A method, device, electronic device and storage medium for determining user satisfaction

Abstract

The embodiment of the present invention discloses a method, device, electronic device and storage medium for determining user satisfaction. The method for determining user satisfaction includes: obtaining user log data of a user; determining a user satisfaction index association matrix of user satisfaction indexes according to the user log data; determining at least one user satisfaction key index according to the user satisfaction index association matrix; determining a user satisfaction key index association matrix according to the user satisfaction index association matrix and each of the user satisfaction key indexes; determining a key index satisfaction score of each of the user satisfaction key indexes according to the user satisfaction key index association matrix; determining a user satisfaction score according to each of the key index satisfaction scores to determine user satisfaction. The technical solution of the embodiment of the present invention can quickly and accurately determine user satisfaction, thereby improving the efficiency and accuracy of determining user satisfaction.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of computer technology, and in particular, to a method, device, electronic device, and storage medium for determining user satisfaction. Background Art

[0002] In recent years, customer satisfaction surveys have gained widespread attention at home and abroad, especially in the service industry, where customer satisfaction surveys have become one of the important means for companies to discover problems and improve services. It is particularly important to understand customer needs, problems existing in the company, and differences with competitors through satisfaction surveys, so as to improve service work in a targeted manner.

[0003] The existing methods for determining user satisfaction usually include the following two methods: one is to establish a user experience management platform, detect various quantitative indicators of users in real time, and optimize and enhance the user experience through cumbersome rules and manual methods. The other is to detect and identify the feedback content based on user experience research, and determine whether it is a dissatisfied user through keyword matching.

[0004] However, the first method mentioned above relies heavily on the accumulation of existing indicator rule data through cumbersome rules and manual judgment schemes, which has poor timeliness, slow updates, and cannot locate dissatisfied users in a timely manner. The second method mentioned above determines whether it is a dissatisfied user by keyword matching, which cannot accurately determine the user's satisfaction. Summary of the invention

[0005] The embodiments of the present invention provide a method, device, electronic device and storage medium for determining user satisfaction, which can quickly and accurately determine user satisfaction, thereby improving the efficiency and accuracy of determining user satisfaction.

[0006] According to one aspect of the present invention, a method for determining user satisfaction is provided, comprising:

[0007] Get the user's user log data;

[0008] Determine a user satisfaction index association matrix of user satisfaction indexes according to the user log data;

[0009] Determine at least one key indicator of user satisfaction according to the user satisfaction indicator association matrix;

[0010] Determine a user satisfaction key indicator association matrix according to the user satisfaction indicator association matrix and each of the user satisfaction key indicators;

[0011] Determine the key indicator satisfaction score of each of the key indicators of user satisfaction according to the key indicator association matrix of user satisfaction;

[0012] The user satisfaction score is determined based on the satisfaction scores of each of the key indicators to determine user satisfaction.

[0013] According to another aspect of the present invention, there is provided a device for determining user satisfaction, comprising:

[0014] A user log data acquisition module is used to acquire the user log data of the user;

[0015] A user satisfaction index association matrix determination module, used to determine a user satisfaction index association matrix of user satisfaction indexes according to the user log data;

[0016] A user satisfaction key indicator determination module, used to determine at least one user satisfaction key indicator according to the user satisfaction indicator association matrix;

[0017] A user satisfaction key indicator correlation matrix determination module, used to determine a user satisfaction key indicator correlation matrix according to the user satisfaction indicator correlation matrix and each of the user satisfaction key indicators;

[0018] A key indicator satisfaction score determination module is used to determine the key indicator satisfaction score of each of the user satisfaction key indicators according to the user satisfaction key indicator association matrix;

[0019] The user satisfaction determination module is used to determine the user satisfaction score according to the satisfaction score of each key indicator to determine the user satisfaction.

[0020] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0021] at least one processor; and

[0022] a memory communicatively connected to the at least one processor; wherein,

[0023] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the user satisfaction determination method described in any embodiment of the present invention.

[0024] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the user satisfaction determination method described in any embodiment of the present invention when executed.

[0025] The technical solution of the embodiment of the present invention obtains the user log data of the user, and determines the user satisfaction indicator association matrix of the user satisfaction indicator according to the user log data, determines at least one user satisfaction key indicator according to the user satisfaction indicator association matrix, determines the user satisfaction key indicator association matrix according to the user satisfaction indicator association matrix and each user satisfaction key indicator, determines the key indicator satisfaction score of each user satisfaction key indicator according to the user satisfaction key indicator association matrix, thereby determines the user satisfaction score according to each key indicator satisfaction score, and further determines the user satisfaction, solves the problem that the existing user satisfaction determination method cannot determine the user satisfaction in time and cannot determine the user satisfaction accurately, can quickly and accurately determine the user satisfaction, thereby improving the efficiency and accuracy of determining the user satisfaction.

[0026] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0028] Figure 1 is a flow chart of a method for determining user satisfaction provided by Embodiment 1 of the present invention;

[0029] Figure 2 is a flow chart of a method for determining user satisfaction provided by Embodiment 2 of the present invention;

[0030] Figure 3 is an example flow chart of a method for determining user satisfaction provided by Embodiment 2 of the present invention;

[0031] Figure 4 is a schematic diagram of a user satisfaction determination device provided in Embodiment 3 of the present invention;

[0032] Figure 5 It is a structural schematic diagram of an electronic device for implementing the method for determining user satisfaction of an embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0034] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] Embodiment 1

[0036] Figure 1 This is a flowchart of a method for determining user satisfaction provided by the first embodiment of the present invention. This embodiment is applicable to the situation of quickly and accurately determining user satisfaction. The method can be executed by a user satisfaction determination device, which can be implemented by software and / or hardware, and can generally be directly integrated into an electronic device that executes the method. The electronic device can be a terminal device or a server device. The embodiment of the present invention does not limit the type of electronic device that executes the method for determining user satisfaction. Specifically, Figure 1 As shown, the method for determining user satisfaction may specifically include the following steps:

[0037] S110: Obtain user log data of the user.

[0038] The user log data may be data recording user behaviors, such as data recording user online behaviors, or data recording user transaction behaviors, etc., and the embodiments of the present invention do not limit this.

[0039] In the embodiment of the present invention, the user log data of the user is obtained to determine the user satisfaction index association matrix of the user satisfaction index according to the user log data. It is understandable that the user behavior can be determined by analyzing the user log data, and then the user satisfaction can be determined.

