Data acquisition method and computing device cluster

Abstract

The present application relates to the technical field of computers, and discloses a data acquisition method and a computing device cluster, for use in a scenario of acquiring preference data of a user for a parameter of an object and a value of the parameter. The method comprises: obtaining first information, the first information being used for indicating M parameters selected by a user and at least one value of each parameter among the M parameters, the M parameters corresponding to one object, and M being a positive integer; determining a questionnaire on the basis of the first information, the questionnaire comprising a first set, the first set comprising N elements, each element in the N elements comprising a value of at least one parameter, the at least one parameter pertaining to the M parameters, parameters comprised in the N elements being the same, values of at least one same parameter in the N elements being different, and N being a positive integer; and obtaining second information on the basis of the questionnaire, so as to complete data acquisition of the user, the second information being used for indicating an element selected by the user from among the N elements. Therefore, the data acquisition efficiency is improved.

Description

A data collection method and computing device cluster

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of the People's Republic of China on August 30, 2023, with application number 202311102946.4 and invention name "A Data Collection Method and Computing Device Cluster", the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present application relates to the field of computer technology, and in particular to a data acquisition method and a computing device cluster. Background Art

[0004] Quantifying product value is necessary during the product design and development phases, or before sales, to help companies make better product decisions. Currently, companies often indirectly quantify product value through choice-based conjoint analysis (CBC). This method assumes that a product is composed of multiple attributes (e.g., a mobile phone has appearance, price, and brand), and each attribute has multiple levels (e.g., price has levels of 1,000 yuan, 2,000 yuan, and 5,000 yuan). By collecting consumer preference data for multiple product attributes and multiple levels of each attribute, the product's value can be quantified based on this preference data. For example, two virtual products are presented to consumers in the form of a choice task: one virtual product is brand A, priced at 1,000 yuan, and has low resolution, while the other virtual product is brand B, priced at 3,000 yuan, and has high resolution. The consumer can choose a preferred virtual product. In other words, the consumer's preference data indicates the virtual product they chose, and companies can then quantify the product's value based on this preference data.

[0005] However, CBC requires two assumptions: Assumption 1: Consumers are homogeneous, meaning each consumer must complete the same multiple choice tasks; Assumption 2: Consumers are very patient and willing to complete multiple choice tasks. In actual market research, consumers often have low patience when faced with multiple choice tasks. Furthermore, consumers are often heterogeneous, with different preferences. If a choice task consistently includes an attribute that a consumer is not interested in, such as repeatedly asking someone who dislikes apples to choose which fruit they prefer between apples and another fruit, this can reduce their patience and may cause them to stop choosing midway, affecting data collection efficiency.

[0006] Summary of the Invention

[0007] The embodiments of the present application provide a data collection method and a computing device cluster for improving the efficiency of data collection.

[0008] In a first aspect, an embodiment of the present application provides a data collection method, which can be executed by a terminal device or a server. Taking the method executed by a terminal device as an example, the method includes: the terminal device can obtain first information, and the first information is used to indicate M parameters selected by the user, and to indicate at least one value of each parameter in the M parameters, the M parameters correspond to an object, and M is a positive integer; the terminal device can determine a questionnaire based on the first information, and the questionnaire includes a first set, the first set includes N elements, each element of the N elements includes the value of at least one parameter, the at least one parameter belongs to the M parameters, the parameters included in the N elements are the same, and at least one of the same parameters in the N elements has a different value, and N is a positive integer; the terminal device can obtain second information based on the questionnaire to complete data collection of the user, and the second information is used to indicate the element selected by the user from the N elements.

[0009] In the above scheme, the embodiment of the present application can obtain the user's preferences for multiple parameters of an object and multiple values ​​of each parameter through the first information. Therefore, the set of questionnaires displayed to the user can be obtained based on the user's preferred parameters and / or preferred values, so that the questionnaire meets the user's personalized needs, which is conducive to improving the user's patience and thus improving the efficiency of data collection. In addition, the embodiment of the present application can further obtain the user's preferences for multiple parameters of an object and multiple values ​​of each parameter through the questionnaire, making the collected user data more targeted, which is conducive to setting more personalized content for the user to improve the user experience.

[0010] In one possible implementation, when the terminal device determines the questionnaire based on the first information, the terminal device can determine that the first parameter among the M parameters is the first parameter in the first set, and determine that the N values ​​of the first parameter are the N values ​​of the first parameter in the first set, and the N values ​​of the first parameter belong to at least one value of the first parameter among the M parameters; the terminal device can determine that the second parameter among the M parameters that meets the first condition is the i-th parameter in the first set, and determine that the N values ​​of the second parameter are the N values ​​of the i-th parameter in the first set, and the N values ​​of the second parameter belong to at least one value of the second parameter among the M parameters, where i is an integer greater than 1.

[0011] The first set of parameters in the questionnaire includes the user's preferred values, so that the questionnaire meets the user's personalized needs. In addition, the parameters in the first set other than the first parameter meet the first condition. Therefore, by setting different first conditions, first sets that meet different needs can be obtained.

[0012] In one possible implementation, the first condition includes: the difference between the first weight and the second weight is less than a first threshold, the first weight being the weight corresponding to any one of the first to i-1th parameters in the first set, and the second weight being the weight corresponding to the second parameter; the remaining number of occurrences in the questionnaire being greater than a second threshold, the remaining number of occurrences being related to a preset total number of occurrences; and the parameter being different from the first to i-1th parameters in the first set. By setting the i-th parameter in the first set to satisfy this first condition, the difference between the weights of the different parameters in the first set can be kept small, thereby minimizing the probability of a user selecting any one of the N elements in the first set. Furthermore, the number of occurrences of the different parameters in the first set in the questionnaire can be balanced.

[0013] In one possible implementation, the first condition includes: the remaining number of occurrences in the questionnaire is greater than a second threshold, the remaining number of occurrences being related to a preset total number of occurrences; and the parameter being different from the first through i-1th parameters in the first set. By setting the i-th parameter in the first set to satisfy this first condition, the number of occurrences of different parameters in the first set in the questionnaire can be balanced.

[0014] In one possible implementation, when the terminal device determines that the second parameter among the M parameters that meets the first condition is the i-th parameter in the first set, when the number of parameters among the M parameters that meet the first condition is greater than 1, the terminal device can determine a parameter from the parameters that meet the first condition as the second parameter, wherein the second parameter corresponds to a first distance, the first distance is the minimum value of the distances corresponding to the M parameters, and the first distance is the distance between the second parameter and the first parameter to the i-1-th parameter in the first set.

[0015] By determining at least one parameter from the M parameters whose remaining number of occurrences in the questionnaire is greater than the second threshold, and determining from the at least one parameter a parameter with the smallest distance from all the parameters determined in the first set as the i-th parameter in the first set, not only the number of occurrences of different parameters in the first set in the questionnaire is balanced, but also the difference between the weights of different parameters in the first set will not be too large, so that the probability of the user selecting any one element from the N elements in the first set will not be too large.

[0016] In one possible implementation, the distance between the second parameter and the first parameter to the i-1th parameter in the first set is the minimum value of the difference between the weight of the second parameter and the weight of the first parameter to the i-1th parameter in the first set.

[0017] The distance between any parameter and some parameters in any set is defined as the minimum value of the difference between the weight of any parameter and the weight of the some parameters in any set, so that it is possible to determine whether the difference between the weight of any parameter and the weights of all parameters determined in the first set is too large through the distance between any parameter and all parameters determined in the first set.

[0018] In one possible implementation, the questionnaire further includes a second set, where the second set is determined before the first set is determined, and the first condition includes: the second parameter is included in the second set; and the second parameter is different from the first to i-1th parameters in the first set. By setting the i-th parameter in the first set to satisfy this first condition, if the number of remaining occurrences of a parameter that is different from any parameter determined in the first set is insufficient in the questionnaire, a parameter that is different from any parameter determined in the first set can be determined from the previously determined second set as the i-th parameter in the first set.

[0019] In one possible implementation, when the terminal device determines that the second parameter among the M parameters is the i-th parameter in the first set, when the number of parameters in the M parameters that satisfy the first condition is greater than 1, the terminal device can determine a parameter from the parameters that satisfy the first condition as the second parameter; wherein the second parameter corresponds to a second distance, the M parameters also include a third parameter that satisfies the second condition, the third parameter corresponds to a third distance, the sum of the second distance and the third distance is the smallest, the second distance is the distance between the second parameter and the first parameter to the i-1-th parameter in the first set, and the third distance is the distance between the third parameter and all parameters in the second set except the second parameter.

[0020] By traversing the previously determined second set, the second parameter in the second set is used as the i-th parameter in the first set. Since the distance from the second parameter to all the parameters determined in the first set is minimized by the sum of the distances from the third parameter to all the parameters in the second set except the second parameter, the difference between the weights of the different parameters in the first set is minimized, and thus the probability of the user selecting any one of the N elements in the first set is minimized.

