CN107835231B

CN107835231B - Feedback information processing method and terminal equipment

Info

Publication number: CN107835231B
Application number: CN201710979746.5A
Authority: CN
Inventors: 朱鹏程; 陈海涛
Original assignee: Ping An Technology Shenzhen Co Ltd
Current assignee: Ping An Technology Shenzhen Co Ltd
Priority date: 2017-10-19
Filing date: 2017-10-19
Publication date: 2020-01-03
Anticipated expiration: 2037-10-19
Also published as: WO2019076017A1; CN107835231A

Abstract

The invention provides a feedback information processing method and terminal equipment, which are applicable to the technical field of Internet, and the method comprises the following steps: sending out information request messages about a plurality of different interaction channels; acquiring information response messages returned based on each information request message in a preset period, and acquiring effective response information in the information response messages; respectively acquiring the attribute type of each effective response message; respectively acquiring the quantity of effective response information in each attribute type for the effective response information with the same identification frame, and inputting the acquired quantity of the effective response information into a preset parameter calculation model to output feedback information evaluation parameters of the interaction channel type corresponding to the identification frame in a preset period; and displaying the feedback information evaluation parameters corresponding to the interaction channel types in a feedback information evaluation table. The feedback information evaluation parameter obtained by calculation has higher reference value, so that the effective utilization rate of the feedback information processing result is improved.

Description

Feedback information processing method and terminal equipment

Technical Field

The invention belongs to the technical field of internet, and particularly relates to a feedback information processing method and terminal equipment.

Background

Currently, each large enterprise usually calls back to the client regularly, so as to collect the feedback information of the client. By analyzing and processing various collected feedback information, the demands of the customers can be known in time, so that internal services and products can be correspondingly improved according to the real-time demands of the customers, and the competitiveness of enterprises is improved. For example, Net Promoter Score (NPS), also known as net promoter Score or public praise, is an index that measures how likely a client will recommend a business or service to others, and is a customer loyalty analysis measure of how popular the current society is. By closely tracking the feedback information to calculate the net recommendation value, the enterprise can be promoted to be capable of developing steadily and rapidly to a certain extent.

In the prior art, by visiting a customer back by phone, a customer satisfaction can be determined by a telephone salesperson based on the attitude feedback condition of the customer, and then after the return visit process is completed, comprehensive analysis processing is performed on a large amount of collected feedback information so as to determine the integral customer satisfaction of an enterprise. However, in the actual sales mode, an enterprise often performs interactive operation with customers through multiple types of service interaction channels, and since the processing result of the feedback information can only reflect the overall competitiveness of the enterprise, it is difficult to improve the sales modes of different service interaction channels according to the result.

Disclosure of Invention

In view of this, embodiments of the present invention provide a feedback information processing method and a terminal device, so as to solve the problem that it is difficult to improve the selling modes of different service interaction channels according to an obtained feedback information processing result in the prior art.

A first aspect of an embodiment of the present invention provides a method for processing feedback information, including:

sending out information request messages about a plurality of different interaction channels;

obtaining information response messages returned based on each information request message in a preset period, and filtering invalid response messages to obtain one or more pieces of valid response messages, wherein the information response messages carry identification frames, and different identification frames correspond to different interaction channel types;

respectively obtaining the attribute type of each effective response message, wherein the attribute type is determined according to the score information in the effective response messages;

respectively acquiring the quantity of effective response information in each attribute type for the effective response information with the same identification frame, and inputting the acquired quantity of the effective response information into a preset parameter calculation model to output feedback information evaluation parameters of the interaction channel type corresponding to the identification frame in the preset period;

and displaying the feedback information evaluation parameters corresponding to the interaction channel types in a feedback information evaluation table.

A second aspect of the embodiments of the present invention provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the following steps:

A third aspect of embodiments of the present invention provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the steps of:

In the embodiment of the invention, by sending out the information request messages about a plurality of different interaction channels, the feedback information evaluation parameters of the interaction channel types corresponding to the identification frames in the preset period can be automatically calculated according to the identification frames and the score information carried by each received information response message; by displaying all feedback information evaluation parameters in the feedback information evaluation table together, an enterprise manager can quickly acquire the feedback information evaluation parameters corresponding to all interaction channels in the latest time period only by regularly checking the feedback information evaluation table, so that enterprise service and competitive analysis of products on the interaction channels are executed based on the feedback information evaluation parameters, and accordingly, an enterprise can conveniently make an adaptive sales improvement scheme.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.

