Evaluation implementation method, device and storage medium

Abstract

The present invention discloses an evaluation implementation method, device and storage medium, the method comprising: determining a first questionnaire based on a first tag set; the first tag set comprises: user preference tags; the user preference tags are determined based on historical user data; obtaining parameters of target features, and determining a first device based on the parameters of the target features; the parameters of the target features are determined based on environmental status and behavioral status; sending the first questionnaire to the first device; the first questionnaire is presented by the first device; and receiving a response result for the first questionnaire sent by the first device.

Description

Technical Field

[0001] The present invention relates to the field of business support, and in particular to an evaluation implementation method, device and storage medium. Background Art

[0002] With the advancement of society and technology, users' expectations for networks, businesses, and services are becoming increasingly stringent. Telecom operators, e-commerce, retail, finance, insurance, and other industries often use user surveys and evaluations to measure service satisfaction and monitor Net Promoter Scores (NPS). These surveys listen to user feedback, identify business issues, and promptly adjust user operations strategies to improve operational effectiveness.

[0003] How to intelligently select the best survey content, invitation timing, channel equipment, and survey interaction methods based on differences in users' own environments, behaviors, device characteristics, etc., and more comprehensively collect the real status and feedback of users during the survey process, is a key factor in improving user engagement and evaluation quality. Summary of the Invention

[0004] In view of this, the main purpose of the present invention is to provide an evaluation implementation method, device and storage medium.

[0005] To achieve the above object, the technical solution of the present invention is achieved as follows:

[0006] An embodiment of the present invention provides an evaluation implementation method, which is applied to a server. The method includes:

[0007] Determining a first questionnaire based on a first tag set; the first tag set includes: user preference tags; the user preference tags are determined based on historical user data;

[0008] Acquire parameters of a target feature, and determine a first device based on the parameters of the target feature; the parameters of the target feature are determined based on an environmental state and a behavioral state;

[0009] sending the first questionnaire to a first device; and presenting the first questionnaire by the first device;

[0010] Receive a response result to the first questionnaire sent by the first device.

[0011] In the above solution, determining the first questionnaire based on the first tag set includes:

[0012] Determining the recommendation degree of each question based on the correlation between the user preference tag in the first tag set and each question in the questionnaire question bank; determining a first target question based on the recommendation degree of each question; the questionnaire question bank includes at least one question;

[0013] Determining a relevance between the first target topic and at least one first topic in the questionnaire question bank other than the first target topic; determining a first comprehensive score for each first topic based on the relevance and recommendation level corresponding to each first topic; and determining a second target topic based on the first comprehensive score corresponding to each first topic;

[0014] Determining a relevance between the second target topic and at least one second topic in the questionnaire question bank other than the first target topic and the second target topic; determining a second comprehensive score corresponding to each second topic based on the relevance and recommendation level corresponding to each second topic; and determining a third target topic based on the second comprehensive score corresponding to each second topic;

[0015] This cycle is repeated until a preset number of target topics are determined, and the first questionnaire is obtained based on the preset number of target topics.

[0016] In the above solution, obtaining the parameters of the target feature and determining the first device based on the parameters of the target feature include:

[0017] obtaining a parameter of at least one first feature;

[0018] Selecting a first feature that meets preset feature requirements from the at least one first feature as a target feature;

[0019] Obtaining a probability for at least one candidate device based on the parameters of the target feature; the probability represents the likelihood of obtaining a response result by conducting a questionnaire evaluation on the corresponding candidate device;

[0020] Based on the probability corresponding to each candidate device in the at least one candidate device, a target device that meets a preset probability requirement is determined; the meeting the preset probability requirement indicates that the probability exceeds a preset threshold.

[0021] In the above solution, the number of the target feature is at least one;

[0022] Obtaining a probability for at least one candidate device based on the parameter of the target feature includes:

[0023] Calculate, according to the parameters of each target feature in at least one target feature, the product of the impact factor corresponding to each target feature and the parameter;

[0024] A probability for at least one candidate device is obtained based on the product of the impact factor corresponding to each target feature and the parameter of the target feature.

[0025] In the above solution, the method further includes:

[0026] Obtaining user behavior data within a first time period; the first time period represents the time when a response result is generated;

[0027] Determining the credibility of the response result based on the user behavior data;

[0028] Based on the credibility, the response result is adjusted to obtain a target response result.

[0029] In the above solution, the user behavior data includes at least one of the following: voice, body movement, expression;

[0030] Determining the credibility of the response result based on the user behavior data includes:

[0031] Analyzing at least one of the voice, the body movement, and the expression using a preset behavior analysis model to obtain at least one credibility value;

[0032] The credibility is determined according to the at least one credibility value and the weight corresponding to each user behavior data.

[0033] In the above solution, the user behavior data includes: user behavior sub-data for each question;

[0034] Determining the credibility of the response result based on the user behavior data includes:

[0035] Analyze the user behavior sub-data corresponding to each question using a preset behavior analysis model to obtain at least one credible value corresponding to each question;

[0036] Determining the credibility of each topic based on the at least one credibility value corresponding to each topic and the weight corresponding to each user behavior data;

[0037] Accordingly, adjusting the response result based on the credibility includes:

[0038] According to the credibility of each question, the score of each question in the answer result is adjusted.

[0039] An embodiment of the present invention provides an evaluation implementation method, which is applied to a device. The method includes:

[0040] Receive and present a first questionnaire; the first questionnaire is determined based on a first tag set; the first tag set includes: a user preference tag; the user preference tag is determined based on historical user data;

[0041] Obtain the response results for the first questionnaire;

[0042] The reply result is sent to the server.

[0043] In the above solution, the method further includes:

[0044] collecting a parameter of at least one first feature;

[0045] The collected parameters of at least one first feature are sent to the server.

[0046] In the above solution, the method further includes:

[0047] Collecting user behavior data; the corresponding user behavior data includes at least one of the following: voice, body movement, and expression; the user behavior data is used to adjust the response result;

[0048] The user behavior data is sent to the server.

[0049] In the above solution, the collection of user behavior data includes:

[0050] Determining a topic corresponding to at least one collection time period and user behavior sub-data collected in each collection time period in at least one collection time period;

[0051] The sending of the user behavior data to the server includes sending the user behavior sub-data and the corresponding topic collected in each collection time period of the at least one collection time period to the server.

[0052] An embodiment of the present invention provides an evaluation implementation device, which is applied to a server, and includes:

[0053] A first processing module is configured to determine a first questionnaire based on a first tag set, wherein the first tag set includes user preference tags, and the user preference tags are determined based on historical user data;

[0054] and obtaining parameters of target features, and determining the first device based on the parameters of the target features; the parameters of the target features are determined based on the environmental state and the behavioral state;

[0055] A first communication module is configured to send the first questionnaire to a first device; the first questionnaire is presented by the first device;

[0056] And, receiving the response result to the first questionnaire sent by the first device.

[0057] In the above solution, the first processing module is used to determine the recommendation degree of each question based on the correlation between the user preference tag in the first tag set and each question in the questionnaire question bank; and determine the first target question based on the recommendation degree of each question; the questionnaire question bank includes at least one question;

[0058] Determining a relevance between the first target topic and at least one first topic in the questionnaire question bank other than the first target topic; determining a first comprehensive score for each first topic based on the relevance and recommendation level corresponding to each first topic; and determining a second target topic based on the first comprehensive score corresponding to each first topic;

[0059] Determining a relevance between the second target topic and at least one second topic in the questionnaire question bank other than the first target topic and the second target topic; determining a second comprehensive score corresponding to each second topic based on the relevance and recommendation level corresponding to each second topic; and determining a third target topic based on the second comprehensive score corresponding to each second topic;

[0060] This cycle is repeated until a preset number of target topics are determined, and the first questionnaire is obtained based on the preset number of target topics.