[0021] In one possible implementation, the second condition includes: the remaining number of occurrences in the questionnaire is greater than a second threshold; and the parameter is different from all parameters in the second set except the second parameter. By setting the third parameter to meet this second condition, the number of occurrences of different parameters in the second set in the questionnaire can be balanced after the second parameter in the second set is replaced by the third parameter.

[0022] In a possible implementation, after the terminal device determines a parameter from the parameters that meet the first condition as the second parameter, the terminal device may further replace the second parameter in the second set with the third parameter.

[0023] Because the remaining number of occurrences of the third parameter in the questionnaire is greater than the second threshold, the number of occurrences of the different parameters in the second set in the questionnaire is balanced. Furthermore, because the distance from the second parameter to all parameters already determined in the first set is minimized by the sum of the distances from the third parameter to all parameters in the second set other than the second parameter, the difference between the weights of the different parameters in the second set is minimized, thereby minimizing the probability of a user selecting any one of the N elements in the second set.

[0024] In one possible implementation, the terminal device may also determine a third set based on the first information; the terminal device may also determine a first loss corresponding to the third set, the first loss being used to indicate the difference between the prior probabilities corresponding to the N values ​​of the fourth parameter in the third set, and the fourth parameter being any parameter in the third set; the terminal device may also perform a first update operation on the N values ​​of the fourth parameter in the third set to obtain the first set, wherein the N values ​​of the fourth parameter in the first set have at least one value different from the N values ​​of the fourth parameter in the third set, the first set corresponds to a second loss, the second loss being used to indicate the difference between the prior probabilities corresponding to the N values ​​of the fourth parameter in the first set, and the second loss being smaller than the first loss.

[0025] The first set is obtained by replacing any one of the N values ​​of the fourth parameter in the third set with a value different from the value of the fourth parameter. The difference between the prior probabilities corresponding to the N values ​​of the fourth parameter in the first set is lower than that of the third set, so that the probability of the user selecting any one of the N elements in the first set is not too large.

[0026] In a possible implementation, when the terminal device performs a first update operation on the N values ​​of the fourth parameter in the third set to obtain the first set, the terminal device may perform a first update operation on the N values ​​of the fourth parameter in the third set to obtain a fourth set; the terminal device may determine a first difference corresponding to the fourth set, where the first difference is used to indicate the difference between the utilities corresponding to the N elements in the fourth set, and the utility corresponding to any one of the N elements is used to indicate the sum of the prior probabilities corresponding to the values ​​of all parameters included in the any one element; the terminal device may perform a second update operation on the N values ​​of the fifth parameter in the fourth set to obtain the first set, wherein the fifth parameter is any parameter in the fourth set, the value of the fifth parameter of the first element in the first set is the value of the fifth parameter of the second element in the fourth set, and the value of the fifth parameter of the second element in the first set is the value of the fifth parameter of the first element in the fourth set, the first set corresponds to a second difference, the second difference is used to indicate the difference between the utilities corresponding to the N elements in the first set, and the second difference is smaller than the first difference.

[0027] The first set is obtained by exchanging the value of the fifth parameter of the first element and the value of the fifth parameter of the second element in the fourth set. The difference between the utilities corresponding to the first element and the second element in the first set is lower than that in the fourth set, so that the probability of the user selecting any one of the N elements in the first set is not too large.

[0028] In one possible implementation, when the terminal device performs a second update operation on the N values ​​of the fifth parameter in the fourth set to obtain the first set, the terminal device may perform a second update operation on the N values ​​of the fifth parameter in the fourth set to obtain a fifth set; the terminal device may determine the number of times the value of the fifth parameter of the first element in the fifth set has appeared in the questionnaire; if the number of times the value of the fifth parameter of the first element in the fifth set has appeared is greater than a third threshold, the terminal device may perform a third update operation on the value of the fifth parameter of the first element in the fifth set to obtain the first set; wherein the number of times the value of the fifth parameter of the first element in the first set has appeared in the questionnaire is less than the third threshold, the first set corresponds to a third difference, the third difference is used to indicate the difference between the utilities corresponding to the N elements in the first set, the third difference is less than or equal to the second difference, the first set corresponds to a third loss, the third loss is used to indicate the difference between the prior probabilities corresponding to the N values ​​of the fifth parameter in the first set, the fifth set corresponds to a fourth loss, the fourth loss is used to indicate the difference between the prior probabilities corresponding to the N values ​​of the fifth parameter in the fifth set, and the difference between the third loss and the fourth loss is less than the fourth threshold.

[0029] By replacing the value of a parameter with a higher number of occurrences in the questionnaire with the value of the parameter with a lower number of occurrences in the questionnaire, the number of occurrences of different values ​​of any parameter in the questionnaire is balanced.

[0030] In the second aspect, the present application also provides a data acquisition device, which can exist independently or be set in a terminal device or in a server. The device has the function of implementing the method described in the first aspect or any possible design of the first aspect. The function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions, such as an interface unit, a processing unit, etc., and can also include a storage unit. The interface unit can be a human-computer interaction interface, or a human-computer interaction interface, or an input and output port of a device, etc., which is not limited in the embodiments of the present application. The processing unit can be a processor or a processing chip, etc., which is not limited in the embodiments of the present application. The storage unit can be used to store multiple index libraries. Of course, the storage unit can also be set in other devices, such as access network devices, core network devices, etc., which is not limited in the embodiments of the present application.

[0031] An interface unit is configured to obtain first information, wherein the first information is configured to indicate M parameters selected by a user and at least one value of each of the M parameters, wherein the M parameters correspond to one object, and M is a positive integer;

[0032] a processing unit, configured to determine a questionnaire based on the first information, the questionnaire comprising a first set, the first set comprising N elements, each of the N elements comprising a value of at least one parameter, the at least one parameter belonging to the M parameters, the N elements comprising the same parameters, and at least one of the N elements having the same parameter having a different value, where N is a positive integer;

[0033] An interface unit is configured to obtain second information based on the questionnaire to complete data collection on the user, wherein the second information is used to indicate an element selected by the user from the N elements.

[0034] In one possible implementation, the processing unit is specifically used to: determine that the first parameter among the M parameters is the first parameter in the first set, and determine that the N values ​​of the first parameter are the N values ​​of the first parameter in the first set, and the N values ​​of the first parameter belong to at least one value of the first parameter among the M parameters; determine that the second parameter among the M parameters that meets the first condition is the i-th parameter in the first set, and determine that the N values ​​of the second parameter are the N values ​​of the i-th parameter in the first set, and the N values ​​of the second parameter belong to at least one value of the second parameter among the M parameters, where i is an integer greater than 1.

[0035] In one possible implementation, the first condition includes: the difference between the first weight and the second weight is less than a first threshold, the first weight is the weight corresponding to any one of the first parameter to the i-1th parameter in the first set, and the second weight is the weight corresponding to the second parameter; the remaining number of occurrences in the questionnaire is greater than a second threshold; and, it is different from the first parameter to the i-1th parameter in the first set.

[0036] In a possible implementation, the first condition includes: the remaining number of occurrences in the questionnaire is greater than a second threshold; and is different from the first parameter to the i-1th parameter in the first set.

[0037] In one possible implementation, the processing unit is specifically used to: when the number of parameters in the M parameters that satisfy the first condition is greater than 1, determine a parameter from the parameters that satisfy the first condition as the second parameter, wherein the second parameter corresponds to a first distance, the first distance is the minimum value of the distances corresponding to the M parameters, and the first distance is the distance between the second parameter and the first parameter to the i-1th parameter in the first set.

[0038] In one possible implementation, the distance between the second parameter and the first parameter to the i-1th parameter in the first set is the minimum value of the difference between the weight of the second parameter and the weight of the first parameter to the i-1th parameter in the first set.

[0039] In one possible implementation, the questionnaire also includes a second set, which is a set determined before determining the first set, and the first condition includes: the second parameter is included in the second set; and is different from the first to i-1th parameters in the first set.

[0040] In one possible implementation, the processing unit is specifically configured to: when the number of parameters in the M parameters that satisfy the first condition is greater than 1, determine a parameter from the parameters that satisfy the first condition as the second parameter; wherein the second parameter corresponds to a second distance, the M parameters also include a third parameter that satisfies the second condition, the third parameter corresponds to a third distance, the sum of the second distance and the third distance is the smallest, the second distance is the distance between the second parameter and the first parameter to the i-1th parameter in the first set, and the third distance is the distance between the third parameter and all parameters in the second set except the second parameter.

[0041] In a possible implementation, the second condition includes: the remaining number of occurrences in the questionnaire is greater than a second threshold; and all parameters in the second set except the second parameter are different.

[0042] In a possible implementation, the processing unit is further configured to replace the second parameter in the second set with the third parameter.

[0043] In one possible implementation, the processing unit is further used to: determine a third set based on the first information; determine a first loss corresponding to the third set, the first loss being used to indicate the difference between the prior probabilities corresponding to the N values ​​of the fourth parameter in the third set, and the fourth parameter being any parameter in the third set; perform a first update operation on the N values ​​of the fourth parameter in the third set to obtain the first set, wherein at least one value among the N values ​​of the fourth parameter in the first set is different from the N values ​​of the fourth parameter in the third set, the first set corresponds to a second loss, the second loss being used to indicate the difference between the prior probabilities corresponding to the N values ​​of the fourth parameter in the first set, and the second loss being less than the first loss.