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

fig. 2 is a flowchart illustrating a specific implementation of the feedback information processing method S103 according to an embodiment of the present invention;

fig. 3 is a flowchart of an implementation of a method for processing feedback information according to another embodiment of the present invention;

fig. 4 is a flowchart of an implementation of a feedback information processing method according to another embodiment of the present invention;

fig. 5 is a flowchart of a specific implementation of the feedback information processing method S101 according to an embodiment of the present invention;

fig. 6 is a block diagram of a processing apparatus for feedback information according to an embodiment of the present invention;

fig. 7 is a block diagram of a processing apparatus for processing feedback information according to another embodiment of the present invention;

fig. 8 is a block diagram of a feedback information processing apparatus according to another embodiment of the present invention;

fig. 9 is a schematic diagram of a terminal device according to an embodiment of the present invention.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

In order to explain the technical means of the present invention, the following description will be given by way of specific examples.

Fig. 1 shows an implementation flow of a processing method for feedback information provided by an embodiment of the present invention, where the method flow includes steps S101 to S105. The specific implementation principle of each step is as follows.

S101: and sending out information request messages about a plurality of different interaction channels.

The interaction channel, i.e. the contact point, refers to a contact object for the enterprise to interact with the client, and includes, for example, a business network, an enterprise network public platform service number, an enterprise official network web page, an enterprise service APP, and the like. Enterprises can promote services and products through the different interaction channels. Through any of the above interaction channels, the enterprise can contact various types of customers to complete the purchase flow of services/products.

In the embodiment of the invention, historical interaction information corresponding to each interaction channel is obtained. And sending the pre-generated information request message to the customer communication account associated with the historical interactive information according to the customer communication account in the historical interactive information. Because the historical interaction information of each interaction channel is different, the sent information request messages of the same type can reach different client communication accounts. And according to the interaction channel corresponding to the historical interaction information, when the information request message is sent, adding an identification frame for describing the interaction channel into the information request message.

For example, when the client communication account is an email address, for email addresses in different historical interaction information corresponding to different interaction channels, information request messages in a specified format are respectively sent to the email addresses of the historical interaction clients, so that sending of the information request messages related to the different interaction channels is achieved.

S102: and obtaining information response messages returned based on each information request message in a preset period, and filtering invalid response messages to obtain one or more pieces of valid response messages, wherein the information response messages carry identification frames, and different identification frames correspond to different interaction channel types.

When the client receives the information request message through the terminal device, the client can browse the message information carried by the information request message in the terminal device, wherein the message information comprises the detailed content of the problem required to be researched by the enterprise. For example, the message information may be a piece of return access volume information. If the customer completes the filling of feedback opinions in the message information or completes the selection operation of the investigation question answer options, the information response message based on the information request message can be received when the customer clicks a submit key or a confirm key. The information response message comprises the feedback opinions or the selected answer options filled in the message information by the client. And, the information response message carries an identification frame, which is the same as the identification frame in the corresponding information request message.

In the embodiment of the invention, the information response message returned based on each information request message in the preset period is obtained, wherein the preset period is the time period information input by the user. For example, if the preset period is 24 hours, every 24 hours, each message response message received within the last 24 hours is screened out.

Because the feedback opinions of the client may include characters which are input by the client by mistake or maliciously and irrelevant to the actual advice opinions, and the enterprise cannot acquire effective feedback information according to the characters, the received information response messages need to be analyzed to screen out the effective response information. The process comprises the following steps: identifying whether a plurality of characters continuously appearing in the information response message can form a word containing actual semantics or not through a preset algorithm; and if a plurality of characters continuously appearing in the information response message cannot form words containing actual semantics, determining that the information response message is invalid response information. And if a plurality of characters continuously appearing in the information response message can form words containing actual semantics, determining the information response message as effective response information.

S103: and respectively acquiring the attribute type of each effective response message, wherein the attribute type is determined according to the score information in the effective response messages.

