Method, device, computing equipment and medium for processing item demand

Abstract

The present disclosure provides a method for processing item demand executed by a computing device, comprising: obtaining stored historical data from a data storage platform, the historical data including user behavior data, item demand data, and item attribute data, the user behavior data characterizing the user's behavior with respect to first-category items and second-category items, the item demand data characterizing the attention paid to first-category items and second-category items, and the item attribute data characterizing the attributes of first-category items and second-category items; processing the historical data to obtain multiple evaluation values ​​for first-category items, the multiple evaluation values ​​including a first evaluation value corresponding to the user behavior data, a second evaluation value corresponding to the item demand data, and a third evaluation value corresponding to the item attribute data; determining an overall evaluation value based on the multiple evaluation values ​​and multiple weight values ​​corresponding to the multiple evaluation values. The present disclosure also provides an item demand processing device, a computing device, and a medium.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and more specifically, to a method for processing item demand, an apparatus for processing item demand, a computing device, and a computer-readable storage medium. Background Art

[0002] In the related art, the demand for an item is usually assessed by manual analysis. For example, the survey results are obtained through questionnaire surveys, and the survey results are manually analyzed to assess the demand for an item. The related art method is costly, inefficient, and the assessment results are too dependent on human subjectivity. Summary of the invention

[0003] In view of this, the present disclosure provides an optimized method for processing item demand, an apparatus for processing item demand, a computing device, and a computer-readable storage medium.

[0004] One aspect of the present disclosure provides a method for processing item demand executed by a computing device, comprising: obtaining stored historical data from a data storage platform, wherein the historical data includes user behavior data, item demand data, and item attribute data, wherein the user behavior data characterizes the user's behavior with respect to items of a first category and items of a second category, the item demand data characterizes the attention paid to items of the first category and items of the second category, and the item attribute data characterizes the attributes of items of the first category and items of the second category. Processing the historical data, a plurality of evaluation values ​​for items of the first category are obtained, wherein the plurality of evaluation values ​​include a first evaluation value corresponding to the user behavior data, a second evaluation value corresponding to the item demand data, and a third evaluation value corresponding to the item attribute data. Based on the plurality of evaluation values ​​and a plurality of weight values ​​corresponding to the plurality of evaluation values, an overall evaluation value is determined, wherein the overall evaluation value characterizes the demand for items of the first category.

[0005] According to an embodiment of the present disclosure, the above-mentioned processing of the historical data to obtain multiple evaluation values ​​for the first category of items includes: processing the historical data to obtain N features, N is an integer greater than or equal to 3, determining the time of occurrence, the number of occurrences and the degree of association of each feature of the N features, wherein the degree of association characterizes the association between each feature and the first category of items or the second category of items, and determining the multiple evaluation values ​​based on the time of occurrence, the number of occurrences and the degree of association of each feature.

[0006] According to an embodiment of the present disclosure, the above-mentioned determination of the time of occurrence, the number of occurrences and the degree of association of each feature of the N features includes, for each feature: determining M numbers of occurrences for the feature, wherein the M numbers of occurrences correspond one-to-one to M time periods, each number of occurrences represents the number of times the feature appears in the corresponding time period, and M is an integer greater than or equal to 1; determining M degrees of association for the feature, wherein the M degrees of association correspond one-to-one to the M time periods, each degree of association represents the ratio between the number of occurrences of the feature associated with the first category of items and the total number of occurrences, and the total number of occurrences represents the sum of the number of occurrences of the feature associated with the first category of items and the number of occurrences of the feature associated with the second category of items.

[0007] According to an embodiment of the present disclosure, the above N features include N 1 The first feature, N 2 The second feature, N 3 The third feature, N 1 、N 2 、N 3 are integers greater than or equal to 1, and N 1 +N 2 +N 3 = N. The determining of the plurality of evaluation values ​​based on the time, number and relevance of each feature comprises: for the N 1 For each of the first features, based on the time coefficient associated with the M time periods, the M occurrence times, and the M associations, the first evaluation value is determined. 2 For each of the second features, based on the time coefficient associated with the M time periods, the M number of occurrences, and the M degrees of association, the second evaluation value is determined. 3 For each third feature among the second features, the third evaluation value is determined based on the time coefficient associated with the M time periods, the M occurrence times, and the M association degrees.