[0044] In one possible implementation, the processing unit is further configured to: perform a first update operation on the N values ​​of the fourth parameter in the third set to obtain a fourth set; determine a first difference corresponding to the fourth set, where the first difference is used to indicate a difference between utilities corresponding to the N elements in the fourth set, and the utility corresponding to any one of the N elements is used to indicate a sum of prior probabilities corresponding to values ​​of all parameters included in the any one element; and perform a second update operation on the N values ​​of the fifth parameter in the fourth set to obtain the first set, where the fifth parameter is any one of the parameters in the fourth set, the value of the fifth parameter of the first element in the first set is the value of the fifth parameter of the second element in the fourth set, and the value of the fifth parameter of the second element in the first set is the value of the fifth parameter of the first element in the fourth set, and the first set corresponds to a second difference, where the second difference is used to indicate a difference between the utilities corresponding to the N elements in the first set, and the second difference is smaller than the first difference.

[0045] In one possible implementation, the processing unit is further configured to: perform a second update operation on the N values ​​of the fifth parameter in the fourth set to obtain a fifth set; determine the number of times the value of the fifth parameter of the first element in the fifth set has appeared in the questionnaire; and if the number of times the value of the fifth parameter of the first element in the fifth set has appeared is greater than a third threshold, perform a third update operation on the value of the fifth parameter of the first element in the fifth set to obtain the first set; wherein the number of times the value of the fifth parameter of the first element in the first set has appeared in the questionnaire is less than the third threshold, the first set corresponds to a third difference, the third difference is used to indicate the difference between the utilities corresponding to the N elements in the first set, the third difference is less than or equal to the second difference, the first set corresponds to a third loss, the third loss is used to indicate the difference between the prior probabilities corresponding to the N values ​​of the fifth parameter in the first set, the fifth set corresponds to a fourth loss, the fourth loss is used to indicate the difference between the prior probabilities corresponding to the N values ​​of the fifth parameter in the fifth set, and the difference between the third loss and the fourth loss is less than a fourth threshold.

[0046] In a third aspect, embodiments of the present application further provide a computing device cluster comprising at least one computing device, each computing device comprising a processor and a memory. The processor is configured to support a terminal device or server in executing the method of the first aspect or any possible design of the first aspect. The memory is coupled to the processor and stores program instructions and data necessary for the communication device. The communication device may also include a communication interface for communicating with other devices.

[0047] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium includes computer program instructions. When the computer program instructions are executed by a computing device cluster, the computing device cluster executes the method of the first aspect or any possible design of the first aspect.

[0048] In a fifth aspect, an embodiment of the present application further provides a computer program product comprising instructions, which, when executed by a computing device cluster, enables the computing device cluster to execute the method of the first aspect or any possible design of the first aspect.

[0049] In a sixth aspect, an embodiment of the present application further provides a chip, which can be coupled to a memory and used to call a computer program stored in the memory to execute the method of the first aspect or any possible design of the first aspect.

[0050] The beneficial effects of the above-mentioned second to sixth aspects and their possible designs can refer to the description of the beneficial effects of the method described in the above-mentioned first aspect and any possible design thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] FIG1 is a schematic diagram showing the principle of the selection-based conjoint analysis method;

[0052] FIG2 is a schematic diagram of the structure of a data acquisition system provided in an embodiment of the present application;

[0053] FIG3 is a flow chart of a data acquisition method provided in an embodiment of the present application;

[0054] FIG4a is a schematic diagram of an interface provided in an embodiment of the present application;

[0055] FIG4 b is another schematic diagram of an interface provided in an embodiment of the present application;

[0056] FIG4c is another interface schematic diagram provided in an embodiment of the present application;

[0057] FIG4d is another interface schematic diagram provided in an embodiment of the present application;

[0058] FIG5 is a schematic diagram of the structure of a computing device provided in an embodiment of the present application;

[0059] FIG6 is a schematic diagram of the structure of a computing device cluster provided in an embodiment of the present application;

[0060] FIG7 is a schematic diagram of a connection method between computing device clusters provided in an embodiment of the present application. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the embodiments of the present application will be described in detail below with reference to the accompanying drawings. The terms used in the implementation methods of the present application are only used to explain the specific embodiments of the present application and are not intended to limit the present application.

[0062] Before introducing the specific solutions provided in the embodiments of the present application, some of the terms in the embodiments of the present application are explained to facilitate understanding by those skilled in the art, and the terms in the present application are not limited.

[0063] (1) In the embodiments of the present application, "multiple" refers to two or more. In view of this, in the embodiments of the present application, "multiple" can also be understood as "at least two". "At least one" can be understood as one or more, for example, one, two or more. For example, including at least one means including one, two or more, and does not limit which ones are included. For example, including at least one of A, B and C, then the included ones may be A, B, C, A and B, A and C, B and C, or A, B and C. "And / or" describes the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / ", unless otherwise specified, generally indicates that the previous and subsequent associated objects are in an "or" relationship.

[0064] Unless otherwise specified, ordinal numbers such as "first" and "second" in the embodiments of the present application are used to distinguish multiple objects and are not used to limit the order, timing, priority or importance of multiple objects.

[0065] (2) Value quantification: The value of a product needs to be quantified during the product design phase, product development phase, or before it is sold to help companies make better product decisions. For example, the value of Product 1 can be quantified by the benefits brought by the difference between Product 1 and Product 2, where Product 2 is a product similar to Product 1 on the market, i.e., direct quantification. Alternatively, the value of Product 1 can be quantified by consumers’ preferences for the attributes that make up Product 1 (e.g., a mobile phone has attributes such as appearance, price, and brand) and the levels of the attributes (e.g., the price attribute has levels of 1,000 yuan, 2,000 yuan, 5,000 yuan, etc.), i.e., indirect quantification.

[0066] (3) Conjoint analysis is a method for indirectly quantifying the value of a product. This method assumes that a product is composed of multiple attributes, and each attribute has multiple levels. Since consumers will comprehensively consider multiple attributes of a product and multiple levels of each attribute in the process of selecting a product, this method can quantify the value of a product by studying the role of multiple attributes of a product and multiple levels of each attribute in consumers’ product selection. In other words, this method can collect consumers’ preference data for multiple attributes of a product and multiple levels of each attribute, and quantify the value of the product based on this preference data.

[0067] Conjoint analysis methods include score-based and choice-based conjoint analysis (CBC). Score-based conjoint analysis doesn't quite align with real-world consumer purchasing behavior and is therefore rarely used in actual market research. In contrast, choice-based conjoint analysis better simulates real-world consumer purchasing behavior by examining consumers' choices among multiple product attributes and multiple levels of each attribute.

[0068] For example, Figure 1 is a schematic diagram of the principle of the selection-based conjoint analysis method. As shown in Figure 1, its core is to perform orthogonal combinations of multiple product attributes and multiple levels of each attribute to generate multiple virtual products. Through orthogonal comparison of multiple virtual products, consumers are asked to select their preferred virtual products, thereby collecting consumer preference data for multiple product attributes and multiple levels of each attribute, and quantifying the value of the product based on this preference data. The specific steps are as follows:

[0069] Step 1: Determine the attributes and attribute levels of the product. For example, if the attributes of the product can be brand and resolution, the attribute levels can be specific brands and specific resolutions.

[0070] Step 2: Construct virtual products with orthogonal properties, meaning the levels of the attributes that make up the virtual product are orthogonal. For example, if a product has five attributes, each with four levels, a full factorial experimental design would result in 4 × 4 × 4 × 4 × 4 = 1024 virtual products, far exceeding the range of consumers' rational judgment. Therefore, the selection-based conjoint analysis method uses an orthogonal experimental design, selecting orthogonal local components to represent the overall population, thereby reducing the number of virtual products.

[0071] Step 3: Randomly select at least two virtual products from the constructed virtual products to generate a selection task. The number of generated selection tasks must be no less than the number of attribute levels. For example, two virtual products are selected to generate a selection task and presented to consumers: one virtual product is brand A, priced at 1,000 yuan, and has a low resolution; the other virtual product is brand B, priced at 3,000 yuan, and has a high resolution. The consumer can choose which virtual product they prefer.

[0072] Step 4: Consumers select their preferred virtual products from all selection tasks in turn.

[0073] Step 5: Analyze the data collected in step 4 and quantify the value of the product.

[0074] However, steps 1-3 above require two assumptions when generating the selection tasks: Assumption 1: Consumers are homogeneous, meaning each consumer must complete the same multiple selection tasks; Assumption 2: Consumers are very patient and willing to complete multiple selection tasks. In actual market research, however, consumers often have low patience when faced with multiple selection tasks. Furthermore, consumers are often heterogeneous, with different preferences. If a selection task consistently includes an attribute that a consumer is not interested in, such as repeatedly asking someone who dislikes apples to choose a preferred fruit between apples and another fruit, this can reduce consumer patience and may cause them to stop choosing midway, affecting data collection efficiency and, consequently, the subsequent value quantification process.