In the embodiment of the invention, a client can select answer options of the research question from the message information and generate different score information according to different answer options, so that effective response information returned based on the information request message contains different score information.

Illustratively, the research question in the message information may be, for example, "? for whether you would like to recommend the product to your friends or colleagues", and the answer option of the research question is 0-10 points, the recommendation index of the customer to the product increases from 0 point option to 10 point option, if the answer option selected by the customer is 10, the score information of the obtained valid response information based on the message information is 10.

And after reading the score information of each effective response information, determining the attribute type of the effective response information according to the score interval to which the score information belongs. The attribute types include a recommendation attribute, a neutral attribute, and a criticizing attribute. Specifically, if the score information of the effective response information belongs to a first numerical interval, determining the attribute type of the effective response information as a recommended attribute; and if the score information of the effective response information belongs to the second numerical value interval, determining the attribute type of the effective response information as the criticizing attribute. Wherein the minimum value of the first interval is greater than the maximum value of the second interval.

For example, in the above example, the first numerical range may be 9 to 10 minutes, and the second numerical range may be 0 to 6 minutes. If the score information of a certain valid response information is between 9 and 10, the attribute category of the valid response information is determined as the recommended attribute. If the score information of a certain valid response information is between 0 and 6, the attribute category of the valid response information is determined as the criticizing attribute. If the score information of a certain valid response information is between 7 and 8, the attribute category of the valid response information is determined as the neutral attribute.

As an embodiment of the present invention, fig. 3 shows a specific implementation flow of the feedback information processing method S103 provided by the embodiment of the present invention, which is detailed as follows:

s1031: and extracting each characteristic item in the effective response information for the effective response information without the score information.

Since the customer can select the score information option related to the research question in the information request message and can also input the text feedback opinions, if the customer only inputs the text feedback opinions but does not select the score information, the detected effective response information only contains the text feedback opinions but does not contain the score information. At this time, each piece of effective response information not containing the score information is screened, and the feature item of each piece of effective response information is extracted. The characteristic item represents characters with commendatory and devaluation property and capable of reflecting the emotional attitude of the user in the effective response information.

Illustratively, each participle in the effective response information is acquired, each participle is identified through a preset semantic identification algorithm to extract the participle with the commendable and depreciated part of speech, and each extracted participle is output as a feature item in the effective response information.

S1032: and acquiring the characteristic characters adjacent to the characteristic items before, and detecting the quantization levels of the characteristic characters.

For each feature item in the valid response information, a feature character preceding the feature item is detected. The characteristic character is a degree adverb, which may be one or more characters. And determining the quantization grade corresponding to the characteristic character detected at the current moment according to a pre-established corresponding relation table of the characteristic character and the quantization grade. The higher the definition degree of the feature item by the feature character is, the higher the corresponding quantization level is.

S1033: and determining a weight floating coefficient of the feature item according to the positive polarity and the negative polarity of the feature character and the quantization level.

And determining the positive polarity and the negative polarity of the characteristic characters through a preset semantic recognition algorithm. Wherein, positive polarity indicates that the characteristic character is a positive adverb, and negative polarity indicates that the characteristic character is a negative adverb. For example, if the feature character is "very", it is positive; if the signature is "almost none," it is negative.

According to the positive and negative polarities and the quantization levels of the characteristic characters before each characteristic item, the weight floating coefficient of the characteristic item is calculated, specifically, the positive polarity is digitalized into a sign "+" for representing a positive value, and the negative polarity is digitalized into a sign "-" for representing a negative value. And multiplying the positive polarity and the negative polarity of the characteristic character with the quantization level of the characteristic character to obtain a weight floating coefficient of the characteristic item.

For example, if the characters included in the valid response message are "i't like the interactive interface of the product very much and the operation is too cumbersome", the recognized feature items are "like" and "cumbersome", and the adjacent feature characters are "very little" and "too" respectively. Wherein the feature character "very low" has a negative polarity and the feature character "too" has a positive polarity. In a pre-established corresponding relation table of the feature characters and the quantization levels, if the quantization level corresponding to the feature character 'very poor' is 8 and the quantization level corresponding to the feature character 'too' is 10, the weight floating coefficient of the feature item 'like' is-8 and the weight floating coefficient of the feature item 'fussy' is + 10.