[0008] According to an embodiment of the present disclosure, the user behavior data includes at least one of the following: user search data for items in the first category and items in the second category, user comment data for items in the first category and items in the second category, and user complaint data for items in the first category and items in the second category. 1 The first feature includes at least one of the following: a functional feature of the item, a feature of a usage scenario of the item, a feature of a user's emotion toward the item, and a feature of a user's emotion degree toward the item.

[0009] According to an embodiment of the present disclosure, the above-mentioned item demand data includes at least one of the following: item production quantity data, item sales data, and item market demand trend data. 2The second feature includes at least one of the following: a hot item information feature, a periodic item function feature, a non-periodic item function feature, and an item revenue feature.

[0010] According to an embodiment of the present disclosure, the above-mentioned item attribute data includes at least one of the following: item image data, item title data, and item information description data. 3 The third feature includes a feature describing the function of the item.

[0011] Another aspect of the present disclosure provides a device for processing item demand, comprising: an acquisition module, a processing module, and a determination module. The acquisition module is used to acquire the stored historical data from the data storage platform, wherein the historical data includes user behavior data, item demand data, and item attribute data, wherein the user behavior data characterizes the user's behavior toward the first category of items and the second category of items, the item demand data characterizes the attention paid to the first category of items and the second category of items, and the item attribute data characterizes the attributes of the first category of items and the second category of items. The processing module is used to process the historical data to obtain multiple evaluation values ​​for the first category of items, wherein the multiple evaluation values ​​include a first evaluation value corresponding to the user behavior data, a second evaluation value corresponding to the item demand data, and a third evaluation value corresponding to the item attribute data. The determination module is used to determine an overall evaluation value based on the multiple evaluation values ​​and multiple weight values ​​corresponding to the multiple evaluation values, wherein the overall evaluation value characterizes the demand for the first category of items.

[0012] According to an embodiment of the present disclosure, the processing module includes: a processing submodule, a first determining submodule, and a second determining submodule. The processing submodule is used to process the historical data to obtain N features, where N is an integer greater than or equal to 3. The first determining submodule is used to determine the time of occurrence, the number of occurrences, and the degree of association of each feature in the N features, wherein the degree of association characterizes the association between each feature and the first category of items or the second category of items. The second determining submodule is used to determine the multiple evaluation values ​​based on the time of occurrence, the number of occurrences, and the degree of association of each feature.

[0013] According to an embodiment of the present disclosure, the above-mentioned first determination submodule is also used to: for each feature: determine M occurrence times for the feature, wherein the M occurrence times correspond one-to-one to M time periods, each occurrence time represents the number of times the feature appears in the corresponding time period, and M is an integer greater than or equal to 1; determine M association degrees for the feature, wherein the M association degrees correspond one-to-one to the M time periods, each association degree represents the ratio between the number of times the feature is associated with the first category of items and the total number of times, and the total number of times represents the sum of the number of times the feature is associated with the first category of items and the number of times the feature is associated with the second category of items.

[0014] According to an embodiment of the present disclosure, the above N features include N 1 The first feature, N 2 The second feature, N 3 The third feature, N 1 、N 2 、N 3 are integers greater than or equal to 1, and N 1 +N 2 +N 3 = N. The determining of the plurality of evaluation values ​​based on the time, number and relevance of each feature comprises: for the N 1 For each of the first features, based on the time coefficient associated with the M time periods, the M occurrence times, and the M associations, the first evaluation value is determined. 2 For each of the second features, based on the time coefficient associated with the M time periods, the M number of occurrences, and the M degrees of association, the second evaluation value is determined. 3 For each third feature among the second features, the third evaluation value is determined based on the time coefficient associated with the M time periods, the M occurrence times, and the M association degrees.

[0015] According to an embodiment of the present disclosure, the user behavior data includes at least one of the following: user search data for items in the first category and items in the second category, user comment data for items in the first category and items in the second category, and user complaint data for items in the first category and items in the second category. 1 The first feature includes at least one of the following: a functional feature of the item, a feature of a usage scenario of the item, a feature of a user's emotion toward the item, and a feature of a user's emotion degree toward the item.