[0061] In the above solution, the first processing module is used to obtain parameters of at least one first feature;

[0062] Selecting a first feature that meets preset feature requirements from the at least one first feature as a target feature;

[0063] Obtaining a probability for at least one candidate device based on the parameters of the target feature; the probability represents the likelihood of obtaining a response result by conducting a questionnaire evaluation on the corresponding candidate device;

[0064] Based on the probability corresponding to each candidate device in the at least one candidate device, a target device that meets a preset probability requirement is determined; the meeting the preset probability requirement indicates that the probability exceeds a preset threshold.

[0065] In the above solution, the number of the target feature is at least one;

[0066] The first processing module is configured to calculate, based on the parameters of each target feature in at least one target feature, a product of an impact factor and a parameter corresponding to each target feature;

[0067] A probability for at least one candidate device is obtained based on the product of the impact factor corresponding to each target feature and the parameter of the target feature.

[0068] In the above solution, the first communication module is further used to obtain user behavior data within a first time period; the first time period represents the time when the reply result is generated;

[0069] The first processing module is further configured to determine the credibility of the reply result based on the user behavior data;

[0070] Based on the credibility, the response result is adjusted to obtain a target response result.

[0071] In the above solution, the user behavior data includes at least one of the following: voice, body movement, expression;

[0072] The first processing module is further configured to analyze at least one of the sound, the body movement, and the expression using a preset behavior analysis model to obtain at least one credibility value;

[0073] The credibility is determined according to the at least one credibility value and the weight corresponding to each user behavior data.

[0074] In the above solution, the user behavior data includes: user behavior sub-data for each question;

[0075] The first processing module is further configured to analyze the user behavior sub-data corresponding to each question using a preset behavior analysis model to obtain at least one credibility value corresponding to each question;

[0076] Determining the credibility of each topic based on the at least one credibility value corresponding to each topic and the weight corresponding to each user behavior data;

[0077] Correspondingly, the first processing module is further configured to adjust the score for each question in the response result according to the credibility corresponding to each question.

[0078] An embodiment of the present invention provides an evaluation implementation apparatus, which is applied to a device. The apparatus includes:

[0079] A second communication module is configured to receive and present a first questionnaire; the first questionnaire is determined based on a first tag set; the first tag set includes: a user preference tag; the user preference tag is determined based on historical user data;

[0080] A second processing module is used to obtain a response result for the first questionnaire;

[0081] The second communication module is further configured to send the reply result to the server.

[0082] In the above solution, the device further comprises: a collection module for collecting parameters of at least one first feature;

[0083] The second communication module is further configured to send the collected parameters of the at least one first feature to the server.

[0084] In the above solution, the collection module is further used to collect user behavior data; the corresponding user behavior data includes at least one of the following: sound, body movement, expression; the user behavior data is used to adjust the response result;

[0085] The second communication module is further configured to send the user behavior data to a server.

[0086] In the above solution, the collection module is used to determine the topic corresponding to at least one collection time period and the user behavior sub-data collected in each collection time period in at least one collection time period;

[0087] Correspondingly, the second communication module is configured to send the user behavior sub-data and corresponding topics collected in each of the at least one collection time period to the server.

[0088] An embodiment of the present invention provides an evaluation implementation device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any one of the methods described above performed by the server side are implemented; or

[0089] When the processor executes the program, the steps of any one of the methods performed by the above-mentioned device side are implemented.

[0090] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of any one of the methods performed by the server side are implemented; or

[0091] When the computer program is executed by a processor, the steps of any one of the methods performed by the above-mentioned device side are implemented.

[0092] An embodiment of the present invention provides an evaluation implementation method, device, and storage medium. The method includes: a server determining a first questionnaire based on a first tag set; the first tag set includes: a user preference tag; the user preference tag is determined based on historical user data; obtaining parameters of a target feature, and determining a first device based on the parameters of the target feature; the parameters of the target feature are determined based on an environmental state and a behavioral state; sending the first questionnaire to the first device; the first device presents the first questionnaire; and receiving a response result to the first questionnaire sent by the first device. In this way, user participation rate is increased and evaluation quality is improved.

[0093] Correspondingly, an embodiment of the present invention provides another evaluation implementation method, device and storage medium, the method including: a device receives and presents a first questionnaire; the first questionnaire is determined based on a first tag set; the first tag set includes: user preference tags; the user preference tags are determined based on historical user data; a response result for the first questionnaire is obtained; the response result is sent to a server; in this way, the user participation rate is increased and the evaluation quality is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0094] Figure 1 A flowchart of an evaluation implementation method provided by an embodiment of the present invention;

[0095] Figure 2 A flowchart of another evaluation implementation method provided by an embodiment of the present invention;

[0096] Figure 3 A flowchart of another evaluation implementation method provided by an embodiment of the present invention;

[0097] Figure 4 A schematic diagram of collaborative cross-analysis of response results and multi-dimensional data provided by an embodiment of the present invention;

[0098] Figure 5 A schematic diagram of the structure of an evaluation implementation device provided by an embodiment of the present invention;

[0099] Figure 6 A schematic structural diagram of another evaluation implementation device provided by an embodiment of the present invention;

[0100] Figure 7 A schematic structural diagram of another evaluation implementation device provided in an embodiment of the present invention;

[0101] Figure 8 A schematic structural diagram of another evaluation implementation device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0102] The present invention will be further described in detail with reference to the embodiments, and the related technologies will be described first.

[0103] User survey and evaluation is a method of collecting and aggregating data using scientific methods, providing basic data support for enterprises to monitor service status, business quality, overall satisfaction, market analysis, etc.

[0104] The current mainstream survey method is to push questionnaires to users' mobile phones or computers for invitations and evaluations via email or text messages. All users are treated equally. Since the user's own and surrounding environmental conditions are not taken into consideration, users may be perfunctory or have a high refusal rate. At the same time, the user information collected by the current common survey method is mainly text information of user feedback, and the information type is single. Because the survey is based on the user's subjective feedback, the single information will distort the user's true attitude.

[0105] The main implementation method of current user surveys is to push evaluation tasks to a large number of users indiscriminately. Users provide information feedback through World Wide Web (WEB) pages. Factors such as user environment, user status, convenience, and false information are not taken into consideration. This may lead to problems such as user perfunctoriness, poor interview experience, high rejection rate, and incomplete information. This leads to distorted and inaccurate overall survey results, further affecting corporate decision-making and business service improvements.

[0106] With the progress of society and the development of science and technology, the types and forms of devices that can access the Internet have become more diverse. Especially in recent years, with the rise of smart homes, devices that can contact and interact with users have become intelligent and universal, which has brought convenience to various forms of surveys; but at the same time, a single device has also become a bottleneck for user information collection. Because the most direct way to reach users was through mobile terminals before, but with the generalization of terminals, mobile terminals are currently just one type of network access, which is also one of the reasons for the decline in survey response rates.

[0107] How to intelligently select the best survey content, invitation timing, channel equipment, and survey interaction methods based on differences in users' own environments, behaviors, device characteristics, etc., and more comprehensively collect the real status and feedback of users during the survey process, is a key factor in improving user engagement and evaluation quality.