[0040] S120: Determine a user satisfaction index association matrix of user satisfaction indexes according to the user log data.

[0041] The user satisfaction index may be an index that can characterize user satisfaction, such as Internet access delay rate or return rate, etc., which is not limited in the embodiment of the present invention. The user satisfaction index association matrix may be a matrix constructed by user satisfaction indexes. It is understandable that the user satisfaction index association matrix may include at least two matrix elements, namely, user and user satisfaction index.

[0042] In an embodiment of the present invention, after obtaining the user log data of the user, a user satisfaction index association matrix of the user satisfaction index can be further determined according to the user log data. For example, if the user satisfaction index is the Internet access delay rate, the user satisfaction index association matrix of the user satisfaction index can be determined according to the Internet access request time and the Internet access connection time in the user log data.

[0043] S130. Determine at least one key indicator of user satisfaction according to the user satisfaction indicator association matrix.

[0044] Among them, the key indicator of user satisfaction can be an indicator obtained by screening the user satisfaction indicators. It is understandable that there can be multiple user satisfaction indicators, but when the number of user satisfaction indicators increases, the weight of each user satisfaction indicator affecting user satisfaction also becomes more vague. Therefore, it is necessary to simplify the number of user satisfaction indicators to obtain the key indicator of user satisfaction, that is, the key indicator of user satisfaction can be an indicator in the user satisfaction indicator. Exemplarily, if the user satisfaction index includes indicator A, indicator B, indicator C, indicator D and indicator E, the key indicator of user satisfaction can be indicator A and indicator B, or indicator B, indicator C and indicator D, etc., and the embodiment of the present invention does not limit this.

[0045] In the embodiment of the present invention, after determining a user satisfaction index association matrix of user satisfaction indexes according to user log data, at least one user satisfaction key index may be further determined according to the user satisfaction index association matrix.

[0046] S140: Determine a user satisfaction key indicator association matrix according to the user satisfaction indicator association matrix and each of the user satisfaction key indicators.

[0047] The user satisfaction key indicator correlation matrix may be a matrix constructed by the user satisfaction key indicators. It is understandable that the user satisfaction key indicator correlation matrix may include at least two matrix elements: user and user satisfaction key indicator.

[0048] In an embodiment of the present invention, after determining at least one user satisfaction key indicator according to the user satisfaction indicator association matrix, a user satisfaction key indicator association matrix can be further determined according to the user satisfaction indicator association matrix and each user satisfaction key indicator. Exemplarily, determining the user satisfaction key indicator association matrix according to the user satisfaction indicator association matrix and each user satisfaction key indicator can be to extract each user satisfaction key indicator in the user satisfaction indicator association matrix to construct the user satisfaction key indicator association matrix.

[0049] S150: Determine a key indicator satisfaction score for each of the key indicators of user satisfaction according to the key indicator association matrix of user satisfaction.

[0050] The key indicator satisfaction score may be a user satisfaction score for the user satisfaction key indicator. For example, if the user satisfaction key indicator is the Internet latency rate, the key indicator satisfaction score may be a user satisfaction score for the Internet latency rate.

[0051] In an embodiment of the present invention, after determining the user satisfaction key indicator association matrix according to the user satisfaction indicator association matrix and each user satisfaction key indicator, the key indicator satisfaction score of each user satisfaction key indicator can be further determined according to the user satisfaction key indicator association matrix.

[0052] S160: Determine a user satisfaction score according to the satisfaction scores of the key indicators to determine user satisfaction.

[0053] The user satisfaction score may be an overall user satisfaction score, for example, a user's online experience satisfaction score, or a user's shopping experience satisfaction score, etc. This is not limited in the embodiments of the present invention.

[0054] In an embodiment of the present invention, after determining the key indicator satisfaction score of each user satisfaction key indicator according to the user satisfaction key indicator association matrix, the user satisfaction score can be further determined according to each key indicator satisfaction score to determine the user satisfaction. Exemplarily, the user satisfaction score can be determined according to the satisfaction score of each key indicator, or according to the sum of the satisfaction scores of each key indicator, or according to the weighted value of the satisfaction scores of each key indicator, and the embodiment of the present invention does not limit this.

[0055] The technical solution of this embodiment obtains the user log data of the user, and determines the user satisfaction indicator association matrix of the user satisfaction indicator according to the user log data, determines at least one user satisfaction key indicator according to the user satisfaction indicator association matrix, determines the user satisfaction key indicator association matrix according to the user satisfaction indicator association matrix and each user satisfaction key indicator, determines the key indicator satisfaction score of each user satisfaction key indicator according to the user satisfaction key indicator association matrix, thereby determines the user satisfaction score according to each key indicator satisfaction score, and further determines the user satisfaction, which solves the problem that the existing user satisfaction determination method cannot determine the user satisfaction in time and cannot determine the user satisfaction accurately, and can quickly and accurately determine the user satisfaction, thereby improving the efficiency and accuracy of determining the user satisfaction.

[0056] Embodiment 2

[0057] Figure 2 It is a flow chart of a method for determining user satisfaction provided in the second embodiment of the present invention. This embodiment is a further refinement of the above-mentioned technical solutions, and provides a user satisfaction index association matrix for determining user satisfaction indexes according to user log data, determining at least one user satisfaction key index according to the user satisfaction index association matrix, determining the key index satisfaction score of each user satisfaction key index according to the user satisfaction key index association matrix, and multiple specific optional implementation methods for determining the user satisfaction score according to each key index satisfaction score. The technical solution in this embodiment can be combined with each optional solution in one or more of the above-mentioned embodiments. Figure 2 As shown, the method may include the following steps:

[0058] S210: Obtain user log data of the user.

[0059] Optionally, the user log data may include user online log data; the user online log data may include user online service log data and user online signaling log data.