[0016] According to an embodiment of the present disclosure, the above-mentioned item demand data includes at least one of the following: item production quantity data, item sales data, and item market demand trend data. 2The second feature includes at least one of the following: a hot item information feature, a periodic item function feature, a non-periodic item function feature, and an item revenue feature.

[0017] According to an embodiment of the present disclosure, the above-mentioned item attribute data includes at least one of the following: item image data, item title data, and item information description data. 3 The third feature includes the item function description feature.

[0018] Another aspect of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the above method when executed.

[0019] Another aspect of the present disclosure provides a computer program, which includes computer executable instructions, and the instructions are used to implement the method described above when executed.

[0020] According to the embodiments of the present disclosure, the above-mentioned method or device for processing item demand can at least partially solve the problems in related technologies of high item demand assessment cost, low efficiency, and excessive reliance on human subjectivity in assessment results. Therefore, it is possible to obtain an assessment value for the item by processing user behavior data, item demand data, and item attribute data, thereby facilitating determination of the degree of demand for the item based on the assessment value, thereby achieving a technical effect of making the assessment value more accurate, effective, and objective. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0022] Figure 1 The system architecture of the method and device for processing item demand according to an embodiment of the present disclosure is schematically shown;

[0023] Figure 2 A flowchart schematically shows a method for processing item demand according to an embodiment of the present disclosure;

[0024] Figure 3 A schematic diagram schematically shows a method for processing item demand according to an embodiment of the present disclosure;

[0025] Figure 4 Schematically shows a flow chart for determining multiple evaluation values ​​according to an embodiment of the present disclosure;

[0026] Figure 5 A block diagram schematically shows an apparatus for processing item demand according to an embodiment of the present disclosure;

[0027] Figure 6A block diagram schematically shows a processing module according to an embodiment of the present disclosure; and

[0028] Figure 7 The block diagram of a computer system suitable for evaluating demand for items according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0029] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0030] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0031] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0032] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0033] An embodiment of the present disclosure provides a method for processing item demand executed by a computing device, comprising: obtaining stored historical data from a data storage platform, the historical data comprising user behavior data, item demand data, and item attribute data, the user behavior data characterizing the user's behavior with respect to first-category items and second-category items, the item demand data characterizing the attention paid to first-category items and second-category items, and the item attribute data characterizing the attributes of first-category items and second-category items. Processing the historical data, obtaining multiple evaluation values ​​for first-category items, the multiple evaluation values ​​comprising a first evaluation value corresponding to the user behavior data, a second evaluation value corresponding to the item demand data, and a third evaluation value corresponding to the item attribute data. Based on the multiple evaluation values ​​and multiple weight values ​​corresponding to the multiple evaluation values, an overall evaluation value is determined, and the overall evaluation value characterizes the demand for first-category items.

[0034] Figure 1 The system architecture of the method and device for processing item demand according to the embodiment of the present disclosure is schematically shown. It should be noted that: Figure 1 What is shown is merely an example of a system architecture to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0035] like Figure 1 As shown, the system architecture 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0036] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only examples).

[0037] The terminal devices 101 , 102 , and 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0038] The server 105 may be a server that provides various services, such as a background management server (only an example) that provides support for websites browsed by users using the terminal devices 101, 102, and 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0039] It should be noted that the method for processing item demand provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the device for processing item demand provided in the embodiment of the present disclosure can generally be set in the server 105. The method for processing item demand provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105. Accordingly, the device for processing item demand provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105.

[0040] For example, the historical data of the embodiment of the present disclosure can be received by and stored in the terminal devices 101, 102, and 103, and the historical data can be sent to the server 105 through the terminal devices 101, 102, and 103. The server 105 can process the historical data to obtain multiple evaluation values ​​for the first category of items, and determine the overall evaluation value based on the multiple evaluation values ​​and multiple weight values ​​corresponding to the multiple evaluation values.

[0041] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0042] Figure 2 The flowchart of the method for processing item demand according to the embodiment of the present disclosure is schematically shown.

[0043] like Figure 2 As shown, the method may include, for example, the following operations S210 to S230.

[0044] Figure 3 A schematic diagram schematically shows a method for processing item demand according to an embodiment of the present disclosure.