[0108] Based on this, the method provided by an embodiment of the present invention is that the server determines the first questionnaire based on the first tag set; the first tag set includes: user preference tags; the user preference tags are determined based on historical user data; the parameters of the target features are obtained, and the first device is determined based on the parameters of the target features; the parameters of the target features are determined based on the environmental state and the behavioral state; the first questionnaire is sent to the first device; the first questionnaire is presented by the first device; the reply result for the first questionnaire sent by the first device is received; accordingly, the device receives and presents the first questionnaire; the first questionnaire is determined based on the first tag set; the first tag set includes: user preference tags; the user preference tags are determined based on historical user data; the reply result for the first questionnaire is obtained; the reply result is sent to the server.

[0109] Figure 1 A flow chart of an evaluation implementation method provided by an embodiment of the present invention; Figure 1 As shown, the method is applied to a server, and the method includes:

[0110] Step 101: Determine a first questionnaire based on a first tag set; the first tag set includes: user preference tags; the user preference tags are determined based on historical user data;

[0111] Step 102: Acquire parameters of target features, and determine a first device based on the parameters of the target features; the parameters of the target features are determined based on an environmental state and a behavioral state;

[0112] Step 103: Send the first questionnaire to a first device; the first questionnaire is presented by the first device;

[0113] Step 104: Receive a response result to the first questionnaire sent by the first device.

[0114] In some embodiments, the method further includes determining a first tag set for each user.

[0115] Specifically, determining the first tag set for each user includes:

[0116] Obtain historical user data for multiple users (which can be all users of services provided by the operator) within a preset historical time period; the historical user data includes at least one of the following: basic information, communication consumption, device information, service usage behavior, Internet access behavior, location, service complaints, and historical survey and evaluation data;

[0117] Performing standardization on historical user data of multiple users to obtain standardized data of the multiple users;

[0118] For each user's corresponding normalized data, a first tag set corresponding to the user is determined, wherein the first tag set includes at least one user preference tag.

[0119] Standardization can be performed using any standardization rule. For numerical data, examples include min-max standardization and z-score standardization. Min-max standardization applies a linear transformation to the original data. Let minA and maxA represent the minimum and maximum values ​​of attribute A, respectively. Using min-max standardization, an original value x of A is mapped to a value x' in the interval [0, 1]. The formula is: new data = (original data - minimum value) / (maximum value - minimum value). Z-score standardization standardizes data based on the original data's mean and standard deviation; new data = (original data - mean) / standard deviation.

[0120] Here, for each user among the multiple users, after the normalized data is processed, determining a first tag set corresponding to each user includes:

[0121] For the normalized data corresponding to each user, at least one user preference tag corresponding to each user is determined, and based on the determined at least one user preference tag, a first tag set corresponding to the user is determined.

[0122] For example, the standardized data includes the following standardized information: basic information, communication consumption, device information, service usage behavior, Internet behavior, location, service complaints, and historical survey and evaluation data;

[0123] Basic information may include: gender, age, region, occupation, etc.;

[0124] Communication expenses may include: consumption fees (such as monthly expenses), subscription amounts for different services (such as 5G (5th-Generation) data, 4G (4th-Generation) data, number of text messages, call duration, etc.);

[0125] Device information, which may include: smart TVs, smart speakers, smart refrigerators, smart projectors, mobile phones, computers, tablets (Pad, portable Android devices), smart photo albums, smart wearable devices, etc.

[0126] Service usage, including: service activation (e.g., 4G service activation, 5G service activation, call service activation, VR service activation, etc.);

[0127] Internet use behavior, which may include: mobile data, wireless network (Wi-Fi), Internet usage duration, and the duration of use of different types of applications (e.g., video app usage, social app usage, and gaming app usage);

[0128] The location may include: the location of different devices, the location of the base station providing signals to the device, and the cell supported by the base station providing services; it may further determine whether the device is indoors or outdoors, and if it is determined that the device is indoors, it may further determine that it is in a bedroom, living room, etc. The specific implementation may be based on the positioning function of the device, which will not be elaborated here;

[0129] Business complaints may include: services that users have complained about (such as complaints about 4G network quality);

[0130] Historical survey and evaluation data may include: survey and evaluation questionnaires that users have processed, corresponding response results, and corresponding feature information (feature information includes: the method used for response, response time, status at the time of response, etc.).

[0131] Based on the above content, user preference tags can be determined, such as: 4G users, virtual reality technology (VR) users, dissatisfied with 4G quality, 4G self-funded, wireless Internet (WIFI) users, etc.

[0132] In some embodiments, determining the first questionnaire based on the first tag set includes:

[0133] Determining the recommendation degree of each question based on the correlation between the user preference tag in the first tag set and each question in the questionnaire question bank, and determining a first target question based on the recommendation degree of each question; the questionnaire question bank includes at least one question;

[0134] Determining a relevance between the first target topic and at least one first topic in the questionnaire question bank other than the first target topic; determining a first comprehensive score for each first topic based on the relevance and recommendation level corresponding to each first topic; and determining a second target topic based on the first comprehensive score corresponding to each first topic;

[0135] Determining a relevance between the second target topic and at least one second topic in the questionnaire question bank other than the first target topic and the second target topic; determining a second comprehensive score corresponding to each second topic based on the relevance and recommendation level corresponding to each second topic; and determining a third target topic based on the second comprehensive score corresponding to each second topic;

[0136] This cycle is repeated until a preset number of target topics are determined, and the first questionnaire is obtained based on the preset number of target topics.

[0137] The questionnaire question bank includes at least one preset question. The first tag set includes user preference tags for corresponding users generated based on historical user data.

[0138] In another embodiment, determining the first questionnaire based on the first tag set includes:

[0139] Determining the recommendation degree of each question based on the correlation between the user preference tag in the first tag set and each question in the questionnaire question bank, and determining a first target question based on the recommendation degree of each question; the questionnaire question bank includes at least one question;

[0140] Determining a relevance between the first target topic and at least one first topic in the questionnaire question bank other than the first target topic; determining a first comprehensive score for each first topic based on the relevance and recommendation degree corresponding to each first topic;

[0141] Sorting based on the first comprehensive score corresponding to each of the first questions to determine a first preset number of second target questions;

[0142] Obtaining a second preset number of target topics according to the first target topic and the first preset number of second target topics (equivalent to obtaining a preset number of target topics);

[0143] The first questionnaire is obtained based on the second preset number of target questions.

[0144] The following provides a specific example description, wherein determining the first questionnaire based on the first tag set includes:

[0145] Step 001: Calculate the relevance (or relevance) of at least one question in the questionnaire question bank and the user's preference tag one by one according to preset rules, and determine the recommendation degree for each question based on the relevance;

[0146] Here, the step of calculating the correlation between at least one question in the questionnaire question bank and the user preference tag according to a preset rule, and determining the recommendation degree for each question based on the correlation, includes:

[0147] The correlation between the content of each question and the user preference tag is calculated one by one according to the preset rules.

[0148] The preset rule can be pre-set and can be any correlation calculation method.

[0149] Step 002: Arrange the candidate questions from highest to lowest according to their recommendation values, and select the candidate question with the highest recommendation value as the first question (i.e., the first target question) and add it to the survey questionnaire to be sent, i.e., the first questionnaire;

[0150] The step 002 includes:

[0151] Calculate the correlation between different user preference tags and each question, and determine the question with the highest correlation with the user preference tag as the candidate question;

[0152] When there is only one candidate topic, the determined topic is used as the first topic;

[0153] Corresponding to the fact that there are at least two candidate topics, the at least two candidate topics are screened in combination with other user preference tags to obtain the first topic.