[0060] Among them, the user Internet log data may be data recording the user's Internet behavior. The user Internet service log data may be Internet log data recording various services of the user, for example, it may be VoLTE (Voice over LTE, 4G high-definition voice service) call data, video data, web page data, instant messaging data, music data or game data, etc., and the embodiment of the present invention does not limit this. The user Internet signaling log data may be data recording the signaling log generated by the user when surfing the Internet. Optionally, the user Internet signaling log data may include user Internet network signaling log data and user Internet MR (Measurement Report, measurement report) signaling log data. Exemplarily, the user Internet service log data may include mobile phone number data, start time data, end time data, IMEI (International Mobile Equipment Identity, International Mobile Equipment Identity) data, IMSI (International Mobile Subscriber Identity, International Mobile Subscriber Identity) data, ECI (E-UTRAN Cell Identifier, E-UTRAN Cell Unique Identifier) ​​data, service duration data or service status data, etc. User Internet access network signaling log data may include: mobile phone number data, start time data, end time data, IMEI data, IMSI data, ECI data, process type data or process status data, etc. User Internet access MR signaling log data may include: start time data, end time data, ECI data, RSRP (Reference Signal Receiving Power) measurement value data, RSRQ (Reference Signal Receiving Quality) measurement value data or TADV (Timing advance) measurement value data, etc.

[0061] Specifically, obtaining the user log data of the user may be obtaining the user online service log data and the user online signaling log data of the user. Optionally, the user log data may include the user log data of the current day and the previous N days. Obtaining the user online service log data and the user online signaling log data of the user may be obtained according to a preset collection specification.

[0062] S220. Determine user satisfaction index data of at least one of the user satisfaction indicators based on the user log data; wherein the user satisfaction index data is index data of a combination of user mobile phone number dimension, time dimension, communication cell dimension and communication base station dimension.

[0063] The user satisfaction index data may be index value data of the user satisfaction index.

[0064] In an embodiment of the present invention, after obtaining the user log data of the user, user satisfaction index data of at least one user satisfaction index can be further determined based on the user log data. Specifically, the user satisfaction index data can be index data of a combination of the user's mobile phone number dimension, the time dimension, the communication cell dimension, and the communication base station dimension. Exemplarily, the user satisfaction index data can be index data of the user's mobile phone number A, time A, communication cell A, and communication base station A, or index data of the user's mobile phone number A, time B, communication cell A, and communication base station A, or index data of the user's mobile phone number A, time B, communication cell A, and communication base station B, etc., and the embodiment of the present invention does not limit this.

[0065] Optionally, user satisfaction indicators may include success / failure rate user satisfaction indicators, latency user satisfaction indicators, and measurement user satisfaction indicators. Specifically, by aggregating user log data according to the combined dimensions of user mobile phone number dimension, time dimension, communication cell dimension, and communication base station dimension, the number of success / failure times and the number of requests can be determined by accumulation, and the user satisfaction indicator data of the success / failure rate user satisfaction indicator can be determined according to the percentage of the number of success / failure times and the number of requests; the total latency and the total number of requests can be determined by accumulation, and the user satisfaction indicator data of the latency user satisfaction indicator can be determined by dividing the total latency by the total number of requests; the total measurement value and the total number of measurements can be determined by accumulation, and the user satisfaction indicator data of the measurement user satisfaction indicator can be determined by dividing the total measurement value by the total number of measurements.

[0066] S230. Establish the user satisfaction index association matrix according to the user satisfaction index data; wherein the matrix elements of the user satisfaction index association matrix include: the user mobile phone number dimension, the time dimension, the communication cell dimension, the communication base station dimension and the user satisfaction index data.

[0067] In an embodiment of the present invention, after determining user satisfaction index data of at least one user satisfaction index according to user log data, a user satisfaction index association matrix can be further established according to the user satisfaction index data. Specifically, the matrix elements of the user satisfaction index association matrix include: user mobile phone number dimension, time dimension, communication cell dimension, communication base station dimension and user satisfaction index data. Exemplarily, the user satisfaction index association matrix is ​​shown in Table 1.

[0068] Table 1 User satisfaction index correlation matrix

[0069]

[0070] Optionally, if the user satisfaction index data of a certain dimension cannot be determined based on the user log data, the mode value of the user satisfaction index can be determined as the user satisfaction index data. Exemplarily, as shown in Table 1, if data 1-2 cannot be determined based on the user log data, data 1-2 can be determined based on the mode values ​​of data 1-1, data 1-3, and data 1-4.

[0071] S240: Obtain target association matrix element data of the user satisfaction index association matrix.

[0072] The target association matrix element data may be the target data in the matrix element of the user satisfaction index association matrix. For example, as shown in Table 1, the target association matrix element data may be data 1-1, data 2-1 or data 3-2, etc., which is not limited in the embodiment of the present invention.

[0073] In an embodiment of the present invention, after establishing a user satisfaction index association matrix according to user satisfaction index data, target association matrix element data of the user satisfaction index association matrix may be further obtained to normalize the target association matrix element data.

[0074] S250, normalizing the target association matrix element data to obtain a user satisfaction index normalized association matrix.

[0075] The user satisfaction index normalized correlation matrix may be a matrix obtained by normalizing the element data of the target correlation matrix.

[0076] In an embodiment of the present invention, after obtaining the target association matrix element data of the user satisfaction index association matrix, the target association matrix element data can be further normalized to obtain a user satisfaction index normalized association matrix. It can be understood that the user satisfaction index can include an index with a higher satisfaction level as the index value is larger and an index with a higher satisfaction level as the index value is smaller.

[0077] Optionally, if the user satisfaction index is an index whose satisfaction increases as the index value increases, when the target association matrix element data of the user satisfaction index is normalized, the formula (y-min) / (max-min) can be used to determine the normalized data corresponding to the target association matrix element data in the normalized association matrix of the user satisfaction index. If the user satisfaction index is an index whose satisfaction increases as the index value decreases, when the target association matrix element data of the user satisfaction index is normalized, the formula (max-y) / (max-min) can be used to determine the normalized data corresponding to the target association matrix element data in the normalized association matrix of the user satisfaction index. Wherein, y is the target association matrix element data of the user satisfaction index, min is the minimum user satisfaction index data in the user satisfaction index, and max is the maximum user satisfaction index data in the user satisfaction index.

[0078] S260 . Determine a user satisfaction index covariance matrix of the user satisfaction index normalized correlation matrix according to the user satisfaction index normalized correlation matrix.

[0079] S270. Determine a user satisfaction index characteristic value according to the user satisfaction index covariance matrix.

[0080] The user satisfaction index covariance matrix may be a covariance matrix of the user satisfaction index, and the satisfaction index eigenvalue may be an eigenvalue of the user satisfaction index.