[0075] In response to the problem of low efficiency of data collection described in the above content, an embodiment of the present application provides a data collection method. This method can be applied to collecting user preference data for multiple parameters (i.e., the above-mentioned attributes) of a certain object (i.e., the above-mentioned product) and multiple values ​​(i.e., the above-mentioned levels) of each parameter, so as to quantify the value of the object based on the preference data. This method can be applied to a data collection system, which may include one or more terminal devices and / or one or more servers. Of course, in addition to terminal devices and servers, the data collection system provided in the embodiment of the present application may also include other devices, such as access network devices, core network devices, etc., which are not limited to the embodiment of the present application. In addition, any device in the embodiment of the present application may integrate functions into an independent physical unit, or distribute functions across multiple independent physical units, which are not limited to the embodiment of the present application.

[0076] For example, Figure 2 is a schematic diagram of the structure of a data acquisition system provided in an embodiment of the present application. Figure 2 shows a schematic diagram of a terminal device and a server, namely terminal device 100 and server 200, respectively. In actual applications, the number of terminal devices and / or servers included in the system is not limited to this.

[0077] In a possible implementation, after obtaining the first information, the terminal device 100 may determine a questionnaire based on the first information, and obtain the second information based on the questionnaire to complete the data collection of the user.

[0078] In another possible implementation, after obtaining the first information, the terminal device 100 may send the first information to the server 200. The server 200 may determine a questionnaire based on the first information and send the questionnaire to the terminal device 100. The terminal device 100 may obtain second information based on the questionnaire and send the second information to the server 200 to complete the data collection of the user.

[0079] It is understood that the terminal device 100 can be a device equipped with a display screen and capable of human-computer interaction through the display screen. For example, the terminal device 100 can be a mobile phone, a tablet computer, an in-vehicle device, an augmented reality (AR) / virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), a wearable device, etc. The embodiments of the present application do not impose any restrictions on the specific type of the terminal device 100.

[0080] Server 200 can refer to a single server or a server cluster consisting of multiple servers. Specifically, server 200 can be a cloud server, also known as a cloud, cloud, cloud server, or cloud controller. A cloud server is a general term for devices or components with data processing capabilities, including physical devices such as hosts or processors, virtual devices such as virtual machines or containers, and chips or integrated circuits.

[0081] The information interaction between the terminal device 100 and the server 200 may refer to direct interaction between the terminal device 100 and the server 200 via a wired or wireless manner, or it may refer to indirect interaction between the terminal device 100 and the server 200 via one or more other devices, which is not limited in the embodiments of the present application.

[0082] The above content describes the possible application scenarios and applicable system architecture of the data acquisition method provided in the embodiment of the present application. The data acquisition method provided in the embodiment of the present application will be further introduced below in conjunction with the structure of the data acquisition system shown in Figure 2 above.

[0083] Exemplarily, Figure 3 is a flow chart of a data acquisition method provided in an embodiment of the present application. The data acquisition method can be applied to the data acquisition system shown in Figure 2 or with a functional structure similar to that of Figure 2, and the embodiment of the present application does not impose any specific restrictions here. The specific process of the data acquisition method is described as follows. In the following introduction, the method is applied to the data acquisition system shown in Figure 2 as an example. For example, the terminal device described below can be the terminal device 100 in the system shown in Figure 2, and the server described below can be the server 200 in the system shown in Figure 2. In the embodiment of the present application, the data acquisition system is used as an example to introduce the execution subject of the method, or the execution subject of the method can also be other devices or systems, such as a chip, chip system or processor applied to the data acquisition system.

[0084] S301: Obtain first information.

[0085] In an embodiment of the present application, the first information can be used to indicate M parameters selected by the user, and to indicate at least one value of each of the M parameters, where the M parameters correspond to one object and M is a positive integer.

[0086] The M parameters may include at least one target parameter selected by a user from at least one candidate parameter of an object. The at least one value of each parameter in the M parameters may include at least one target value selected by a user from at least one candidate value of each target parameter in the at least one target parameter.

[0087] The object can be a product or service that can be sold, such as a mobile phone, a television, etc.; the parameters of the object can be the parameters that constitute the object, such as a mobile phone has parameters such as brand, price, and appearance; the value of the parameter can be various specific parameters, such as the price has values ​​of 1,000 yuan, 2,000 yuan, 3,000 yuan, etc.

[0088] In a specific implementation, the terminal device may display an interface as shown in FIG4a on its display screen. This interface may display at least one candidate parameter for the vehicle display screen, such as display screen type, material, Blu-ray certification, audio playback mode, interaction mode, content source, and resolution, as well as text prompting the user to select at least one target parameter from the at least one candidate parameter for the vehicle display screen, such as "Please select the parameter you consider relatively important from the following parameters." The user can select the display screen type, Blu-ray certification, audio playback mode, interaction mode, content source, and resolution.

[0089] When the terminal device detects a user selecting a display type, Blu-ray certification, and sound playback mode, in response to the operation, the terminal device may display an interface as shown in FIG4b on the display screen. The interface may display at least one candidate value for the display type, Blu-ray certification, and sound playback mode, such as display type: Type 1, Type 2, Type 3; Blu-ray certification: With Blu-ray certification, Without Blu-ray certification; and sound playback mode: Player play, Headphone play, Player play, and Headphone play, as well as text prompting the user to select at least one target value from the at least one candidate value, such as "Please select the value of the parameter you consider relatively important from the following parameters." The user may select Type 1 or Type 3 from Type 1, Type 2, and Type 3.

[0090] In one possible implementation, when a terminal device displays at least one candidate value for a target parameter on a display screen, the terminal device may determine whether to display the at least one candidate value for the target parameter based on a relationship among the at least one candidate value for the target parameter. The relationship among the at least one candidate value for the target parameter includes a parallel relationship, a mutually exclusive relationship, and an inclusive relationship.

[0091] For example, three candidate values ​​of display screen types (such as type 1, type 2, and type 3) are in a parallel relationship, and the user can select at least one target value from these three candidate values. Therefore, the terminal device can display these three candidate values ​​on the display screen for the user to select.

[0092] For example, the two candidate values ​​of blue light certification (such as blue light certification and no blue light certification) are mutually exclusive. The user can only select one target value from these two candidate values. Therefore, the terminal device may not display these two candidate values ​​on the display screen for the user to choose, but directly use these two candidate values ​​as target values.

[0093] For another example, the three candidate values ​​for the sound playing mode (such as player play, headphone play, player play and headphone play) are in an inclusion relationship, player and headphone play are parent candidate values, player play and headphone play are child candidate values, and the user selects the parent candidate value as the target value, which is equivalent to selecting all the child candidate values ​​of the parent candidate value as the target value. Therefore, the terminal device can display the child candidate values ​​among the three candidate values ​​on the display screen for the user to select, but does not display the parent candidate value among the three candidate values ​​on the display screen for the user to select, but directly uses the parent candidate value among the three candidate values ​​as the target value.

[0094] In another possible implementation, before displaying at least one candidate value for a target parameter on a display screen, the terminal device may determine the prior probability of each of the at least one candidate value for the target parameter through preliminary experiments. The prior probability of a first candidate value for the target parameter indicates the probability that a user will select the first candidate value from the at least one candidate value for the target parameter. For example, a brand has three parameters: Brand 1, Brand 2, and Brand 3. With Brand 1 as the benchmark, the prior probability of Brand 1 is 0, the prior probability of Brand 2 is 0.1, and the prior probability of Brand 3 is 0.2.

[0095] After the user determines at least one target value from at least one candidate value for the target parameter, that is, after the terminal device obtains the at least one target value for the target parameter, the terminal device may update the prior probability of each of the at least one target value for the target parameter. The prior probability of the first target value for the target parameter indicates the probability that the user selected the first target value from the at least one target value for the target parameter. For example, after the user selects Brand 2 and Brand 3 from Brand 1, Brand 2, and Brand 3, the prior probabilities of Brand 2 and Brand 3 are updated. With Brand 2 as the benchmark, the prior probability of Brand 2 is updated to 0, and the prior probability of Brand 3 is updated to 0.1.

[0096] S302: Determine a questionnaire based on the first information.

[0097] In an embodiment of the present application, a questionnaire may include a first set. The first set includes N elements, each of the N elements includes the value of at least one parameter, at least one parameter belongs to the M parameters indicated by the first information obtained in S302 above, the parameters included in the N elements are the same, and at least one of the N elements has a different value for the same parameter, and N is a positive integer. A questionnaire is a way to display the first set. The present application can display the first set to the user through a questionnaire to determine the preferred elements selected by the user from different elements in the first set. Of course, the present application can also display the first set in other ways, and the embodiment of the present application does not impose specific restrictions on this.

[0098] For example, the questionnaire includes set 1, set 1 includes element 1 and element 2, and the relationship between element 1 and element 2 in set 1 can be shown in Table 1.