[0154] For example, user preference tags include: 4G users, VR users. The relevance between 4G users, VR users and each topic is calculated, and topic one corresponding to "4G users" and topic two corresponding to "VR users" are obtained respectively. The relevance of the two is the same and the highest. At this time, other tags related to 4G users (such as the usage time of 4G-related services, etc.) and other tags related to VR users (such as the usage time of VR-related services, etc.) can be combined to calculate the recommendation degree of topic one and the recommendation degree of topic two.

[0155] Assuming that the usage time of 4G-related services is greater than the usage time of VR-related services, in order to increase the recommendation of question one, question one will be selected as the first question.

[0156] Step 003: Calculate the relevance of the content of the first question (i.e., the first question) with the candidate questions not displayed in the questionnaire question bank (i.e., all other questions except the first question); and comprehensively evaluate and score each candidate question based on its recommendation and relevance to obtain a comprehensive score.

[0157] Step 004: Arrange the next questions in descending order according to the comprehensive scores, and add the next question that is most relevant to the user to the survey questionnaire to be sent;

[0158] Step 005: Repeat steps 003-004 above. When the preset maximum number of questionnaire questions has been reached, the candidate question recommendation is terminated, and a survey questionnaire is obtained based on the determined candidate questions.

[0159] As shown in Table 1 below, Table 1 shows the comprehensive scores of questionnaire questions. Question 1 has the highest recommended score and is the first question in the first questionnaire. Question 5 has the highest comprehensive score and is the second question in the first questionnaire. Question 3 has the second highest comprehensive score and is the third question in the first questionnaire. This continues in this order, with Questions 2...N being the next questions in turn. This is how we get the final first questionnaire.

[0160] The following recommended values ​​represent the values ​​with the highest correlation between the corresponding questions and each user's preference tags;

[0161] The following correlation represents the correlation between the corresponding question and the first question (i.e., question 1).

[0162]

[0163]

[0164] Table 1

[0165] The first questionnaire generated in the above manner contains questions related to the user's user preference tags; users are more concerned about related questions, and the questionnaire survey results they provide are more authentic, thus improving the quality and credibility of the questionnaire survey.

[0166] In some embodiments, acquiring a parameter of a target feature and determining the first device based on the parameter of the target feature includes:

[0167] obtaining a parameter of at least one first feature;

[0168] Selecting a first feature that meets preset feature requirements from the at least one first feature as a target feature;

[0169] Obtaining a probability for at least one candidate device based on the parameters of the target feature; the probability represents the likelihood of obtaining a response result by conducting a questionnaire evaluation on the corresponding candidate device;

[0170] Based on the probability corresponding to each candidate device in the at least one candidate device, a target device that meets a preset probability requirement is determined; the meeting the preset probability requirement indicates that the probability exceeds a preset threshold.

[0171] Here, the number of the first features may be one or more;

[0172] The number of target features obtained by screening can be one or more.

[0173] The preset feature requirements include: at least one reference feature; the reference feature is a feature that has a significant impact on the success of the survey.

[0174] The first feature that meets the preset feature requirements is a feature belonging to the reference feature.

[0175] In some embodiments, the number of the target feature is at least one;

[0176] Obtaining a probability for at least one candidate device based on the parameter of the target feature includes:

[0177] Calculate, according to the parameters of each target feature in at least one target feature, the product of the impact factor corresponding to each target feature and the parameter;

[0178] A probability for at least one candidate device is obtained based on the product of the impact factor corresponding to each target feature and the parameter of the target feature.

[0179] Specifically, the following formula can be used to calculate the probability of targeting at least one candidate device:

[0180]

[0181] Among them, p(u i ,t j ) represents the probability of successfully sending a questionnaire to device j of user i;

[0182] w ik =f(x ik ) represents the target feature x of user i ik The corresponding impact factor is w ik The impact factor (w ik ) is the weight; the x ik is the parameter of the target feature, that is, the specific value;

[0183] Target features include: device type (based on the user's multiple devices and user preferences), thus determining the probability of selecting the corresponding device;

[0184] The target features may also include: push time (determined based on the desired push time), so as to determine the probability corresponding to the selection of the corresponding time;

[0185] Target features may also include other features, such as user location (e.g., living room, kitchen, bedroom, etc.), busy / idle status (a user status feature), active / static status (a user status feature), user behavior preferences (e.g., user preferred device, usage time, frequency, etc.), date and time features (e.g., whether it's a weekday, current time period), device information (e.g., device type, device status, interaction method (voice, touchscreen, gesture, etc.), device location, etc.). The first feature mentioned above at least includes the content included in the target feature above, and will not be repeated here.

[0186] The following describes the values ​​of the parameters of different target features;

[0187] For device types, it can be determined in combination with device-related information (such as multiple devices owned by the user and the user's preferred devices in the user's behavior preferences), and values ​​can be configured for multiple devices separately. For example: the first device (such as a mobile phone, the most preferred) corresponds to 50%, the second device (such as a smart TV, the second most preferred) corresponds to 30%, and so on. Values ​​can be configured for multiple devices; the total value of the values ​​of the above multiple devices can be 1.

[0188] The push time can be determined in combination with time-related information (such as the usage time of different devices, the current time (such as weekdays, weekends), etc.), and the 24 hours of a day can be divided, and different time periods correspond to different values; for example: the value of the evening time period (such as 20:00-22:00) is 40%, the value of the rest time period (such as 12:30-13:00) is 30%, and so on. Values ​​can be configured for different time periods; the total value of the values ​​of the above multiple different time periods can be 1.

[0189] For location features, the relationship between device location and user location can be combined to determine the location. In addition, the corresponding location relationship values ​​for different device types are also different. For example, the requirements for the corresponding location relationship for mobile phones and smart speakers are different. In other words, different values ​​corresponding to the location information can be configured for different devices to be predicted. For example, for mobile phones, the value for a distance of less than 1 meter is 60%, and the value for a distance of more than 10 meters is 10%. For smart speakers, the value for a distance of 1-5 meters is 60%, and the value for a distance of more than 5 meters is 10%.

[0190] For busy and idle states, different values ​​can be configured for busy and idle states, such as 10% for busy and 90% for idle.

[0191] For the dynamic and static states, different values ​​are configured for the dynamic state and the static state, such as 10% for the dynamic state and 90% for the static state.

[0192] It should be noted that the above values ​​are only examples. In actual applications, developers can configure them based on their experience, needs, and data related to successful questionnaires. There is no limitation here.

[0193] The above user-related information such as user busy / idle status, active / static status, user location, etc. can be sent to the server after being detected by the device.

[0194] The devices may be smart home devices, including smart TVs, smart speakers, smart refrigerators, smart projectors, mobile phones, computers, tablet computers (PADs), smart photo albums, smart wearable devices, and other devices that can interact with users. Different devices correspond to different interaction methods, as shown in Table 2. The devices are scheduled by the server.

[0195] In this embodiment of the present invention, it is necessary to select one device from among various devices to send the questionnaire. The selected device is the one with the highest probability that the user will receive and conduct the survey. Each device has multiple interaction modes, as shown in Table 2 below:

[0196]

[0197]

[0198] Table 2

[0199] In some embodiments, the method further comprises:

[0200] Obtaining user behavior data within a first time period; the first time period represents the time when a response result is generated;

[0201] Determining the credibility of the response result based on the user behavior data;

[0202] Based on the credibility, the response result is adjusted to obtain a target response result.