[0081] In an embodiment of the present invention, after normalizing the original data of the target correlation matrix to obtain a normalized correlation matrix of user satisfaction indicators, the user satisfaction indicator covariance matrix of the normalized correlation matrix of user satisfaction indicators can be further determined based on the normalized correlation matrix of user satisfaction indicators, so as to determine the user satisfaction indicator eigenvalues ​​based on the user satisfaction indicator covariance matrix.

[0082] S280: Sorting the user satisfaction indicators according to the characteristic values ​​of the user satisfaction indicators, so as to determine at least one key indicator of user satisfaction according to the result of the sorting of the user satisfaction indicators.

[0083] The user satisfaction index ranking result may be a result obtained by ranking the user satisfaction indexes.

[0084] In an embodiment of the present invention, after determining the user satisfaction index characteristic value according to the user satisfaction index covariance matrix, the user satisfaction index can be further sorted according to the user satisfaction index characteristic value to determine at least one user satisfaction key index according to the user satisfaction index sorting result.

[0085] Optionally, the user satisfaction index is sorted according to the characteristic value of the user satisfaction index, and the user satisfaction index can be sorted in positive order according to the size of the characteristic value of the user satisfaction index. For example, the characteristic value of the user satisfaction index A is λ A , the user satisfaction index characteristic value of user satisfaction index B is λ B , the user satisfaction index characteristic value of user satisfaction index C is λ C , if λ B >λ A >λ C , then the ranking result of user satisfaction index is user satisfaction index B->user satisfaction index A->user satisfaction index C.

[0086] Optionally, at least one key user satisfaction indicator is determined according to the ranking result of the user satisfaction indicators, and the key user satisfaction indicator can be determined according to the following formula:

[0087]

[0088] Among them, k represents the number of key indicators of user satisfaction, j represents the jth user satisfaction indicator, n represents the total number of user satisfaction indicators, and λ j The user satisfaction index characteristic value representing the j-th user satisfaction index.

[0089] Specifically, the value of k can be determined according to the above formula, that is, the number of key user satisfaction indicators can be determined according to the above formula, and the first k user satisfaction indicators in the user satisfaction indicator ranking result can be further used as key user satisfaction indicators.

[0090] S290: Determine a user satisfaction key indicator association matrix according to the user satisfaction indicator association matrix and each of the user satisfaction key indicators.

[0091] S2100: Obtain user satisfaction key indicator data and user satisfaction key indicator time data of each of the user satisfaction key indicators in the user satisfaction key indicator association matrix.

[0092] Among them, the user satisfaction key indicator data may be the indicator value data of the user satisfaction key indicator. The user satisfaction key indicator time data may be the time data corresponding to the user satisfaction key indicator. For example, as shown in Table 1, the user satisfaction key indicator time data may be time 1, time 2, or time 3, etc., which is not limited in the embodiment of the present invention.

[0093] In an embodiment of the present invention, after determining the user satisfaction key indicator association matrix based on the user satisfaction indicator association matrix and each user satisfaction key indicator, user satisfaction key indicator data and user satisfaction key indicator time data of each user satisfaction key indicator in the user satisfaction key indicator association matrix can be further obtained.

[0094] S2110. Sort each of the user satisfaction key indicators according to the user satisfaction key indicator data and the user satisfaction key indicator time data to obtain first limit indicator data and second limit indicator data for each of the user satisfaction key indicators.

[0095] The first limit indicator data may be user satisfaction key indicator data corresponding to a limit of the user satisfaction key indicator, and the second limit indicator data may be user satisfaction key indicator data corresponding to another limit of the user satisfaction key indicator.

[0096] In an embodiment of the present invention, after obtaining the user satisfaction key indicator data and the user satisfaction key indicator time data of each user satisfaction key indicator in the user satisfaction key indicator association matrix, each user satisfaction key indicator can be further sorted according to the user satisfaction key indicator data and the user satisfaction key indicator time data to obtain the first boundary indicator data and the second boundary indicator data of each user satisfaction key indicator.

[0097] Optionally, the first limit indicator data may be the user satisfaction key indicator data corresponding to the user satisfaction key indicator at the 20% ranking position after the user satisfaction key indicators are sorted. The second limit indicator data may be the user satisfaction key indicator data corresponding to the user satisfaction key indicator at the 80% ranking position after the user satisfaction key indicators are sorted. Exemplarily, if there are 10 user satisfaction key indicators, after the user satisfaction key indicators are sorted, the ranking result of the user satisfaction key indicators is user satisfaction key indicator 3->user satisfaction key indicator 5->user satisfaction key indicator 2->user satisfaction key indicator 6->user satisfaction key indicator 4->user satisfaction key indicator 1->user satisfaction key indicator 8->user satisfaction key indicator 10->user satisfaction key indicator 9->user satisfaction key indicator 7, then the first limit indicator data may be the user satisfaction key indicator data corresponding to the user satisfaction key indicator 5, and the second limit indicator data may be the user satisfaction key indicator data corresponding to the user satisfaction key indicator 10.

[0098] Optionally, the user satisfaction key indicators are sorted according to the user satisfaction key indicator data and the user satisfaction key indicator time data, which can be to sort the user satisfaction key indicator data of the same user satisfaction key indicator on the same day in positive order. Exemplarily, the user satisfaction key indicator data of the user satisfaction key indicator 1 of the user mobile phone number A is data 1, and the user satisfaction key indicator time data is time 1, the user satisfaction key indicator data of the user satisfaction key indicator 1 of the user mobile phone number B is data 2, and the user satisfaction key indicator time data is time 1, the user satisfaction key indicator data of the user satisfaction key indicator 1 of the user mobile phone number C is data 3, and the user satisfaction key indicator time data is time 2, then the user satisfaction key indicator 1 of different user mobile phone numbers at time 1 is sorted, that is, the data 1 of the user mobile phone number A and the data 2 of the user mobile phone number B are sorted in positive order according to the size of data 1 and data 2.

[0099] Optionally, after sorting the user satisfaction key indicator data of the same user satisfaction key indicator on the same day in ascending order, the first limit indicator data of each day and the second limit indicator data of each day of the user satisfaction key indicator can be further determined, and the average value of the first limit indicator data of each day can be used as the first limit indicator data of the user satisfaction key indicator, and the average value of the second limit indicator data of each day can be used as the second limit indicator data of the user satisfaction key indicator.

[0100] S2120. Determine a key indicator satisfaction score for each of the user satisfaction key indicators based on the first limit indicator data and the second limit indicator data.