[0099] Table 1

[0100] In a specific implementation, after the terminal device obtains the first information, the terminal device may determine the questionnaire based on the first information. Alternatively, after the terminal device obtains the first information, the terminal device may send the first information to a server, and the server may determine the questionnaire based on the first information and send the questionnaire to the terminal device. This embodiment of the present application does not impose specific limitations on this. For ease of explanation, this application uses the example of a terminal device determining the questionnaire based on the first information.

[0101] In one possible implementation, the number of sets in the questionnaire may be one or more. Specifically, the terminal device may determine the number of sets in the questionnaire based on the parameters indicated by the first information and the number of parameter values. For example, if the first information indicates four parameters (i.e., M is 4), namely parameter 1, parameter 2, parameter 3, and parameter 4, parameter 1 has two values, parameter 2 has three values, parameter 3 has four values, and parameter 4 has four values, then the number of sets in the questionnaire is 2+3+4+4-4+5=14.

[0102] In another possible implementation, when there are multiple sets in the questionnaire, the terminal device may determine the multiple sets at one time based on the first information, and then display the multiple sets in sequence through the display screen to collect the user's preference data for different elements in each of the multiple sets; or, the terminal device may determine a set based on the first information, and then display the set in sequence through the display screen to collect the user's preference data for different elements in the set, and then determine another set based on the first information, and display the another set in sequence through the display screen to collect the user's preference data for different elements in the another set, wherein the latter set may be related to or unrelated to the user's preference data for different elements in the former set. The embodiments of the present application do not impose specific restrictions on this. For ease of explanation, the present application takes the example of a terminal device determining multiple sets at one time based on the first information.

[0103] Exemplarily, the terminal device may perform the following steps A1-A2 to determine the first set:

[0104] Step A1: Determine that a first parameter among the M parameters is the first parameter in the first set, and determine that N values ​​of the first parameter are N values ​​of the first parameter in the first set, and the N values ​​of the first parameter belong to at least one value of the first parameter among the M parameters.

[0105] Specifically, the terminal device may perform unequal probability sampling on M parameters to obtain the first parameter, and perform unequal probability sampling on at least one value of the first parameter to obtain N values ​​of the first parameter.

[0106] Among them, the sampling probability of any one of the M parameters is positively correlated with the remaining number of occurrences of the any parameter in the questionnaire, the sampling probability of any value of the any parameter is positively correlated with twice the remaining number of occurrences of the any parameter in the questionnaire, the remaining number of occurrences of the any parameter in the questionnaire is the total number of occurrences of the any parameter in the questionnaire minus the number of occurrences of the any parameter in the questionnaire, and the total number of occurrences of the any parameter in the questionnaire is negatively correlated with the number of values ​​of the any parameter.

[0107] For example, the first information indicates four parameters (i.e., M is 4), namely parameter 1, parameter 2, parameter 3, and parameter 4. Parameter 1 has three values, namely value 1, value 2, and value 3. Unequal probability sampling is performed on parameters 1, 2, 3, and 4 to obtain the first parameter in the first set. Here, the sampling probability of parameter 1, Q1, is ∝(T1-T2), where ∝ is the sign of direct proportion, T1 is the total number of times parameter 1 appears in the questionnaire, T1 is ∝(1 / 2), and T2 is the number of times parameter 1 has appeared in the questionnaire. When unequal probability sampling is performed on the values ​​of parameter 1 to obtain N values ​​of the first parameter, the sampling probability of value 1, Q2, is ∝(2*T1).

[0108] Step A2: Determine that the second parameter among the M parameters is the i-th parameter in the first set, and determine that the N values ​​of the second parameter are the N values ​​of the i-th parameter in the first set, the second parameter satisfies the first condition, the N values ​​of the second parameter belong to at least one value of the second parameter among the M parameters, and i is an integer greater than 1.

[0109] Specifically, the terminal device may determine the second parameter through three solutions according to the three first conditions. The following describes in detail the specific implementations of the three solutions with reference to specific examples:

[0110] Solution 1: Determine any one of the M parameters that meets the first condition in the first possible implementation as the second parameter.

[0111] In a first possible implementation, the first condition may include: the difference between the first weight and the second weight is less than a first threshold value, the first weight is the weight corresponding to any one parameter from the first parameter to the i-1th parameter in the first set, and the second weight is the weight corresponding to the second parameter; the remaining number of occurrences in the questionnaire is greater than the second threshold value; and, it is different from the first parameter to the i-1th parameter in the first set.

[0112] The weight of a parameter can be the difference between the first prior probability of the parameter and the second prior probability of the parameter. The first prior probability of the parameter is the prior probability of the value with the highest prior probability among the parameter values, and the second prior probability of the parameter is the prior probability of the value with the lowest prior probability among the parameter values. For example, a brand has four parameters: Brand 1, Brand 2, and Brand 3. When Brand 1 is used as the benchmark, the prior probability of Brand 1 is 0, the prior probability of Brand 2 is 0.1, and the prior probability of Brand 3 is 0.2. Therefore, the weight of the brand is the difference between the prior probabilities of Brand 3 and Brand 1, which is 0.2.

[0113] For example, the first information indicates four parameters (i.e., M is 4), namely parameter 1, parameter 2, parameter 3, and parameter 4. Parameter 1 has two values, parameter 2 has three values, parameter 3 has four values, and parameter 4 has four values. After determining that parameter 1 is the first parameter of the first set, if the difference between the weights of parameters 2, 3, and 4 and the weight of parameter 1 is less than a first threshold, the remaining number of occurrences of parameters 2 and 3 in the questionnaire is greater than a second threshold, and the remaining number of occurrences of parameter 4 in the questionnaire is less than or equal to the second threshold, it can be determined that parameters 2 and 3 both meet the first condition of the first possible implementation method described above, and parameter 4 does not meet the first condition of the first possible implementation method described above. Therefore, unequal probability sampling can be performed on parameters 2 and 3 to obtain the second parameter of the first set. The sampling probability of parameter 2 is Q3∝(T3-T4), where T3 is the total number of occurrences of parameter 2 in the questionnaire, T3∝(1 / 3), and T4 is the number of occurrences of parameter 2 in the questionnaire. The sampling probability of parameter 3 Q4∝(T5-T6), T5 is the total number of times parameter 3 appears in the questionnaire, T5∝(1 / 4), T6 is the number of times parameter 3 has appeared in the questionnaire.

[0114] Solution 2: When the number of parameters satisfying the first condition in the second possible implementation manner among the M parameters is greater than 1, one parameter is determined from the parameters satisfying the first condition as the second parameter.

[0115] In a second possible implementation, the first condition may include: the remaining number of occurrences in the questionnaire is greater than a second threshold; and the number of occurrences is different from the first parameter to the (i-1)th parameter in the first set.

[0116] Wherein, the second parameter corresponds to the first distance (also known as the first inter-rank distance). The first distance is the minimum value among the distances corresponding to the M parameters. The first distance is the distance between the second parameter and the first parameter to the i-1th parameter in the first set. The distance between the second parameter and the first parameter to the i-1th parameter in the first set is the minimum value of the difference between the weight of the second parameter and the weight of the first parameter to the i-1th parameter in the first set.

[0117] For example, the first information indicates five parameters (i.e., M is 5), namely parameter 1, parameter 2, parameter 3, parameter 4, and parameter 5. After determining parameter 1 as the first parameter of the first set and determining parameter 2 as the second parameter of the first set, if the differences between the weights of parameters 3, 4, and 5 and the weight of parameter 1 are all greater than or equal to the first threshold, and the differences between the weights of parameters 3, 4, and 5 and the weight of parameter 2 are also greater than or equal to the first threshold, the remaining number of occurrences of parameters 3 and 4 in the questionnaire are both greater than the second threshold, and the remaining number of occurrences of parameter 5 in the questionnaire is less than or equal to the second threshold, then it can be determined that parameters 3, 4, and 5 do not meet the first condition of the first possible implementation method, parameters 3 and 4 both meet the first condition of the second possible implementation method, and parameter 5 does not meet the first condition of the second possible implementation method.

[0118] Therefore, we can determine the first distance d1 corresponding to parameter 3 and the first distance d2 corresponding to parameter 4. Here, d1 is the minimum of r1 and r2, r1 is the difference between the weight of parameter 3 and the weight of parameter 1, and r2 is the difference between the weight of parameter 3 and the weight of parameter 2. d2 is the minimum of r3 and r4, r3 is the difference between the weight of parameter 4 and the weight of parameter 1, and r4 is the difference between the weight of parameter 4 and the weight of parameter 2. If d1 is less than d2, we can determine that parameter 3 is the third parameter of the first set.

[0119] Solution three: When the number of parameters satisfying the first condition in the third possible implementation manner among the M parameters is greater than 1, one parameter is determined from the parameters satisfying the first condition as the second parameter.

[0120] In a third possible implementation, if the questionnaire contains multiple sets, the questionnaire may further include a second set. The second set is determined before the first set is determined, and includes N elements. Each of the N elements includes the value of at least one parameter, at least one of the M parameters acquired in S302 above. The N elements include the same parameters, and at least one of the N elements has a different value for the same parameter. The first condition may include: the second parameter is included in the second set; and the second parameter is different from the first to the (i-1)th parameters in the first set.