[0203] In some embodiments, the user behavior data includes at least one of the following: sound, body movement, expression;

[0204] Determining the credibility of the response result based on the user behavior data includes:

[0205] Analyzing at least one of the voice, the body movement, and the expression using a preset behavior analysis model to obtain at least one credibility value;

[0206] The credibility is determined according to the at least one credibility value and the weight corresponding to each user behavior data.

[0207] In some embodiments, the user behavior data includes: user behavior sub-data for each topic;

[0208] Determining the credibility of the response result based on the user behavior data includes:

[0209] Analyze the user behavior sub-data corresponding to each question using a preset behavior analysis model to obtain at least one credible value corresponding to each question;

[0210] Determining the credibility of each topic based on the at least one credibility value corresponding to each topic and the weight corresponding to each user behavior data;

[0211] Accordingly, adjusting the response result based on the credibility includes:

[0212] According to the credibility of each question, the score of each question in the answer result is adjusted.

[0213] Through the above method, the server collects the current user environment and behavior status, determines the parameters of the target characteristics, and combines the smart home device information. According to the intelligent push strategy of the evaluation task, the server selects the best time, device, and interaction method (that is, selects the first device and push time), and pushes the first questionnaire to the user for a survey invitation, thereby improving the success rate of the survey. In addition, pushing on multiple devices can also increase the fun and thus improve the user experience.

[0214] In some embodiments, the method further includes: determining at least one reference feature and determining an impact factor corresponding to each reference feature; specifically including:

[0215] Acquire a reference data set of a preset number of reference users; the reference data set includes: at least one reference feature and a parameter corresponding to each reference feature;

[0216] Based on the parameters corresponding to the reference features of each user, a decision tree, logistic regression or other model is used for model training. Based on the model training results, the influence factor of each reference feature on the success of the user survey is determined; the influence factor represents the importance of each reference feature on the result;

[0217] According to the impact factors corresponding to the respective reference features, the most important N reference features are selected as the target features.

[0218] Here, the preset number, N, is pre-set and saved by the developer based on the requirements. The reference user is the user who successfully surveyed. The reference data set represents the relevant data set corresponding to the questionnaire that successfully surveyed.

[0219] The above-mentioned determination of at least one reference feature and the determination of the impact factor corresponding to each reference feature are described in detail as follows. Specifically, it includes:

[0220] Step 011: Obtain a reference dataset of users who have successfully participated in the smart home survey, and construct corresponding user features based on historical user data in the reference dataset;

[0221] Here, the user characteristics may include at least one of the following:

[0222] User basic information characteristics: age, gender, region, etc.;

[0223] User location characteristics: User location information that can be detected by smart home, such as living room, kitchen, bedroom, etc.

[0224] User status characteristics: The user's busy and idle status, active and quiet status, etc. collected by smart home can be obtained through analysis of video image information collected by devices such as smart cameras and smart security sensors;

[0225] Smart home device user behavior preferences: smart home device categories, usage time, frequency, etc.;

[0226] Date and time characteristics: whether it is a weekday, current time period;

[0227] Smart home device information: device type, device status, interaction method (voice, touch screen, gesture, etc.), location, etc.;

[0228] User data is characterized as follows: user i =[x i1 ,x i2 ,x i3 ,…,x ik,…,x in ]; where x ik is the kth feature variable corresponding to user i;

[0229] Step 012: Feature importance analysis and model training;

[0230] Step 012 specifically includes:

[0231] Based on historical user data from successful invitation surveys, model training is performed using models such as decision trees and logistic regression. Based on the model training results, the impact factors of each reference feature on the success of the user survey are determined; the impact factors represent the importance of each reference feature in affecting the results.

[0232] The impact factor is expressed as follows: ik =f(x ik ), represents the characteristic variable x of user i ik The corresponding impact factor is w ik ;

[0233] After filtering out the most important n features, the impact factors of all feature variables corresponding to user i are expressed as: w i ={w i1 ,w i2 ,w i3 ,…,w ik ,…,w in};

[0234] Using the above features, the model can be tuned and evaluated using indicators such as accuracy and the area under the ROC curve (AUC) to obtain the optimized model.

[0235] For user i, pushing the assessment task to device j, the probability of survey success can be determined using the following formula:

[0236]

[0237] Among them, x ik is the kth feature variable corresponding to user i; wik is the characteristic variable x of user i ik The corresponding impact factor can be determined based on the model training results; p(u i ,t j ) represents the probability of successfully sending a questionnaire to device j of user i.

[0238] Among them, the model trained in step 012 is used to predict the smart home devices of the users to be surveyed, and the probability of the user successfully participating in the survey under each smart home device is obtained. The smart home device with the highest success probability is selected to push the evaluation task and invite the survey.

[0239] Accordingly, the embodiment of the present invention also provides an evaluation implementation method applied to the device side, specifically in combination with Figure 2 The following is an explanation.

[0240] Figure 2 A flow chart of another evaluation implementation method provided by an embodiment of the present invention; Figure 2 As shown, the method is applied to a device, which is specifically any one of the above smart home devices; the device can interact with a server; the method includes:

[0241] Step 201: Receive and present a first questionnaire; the first questionnaire is determined based on a first tag set; the first tag set includes: user preference tags; the user preference tags are determined based on historical user data;

[0242] Step 202: Obtaining a response result for the first questionnaire;

[0243] Step 203: Send the reply result to the server.

[0244] In some embodiments, the method further comprises:

[0245] collecting a parameter of at least one first feature;

[0246] The collected parameters of at least one first feature are sent to the server.

[0247] The first feature includes at least: user location (such as living room, kitchen, bedroom, etc.), busy / idle status (a user status feature), active / static status (a user status feature), etc. Figure 1 The method is described in detail and will not be repeated here.

[0248] In some embodiments, the method further comprises:

[0249] Collecting user behavior data; the corresponding user behavior data includes at least one of the following: voice, body movement, and expression; the user behavior data is used to adjust the response result;

[0250] The user behavior data is sent to the server.

[0251] In some embodiments, collecting user behavior includes:

[0252] Determining a topic corresponding to at least one collection time period and user behavior sub-data collected in each collection time period in at least one collection time period;

[0253] The sending of the user behavior data to the server includes sending the user behavior sub-data and the corresponding topic collected in each collection time period of the at least one collection time period to the server.

[0254] The use of the above-mentioned data is performed by the server side, which is detailed in Figure 1 The method is described in detail and will not be repeated here.

[0255] Figure 3 A flow chart of another evaluation implementation method provided by an embodiment of the present invention; Figure 3 As shown, the method is applied to a server, which includes: a research and evaluation platform, a smart home control center; including:

[0256] Step 301: The research and evaluation platform collects and pre-processes user-related data;

[0257] Among them, user-related data includes: historical user data, historical survey and evaluation data;

[0258] The historical user data includes: basic information, communication consumption, device information, service usage behavior, Internet access behavior, location, and service complaints;

[0259] The step 301 specifically includes:

[0260] Obtain historical user data (including the above basic information, communication consumption, device information, service usage behavior, Internet behavior, location, service complaints) and historical survey and evaluation data of all users in a certain historical period, and perform standardization processing. The standardization processing method has been Figure 1 The method shown is described and is not limited here.

[0261] Step 302: The research and evaluation platform generates a customized evaluation task for the user;

[0262] Step 302 includes: generating a corresponding evaluation task based on a user's historical user data and historical survey and evaluation data. The evaluation task includes a questionnaire.

[0263] The questionnaire is equivalent to Figure 1 The specific generation method of the first questionnaire is in Figure 1 The method is described in detail and will not be repeated here.