[0101] In an embodiment of the present invention, after sorting each user satisfaction key indicator according to the user satisfaction key indicator data and the user satisfaction key indicator time data to obtain the first boundary indicator data and the second boundary indicator data of each user satisfaction key indicator, the key indicator satisfaction score of each user satisfaction key indicator can be further determined based on the first boundary indicator data and the second boundary indicator data.

[0102] Optionally, determining the key indicator satisfaction score of each user satisfaction key indicator according to the first limit indicator data and the second limit indicator data may include: determining the user satisfaction key indicator business attribute of each user satisfaction key indicator; and determining the key indicator satisfaction score of each user satisfaction key indicator according to the user satisfaction key indicator business attribute and the following formula:

[0103]

[0104] f(x)=(1-p)g(x)+(10-g(x))p

[0105] Among them, x represents the user satisfaction key indicator data of each user satisfaction key indicator; when the business attribute of the user satisfaction key indicator is determined to be the first business attribute, p is the first calculation parameter, and a is the second boundary indicator data parameter; when the business attribute of the user satisfaction key indicator is determined to be the second business attribute, p is the second calculation parameter, and a is the first boundary indicator data parameter.

[0106] Among them, the business attribute of the key indicator of user satisfaction can be a business attribute of the key indicator of user satisfaction, for example, it can be a business attribute with higher satisfaction as the larger the indicator value is, or it can be a business attribute with higher satisfaction as the smaller the indicator value is, and the embodiment of the present invention does not limit this. The first business attribute can be a business attribute of a key indicator of user satisfaction, for example, it can be a business attribute with higher satisfaction as the smaller the indicator value is. The second business attribute can be another business attribute of the key indicator of user satisfaction, for example, it can be a business attribute with higher satisfaction as the larger the indicator value is. Exemplarily, the business attribute of the key indicator of user satisfaction of the success rate type can be a business attribute with higher satisfaction as the larger the indicator value is. The business attribute of the key indicator of user satisfaction of the delay type can be a business attribute with higher satisfaction as the smaller the indicator value is.

[0107] Wherein, the first calculation parameter may be a calculation parameter of the formula. The second calculation parameter may be another calculation parameter of the formula. Exemplarily, the value of the first calculation parameter may be 0, and the value of the second calculation parameter may be 1. The second limit indicator data parameter may be a parameter corresponding to the second limit indicator data. The first limit indicator data parameter may be a parameter corresponding to the first limit indicator data. Exemplarily, the value of the second limit indicator data parameter may be the second limit indicator data divided by 3.57, and the value of the first limit indicator data parameter may be the first limit indicator data divided by 2.97.

[0108] Specifically, after sorting each user satisfaction key indicator according to each user satisfaction key indicator data and each user satisfaction key indicator time data to obtain the first boundary indicator data and the second boundary indicator data of each user satisfaction key indicator, the user satisfaction key indicator business attribute of each user satisfaction key indicator can be further determined, and the key indicator satisfaction score of each user satisfaction key indicator can be determined according to the user satisfaction key indicator business attribute and the above formula. If the user satisfaction key indicator business attribute is the first business attribute, the parameter p of the above formula can be the first calculation parameter, and the parameter a can be the second boundary indicator data parameter. If the user satisfaction key indicator business attribute is the second business attribute, the parameter p of the above formula can be the second calculation parameter, and the parameter a can be the first boundary indicator data parameter. It can be understood that the value range of the key indicator satisfaction score can be 0-10 points.

[0109] S2130. Determine a user satisfaction score according to the satisfaction scores of each of the key indicators to determine user satisfaction.

[0110] Optionally, after determining at least one key user satisfaction indicator according to the user satisfaction indicator association matrix, the method may further include: determining a key indicator weight value of each key user satisfaction indicator according to the user satisfaction indicator association matrix and each key user satisfaction indicator. Determining the user satisfaction score according to the satisfaction score of each key indicator may include: determining the user satisfaction score according to the satisfaction score of each key indicator and the key indicator weight value of each key user satisfaction indicator.

[0111] Among them, the key indicator weight value can be the weight of the user satisfaction key indicator.

[0112] Specifically, after determining at least one key indicator of user satisfaction according to the user satisfaction indicator association matrix, the key indicator weight value of each user satisfaction key indicator can be further determined according to the user satisfaction indicator association matrix and each user satisfaction key indicator, and after determining the key indicator weight value of each user satisfaction key indicator, the user satisfaction score can be determined according to each key indicator satisfaction score and the key indicator weight value of each user satisfaction key indicator.

[0113] Optionally, the key indicator weight value of each user satisfaction key indicator is determined according to the user satisfaction indicator correlation matrix and each user satisfaction key indicator, which can be to obtain the target correlation matrix element data of the user satisfaction indicator correlation matrix, normalize the target correlation matrix element data to obtain the user satisfaction indicator normalized correlation matrix, and determine the user satisfaction indicator covariance matrix of the user satisfaction indicator normalized correlation matrix according to the user satisfaction indicator normalized correlation matrix, determine the user satisfaction indicator eigenvalue according to the user satisfaction indicator covariance matrix, and determine the user satisfaction key indicator eigenvalue of each user satisfaction key indicator according to the user satisfaction indicator eigenvalue, so as to determine the key indicator weight value of each user satisfaction key indicator according to the user satisfaction key indicator eigenvalue. Specifically, the key indicator weight value of each user satisfaction key indicator can be determined according to the formula and formula Determine the key indicator weight value of each key indicator of user satisfaction. Among them, λ i represents the user satisfaction key indicator characteristic value of the i-th user satisfaction key indicator, and k represents the number of user satisfaction key indicators.

[0114] Optionally, the user satisfaction score is determined based on the satisfaction score of each key indicator and the key indicator weight value of each user satisfaction key indicator. The user satisfaction score can be determined by multiplying each key indicator satisfaction score by the key indicator weight value of each user satisfaction key indicator and then adding the two numbers together.

[0115] In a specific example, mobile terminal devices such as mobile phones are an indispensable part of modern society. In addition to normal communication functions, as people's daily lives continue to enrich, more and more life services can be experienced through the Internet on mobile terminals, such as browsing websites, watching videos, shopping, listening to music or playing games. Of course, for different users, the experience of these network services is good and bad, and how network service providers understand the satisfaction of user experience is even more important in the current "Internet +" economic situation, because improving user experience is a differentiated competitive advantage. Therefore, a reasonable way is needed to evaluate users' network experience behavior to help improve user experience satisfaction.