[0121] The second parameter corresponds to the second distance, the M parameters also include a third parameter that satisfies the second condition, the third parameter corresponds to the third distance, the sum of the second and third distances is minimized, the second distance is the distance between the second parameter and the first to i-1th parameters in the first set, and the third distance is the distance between the third parameter and all parameters in the second set except the second parameter. The second condition includes: the remaining number of occurrences in the questionnaire is greater than the second threshold; and the parameter is different from all parameters in the second set except the second parameter.

[0122] Optionally, after determining a parameter as the second parameter from the parameters that meet the first condition in the third possible implementation manner, the second parameter in the second set may be replaced by the third parameter.

[0123] For example, the first information indicates five parameters (i.e., M is 5), namely parameter 1, parameter 2, parameter 3, parameter 4, and parameter 5. After determining parameter 1 as the first parameter of the first set and determining parameter 2 as the second parameter of the first set, if the difference between the weights of parameters 3, 4, and 5 and the weight of parameter 1 is greater than or equal to the first threshold, and the difference between the weights of parameters 3, 4, and 5 and the weight of parameter 2 is also greater than or equal to the first threshold, and the remaining number of occurrences of parameters 3, 4, and 5 in the questionnaire is less than or equal to the second threshold, then it can be determined that parameters 3, 4, and 5 do not meet the first condition of the first and second possible implementations described above.

[0124] If the second set includes three parameters, namely parameter 1, parameter 3, and parameter 4, then it can be determined that parameter 3 and parameter 4 both meet the first condition of the third possible implementation. If the remaining number of occurrences of parameter 2 in the questionnaire is greater than the second threshold, then it can be determined that parameter 2 meets the second condition.

[0125] Therefore, we can determine the first distance d1 corresponding to parameter 3, the first distance d2 corresponding to parameter 4, the second distance d3 corresponding to parameter 2 (the second parameter in the second set: parameter 3), and the second distance d4 (the second parameter in the second set: parameter 4). Here, d1 is the minimum of r1 and r2, r1 is the difference between the weight of parameter 3 and the weight of parameter 1, and r2 is the difference between the weight of parameter 3 and the weight of parameter 2. d2 is the minimum of r3 and r4, r3 is the difference between the weight of parameter 4 and the weight of parameter 1, and r4 is the difference between the weight of parameter 4 and the weight of parameter 2. d3 is the minimum of r5 and r6, r5 is the difference between the weight of parameter 2 and the weight of parameter 1, and r4 is the difference between the weight of parameter 2 and the weight of parameter 3. d4 is the minimum of r5 and r7, and r7 is the difference between the weight of parameter 2 and the weight of parameter 4. If d1+d3 is less than d2+d4, it can be determined that parameter 3 is the third parameter of the first set, and parameter 2 is parameter 3 of the first set, that is, the first set includes parameter 1, parameter 2 and parameter 3, and the second set includes parameter 1, parameter 2 and parameter 4.

[0126] The above scheme uses unequal probability sampling to balance the number of times different parameters appear in multiple sets that users need to choose from, and by limiting the difference between the weights of different parameters of an element, when users select preferred elements from multiple sets, there will be no invalid sets where the difference between the weights of different parameters of an element is too large, thereby improving the efficiency of collecting users' preference data for different elements in multiple sets.

[0127] In one possible implementation, after the terminal device determines the first set, the difference between the prior probabilities of different values ​​of any parameter in the first set may be too large. For example, one parameter of the first element and the second element in set 1 is price, the price value of the first element is 1,000 yuan (the prior probability is 0.7), and the price value of the second element is 10,000 yuan (the prior probability is 0.1). The probability that the user prefers the first element over the first element and the second element in set 1 is too large, resulting in low efficiency in collecting the user's preference data for the first element and the second element in set 1. Therefore, the terminal device can also perform the following steps B1-B3 to optimize the first set determined in the above steps A1-A2 to reduce the difference between the prior probabilities of different values ​​of any parameter corresponding to the first set:

[0128] Step B1: Determine the third set according to the first information.

[0129] For step B1, please refer to the introduction of steps A1-A2 above, which will not be repeated here.

[0130] Step B2: Determine the first loss corresponding to the third set.

[0131] Among them, the first loss is used to indicate the difference between the prior probabilities corresponding to N values ​​of the fourth parameter in the third set, the prior probability corresponding to any one of the N values ​​is used to indicate the probability of the user selecting any one value from at least one value of the fourth parameter, and k is a positive integer.

[0132] For example, set 1 includes 3 parameters, namely parameter 1, parameter 2, and parameter 3. The prior probability of parameter 1 value 1 is 0.1, the prior probability of parameter 1 value 2 is 0.4, and the difference between the prior probabilities of the two values ​​is 0.3, that is, the first loss corresponding to set 1 is 0.3.

[0133] Step B3: Perform a first update operation on the N values ​​of the fourth parameter in the third set to obtain a first set.

[0134] Among them, at least one value of the N values ​​of the fourth parameter in the first set is different from the N values ​​of the fourth parameter in the third set, the first set corresponds to the second loss, the second loss is used to indicate the difference between the prior probabilities corresponding to the N values ​​of the fourth parameter in the first set, and the second loss is less than the first loss.

[0135] Optionally, the N values ​​of the fourth parameter in the first set are N values ​​corresponding to the minimum second loss among at least one value of the fourth parameter.

[0136] For example, the values ​​of parameter 1 include value 1, value 2, value 3, value 4, and value 5. Traverse the values ​​of parameter 1 and select two different values ​​from value 3 (prior probability 0.2), value 4 (prior probability 0.4), and value 5 (prior probability 0.5) as the two values ​​of parameter 1 in set 2. When value 3 and value 4 are selected as the two values ​​of parameter 1 in set 2, the second loss corresponding to set 2 is 0.2 (less than the first loss 0.3 corresponding to set 1); when value 3 and value 5 are selected as the two values ​​of parameter 1 in set 2, the second loss corresponding to set 2 is 0.3 (equal to the first loss 0.3 corresponding to set 1); when value 4 and value 5 are selected as the two values ​​of parameter 1 in set 2, the second loss corresponding to set 2 is 0.1 (less than the first loss 0.3 corresponding to set 1). Therefore, value 4 and value 5 can be selected as the two values ​​of parameter 1 in set 2, which not only makes the second loss corresponding to set 2 less than the first loss corresponding to set 1, but also minimizes the second loss corresponding to set 2.

[0137] In another possible implementation, after the terminal device executes steps B1-B3 to optimize the first set determined in steps A1-A2, the difference in the sum of the prior probabilities corresponding to the values ​​of all parameters of the different elements of the first set may be too large. For example, the sum of the prior probabilities corresponding to the values ​​of all parameters of the first element in set 1 is 0.8, and the sum of the prior probabilities corresponding to the values ​​of all parameters of the first element in set 1 is 0.2. The probability that the user prefers the first element over the first and second elements in set 1 is too high, resulting in low efficiency in collecting the user's preference data for the first and second elements in set 1. Therefore, the terminal device may further execute the following steps C1-C3 to optimize the first set determined in steps B1-B3 to reduce the difference in the sum of the prior probabilities corresponding to the values ​​of all parameters of the different elements in the first set:

[0138] Step C1: performing a first update operation on the N values ​​of the fourth parameter in the third set to obtain a fourth set;

[0139] The step C1 can refer to the introduction of the above step B3, which will not be repeated here.

[0140] Step C2: Determine the first difference value corresponding to the fourth set.

[0141] The first difference is used to indicate the difference between the utilities corresponding to the N elements in the fourth set, and the utility corresponding to any one of the N elements is used to indicate the sum of the prior probabilities corresponding to the values ​​of all parameters included in any one element.

[0142] For example, set 1 includes elements 1 and 2. Element 1 includes parameter 1 with a value of 1 (prior probability of 0.1), parameter 2 with a value of 2 (prior probability of 0.2), and parameter 3 with a value of 3 (prior probability of 0.3). Element 2 includes parameter 1 with a value of 4 (prior probability of 0.2), parameter 2 with a value of 5 (prior probability of 0.1), and parameter 3 with a value of 6 (prior probability of 0.1). The utility corresponding to element 1 is the sum of the prior probabilities of values ​​1, 2, and 3, which is 0.6. The utility corresponding to element 2 is the sum of the prior probabilities of values ​​4, 5, and 6, which is 0.4. Therefore, the first difference corresponding to set 1 is 0.2.

[0143] Step C3: Perform a second update operation on the N values ​​of the fifth parameter in the fourth set to obtain a first set.

[0144] Among them, the fifth parameter is any parameter in the fourth set, the value of the fifth parameter of the first element in the first set is the value of the fifth parameter of the second element in the fourth set, the value of the fifth parameter of the second element in the first set is the value of the fifth parameter of the first element in the fourth set, the first set corresponds to the second difference, the second difference is used to indicate the difference between the utilities corresponding to the N elements in the first set, and the second difference is smaller than the first difference.

