of LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), and other materials.

The camera assembly 806 is used to capture images or video. Optionally, camera assembly 806 includes a front camera and a rear camera. Generally, a front camera is provided at a front panel of the terminal 800, and a rear camera is provided at a rear surface of the terminal 800. In some embodiments, the number of the rear cameras is at least two, and each rear camera is any one of a main camera, a depth-of-field camera, a wide-angle camera and a telephoto camera, so that the main camera and the depth-of-field camera are fused to realize a background blurring function, and the main camera and the wide-angle camera are fused to realize panoramic shooting and VR (Virtual Reality) shooting functions or other fusion shooting functions. In some embodiments, camera assembly 806 may also include a flash. The flash lamp can be a monochrome temperature flash lamp or a bicolor temperature flash lamp. The double-color-temperature flash lamp is a combination of a warm-light flash lamp and a cold-light flash lamp, and can be used for light compensation at different color temperatures.

The audio circuit 807 may include a microphone and a speaker. The microphone is used for collecting sound waves of a user and the environment, converting the sound waves into electric signals, and inputting the electric signals to the processor 801 for processing or inputting the electric signals to the radio frequency circuit 804 to realize voice communication. For the purpose of stereo sound collection or noise reduction, a plurality of microphones may be provided at different portions of the terminal 800. The microphone may also be an array microphone or an omni-directional pick-up microphone. The speaker is used to convert electrical signals from the processor 801 or the radio frequency circuit 804 into sound waves. The loudspeaker can be a traditional film loudspeaker or a piezoelectric ceramic loudspeaker. When the speaker is a piezoelectric ceramic speaker, the speaker can be used for purposes such as converting an electric signal into a sound wave audible to a human being, or converting an electric signal into a sound wave inaudible to a human being to measure a distance. In some embodiments, the audio circuitry 807 may also include a headphone jack.

The positioning component 808 is used to locate the current geographic position of the terminal 800 for navigation or LBS (Location Based Service). The Positioning component 808 may be a Positioning component based on the Global Positioning System (GPS) in the united states, the beidou System in china, or the galileo System in russia.

Power supply 809 is used to provide power to various components in terminal 800. The power supply 809 can be ac, dc, disposable or rechargeable. When the power supply 809 includes a rechargeable battery, the rechargeable battery may be a wired rechargeable battery or a wireless rechargeable battery. The wired rechargeable battery is a battery charged through a wired line, and the wireless rechargeable battery is a battery charged through a wireless coil. The rechargeable battery may also be used to support fast charge technology.

In some embodiments, terminal 800 also includes one or more sensors 810. The one or more sensors 810 include, but are not limited to: acceleration sensor 811, gyro sensor 812, pressure sensor 813, fingerprint sensor 814, optical sensor 815 and proximity sensor 816.

Those skilled in the art will appreciate that the configuration shown in fig. 8 is not intended to be limiting of terminal 800 and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components may be used.

In some embodiments, the computer device is configured as a server. Fig. 9 is a block diagram of a server provided in this embodiment, where the server 900 may generate a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 901 and one or more memories 902, where the memory 902 stores at least one program code, and the at least one program code is loaded and executed by the processors 901 to implement the feedback information Processing method provided in each method embodiment. Of course, the server may also have components such as a wired or wireless network interface, a keyboard, and an input/output interface, so as to perform input/output, and the server may also include other components for implementing the functions of the device, which are not described herein again.

In an exemplary embodiment, there is also provided a computer-readable storage medium having at least one program code stored therein, the at least one program code being executable by a processor in a computer device to perform the feedback information processing method in the above-described embodiments. For example, the computer-readable storage medium may be a ROM (Read-Only Memory), a RAM (Random Access Memory), a CD-ROM (Compact Disc Read-Only Memory), a magnetic tape, a floppy disk, an optical data storage device, and the like.

The present application also provides a computer program product or a computer program comprising computer program code, the computer program code being stored in a computer-readable storage medium, the computer program code being read by a processor of a computer device from the computer-readable storage medium, the computer program code being executed by the processor to cause the computer device to execute the feedback information processing method in the above-mentioned method embodiments.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

The above description is only exemplary of the present application and should not be taken as limiting, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for processing feedback information, the method comprising:

2. The method of claim 1, wherein said extracting a first target word from the plurality of feedback information comprises:

3. The method of claim 2, wherein the determining the difference indication parameter corresponding to the word based on the feedback parameters of the first number of first feedback information and the feedback parameters of the first number of second feedback information comprises:

4. The method of claim 1, wherein said extracting a first target word from the plurality of feedback information comprises:

5. The method of claim 1, wherein determining the first weight for the first target term based on the feedback parameters of the plurality of feedback information comprises:

6. The method of claim 5, further comprising:

7. The method of claim 1, wherein determining the first weight for the first target term based on the feedback parameters of the plurality of feedback information comprises:

selecting fifth feedback information from the plurality of feedback information to obtain a feedback parameter of the fifth feedback information, wherein the fifth feedback information is any one of the plurality of feedback information;

8. The method of claim 7, further comprising:

selecting sixth feedback information from the multiple pieces of feedback information, and acquiring a feedback parameter of the sixth feedback information, wherein the sixth feedback information is any one of the multiple pieces of feedback information different from the fifth feedback information;

9. The method of claim 1, further comprising:

10. The method of claim 1, wherein said extracting a first target word from the plurality of feedback information comprises:

selecting the first target word from the plurality of words.

11. The method of claim 10, wherein extracting from the plurality of feedback information, a plurality of words whose frequency of occurrence satisfies a frequency of occurrence condition comprises:

12. The method of claim 10, wherein extracting from the plurality of feedback information, a plurality of words whose frequency of occurrence satisfies a frequency of occurrence condition comprises:

13. The method of claim 10, wherein extracting from the plurality of feedback information, a plurality of words whose frequency of occurrence satisfies a frequency of occurrence condition comprises:

14. The method of claim 10, wherein extracting from the plurality of feedback information, a plurality of words whose frequency of occurrence satisfies a frequency of occurrence condition comprises:

15. A feedback information processing apparatus, characterized in that the apparatus comprises:

16. A computer device, characterized in that the computer device comprises a processor and a memory, wherein at least one program code is stored in the memory, and the at least one program code is loaded and executed by the processor to implement the feedback information processing method according to any one of claims 1 to 14.

17. A computer-readable storage medium, having at least one program code stored therein, the at least one program code being loaded and executed by a processor to implement the feedback information processing method according to any one of claims 1 to 14.