[0116] Figure 3 is an example flow chart of a method for determining user satisfaction provided by Embodiment 2 of the present invention. Figure 3 As shown, the method may specifically include the following contents:

[0117] (1) Obtain the user's Internet access logs for each service (i.e., the user's Internet access service log data) and signaling logs (i.e., the user's Internet access signaling log data).

[0118] Specifically, obtain the Internet access log and signaling log data of the user's mobile terminal on the current day and within the previous N days in history. Specific Internet services may include VoLTE calls, videos, web pages, instant messaging, music, games, etc. The Internet access log and signaling content fields of various services are specified by a unified collection specification. Various service logs may at least include: mobile phone number, start time, end time, IMEI, IMSI, ECI, service duration or service status and other field contents. Network signaling logs may include: mobile phone number, start time, end time, IMEI, IMSI, ECI, process type or process status, etc. MR signaling logs may include: start time, end time, ECI, RSRP measurement value, RSRQ measurement value or TADV measurement value, etc.

[0119] (2) Calculate network experience related indicators.

[0120] Based on the Internet access logs and signaling logs of the user's mobile terminal on the current day and within the past N days, the indicator data of the combined dimensions of user, time, ECI, and base station are calculated according to the indicator calculation method.

[0121] Among them, the indicator calculation methods are roughly divided into the following categories:

[0122] a. Success / failure rate indicators: Aggregate log data by combined dimensions, add up the "success / failure times" and "number of requests", and finally calculate the percentage of "success / failure times" and "number of requests";

[0123] b. Latency indicators: Aggregate log data by combination dimension, add up the "total latency" and "total number of requests", and finally find the value of "total latency" to "total number of requests";

[0124] c. Measurement indicators: Aggregate log data by combined dimensions, add up the "total measurement value" and "total number of measurements", and finally find the value of the "total measurement value" to the "total number of measurements".

[0125] (3) Generate user indicator association matrix.

[0126] Based on the number of users who normally access the Internet in the mobile network, extract the corresponding indicator data according to the combined dimensions of user, time, ECI, and base station. If the user has an indicator value for the corresponding indicator under the combined dimension, fill in the corresponding indicator position with the value, otherwise fill in the mode value of the column indicator. After this processing, the relationship matrix between user, time, ECI, base station and indicator is obtained, and each row value of the matrix is ​​used as the network experience trajectory vector of the user.

[0127] (4) Screen key indicators, calculate key indicator weights, and define the numerical baseline for key indicators.

[0128] Mobile network users will generate corresponding online logs when using the network. The index data calculated from these online logs can objectively reflect the impact of the network on the user's online experience under normal circumstances. When the user uses more services through the network, that is, when there are more corresponding indicators, it can more accurately reflect the good or bad experience of the user experience of the network, thereby affecting the user's satisfaction. However, when the number of indicators increases, the weight of each indicator affecting user satisfaction becomes more vague. Therefore, on this basis, the key indicator screening method is used, that is, when the number of users remains unchanged, the linear relationship between the values ​​of each indicator is used to simplify the actual number of indicators, so as to achieve the accuracy of weight judgment.

[0129] a. Screening key indicators:

[0130] The indicator data is normalized; for the indicator of "the larger the indicator data, the better", the formula is: (x-min) / (max-min); for the indicator of "the smaller the indicator data, the better", the formula is: (max-x) / (max-min); calculate the covariance matrix, and calculate the eigenvalue λ of the covariance matrix j , and according to the eigenvalue λ jThe indicators are sorted by size; important indicators are confirmed when the utilization rate of information reaches 80% or above, that is, according to the formula The k indicators are determined to be important indicators.

[0131] b. Calculate the weight of key indicators:

[0132] Calculate the cumulative information ratio of key indicators, that is, the cumulative variance contribution rate And according to the formula Calculate the weights of key indicators.

[0133] c. Determine the numerical baseline of key indicators:

[0134] The indicator baseline is defined for the selected key indicators. The specific methods include: extracting the key indicator data of users for multiple days from the user indicator association matrix; performing full positive sorting on each indicator column of each day to obtain the indicator values ​​of its upper limit value (value at the 20% position) and lower limit value (value at the 80% position); averaging the upper and lower limit values ​​calculated for each day to obtain the final upper and lower limit values ​​of each indicator.

[0135] (5) Calculate user business indicator scores and satisfaction scores.

[0136] Based on the analysis of a large amount of historical data, it is found that the distribution of a single indicator follows the gamma distribution, so the following method is designed to calculate the satisfaction score:

[0137] Step 1: Determine the business attributes of the screening indicators, that is, divide the screened indicators into two categories: "the bigger the better" and "the smaller the better", such as the success rate category is the "bigger the better" indicator, and the latency category is the "smaller the better" indicator.

[0138] Step 2: Calculate the score of a single indicator. The algorithm formula for scoring each indicator of the user is as follows:

[0139]

[0140] f(x)=(1-p)g(x)+(10-g(x))p

[0141] Where x is the actual indicator value, and a and p are the parameters of the algorithm. When calculating the score of the "smaller the better" type of indicator, p is equal to 0 and a is equal to the lower limit of the indicator divided by 3.57. When calculating the score of the "bigger the better" type of indicator, p is equal to 1 and a is equal to the upper limit of the indicator divided by 2.97. The value range of f(x) is 0 to 10 points.

[0142] Step 3: Calculate the user satisfaction score. Multiply the scores of each screening indicator by the indicator weight, and then add them up to get the final satisfaction score.

[0143] (6) Output predicted dissatisfied users.

[0144] The judgment of dissatisfied users depends on the satisfaction score calculated in the previous step. When the user's satisfaction score is greater than or equal to 0 and less than or equal to 6, the user is judged as a dissatisfied user.

[0145] The above technical solution can make a relatively quick and reasonable prediction of the user's satisfaction with the use of the network based on objective indicators that reflect the user's Internet access situation and without the need for subjective human intervention and judgment, so that network providers can timely discover and locate the endpoints of their own services, and more accurately appease users who are dissatisfied with the prediction, thereby improving user satisfaction. The key indicator screening algorithm and the satisfaction score calculation algorithm are both verified through big data inductive analysis, and can quickly and accurately obtain the desired results.