[0045] The following will be combined Figure 2 and Figure 3 Operation S210 to operation S230 will be described.

[0046] In operation S210, stored historical data is obtained from a data storage platform.

[0047] According to the embodiment of the present disclosure, historical data includes user behavior data, item demand data, and item attribute data. The historical data can be obtained from a data storage platform, which can be a network platform, including but not limited to an e-commerce platform, a Weibo platform, and a public account platform.

[0048] In the disclosed embodiment, the historical data includes relevant data of first category items and second category items. The first category items are items of interest, and the second category items can be used as reference items, and the second category can include multiple categories.

[0049] In one example, the first category may be a "mobile phone" category, and the second category may include a "headphone", a "computer" category, and the like.

[0050] In the embodiments of the present disclosure, the user behavior data characterizes the user's behavior with respect to the first category items and the second category items, and the behavior includes but is not limited to search behavior, comment behavior, and complaint behavior. For example, the user behavior data includes: the user's search data with respect to the first category items and the second category items, the user's comment data with respect to the first category items and the second category items, and the user's complaint data with respect to the first category items and the second category items.

[0051] In the embodiment of the present disclosure, the item demand data characterizes the attention of the first category items and the second category items. The item demand data includes: item production quantity data, item sales data, and item market demand trend data. That is, the production quantity, item sales, and market demand trend characterize the attention of the item.

[0052] In the embodiment of the present disclosure, the item attribute data characterizes the attributes of the first category items and the second category items. The item attribute data includes: item image data, item title data, and item information description data. Among them, the first category items and the second category items referred to in the embodiment of the present disclosure may include commodities. Taking commodities in an e-commerce platform as an example, the item image data includes the cover image of the commodity, the item title data includes the title information of the commodity, and the item information description data includes the detailed information of the commodity.

[0053] In operation S220, the historical data is processed to obtain a plurality of evaluation values ​​for items of the first category.

[0054] The multiple evaluation values ​​include a first evaluation value corresponding to the user behavior data, a second evaluation value corresponding to the item demand data, and a third evaluation value corresponding to the item attribute data.

[0055] The first evaluation value, the second evaluation value, and the third evaluation value are all used to characterize the degree of demand for items in the first category.

[0056] The first evaluation value is an evaluation value obtained based on user behavior data, and the first evaluation value is used to characterize the degree of demand for items in the first category. The larger the first evaluation value is, the higher the degree of demand for items in the first category is at the user level. The second evaluation value is an evaluation value obtained based on item demand data, and the second evaluation value is used to characterize the degree of demand for items in the first category. The larger the second evaluation value is, the higher the degree of demand for items in the first category is at the market level. The third evaluation value is an evaluation value obtained based on item attribute data, and the third evaluation value is used to characterize the degree of demand for items in the first category. The larger the third evaluation value is, the higher the degree of demand for items in the first category is at the item attribute level.

[0057] In operation S230, an overall evaluation value is determined based on the multiple evaluation values ​​and the multiple weight values ​​corresponding to the multiple evaluation values, where the overall evaluation value represents the demand for the items in the first category.

[0058] For example, the first evaluation value corresponds to the first weight, the second evaluation value corresponds to the second weight, and the third evaluation value corresponds to the third weight. Based on each weight, the corresponding evaluation values ​​are weighted and summed to obtain an overall evaluation value, and the demand for the first category of items can be determined based on the overall evaluation value. Among them, the larger the overall evaluation value, the higher the demand for the first category of items at the overall level of users, markets, and items.

[0059] In one embodiment, before the need to promote, produce or sell items of the first category, historical data can be obtained, and the historical data includes relevant data of the items of the first category and relevant data of the items of the second category. Then, the historical data is processed to obtain multiple evaluation values ​​for the items of the first category, and the multiple evaluation values ​​characterize the degree of demand for the items of the first category from different aspects. An overall evaluation value is determined based on multiple evaluation values ​​and corresponding weights, so as to determine whether it is necessary to promote, produce or sell the items of the first category based on the overall evaluation value. For example, before the need to promote, produce or sell a certain "mobile phone", the historical data can be processed to obtain the relevant evaluation of various "mobile phones" by users or the market, so as to determine the degree of demand for a certain "mobile phone" to be promoted, produced or sold based on the relevant evaluation of various "mobile phones" by users or the market, so as to determine whether to continue to promote, produce or sell the certain "mobile phone". Among them, a certain "mobile phone" and various "mobile phones" all belong to the first category of items.