S1034: and calculating score information corresponding to the effective response information according to the weight ratio corresponding to each feature item and the weight floating coefficient, so as to determine the attribute type of the effective response information according to the score information.

In the embodiment of the invention, different feature items correspond to different weight ratios. The weight ratio corresponding to the feature item represents the contribution degree of the feature item to the positive attitude of the sentence in which the feature item is positioned. The corresponding relation between each characteristic item and the weight ratio is stored in an information base in advance. And searching the weight ratio corresponding to the characteristic item in a preset information base for reading. And calculating the sub-item score of each characteristic item based on the weight ratio and the weight floating coefficient of the characteristic item, and outputting the sum of the sub-item scores of all the characteristic items in the effective response information as the score information corresponding to the effective response information.

And acquiring the attribute type of the effective response information based on the calculated score information. Since the process is the same as the step implementation principle in S103, detailed description is omitted.

For example, if the valid response information only includes a text feedback suggestion that "if you increase the function of searching for information in the mobile application, i would like to recommend the product", etc., it indicates that the client is still likely to recommend the product/service, but the recommendation degree may not be very high, and therefore, the score information corresponding to the valid response information obtained through the above steps S1031 to S1034 may be 6 or 7.

In the embodiment of the invention, the effective response information which does not contain the score information is analyzed and processed, so that the client can determine the subjective recommendation degree of the client based on the feedback opinion input by the client even if the client does not select the specific score information in the information request message, the problem that the effective response information which does not contain the score information cannot be used for calculating the feedback information evaluation parameter corresponding to the interactive channel type is avoided, and the effective utilization rate of the effective response information is improved.

S104: and respectively acquiring the quantity of effective response information in each attribute type for the effective response information with the same identification frame, and inputting the acquired quantity of the effective response information into a preset parameter calculation model so as to output feedback information evaluation parameters of the interaction channel type corresponding to the identification frame in the preset period.

Since the information response packet carries the identification frame for representing the type of the interaction channel, the effective response information also carries the identification frame. And in the plurality of pieces of effective response information, taking the effective response information with the same identification frame as a classification corresponding to the type of the interaction channel. In each classification, a first total number of effective response information with the attribute type as the recommended attribute and a second total number of effective response information with the attribute type as the criticizing attribute are respectively counted.

In the embodiment of the invention, the parameter calculation model comprises a plurality of preset calculation formulas. As a specific implementation example of the present invention, the parameter calculation model is used to calculate NPS parameters such as a feedback reply rate, a recommender amount, a criticizing amount, a recommender proportion, a criticizing amount, and an NPS value of the information request packet, respectively.

Specifically, the calculation formulas of the NPS parameters are as follows:

the feedback reply rate is the total number of effective response messages carrying the identification frame A/the total number of information request messages carrying the identification frame A;

the recommender ratio is the first total number of effective response information carrying the identification frame A and the attribute type is the recommendation attribute/the total number of effective response information carrying the identification frame A;

the critics' proportion is the second total number of the effective response information carrying the identification frame A and the attribute type is the criticizing attribute/the total number of the effective response information carrying the identification frame A;

NPS value-recommender to critic;

the identification frame a is an identification frame corresponding to each of the classifications.

In each classification, inputting a first total number of effective response messages with the attribute type of the recommended attribute, a second total number of effective response messages with the attribute type of the criticizing attribute, a total number of effective response messages and a total number of information request messages into the parameter calculation model, substituting various input parameters into various calculation indicators, and outputting various feedback information evaluation parameters corresponding to the classification, wherein the feedback information evaluation parameters comprise feedback reply rate, recommender quantity, criticizer quantity, recommender proportion, criticizer proportion, NPS value and other NPS parameters.

S105: and displaying the feedback information evaluation parameters corresponding to the interaction channel types in a feedback information evaluation table.

And displaying the feedback information evaluation table generated in real time at the current moment in a monitoring window of the terminal interface. And respectively displaying feedback information evaluation parameters such as feedback reply rate, recommender amount, criticizing agent amount, recommender duty, criticizing agent duty, NPS value and the like corresponding to each interactive channel type in the feedback information evaluation table.