[0146] The technical solution of this embodiment obtains the user log data of the user, and determines the user satisfaction index data of at least one user satisfaction index according to the user log data, so as to establish a user satisfaction index association matrix according to the user satisfaction index data. The target association matrix element data of the user satisfaction index association matrix is ​​obtained, and the target association matrix element data is normalized to obtain the user satisfaction index normalized association matrix, and the user satisfaction index covariance matrix of the user satisfaction index normalized association matrix is ​​determined according to the user satisfaction index normalized association matrix, and the user satisfaction index eigenvalue is determined according to the user satisfaction index covariance matrix, and the user satisfaction index is sorted according to the user satisfaction index eigenvalue, so as to determine at least one user satisfaction key indicator according to the user satisfaction index sorting result, and thus the user satisfaction key indicator association matrix is ​​determined according to the user satisfaction index association matrix and each user satisfaction key indicator. The user satisfaction key indicator data and the user satisfaction key indicator time data of each user satisfaction key indicator in the user satisfaction key indicator association matrix are obtained, and each user satisfaction key indicator is sorted according to the user satisfaction key indicator data and the user satisfaction key indicator time data to obtain the first boundary indicator data and the second boundary indicator data of each user satisfaction key indicator, and the key indicator satisfaction score of each user satisfaction key indicator is determined according to the first boundary indicator data and the second boundary indicator data, so as to determine the user satisfaction score according to each key indicator satisfaction score, thereby determining the user satisfaction, solving the problem that the existing user satisfaction determination method cannot determine the user satisfaction in time and cannot determine the user satisfaction accurately, and can quickly and accurately determine the user satisfaction, thereby improving the efficiency and accuracy of determining the user satisfaction.

[0147] Embodiment 3

[0148] Figure 4is a schematic diagram of a user satisfaction determination device provided by Embodiment 3 of the present invention, such as Figure 4 As shown, the device includes: a user log data acquisition module 410, a user satisfaction index association matrix determination module 420, a user satisfaction key index determination module 430, a user satisfaction key index association matrix determination module 440, a key index satisfaction score determination module 450 and a user satisfaction determination module 460, wherein:

[0149] A user log data acquisition module 410 is used to acquire user log data of a user;

[0150] A user satisfaction index correlation matrix determination module 420, configured to determine a user satisfaction index correlation matrix of user satisfaction indexes according to the user log data;

[0151] A user satisfaction key indicator determination module 430, configured to determine at least one user satisfaction key indicator according to the user satisfaction indicator association matrix;

[0152] A user satisfaction key indicator correlation matrix determination module 440 is used to determine a user satisfaction key indicator correlation matrix according to the user satisfaction indicator correlation matrix and each of the user satisfaction key indicators;

[0153] A key indicator satisfaction score determination module 450 is used to determine the key indicator satisfaction score of each of the user satisfaction key indicators according to the user satisfaction key indicator association matrix;

[0154] The user satisfaction determination module 460 is used to determine the user satisfaction score according to the satisfaction scores of the key indicators to determine the user satisfaction.

[0155] The technical solution of the embodiment of the present invention obtains the user log data of the user, and determines the user satisfaction indicator association matrix of the user satisfaction indicator according to the user log data, determines at least one user satisfaction key indicator according to the user satisfaction indicator association matrix, determines the user satisfaction key indicator association matrix according to the user satisfaction indicator association matrix and each user satisfaction key indicator, determines the key indicator satisfaction score of each user satisfaction key indicator according to the user satisfaction key indicator association matrix, thereby determines the user satisfaction score according to each key indicator satisfaction score, and further determines the user satisfaction, solves the problem that the existing user satisfaction determination method cannot determine the user satisfaction in time and cannot determine the user satisfaction accurately, can quickly and accurately determine the user satisfaction, thereby improving the efficiency and accuracy of determining the user satisfaction.

[0156] Optionally, the user log data may include user online log data; the user online log data may include user online service log data and user online signaling log data.

[0157] Optionally, the user satisfaction index association matrix determination module 420 can be specifically used to: determine user satisfaction index data of at least one user satisfaction index based on user log data; wherein the user satisfaction index data is index data of a combination of user mobile phone number dimension, time dimension, communication cell dimension and communication base station dimension; establish a user satisfaction index association matrix based on the user satisfaction index data; wherein the matrix elements of the user satisfaction index association matrix include: user mobile phone number dimension, time dimension, communication cell dimension, communication base station dimension and user satisfaction index data.

[0158] Optionally, the user satisfaction key indicator determination module 430 can be specifically used to: obtain target correlation matrix element data of the user satisfaction indicator correlation matrix; normalize the target correlation matrix element data to obtain a normalized correlation matrix of the user satisfaction indicators; determine a user satisfaction indicator covariance matrix of the normalized correlation matrix of the user satisfaction indicators based on the normalized correlation matrix of the user satisfaction indicators; determine user satisfaction indicator eigenvalues ​​based on the user satisfaction indicator covariance matrix; sort the user satisfaction indicators based on the user satisfaction indicator eigenvalues ​​to determine at least one user satisfaction key indicator based on the user satisfaction indicator sorting result.

[0159] Optionally, the key indicator satisfaction score determination module 450 may be specifically used for:

[0160] Obtain user satisfaction key indicator data and user satisfaction key indicator time data for each user satisfaction key indicator in the user satisfaction key indicator association matrix; sort each user satisfaction key indicator according to the user satisfaction key indicator data and the user satisfaction key indicator time data to obtain the first boundary indicator data and the second boundary indicator data for each user satisfaction key indicator; determine the key indicator satisfaction score of each user satisfaction key indicator according to the first boundary indicator data and the second boundary indicator data.

[0161] Optionally, the key indicator satisfaction score determination module 450 may be further used to: determine the user satisfaction key indicator business attributes of each user satisfaction key indicator; determine the key indicator satisfaction score of each user satisfaction key indicator according to the user satisfaction key indicator business attributes and the following formula:

[0162]

[0163] f(x)=(1-p)g(x)+(10-g(x))p

[0164] Among them, x represents the user satisfaction key indicator data of each user satisfaction key indicator; when the business attribute of the user satisfaction key indicator is determined to be the first business attribute, p is the first calculation parameter, and a is the second boundary indicator data parameter; when the business attribute of the user satisfaction key indicator is determined to be the second business attribute, p is the second calculation parameter, and a is the first boundary indicator data parameter.