[0264] Step 303: Push the evaluation task to the smart home control center;

[0265] The smart home control center interacts with at least one smart home device; the questionnaire can be sent to the corresponding smart home device through the smart home control center.

[0266] Step 304: The research and evaluation platform calculates the best time and equipment for the research and pushes the evaluation task to the user;

[0267] Step 304 specifically includes: the smart home control center collects the current user environment and behavior status, and sends the collected current user environment and behavior status to the research and evaluation platform;

[0268] The survey and evaluation platform uses intelligent push strategies based on the above-mentioned current user environment and behavior status, combined with smart home device information, to select the best time, device, and interaction method to push the evaluation task to the user for survey invitation.

[0269] Specifically, the smart push strategy is trained based on historical user data that successfully participated in smart home surveys. The training process includes: constructing user features based on historical user data; performing feature importance analysis and model training based on user features; and calculating the impact factor of each user feature on the success of the user survey. The specific process has been Figure 1 The method is described in detail and will not be repeated here.

[0270] The application of intelligent push strategies to select the best timing, device, and interaction method includes:

[0271] Predict smart home devices for users who are about to be surveyed, obtain the probability of users successfully participating in the survey under each smart home device, and select the smart home device with the highest success probability to push the evaluation task and survey invitation.

[0272] The probability calculation can be performed using the following formula:

[0273]

[0274] Among them, x ik is the kth feature variable corresponding to user i; wik is the characteristic variable x of user i ik The corresponding impact factor; p(u i ,t j ) represents the probability of successfully sending a questionnaire to device j of user i.

[0275] The above characteristic variables are equivalent to Figure 1 The parameters of the target features in the method shown; the values ​​of the parameters of the target features and the determination of the influencing factors have been Figure 1 The method is described in detail and will not be repeated here.

[0276] Step 305: When the user performs a survey, the smart home control center synchronously collects data such as the user's expression, voice, and movement, and sends the collected data to the survey and evaluation platform;

[0277] Here, the smart home control center can synchronously collect user expressions, sounds, movements and other data through the smart home devices that communicate with it (a device with a camera, a device with a microphone).

[0278] Step 306: Determine whether the user survey is completed; if it is determined that the user survey is completed, proceed to step 308; if it is determined that the user survey is not completed, proceed to step 307;

[0279] In one embodiment, step 306 specifically includes: the survey and evaluation platform determines whether a response result of the evaluation task has been received, and if it is determined that the response result has been received, then the process proceeds to step 308; if it is determined that the response result has not been received, then the process proceeds to step 307.

[0280] In another embodiment, step 306 specifically includes: the smart home control center determines in real time whether a reply result of the evaluation task is received; if it is determined that the reply result is received, the reply result is sent to the survey and evaluation platform; if it is determined that no reply result is received, step 307 is entered.

[0281] Step 307: Collaborate with other smart home devices to continue researching invitations;

[0282] Here, step 304 may be specifically executed again to determine other smart home devices for investigation.

[0283] Step 308: The survey and evaluation platform performs a multi-dimensional cross-analysis on the survey result data.

[0284] Here, the user survey results are cross-analyzed based on the collected multi-dimensional user data, and the voice, action, expression and other data collected during the survey are comprehensively analyzed to conduct a collaborative cross-analysis of the survey results.

[0285] Step 3081: Determine the user's emotions when conducting the survey.

[0286] Specifically, it may include performing at least one of the following:

[0287] Analyze the speech data, obtain the corresponding speech semantics, and determine the user's first emotion based on the speech semantics;

[0288] Analyze the action data (which may be collected video data or image data) to obtain corresponding action information, and determine the user's second emotion based on the action information;

[0289] The tag data (which may be collected video data or image data) is analyzed to obtain corresponding facial information, and the user's third emotion is determined based on the facial information.

[0290] Step 3082: Further adjust the answers based on the user's emotions.

[0291] Specifically, the first emotion, second emotion, and third emotion can be processed according to a preset processing strategy to obtain a target emotion; the answer result can be adjusted according to the preset adjustment strategy based on the target emotion (for example, if it is determined that the user feels troubled or the emotion is negative, the score can be reduced by one accordingly).

[0292] The specific preset processing strategy is set by the developer according to needs, for example, emotions can be weighted; the specific preset adjustment strategy is set by the developer according to needs, for example, the score can be adjusted accordingly for a certain emotion, or the result can be marked as not highly referenceable.

[0293] Figure 4 A schematic diagram of a collaborative cross-analysis of a response result and multi-dimensional data provided by an embodiment of the present invention; Figure 4 As shown, action information may include: shrugging, pinching waist, etc.; speech semantics may include: troublesome, slow, etc.; facial information may include: frowning, staring, etc.

[0294] The user's emotions are determined based on the above information, and the answer results can be adjusted according to the user's emotions.

[0295] Figure 5 A schematic diagram of the structure of an evaluation implementation device provided by an embodiment of the present invention; Figure 5 As shown, the device is applied to a server, and the device includes: a research and evaluation platform and a smart home control center;

[0296] The smart home control center mainly includes: a smart device feature management module, a user behavior and status recognition module, a smart push decision module, a smart interactive decision module, a survey progress monitoring module and a smart device collaboration module;

[0297] The survey and evaluation platform includes: a questionnaire design module, a questionnaire publishing module, a questionnaire storage library module, a multi-dimensional data analysis module, a quota setting module, a short link module, a sample module, an anti-cheating module, and an incentive module;

[0298] The above-mentioned server implementation method is completed through collaborative processing of the above-mentioned modules.

[0299] In addition, rewards can be provided to users through the incentive module to increase the probability of users replying;

[0300] Through the anti-cheating module, the reply results of the user are detected to obtain more authentic results;

[0301] Through the short link module, a questionnaire is sent to the device via a short link to request the user on the device to respond to the questionnaire;

[0302] Through the quota setting module, the number of questionnaires sent is managed and the response results of the corresponding number of questionnaires required are obtained.

[0303] Modules can be divided according to different functions, but it should be noted that Figure 5 The module division described above is merely an example. In actual applications, the aforementioned processing can be assigned to different program modules as needed. This means that the internal structure of the server can be divided into different program modules to complete all or part of the aforementioned processing. Furthermore, the apparatus and corresponding method embodiments provided in the aforementioned embodiments share the same concept. Their specific implementation processes are detailed in the method embodiments and will not be further elaborated here.

[0304] Figure 6 A schematic diagram of another evaluation implementation device provided by an embodiment of the present invention; the device is applied to a server, such as Figure 6 As shown, the device includes:

[0305] A first processing module is configured to determine a first questionnaire based on a first tag set, wherein the first tag set includes user preference tags, and the user preference tags are determined based on historical user data;

[0306] and obtaining parameters of target features, and determining the first device based on the parameters of the target features; the parameters of the target features are determined based on the environmental state and the behavioral state;

[0307] A first communication module is configured to send the first questionnaire to a first device; the first questionnaire is presented by the first device;

[0308] And, receiving the response result to the first questionnaire sent by the first device.

[0309] Specifically, the first processing module is configured to determine the recommendation degree of each question based on the correlation between the user preference tag in the first tag set and each question in the questionnaire question bank; and determine a first target question based on the recommendation degree of each question; the questionnaire question bank includes at least one question;

[0310] Determining a relevance between the first target topic and at least one first topic in the questionnaire question bank other than the first target topic; determining a first comprehensive score for each first topic based on the relevance and recommendation level corresponding to each first topic; and determining a second target topic based on the first comprehensive score corresponding to each first topic;

[0311] Determining a relevance between the second target topic and at least one second topic in the questionnaire question bank other than the first target topic and the second target topic; determining a second comprehensive score corresponding to each second topic based on the relevance and recommendation level corresponding to each second topic; and determining a third target topic based on the second comprehensive score corresponding to each second topic;

[0312] This cycle is repeated until a preset number of target topics are determined, and the first questionnaire is obtained based on the preset number of target topics.