Preferably, the various input parameters of each category are acquired and the various feedback information evaluation parameters corresponding to the interaction channel types are calculated only when a preset time interval is reached, so that the monitoring window of the terminal interface can refresh and display the feedback information evaluation table in a preset time period. According to the embodiment of the invention, an administrator can quickly and intuitively check each feedback information evaluation parameter corresponding to each interaction channel type within the preset time from the feedback information evaluation table.

For example, for the interaction channel type of the official website of the enterprise, the total number of the effective response information corresponding to the interaction channel type, the total number of the effective response information with the attribute type being the recommended attribute, and the total number of the effective response information with the attribute type being the criticizing attribute received within the last 24 hours are counted only at 12 pm, and it is ensured that the feedback information evaluation parameters respectively corresponding to each interaction channel type on the day can be refreshed at 12 pm every day.

As another embodiment of the present invention, as shown in fig. 4, after S106, the method further includes:

s107: and acquiring a first feature vector of the effective response information, and detecting the similarity between the first feature vector and a second feature vector of preset illegal information.

S108: and if the similarity between the first characteristic vector and the second characteristic vector is greater than a first preset threshold value, acquiring an object identifier corresponding to the effective response information, wherein the object identifier is determined by login information corresponding to the effective response information.

S109: and adding the object identifier to a rejection request record table so as to block the information request message related to the object identifier in the rejection request record table when the information request message is sent again.

And the login information corresponding to the effective response information is used for uniquely identifying the client sending the effective response information. For example, if the client returns an information response message based on an information request message received by the network public platform service number, the login information corresponding to the generated valid response information is the platform account of the client. And generating an object identifier matched with the login information according to the login information used by the client when responding to the information request message so as to add the object identifier to the message response information.

In the embodiment of the invention, various types of illegal information such as political information, junk information and dirty word information are stored in the illegal information base. Vectorizing each piece of illegal information through a preset algorithm to obtain a feature vector of each piece of illegal information. And vectorizing each piece of effective response information through the preset algorithm to obtain the feature vector of each piece of effective response information.

For each feature vector of the valid response information, if the cosine similarity between the feature vector and the feature vector of any illegal information is detected to be greater than a preset threshold value, the client is preliminarily judged to be extremely unwilling to respond to the received information request message, and therefore, the object identifier carried by the valid response information is obtained, and the object identifier is stored in a preset rejection request record table.

When the above S101 is executed again, it is detected in advance whether the object id recorded by the history interactive information exists in the rejection request recording table. If the object identification recorded by the historical interaction information is detected to exist in the rejection request record table in advance, blocking the information request message sent to the object identification; and if the object identifier recorded by the pre-detected historical interaction information does not exist in the rejection request record table, sending the information request message to the object identifier.

In the embodiment of the invention, the object identifier corresponding to the effective response information with higher similarity to illegal information is added to the rejection request record table by setting the rejection request record table, so that a client associated with the object identifier cannot receive an information request message in the subsequent process, the harassment to the client is avoided, and the satisfaction degree of the client to enterprise products can be indirectly improved.

Fig. 5 shows an implementation flow of a feedback information processing method according to another embodiment of the present invention, which is detailed as follows:

s110: and determining the feedback reply rate of the information request message according to the obtained first information total number of the effective response information and the obtained second information total number of the information response message.

And after effective response information in each piece of client feedback information is determined, dividing the total number of the effective response information by the total number of the client feedback information to obtain a feedback reply rate related to the client return access questionnaire.

S111: and if the feedback reply rate is lower than a second preset threshold value, sending an information request message parameter adjustment prompt.

In the embodiment of the invention, if the feedback reply rate is lower than the preset threshold, the message information generated based on the information request message is difficult to attract the client to actively answer the investigation problem probably because the page parameter of the information request message is not suitable for the actual requirement of the client, so that an information request message parameter adjustment prompt is sent out in a window of a popup window of a terminal interface to prompt an administrator whether to adjust the page parameter of the information request message. The window comprises three option keys, and one option key is used for receiving a stacking style adjusting instruction sent by a user; an option key is used for receiving a jump map adjusting instruction sent by a user; and the other option key is used for receiving a canceling adjustment instruction sent by the user.