[0165] Optionally, the user satisfaction determination module 460 can be specifically used to: determine the key indicator weight value of each user satisfaction key indicator based on the user satisfaction indicator association matrix and each user satisfaction key indicator; determine the user satisfaction score based on each key indicator satisfaction score and the key indicator weight value of each user satisfaction key indicator.

[0166] The user satisfaction determination device provided in the embodiment of the present invention can execute the user satisfaction determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0167] Embodiment 4

[0168] Figure 5 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0169] like Figure 5 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0170] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0171] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for determining user satisfaction.

[0172] In some embodiments, the user satisfaction determination method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the user satisfaction determination method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the user satisfaction determination method in any other appropriate manner (e.g., by means of firmware).

[0173] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0174] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0175] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0176] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0177] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0178] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0179] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0180] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for determining user satisfaction, It is characterized in that include: Get the user's user log data; Determine a user satisfaction index association matrix of user satisfaction indexes according to the user log data; Determine at least one key indicator of user satisfaction according to the user satisfaction indicator association matrix; Determine a user satisfaction key indicator association matrix according to the user satisfaction indicator association matrix and each of the user satisfaction key indicators; Determine the key indicator satisfaction score of each of the key indicators of user satisfaction according to the key indicator association matrix of user satisfaction; Determine the user satisfaction score based on the satisfaction score of each of the key indicators to determine user satisfaction; Wherein, determining the key indicator satisfaction score of each of the key indicators of user satisfaction according to the key indicator association matrix of user satisfaction includes: Obtaining user satisfaction key indicator data and user satisfaction key indicator time data of each of the user satisfaction key indicators in the user satisfaction key indicator association matrix; Sorting each of the user satisfaction key indicators according to each of the user satisfaction key indicator data and each of the user satisfaction key indicator time data to obtain first limit indicator data and second limit indicator data of each of the user satisfaction key indicators; Determine the user satisfaction key indicator business attributes of each of the user satisfaction key indicators; Determine the key indicator satisfaction score of each of the key indicators of user satisfaction based on the business attributes of the key indicators of user satisfaction and the following formula: f(x)=(1-p)g(x)+(10-g(x))p Among them, x represents the user satisfaction key indicator data of each of the user satisfaction key indicators; when the business attribute of the user satisfaction key indicator is determined to be the first business attribute, p is the first calculation parameter, and a is the second boundary indicator data parameter; when the business attribute of the user satisfaction key indicator is determined to be the second business attribute, p is the second calculation parameter, and a is the first boundary indicator data parameter.

2. The method according to claim 1, It is characterized in that The user log data includes user online log data; the user online log data includes user online service log data and user online signaling log data.

3. The method according to claim 1 or 2, It is characterized in that The user satisfaction index association matrix for determining the user satisfaction index according to the user log data includes: Determine user satisfaction index data of at least one of the user satisfaction indicators according to the user log data; wherein the user satisfaction index data is index data of a combination of user mobile phone number dimension, time dimension, communication cell dimension and communication base station dimension; The user satisfaction index association matrix is ​​established according to the user satisfaction index data; wherein the matrix elements of the user satisfaction index association matrix include: the user mobile phone number dimension, the time dimension, the communication cell dimension, the communication base station dimension and the user satisfaction index data.

4. The method according to claim 3, It is characterized in that Determining at least one key user satisfaction indicator according to the user satisfaction indicator association matrix includes: Obtain target correlation matrix element data of the user satisfaction index correlation matrix; Normalizing the target association matrix element data to obtain a user satisfaction index normalized association matrix; Determining a user satisfaction index covariance matrix of the user satisfaction index normalized association matrix according to the user satisfaction index normalized association matrix; Determining a user satisfaction index eigenvalue according to the user satisfaction index covariance matrix; The user satisfaction indicators are sorted according to the user satisfaction indicator characteristic values, so as to determine at least one of the user satisfaction key indicators according to the user satisfaction indicator sorting result.

5. The method according to claim 1 or 2, It is characterized in that After determining at least one key indicator of user satisfaction according to the user satisfaction indicator association matrix, the method further includes: Determine the key indicator weight value of each of the user satisfaction key indicators according to the user satisfaction indicator association matrix and each of the user satisfaction key indicators; Wherein, determining the user satisfaction score according to the satisfaction score of each key indicator includes: The user satisfaction score is determined according to the satisfaction score of each key indicator and the key indicator weight value of each user satisfaction key indicator.

6. A user satisfaction determination device, It is characterized in that include: A user log data acquisition module is used to acquire the user log data of the user; A user satisfaction index association matrix determination module, used to determine a user satisfaction index association matrix of user satisfaction indexes according to the user log data; A user satisfaction key indicator determination module, used to determine at least one user satisfaction key indicator according to the user satisfaction indicator association matrix; A user satisfaction key indicator correlation matrix determination module, used to determine a user satisfaction key indicator correlation matrix according to the user satisfaction indicator correlation matrix and each of the user satisfaction key indicators; A key indicator satisfaction score determination module is used to determine the key indicator satisfaction score of each of the user satisfaction key indicators according to the user satisfaction key indicator association matrix; A user satisfaction determination module is used to determine the user satisfaction score according to the satisfaction score of each key indicator to determine the user satisfaction; The key indicator satisfaction score determination module is specifically used to: Obtaining user satisfaction key indicator data and user satisfaction key indicator time data of each of the user satisfaction key indicators in the user satisfaction key indicator association matrix; Sorting each of the user satisfaction key indicators according to each of the user satisfaction key indicator data and each of the user satisfaction key indicator time data to obtain first limit indicator data and second limit indicator data of each of the user satisfaction key indicators; Determine the user satisfaction key indicator business attributes of each of the user satisfaction key indicators; Determine the key indicator satisfaction score of each of the key indicators of user satisfaction based on the business attributes of the key indicators of user satisfaction and the following formula: f(x)=(1-p)g(x)+(10-g(x))p Among them, x represents the user satisfaction key indicator data of each of the user satisfaction key indicators; when the business attribute of the user satisfaction key indicator is determined to be the first business attribute, p is the first calculation parameter, and a is the second boundary indicator data parameter; when the business attribute of the user satisfaction key indicator is determined to be the second business attribute, p is the second calculation parameter, and a is the first boundary indicator data parameter.

7. An electronic device, It is characterized in that The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the user satisfaction determination method according to any one of claims 1 to 5.

8. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the user satisfaction determination method according to any one of claims 1 to 5 when executed.

Images