[0313] Specifically, the first processing module is used to obtain a parameter of at least one first feature;

[0314] Selecting a first feature that meets preset feature requirements from the at least one first feature as a target feature;

[0315] Obtaining a probability for at least one candidate device based on the parameters of the target feature; the probability represents the likelihood of obtaining a response result by conducting a questionnaire evaluation on the corresponding candidate device;

[0316] Based on the probability corresponding to each candidate device in the at least one candidate device, a target device that meets a preset probability requirement is determined; the meeting the preset probability requirement indicates that the probability exceeds a preset threshold.

[0317] Specifically, the number of the target feature is at least one;

[0318] The first processing module is configured to calculate, based on the parameters of each target feature in at least one target feature, a product of an impact factor and a parameter corresponding to each target feature;

[0319] A probability for at least one candidate device is obtained based on the product of the impact factor corresponding to each target feature and the parameter of the target feature.

[0320] Specifically, the first communication module is further configured to obtain user behavior data within a first time period; the first time period represents the time for generating a reply result;

[0321] The first processing module is further configured to determine the credibility of the reply result based on the user behavior data;

[0322] Based on the credibility, the response result is adjusted to obtain a target response result.

[0323] Specifically, the user behavior data includes at least one of the following: voice, body movement, expression;

[0324] The first processing module is further configured to analyze at least one of the sound, the body movement, and the expression using a preset behavior analysis model to obtain at least one credibility value;

[0325] The credibility is determined according to the at least one credibility value and the weight corresponding to each user behavior data.

[0326] Specifically, the user behavior data includes: user behavior sub-data for each topic;

[0327] The first processing module is further configured to analyze the user behavior sub-data corresponding to each question using a preset behavior analysis model to obtain at least one credibility value corresponding to each question;

[0328] Determining the credibility of each topic based on the at least one credibility value corresponding to each topic and the weight corresponding to each user behavior data;

[0329] Correspondingly, the first processing module is further configured to adjust the score for each question in the response result according to the credibility corresponding to each question.

[0330] It should be noted that the evaluation implementation device provided in the above embodiment only uses the division of the above-mentioned program modules as an example to illustrate the implementation of the corresponding evaluation implementation method. In actual applications, the above-mentioned processing can be assigned to different program modules as needed, that is, the internal structure of the server can be divided into different program modules to complete all or part of the processing described above. In addition, the device provided in the above embodiment and the embodiment of the corresponding method are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0331] Figure 7 A schematic diagram of another evaluation implementation device provided by an embodiment of the present invention; the device is applied to a device such as Figure 7 As shown, the device includes:

[0332] A second communication module is configured to receive and present a first questionnaire; the first questionnaire is determined based on a first tag set; the first tag set includes: a user preference tag; the user preference tag is determined based on historical user data;

[0333] A second processing module is used to obtain a response result for the first questionnaire;

[0334] The second communication module is further configured to send the reply result to the server.

[0335] Specifically, the device further includes: a collection module, configured to collect parameters of at least one first feature;

[0336] The second communication module is further configured to send the collected parameters of the at least one first feature to the server.

[0337] Specifically, the collection module is further used to collect user behavior data; the corresponding user behavior data includes at least one of the following: sound, body movement, expression; the user behavior data is used to adjust the response result;

[0338] The second communication module is further configured to send the user behavior data to a server.

[0339] Specifically, the collection module is used to determine a topic corresponding to at least one collection time period, and user behavior sub-data collected in each collection time period in at least one collection time period;

[0340] Correspondingly, the second communication module is configured to send the user behavior sub-data and corresponding topics collected in each of the at least one collection time period to the server.

[0341] It should be noted that the evaluation implementation device provided in the above embodiment only uses the division of the above program modules as an example to illustrate the corresponding evaluation implementation method. In actual applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the corresponding device can be divided into different program modules to complete all or part of the processing described above. In addition, the device provided in the above embodiment and the embodiment of the corresponding method are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0342] Figure 8 A schematic diagram of the structure of an evaluation implementation device provided by an embodiment of the present invention; Figure 8 As shown, the apparatus 80 includes: a processor 801 and a memory 802 for storing a computer program that can be run on the processor;

[0343] In which, when the device can be applied to a server, the processor 801 is used to run the computer program to execute: determining a first questionnaire based on a first tag set; the first tag set includes: user preference tags; the user preference tags are determined based on historical user data; obtaining parameters of target features, and determining a first device based on the parameters of the target features; the parameters of the target features are determined based on environmental status and behavioral status; sending the first questionnaire to the first device; the first questionnaire is presented by the first device; receiving the response result for the first questionnaire sent by the first device.

[0344] When the processor runs the computer program, the corresponding processes of the server in each method of the embodiment of the present invention are implemented, which will not be described here for the sake of brevity.

[0345] In which, when the apparatus can be applied to a device, the processor 801 is used to run the computer program to execute: receiving and presenting a first questionnaire; the first questionnaire is determined based on a first tag set; the first tag set includes: user preference tags; the user preference tags are determined based on historical user data; and obtaining a response result for the first questionnaire.

[0346] When the processor runs the computer program, the corresponding processes of the device in each method of the embodiment of the present invention are implemented, which will not be described here for the sake of brevity.

[0347] In actual application, the device 80 may further include: at least one network interface 803. The various components in the device 80 are coupled together via a bus system 804. It is understood that the bus system 804 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 804 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, Figure 8 In the figure, various buses are labeled as bus system 804. There may be at least one processor 801. The network interface 803 is used for wired or wireless communication between the apparatus 80 and other devices.

[0348] The memory 802 in this embodiment of the present invention is used to store various types of data to support the operation of the device 80 .

[0349] The methods disclosed in the above embodiments of the present invention can be applied to or implemented by processor 801. Processor 801 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits in processor 801 or by software instructions. Processor 801 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc. Processor 801 can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present invention can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium located in memory 802. Processor 801 reads information from memory 802 and, in conjunction with its hardware, completes the steps of the above method.

[0350] In an exemplary embodiment, the device 80 can be implemented by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers (MCUs), microprocessors, or other electronic components to perform the aforementioned method.

[0351] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon;

[0352] Wherein, when the computer-readable storage medium is applied to a server, the computer program is executed by the processor to perform: determining a first questionnaire based on a first tag set; the first tag set includes: user preference tags; the user preference tags are determined based on historical user data; obtaining parameters of target features, and determining a first device based on the parameters of the target features; the parameters of the target features are determined based on environmental status and behavioral status; sending the first questionnaire to the first device; the first questionnaire is presented by the first device; receiving the response result for the first questionnaire sent by the first device.

[0353] When the computer program is executed by the processor, the corresponding processes implemented by the server in each method of the embodiment of the present invention are implemented, which will not be described here for the sake of brevity.

[0354] When the computer-readable storage medium is applied to a device, the computer program, when executed by the processor, performs the following: receiving and presenting a first questionnaire; the first questionnaire is determined based on a first tag set; the first tag set includes: user preference tags; the user preference tags are determined based on historical user data; and obtaining a response result for the first questionnaire.