S112: and if a stacking style adjusting instruction returned according to the information request message parameter adjusting prompt is received, generating a plurality of stacking style controls, wherein each stacking style control corresponds to one pre-stored stacking style sheet, and when any one of the stacking style controls is detected to be triggered, replacing the page style parameter of the information request message with the parameter of the stacking style sheet corresponding to the stacking style control.

And if receiving a laminated style adjusting instruction sent by an information request message parameter adjusting prompt, calling a plurality of CSS laminated style tables which are prestored and matched with the information request message of the current interaction channel type. Different file style parameters such as HTML or XML in the information request message can be represented through different CSS style sheets.

Specifically, a stack style control represents parameters of one CSS style sheet obtained by calling, and a pattern of the stack style control may be an effect diagram of the CSS style sheet. For example, if CSS1 differs from CSS2 in that the background color is different, the background color of CSS1 is blue, and the background color of CSS2 is red, then in the terminal interface, the cascading style control representing the CSS1 style sheet is a blue icon control, and the cascading style control representing the CSS2 style sheet is a red icon control.

And when a triggering instruction based on any stack style control is detected, adjusting the information request message of the information request message to be the parameter of the CSS style sheet corresponding to the stack style control. For example, in the information request message, the CSS style sheet name called by the information request message is replaced with the CSS style sheet name corresponding to the current stack style control.

S113: and if a jump map adjusting instruction returned according to the information request message parameter adjusting prompt is received, changing the page jump parameter in the information request message into the page jump parameter indicated by the jump map adjusting instruction.

When the user terminal displays the message information based on the information request message, each calling question can be sequentially displayed on a display page in the message information. When the previous research question is fed back completely or the feedback is cancelled, the current display page is refreshed, and another research question which is ranked later is displayed in the refreshed display page.

In the embodiment of the invention, if a skip map adjusting instruction sent by an information request message parameter adjusting prompt is received, each research question corresponding to the information request message is displayed, and each answer option corresponding to each research question is displayed below each research question. An identification number is allocated to each answer choice and each investigation question. In the terminal interface, when an answer option selected by an administrator is detected, a skip map edit box is generated to request the administrator to input a page skip parameter associated with the answer option or an identification number of a research question associated with the answer option, wherein the page skip parameter is a page skip link, for example. When the identification number of the research question is detected to exist in the skip map edit box, the page skip link corresponding to the research question is determined according to the identification number so as to associate the answer option with the page skip parameter, and therefore the adjustment of the page skip parameter in the information request message is achieved.

In the message information generated by the information request message adjusted based on the page jump parameter, if a client selects any answer option in the investigation question display page, the client can jump to the display page corresponding to the page jump parameter according to the page jump parameter associated with the answer option.

In the embodiment of the invention, when the feedback reply rate of the information request message is lower than the preset threshold value, an administrator can timely determine whether the page parameters of the information request message need to be adjusted by sending the parameter adjustment prompt of the information request message; by acquiring a skip map adjustment instruction or a stack style adjustment instruction sent by an administrator, the administrator can adjust the parameters of the information request message by simply selecting the CSS style sheet parameters to be adjusted or simply inputting the identification number of the investigation problem, so that the adjustment flexibility of the parameters of the information request message is improved, a client can make effective feedback based on the optimized information request message with higher possibility, and the feedback reply rate is improved.

As an embodiment of the present invention, as shown in fig. 5, the S101 specifically includes:

s1011: and acquiring a plurality of different interaction channels.

S1012: and respectively sending out information request messages related to a plurality of preset object identifications for each interaction channel.

In the embodiment of the invention, the information request message is sent out through different interaction channels. Specifically, historical interaction information of each interaction channel is read, wherein the historical interaction information comprises object identifiers, and information request messages about each read object identifier are sent out respectively. Wherein the object identification represents login information used by the client in the interaction channel.

For historical interaction information corresponding to different interaction channels of the same client, the historical interaction information has different object identifiers, so that the historical interaction information needs to be sent through various types of interaction channels when the information request message related to the object identifiers is sent, and the same client can receive the information request message in different interaction channels.

For example, the client can receive an information request message pushed by an enterprise wechat public number through the micro signal, and can also receive an information request message pushed by a mobile application APP background server through the mobile application APP login number.