[0145] For example, the value 2 of parameter 2 of element 1 in set 1 described in step C2 above is interacted with the value 5 of parameter 2 of element 2 in set 1 to obtain set 2. That is, the value of parameter 2 of element 1 in set 1 is 5, and the value of parameter 2 of element 2 in set 2 is 2. The sum of the prior probabilities of the utility values ​​1, 5, and 3 corresponding to element 1 in set 2 is 0.5, and the sum of the prior probabilities of the utility values ​​4, 2, and 6 corresponding to element 2 in set 2 is 0.5. Therefore, the second difference corresponding to set 2 is 0, which is less than the first difference value of 0.2 corresponding to set 1.

[0146] In another possible implementation, after the terminal device executes steps C1-C3 to optimize the first set determined in steps B1-B3, the number of times different values ​​of any parameter in the first set appear in the questionnaire may not be balanced. For example, the value 1 of parameter 1 appears 8 times in the questionnaire, while the value 2 of parameter 2 appears only once. Therefore, the terminal device may further execute the following steps D1-D3 to optimize the first set determined in steps C1-C3, so that the number of times different values ​​of any parameter in the first set appear in the questionnaire is balanced:

[0147] Step D1: Perform a second update operation on the N values ​​of the fifth parameter in the fourth set to obtain a fifth set.

[0148] The description of step D1 can be found in the above step C3 and will not be repeated here.

[0149] Step D2: Determine the number of times the value of the fifth parameter of the first element in the fifth set has appeared in the questionnaire.

[0150] Step D3: If the number of occurrences is greater than the third threshold, a third update operation is performed on the value of the fifth parameter of the first element in the fifth set to obtain the first set.

[0151] Among them, the value of the fifth parameter of the first element in the first set has appeared the number of times in the questionnaire is less than the third threshold value, the first set corresponds to the third difference, the third difference is used to indicate the difference between the utilities corresponding to the N elements in the first set, the third difference is less than or equal to the second difference, the first set corresponds to the third loss, the third loss is used to indicate the difference between the prior probabilities corresponding to the N values ​​of the fifth parameter in the first set, the fifth set corresponds to the fourth loss, the fourth loss is used to indicate the difference between the prior probabilities corresponding to the N values ​​of the fifth parameter in the fifth set, and the difference between the third loss and the fourth loss is less than the fourth threshold value.

[0152] For example, if the values ​​2, 5, and 8 (with a prior probability of 0.2) of parameter 2 appear in the questionnaire 3, 2, and 1 times, respectively, then the fourth threshold value can be determined as the mean of 3, 2, and 1, 2. The value of parameter 2 of element 2 in set 2 described in step C3 above is replaced from 2 to 8, resulting in set 3. That is, the value of parameter 2 of element 1 in set 3 is 5, and the value of parameter 2 of element 2 in set 3 is 8. The sum of the prior probabilities that the utility values ​​1, 5, and 3 for element 1 in set 3 are 0.5, and the sum of the prior probabilities that the utility values ​​4, 8, and 6 for element 2 in set 3 are 0.5. Therefore, the second difference value corresponding to set 3 is 0, which is equal to the second difference value 0 for set 2. The third loss corresponding to set 3 is 0.1, and the fourth loss corresponding to set 2 is 0.1. The difference between the third and fourth losses is 0, which is less than the fourth threshold value of 0.2.

[0153] S303: Obtain second information according to the questionnaire to complete the data collection of the user.

[0154] In an embodiment of the present application, the second information is used to indicate the element selected by the user from the N elements in the first set. For example, set 1 includes element 1 and element 2, and in set 1, the user prefers element 1.

[0155] In a specific implementation, if the number of sets in the questionnaire determined in S303 is multiple, the terminal device can display an interface as shown in (1) of Figure 4c on the display screen, in which a set 1 can be displayed. Set 1 includes two elements. For example, the values ​​of the three parameters of brand, price, and resolution included in element 1 are brand 1, 3,000 yuan, and low resolution, respectively; the values ​​of the three parameters of brand, price, and resolution included in element 2 are brand 2, 5,000 yuan, and high resolution, respectively. That is, the values ​​of the same parameters in element 1 and element 2 are different. And the text of the user selecting an element from the two elements in set 1, such as "Please select the element that you think is relatively important from the following elements." The user can select element 1 from element 1 and element 2. That is, the user prefers brand 1, 3,000 yuan, and low resolution.

[0156] When the terminal device detects that the user has selected element 1, in response to the operation, the terminal device may display an interface as shown in (2) of FIG4c on the display screen, in which set 2 may be displayed. Set 2 includes two elements. For example, the values ​​of the four parameters of brand, price, resolution, and display screen material included in element 3 are brand 1, 3,000 yuan, low resolution, and material 1, respectively; the values ​​of the four parameters of brand, price, resolution, blue light certification, and display screen material included in element 4 are brand 2, 5,000 yuan, high resolution, and material 2, respectively. That is, the values ​​of the same parameters in element 3 and element 4 are different, and element 3 has one more parameter value than element 1: material 1, and element 4 has one more parameter value than element 2: material 2, as well as text indicating that the user selects one element from the two elements of set 2, such as "Please select the element that you think is relatively important from the following elements." The user can select element 4 from elements 3 and 4. That is, the user prefers brand 2, 5,000 yuan, high resolution, and material 2.

[0157] Alternatively, the terminal device may display an interface as shown in (1) of FIG4d on the display screen, in which a set 1 may be displayed. Set 1 includes two elements, for example, the values ​​of the two parameters of brand and price included in element 1 are brand 1 and RMB 4,000, respectively, and the values ​​of the two parameters of brand and price included in element 2 are brand 2 and RMB 4,000, respectively. That is, only one of the same parameters in element 1 and element 2 has a different value. And the text for the user to select an element from the two elements in set 1, for example, "Please select the element that you think is relatively important from the following elements." The user can select element 2 from element 1 and element 2. That is, the user prefers brand 2.

[0158] When the terminal device detects the user's operation of selecting element 2, in response to the operation, the terminal device can display an interface as shown in (2) of Figure 4d on the display screen, in which set 2 can be displayed. Set 2 includes two elements. For example, the values ​​of the two parameters of brand, price and display material included in element 3 are brand 2 and material 1 respectively, and the values ​​of the two parameters of brand and display material included in element 4 are brand 2 and material 2 respectively. That is, only one of the same parameter values ​​in element 3 and element 4 is different, and the number of parameter values ​​included in element 3 and element 4 is the same as the number of parameter values ​​included in element 1 and element 2. And the text of the user selecting an element from the two elements of set 2, such as "Please select the element that you think is relatively important from the following elements." The user can select element 3 from element 3 and element 4. That is, the user prefers material 1.

[0159] The above scheme can use the first information to obtain the user's preferences for multiple parameters of an object and multiple values ​​for each parameter. Therefore, the set of questionnaires displayed to the user can be based on the user's preferred parameters and / or preferred values, making the questionnaire meet the user's personalized needs, helping to improve the user's patience and thus improving data collection efficiency. In addition, the questionnaire can further obtain the user's preferences for multiple parameters of an object and multiple values ​​for each parameter, making the collected user data more targeted and facilitating the creation of more personalized content for the user, thereby improving the user experience.

[0160] Based on the above embodiments, the present application also provides a computing device. FIG5 is a schematic diagram of the structure of a computing device provided in the present application. The computing device 500 includes a bus 502, a processor 504, a memory 506, and a communication interface 508. The processor 504, the memory 506, and the communication interface 508 communicate with each other via the bus 502. The computing device 500 can be a terminal device or a server. It should be understood that the present application does not limit the number of processors and memories in the computing device 500.

[0161] Bus 502 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, among others. Buses may be classified as address buses, data buses, control buses, and the like. For ease of illustration, FIG5 shows a single line, but this does not imply a single bus or type of bus. Bus 502 may include a path for transmitting information between various components of computing device 500 (e.g., memory 506, processor 504, and communication interface 508).

[0162] The processor 504 may include any one or more processors such as a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0163] The memory 506 may include volatile memory, such as random access memory (RAM). The memory 506 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0164] The memory 506 stores executable program code, and the processor 504 executes the executable program code to implement the functions of the communication module and the processing module, thereby implementing the data acquisition method in the above-mentioned method embodiment. In other words, the memory 506 stores instructions for executing the data acquisition method in the above-mentioned method embodiment.

[0165] The communication interface 508 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the computing device 500 and other devices or a communication network.

[0166] Based on the above embodiments, the present application also provides a computing device cluster. The computing device cluster includes at least one computing device. The computing device can be an electronic device.

[0167] As shown in Figure 6, the computing device cluster includes at least one computing device 500. The memory 506 in one or more computing devices 500 in the computing device cluster may store the same instructions for executing the data collection method in the above method embodiment.

[0168] In some possible implementations, the memory 506 of one or more computing devices 500 in the computing device cluster may also store partial instructions for executing the data collection method in the above method embodiment. In other words, the combination of one or more computing devices 500 can jointly execute instructions for executing the data collection method in the above method embodiment.