[0355] Among them, when the computer program is executed by the processor, the corresponding processes implemented by the device in each method of the embodiment of the present invention are implemented, and for the sake of brevity, they are not described here in detail.

[0356] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0357] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0358] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0359] Those skilled in the art will appreciate that all or part of the steps of the above-mentioned method embodiments may be implemented by hardware associated with program instructions, and the aforementioned program may be stored in a computer-readable storage medium. When the program is executed, the program executes the steps of the above-mentioned method embodiments. The aforementioned storage medium includes various media that can store program codes, such as mobile storage devices, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0360] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0361] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for implementing an evaluation, characterized in that: Applied to a server, the method includes: Determining a first questionnaire based on a first tag set; the first tag set includes: user preference tags; the user preference tags are determined based on historical user data; Acquire parameters of a target feature, and determine a first device based on the parameters of the target feature; the parameters of the target feature are determined based on an environmental state of a user and a behavioral state of the user; sending the first questionnaire to a first device; and presenting the first questionnaire by the first device; Receive the answer result to the first questionnaire sent by the first device; wherein, The determining the first questionnaire based on the first tag set includes: Determining the recommendation level of each question based on the correlation between the user preference tag in the first tag set and each question in the questionnaire question bank; determining the first questionnaire based on the recommendation level of each question; the questionnaire question bank includes at least one question; The acquiring a parameter of a target feature and determining the first device based on the parameter of the target feature includes: Obtaining a probability for at least one candidate device based on the parameters of the target feature; the probability represents the likelihood of obtaining a response result by conducting a questionnaire evaluation on the corresponding candidate device; The first device is determined based on a probability corresponding to each candidate device in the at least one candidate device.

2. The method according to claim 1, characterized in that The step of determining the first questionnaire based on the recommendation level of each of the questions includes: Determining a first target topic based on the recommendation degree of each topic; Determining a relevance between the first target topic and at least one first topic in the questionnaire question bank other than the first target topic; determining a first comprehensive score for each first topic based on the relevance and recommendation level corresponding to each first topic; and determining a second target topic based on the first comprehensive score corresponding to each first topic; Determining a relevance between the second target topic and at least one second topic in the questionnaire question bank other than the first target topic and the second target topic; determining a second comprehensive score corresponding to each second topic based on the relevance and recommendation level corresponding to each second topic; and determining a third target topic based on the second comprehensive score corresponding to each second topic; This cycle is repeated until a preset number of target topics are determined, and the first questionnaire is obtained based on the preset number of target topics.

3. The method according to claim 1 or 2, characterized in that The method further comprises: obtaining a parameter of at least one first feature; Selecting a first feature that meets preset feature requirements from the at least one first feature as a target feature; The determining the first device based on the probability corresponding to each candidate device in the at least one candidate device includes: Based on the probability corresponding to each candidate device in the at least one candidate device, a target device that meets a preset probability requirement is determined; the meeting the preset probability requirement indicates that the probability exceeds a preset threshold.

4. The method according to claim 1, wherein The number of the target features is at least one; Obtaining a probability for at least one candidate device based on the parameter of the target feature includes: Calculate, according to the parameters of each target feature in at least one target feature, the product of the impact factor corresponding to each target feature and the parameter; A probability for at least one candidate device is obtained based on the product of the impact factor corresponding to each target feature and the parameter of the target feature.

5. The method according to claim 1, wherein The method further comprises: Obtaining user behavior data within a first time period; the first time period represents the time when a response result is generated; Determining the credibility of the response result based on the user behavior data; Based on the credibility, the response result is adjusted to obtain a target response result.

6. The method according to claim 5, characterized in that The user behavior data includes at least one of the following: voice, body movement, and expression; Determining the credibility of the response result based on the user behavior data includes: Analyzing at least one of the voice, the body movement, and the expression using a preset behavior analysis model to obtain at least one credibility value; The credibility is determined according to the at least one credibility value and the weight corresponding to each user behavior data.

7. The method according to claim 6, characterized in that The user behavior data includes: user behavior sub-data for each topic; Determining the credibility of the response result based on the user behavior data includes: Analyze the user behavior sub-data corresponding to each question using a preset behavior analysis model to obtain at least one credible value corresponding to each question; Determining the credibility of each topic based on the at least one credibility value corresponding to each topic and the weight corresponding to each user behavior data; Accordingly, adjusting the response result based on the credibility includes: According to the credibility of each question, the score of each question in the answer result is adjusted.

8. A method for implementing an evaluation, characterized in that: Applied to a device, the method includes: Receive and present a first questionnaire; the first questionnaire is determined based on a first tag set; the first tag set includes: a user preference tag; the user preference tag is determined based on historical user data; Obtain the response results for the first questionnaire; Send the reply result to the server; wherein, The device is determined based on a probability corresponding to each candidate device in at least one candidate device, the probability of the at least one candidate device is obtained according to a parameter of a target feature, and the parameter of the target feature is determined based on an environmental state of a user and a behavioral state of the user.

9. The method according to claim 8, characterized in that The method further comprises: collecting a parameter of at least one first feature; The collected parameters of at least one first feature are sent to the server.

10. The method according to claim 8, characterized in that The method further comprises: Collecting user behavior data; the corresponding user behavior data includes at least one of the following: voice, body movement, and expression; the user behavior data is used to adjust the response result; The user behavior data is sent to the server.

11. The method according to claim 10, characterized in that The collection of user behavior data includes: Determining a topic corresponding to at least one collection time period and user behavior sub-data collected in each collection time period in at least one collection time period; The sending of the user behavior data to the server includes sending the user behavior sub-data and the corresponding topic collected in each collection time period of the at least one collection time period to the server.

12. An evaluation implementation device, characterized in that: Applied to a server, the device includes: A first processing module is configured to determine a first questionnaire based on a first tag set, wherein the first tag set includes user preference tags, and the user preference tags are determined based on historical user data; and obtaining parameters of a target feature, and determining a first device based on the parameters of the target feature; the parameters of the target feature are determined based on an environmental state of a user and a behavioral state of the user; A first communication module is configured to send the first questionnaire to a first device; the first questionnaire is presented by the first device; and receiving a response result to the first questionnaire sent by the first device; wherein, The first processing module is specifically configured to determine the recommendation degree of each question based on the correlation between the user preference tag in the first tag set and each question in the questionnaire question bank; and determine the first questionnaire based on the recommendation degree of each question; the questionnaire question bank includes at least one question; And, based on the parameters of the target feature, a probability for at least one candidate device is obtained; the probability represents the possibility of obtaining an answer result by conducting a questionnaire evaluation through the corresponding candidate device; based on the probability corresponding to each candidate device in the at least one candidate device, the first device is determined.

13. An evaluation implementation device, characterized in that: Applied to equipment, the device comprises: A second communication module is configured to receive and present a first questionnaire; the first questionnaire is determined based on a first tag set; the first tag set includes: a user preference tag; the user preference tag is determined based on historical user data; A second processing module is used to obtain a response result for the first questionnaire; The second communication module is further configured to send the reply result to the server; wherein, The device is determined based on a probability corresponding to each candidate device in at least one candidate device, the probability of the at least one candidate device is obtained according to a parameter of a target feature, and the parameter of the target feature is determined based on an environmental state of a user and a behavioral state of the user.

14. An evaluation implementation device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method according to any one of claims 1 to 7 are implemented; or When the processor executes the program, the steps of the method according to any one of claims 8 to 11 are implemented.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented; or When the computer program is executed by a processor, the steps of the method according to any one of claims 8 to 11 are implemented.

Images