In the embodiment of the invention, the information request message is sent through a plurality of different interaction channels, so that the information request message can be received in real time when a customer purchases enterprise products/services, and the response probability of the customer to the information request message is improved. The analysis processing is performed based on a larger amount of feedback information, and a feedback information processing result with a higher reference value can be obtained.

It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

Fig. 6 shows a block diagram of a processing apparatus for processing feedback information according to an embodiment of the present invention, which corresponds to the method for processing feedback information described in the foregoing embodiment.

Referring to fig. 6, the apparatus includes:

a sending unit 601, configured to send an information request message related to multiple different interaction channels.

A first obtaining unit 602, configured to obtain an information response packet returned based on each information request packet in a preset period, and filter invalid response information therein to obtain one or more pieces of valid response information, where the information response packet carries an identification frame, and different identification frames correspond to different interaction channel types.

A second obtaining unit 603, configured to obtain an attribute type of each piece of effective response information, where the attribute type is determined according to score information in the effective response information.

An output unit 604, configured to obtain, for the effective response information with the same identification frame, the number of effective response information in each attribute type, and input the obtained number of effective response information into a preset parameter calculation model, so as to output a feedback information evaluation parameter of the interaction channel type corresponding to the identification frame in the preset period.

The presentation unit 605 is configured to present the feedback information evaluation parameter corresponding to the interaction channel type in a feedback information evaluation table.

Optionally, the second obtaining unit 603 includes:

and the extracting subunit is used for extracting each characteristic item in the effective response information for the effective response information without the score information.

And the acquisition subunit is used for acquiring the characteristic characters adjacent to the characteristic items before and detecting the quantization levels of the characteristic characters.

And the determining subunit is used for determining the weight floating coefficient of the feature item according to the positive polarity and the negative polarity of the feature character and the quantization level.

And the calculating subunit is configured to calculate, according to the weight ratio corresponding to each feature item and the weight floating coefficient, score information corresponding to the effective response information, so as to determine an attribute type of the effective response information according to the score information.

Optionally, as shown in fig. 7, the apparatus for processing feedback information further includes:

the detecting unit 606 is configured to obtain a first feature vector of the valid response information, and detect a similarity between the first feature vector and a second feature vector of preset illegal information.

A third obtaining unit 607, configured to obtain an object identifier corresponding to the valid response information if the similarity between the first feature vector and the second feature vector is greater than a first preset threshold, where the object identifier is determined by the login information corresponding to the valid response information.

A blocking unit 608, configured to add the object identifier to a reject request record table, so as to block the information request packet related to the object identifier in the reject request record table when the information request packet is sent again.

Optionally, as shown in fig. 8, the apparatus for processing feedback information further includes:

the determining unit 609 is configured to determine a feedback reply rate of the information request packet according to the obtained first total information amount of the effective response information and the obtained second total information amount of the information response packet.

A prompting unit 610, configured to send an information request message parameter adjustment prompt if the feedback reply rate is lower than a second preset threshold.

A generating unit 611, configured to generate a plurality of stack style controls if a stack style adjustment instruction returned according to the information request packet parameter adjustment prompt is received, where each stack style control corresponds to one pre-stored stack style table, so that when it is detected that any one of the stack style controls is triggered, a page style parameter of the information request packet is replaced with a parameter of the stack style table corresponding to the stack style control.

A changing unit 612, configured to change the page jump parameter in the information request message to the page jump parameter indicated by the jump map adjustment instruction if the jump map adjustment instruction returned according to the information request message parameter adjustment prompt is received.

In the embodiment of the invention, the client return access questionnaires are sent out at a plurality of different contacts, so that the effective response information can be automatically classified according to the contact labels carried by each received effective response information; different contact labels can represent different sales channels, so that the NPS parameters of the sales channels can be calculated by counting the effective response information of each attribute type obtained by each classification category; by displaying a plurality of different NPS parameters in the NPS report together, an enterprise manager can quickly acquire the NPS value corresponding to each sales channel only by checking the NPS report, so that the enterprise manager can execute competitive analysis of enterprise services and products on the sales channel based on the NPS value, and an enterprise can conveniently make an adaptive channel sales improvement scheme, so that the embodiment of the invention improves the effective utilization rate of the NPS value.