[0169] It is understood that the memory 506 in different computing devices 500 in the computing device cluster can store different instructions, each for executing a portion of the functions of the electronic device. In other words, the instructions stored in the memory 506 in different computing devices 500 can implement the functions of one or more modules in the communication module and the processing module.

[0170] In some possible implementations, one or more computing devices in a computing device cluster may be connected via a network. The network may be a wide area network (WAN) or a local area network (LAN), among others. FIG. 7 illustrates one possible implementation. As shown in FIG. 7 , two computing devices 500A and 500B are connected via a network. Specifically, the connection to the network is achieved via a communication interface within each computing device. In this type of possible implementation, the memory 506 within the computing device 500A stores instructions for executing the functions of the communication module. Simultaneously, the memory 506 within the computing device 500B stores instructions for executing the functions of the processing module.

[0171] It should be understood that the functionality of the computing device 500A shown in FIG7 may also be implemented by multiple computing devices 500. Similarly, the functionality of the computing device 500B may also be implemented by multiple computing devices 500.

[0172] Based on the above embodiments, embodiments of the present application further provide a computer-readable storage medium, which can be any available medium capable of being stored by a computing device or a data storage device such as a data center that includes one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive). The computer-readable storage medium includes instructions that instruct the computing device to execute the data acquisition method of the above method embodiment.

[0173] Based on the above embodiments, embodiments of the present application further provide a computer program product comprising instructions. The computer program product may be software or a program product comprising instructions that can be run on a computing device or stored in any available medium. When the computer program product is run on at least one computing device, the at least one computing device executes the data collection method of the above method embodiments.

[0174] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0175] The present application is described with reference to the flowcharts and / or block diagrams of the methods, apparatus (systems), and computer program products according to the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data acquisition device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data acquisition device produce a device for implementing the functions specified in one or more processes in the flowchart and / or one or more blocks in the block diagram.

[0176] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data acquisition device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0177] These computer program instructions can also be loaded onto a computer or other programmable data acquisition device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0178] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A data collection method, characterized in that: include: Acquire first information, where the first information is used to indicate M parameters selected by a user and at least one value of each of the M parameters, where the M parameters correspond to one object, and M is a positive integer; Determine a questionnaire according to the first information, the questionnaire includes a first set, the first set includes N elements, each of the N elements includes a value of at least one parameter, the at least one parameter belongs to the M parameters, the parameters included in the N elements are the same, and at least one of the same parameters in the N elements has a different value, and N is a positive integer; Second information is obtained according to the questionnaire to complete data collection of the user, wherein the second information is used to indicate an element selected by the user from the N elements.

2. The method according to claim 1, characterized in that Determining a questionnaire according to the first information includes: determining that a first parameter of the M parameters is a first parameter in the first set, and determining that N values ​​of the first parameter are N values ​​of the first parameter in the first set, the N values ​​of the first parameter belonging to at least one value of the first parameter of the M parameters; Determine that a second parameter among the M parameters that satisfies the first condition is the i-th parameter in the first set, and determine that the N values ​​of the second parameter are the N values ​​of the i-th parameter in the first set, the N values ​​of the second parameter belong to at least one value of the second parameter among the M parameters, and i is an integer greater than 1.

3. The method according to claim 2, characterized in that The first condition includes: The difference between the first weight and the second weight is less than a first threshold, the first weight is the weight corresponding to any one of the first parameter to the i-1th parameter in the first set, and the second weight is the weight corresponding to the second parameter; The remaining number of occurrences in the questionnaire is greater than a second threshold, and the remaining number of occurrences is related to a preset total number of occurrences; and, Different from the first parameter to the (i-1)th parameter in the first set.

4. The method according to claim 2, characterized in that The first condition includes: The remaining number of occurrences in the questionnaire is greater than a second threshold, and the remaining number of occurrences is related to a preset total number of occurrences; and, Different from the first parameter to the (i-1)th parameter in the first set.

5. The method according to claim 4, characterized in that Determining that a second parameter among the M parameters that satisfies a first condition is an i-th parameter in the first set includes: When the number of parameters satisfying the first condition among the M parameters is greater than 1, a parameter satisfying the first condition is determined as the second parameter, wherein the second parameter corresponds to a first distance, the first distance is the minimum value of the distances corresponding to the M parameters, and the first distance is the distance between the second parameter and the first parameter to the i-1th parameter in the first set.

6. The method according to claim 5, characterized in that The distance between the second parameter and the first parameter to the i-1th parameter in the first set is the minimum value of the difference between the weight of the second parameter and the weight of the first parameter to the i-1th parameter in the first set.

7. The method according to claim 2, characterized in that The questionnaire further includes a second set, where the second set is a set determined before the first set is determined, and the first condition includes: The second parameter is included in the second set; and, Different from the first parameter to the (i-1)th parameter in the first set.

8. The method according to claim 7, characterized in that Determining that a second parameter among the M parameters that satisfies a first condition is an i-th parameter in the first set includes: When the number of parameters satisfying the first condition among the M parameters is greater than 1, determining one parameter from the parameters satisfying the first condition as the second parameter; Among them, the second parameter corresponds to a second distance, the M parameters also include a third parameter that satisfies the second condition, the third parameter corresponds to a third distance, the sum of the second distance and the third distance is the smallest, the second distance is the distance between the second parameter and the first parameter to the i-1th parameter in the first set, and the third distance is the distance between the third parameter and all parameters in the second set except the second parameter.

9. The method according to claim 8, characterized in that The second condition includes: The remaining number of occurrences in the questionnaire is greater than a second threshold; and, Different from all parameters in the second set except the second parameter.

10. The method according to claim 8 or 9, characterized in that After determining a parameter from the parameters satisfying the first condition as the second parameter, the method further includes: The second parameter in the second set is replaced with the third parameter.

11. The method according to any one of claims 1 to 10, characterized in that: The method further comprises: Determine a third set according to the first information; Determine a first loss corresponding to the third set, where the first loss is used to indicate a difference between prior probabilities corresponding to N values ​​of a fourth parameter in the third set, where the fourth parameter is any one parameter in the third set; A first update operation is performed on the N values ​​of the fourth parameter in the third set to obtain the first set, wherein the N values ​​of the fourth parameter in the first set are different from at least one value of the N values ​​of the fourth parameter in the third set, the first set corresponds to a second loss, the second loss is used to indicate the difference between the prior probabilities corresponding to the N values ​​of the fourth parameter in the first set, and the second loss is less than the first loss.

12. The method according to claim 11, characterized in that Performing a first update operation on the N values ​​of the fourth parameter in the third set to obtain the first set includes: Performing a first update operation on the N values ​​of the fourth parameter in the third set to obtain a fourth set; Determine a first difference corresponding to the fourth set, the first difference being used to indicate a difference between utilities corresponding to N elements in the fourth set, the utility corresponding to any one of the N elements being used to indicate a sum of prior probabilities corresponding to values ​​of all parameters included in the any one element; A second update operation is performed on the N values ​​of the fifth parameter in the fourth set to obtain the first set, wherein the fifth parameter is any parameter in the fourth set, the value of the fifth parameter of the first element in the first set is the value of the fifth parameter of the second element in the fourth set, the value of the fifth parameter of the second element in the first set is the value of the fifth parameter of the first element in the fourth set, the first set corresponds to a second difference, the second difference is used to indicate the difference between the utilities corresponding to the N elements in the first set, and the second difference is smaller than the first difference.

13. The method according to claim 11, characterized in that Performing a second update operation on the N values ​​of the fifth parameter in the fourth set to obtain the first set includes: Performing a second update operation on the N values ​​of the fifth parameter in the fourth set to obtain a fifth set; determining the number of times the value of the fifth parameter of the first element in the fifth set has appeared in the questionnaire; If the number of occurrences is greater than a third threshold, performing a third update operation on the value of the fifth parameter of the first element in the fifth set to obtain the first set; Among them, the value of the fifth parameter of the first element in the first set has appeared the number of times in the questionnaire is less than the third threshold value, the first set corresponds to a third difference, the third difference is used to indicate the difference between the utilities corresponding to the N elements in the first set, the third difference is less than or equal to the second difference, the first set corresponds to a third loss, the third loss is used to indicate the difference between the prior probabilities corresponding to the N values ​​of the fifth parameter in the first set, the fifth set corresponds to a fourth loss, the fourth loss is used to indicate the difference between the prior probabilities corresponding to the N values ​​of the fifth parameter in the fifth set, and the difference between the third loss and the fourth loss is less than the fourth threshold value.

14. A computing device cluster, characterized in that: The computing device cluster includes at least one computing device, each computing device in the at least one computing device includes a processor and a memory; the memory is used to store computer program instructions; The processor calls the computer program instructions stored in the memory to execute the method according to any one of claims 1 to 13.

15. A computer-readable storage medium, characterized in that: The method comprises computer program instructions, and when the computer program instructions are executed by a computing device, the computing device performs the method according to any one of claims 1 to 13.

16. A computer program product comprising instructions, characterized in that When the instructions are executed by a computing device, the computing device is caused to perform the method as claimed in any one of claims 1 to 13.

Images