Fig. 9 is a schematic diagram of a terminal device according to an embodiment of the present invention. As shown in fig. 9, the terminal device 9 of this embodiment includes: a processor 90, a memory 91 and a computer program 92, such as a net recommendation acquisition program, stored in said memory 91 and executable on said processor 90. The processor 90, when executing the computer program 92, implements the steps in the above-described embodiments of the method for processing feedback information, such as the steps 101 to 105 shown in fig. 1. Alternatively, the processor 90, when executing the computer program 92, implements the functions of each module/unit in each device embodiment described above, such as the functions of the units 601 to 605 shown in fig. 6.

Illustratively, the computer program 92 may be partitioned into one or more modules/units that are stored in the memory 91 and executed by the processor 90 to implement the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution process of the computer program 92 in the terminal device 9.

The terminal device 9 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The terminal device may include, but is not limited to, a processor 90, a memory 91. Those skilled in the art will appreciate that fig. 9 is only an example of a terminal device 9, and does not constitute a limitation to the terminal device 9, and may include more or less components than those shown, or combine some components, or different components, for example, the terminal device may also include an input-output device, a network access device, a bus, etc.

The Processor 90 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 91 may be an internal storage unit of the terminal device 9, such as a hard disk or a memory of the terminal device 9. The memory 91 may also be an external storage device of the terminal device 9, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the terminal device 9. Further, the memory 91 may also include both an internal storage unit and an external storage device of the terminal device 9. The memory 91 is used for storing the computer program and other programs and data required by the terminal device. The memory 91 may also be used to temporarily store data that has been output or is to be output.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/terminal device are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. . Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.

The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.

Claims

1. A method for processing feedback information, comprising:

displaying the feedback information evaluation parameters corresponding to the interaction channel types in a feedback information evaluation table;

the method for processing the feedback information further comprises the following steps:

determining the feedback reply rate of the information request message according to the obtained first information total number of the effective response information and the obtained second information total number of the information response message;

if the feedback reply rate is lower than a second preset threshold value, sending an information request message parameter adjustment prompt;

if a stacking style adjusting instruction returned according to the information request message parameter adjusting prompt is received, generating a plurality of stacking style controls, wherein each stacking style control corresponds to one pre-stored stacking style sheet, and when any one stacking style control is detected to be triggered, replacing the page style parameter of the information request message with the parameter of the stacking style sheet corresponding to the stacking style control;

and if a jump map adjusting instruction returned according to the information request message parameter adjusting prompt is received, changing the page jump parameter in the information request message into the page jump parameter indicated by the jump map adjusting instruction.

2. The processing method of claim 1, wherein the obtaining the attribute type of each of the valid response messages respectively comprises:

extracting each characteristic item in the effective response information for the effective response information without the score information;

acquiring characteristic characters adjacent to the characteristic items before and detecting the quantization levels of the characteristic characters;

determining a weight floating coefficient of the feature item according to the positive polarity and the negative polarity of the feature character and the quantization level;

and calculating score information corresponding to the effective response information according to the weight ratio corresponding to each feature item and the weight floating coefficient, so as to determine the attribute type of the effective response information according to the score information.

3. The processing method of claim 1, further comprising:

acquiring a first feature vector of the effective response information, and detecting the similarity between the first feature vector and a second feature vector of preset illegal information;

if the similarity between the first feature vector and the second feature vector is greater than a first preset threshold, acquiring an object identifier corresponding to the effective response information, wherein the object identifier is determined by login information corresponding to the effective response information;

and adding the object identifier to a rejection request record table so as to block the information request message related to the object identifier in the rejection request record table when the information request message is sent again.

4. The processing method as claimed in claim 3, wherein said issuing information request messages for a plurality of different interaction channels comprises:

acquiring a plurality of different interaction channels;

and respectively sending out information request messages related to a plurality of preset object identifications for each interaction channel.

5. A terminal device comprising a memory and a processor, the memory having stored therein a computer program operable on the processor, wherein the processor, when executing the computer program, implements the steps of:

when the processor executes the computer program, the following steps are also realized:

6. The terminal device of claim 5, wherein the step of respectively obtaining the attribute type of each valid response message specifically includes:

7. The terminal device of claim 5, wherein the processor, when executing the computer program, further performs the steps of:

8. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 4.