[0060] It can be understood that the embodiments of the present disclosure obtain multiple evaluation values ​​for the first category of items by acquiring and processing historical data, and perform weighted summation of the multiple evaluation values ​​based on corresponding weights to obtain an overall evaluation value, so as to facilitate determining the degree of demand for the first category of items based on the overall evaluation value. Among them, the historical data includes three types of data: user behavior data, item demand data, and item attribute data. The overall evaluation value obtained based on the three types of data more accurately and objectively represents the degree of demand for the first category of items.

[0061] Figure 4 The flowchart of determining multiple evaluation values ​​according to an embodiment of the present disclosure is schematically shown.

[0062] like Figure 4 As shown, the above operation S220 processes the historical data to obtain multiple evaluation values ​​for the first category of items, for example, including operations S221 to S223.

[0063] In operation S221, the historical data is processed to obtain N features, where N is an integer greater than or equal to 3.

[0064] For example, processing user behavior data to obtain N 1 The first feature is processed to obtain N 2 The second feature is processed to obtain N 3 The third characteristics, where N 1 +N 2 +N 3 =N.

[0065] In operation S222, the time when each feature of the N features appears, the number of times it appears, and the degree of association are determined, wherein the degree of association represents the association between each feature and the first category of items or the second category of items.

[0066] For example, taking the example of processing user behavior data to obtain a first feature "battery life", the time when the first feature "battery life" appears is, for example, the time when the user searches for battery life, comments on battery life, or complains about battery life. The number of times the feature "battery life" appears is the number of times it is searched, commented on, or complained by users. The correlation represents whether each time the feature "battery life" appears, it is for items in the first category or for items in the second category. Taking the first category of items being "mobile phones" and the second category of items being "computers" as examples, the correlation represents whether each time the feature "battery life" appears, it represents the battery life of the mobile phone or the battery life of the computer.

[0067] In operation S223, a plurality of evaluation values ​​are determined based on the time at which each feature appears, the number of times it appears, and the degree of association.

[0068] For example, based on N1 The first evaluation value is determined based on the time, number of occurrences and correlation of each first feature in the N first features. 2 The second evaluation value is determined based on the time, number of occurrences and correlation of each second feature in the N second features. 3 The third evaluation value is determined by the time, number of occurrences and correlation of each third feature in the third features.

[0069] According to an embodiment of the present disclosure, the above operation S222 determines the time, number of occurrences and correlation of each feature in the N features, including performing the following operations for each feature:

[0070] First, M occurrence counts for the feature are determined, where the M occurrence counts correspond to M time periods one by one, each occurrence count represents the number of times the feature appears in the corresponding time period, and M is an integer greater than or equal to 1. Each time period is, for example, 1 day, 1 month, 1 year, and so on.

[0071] For example, if each time period is 1 month, when the historical data includes data from the past year, M time periods are 12 months, that is, M is 12. The M occurrence counts are, for example, the number of times the feature appears in each month in the past 12 months, that is, 12 occurrence counts are obtained. For example, the number of times the feature appears in the past 12 months is a 1 times, a 2 times, a 3 times, ..., a 12 times, then M = 12, the number of occurrences is a 1 times, a 2 times, a 3 times, ..., a 12 Among them, the more times the feature appears in each time period, the greater the importance of the feature.

[0072] Then, M association degrees for the feature are determined, where the M association degrees correspond one-to-one to the M time periods, and each association degree represents the ratio between the number of times the feature is associated with the first category of items and the total number of times, and the total number of times represents the sum of the number of times the feature is associated with the first category of items and the number of times the feature is associated with the second category of items.

[0073] Take one month in the past 12 months as an example, take the feature "battery life" as an example, take the first category of items as "mobile phones", and the second category of items as "computers" and "power banks". The total number of times the feature "battery life" appeared in that month is a 1 times, the feature "Endurance" appears a 11 The second is the battery life of the "mobile phone", and a 12The second is the battery life of "computer" or "power bank", where a 1 =a 11 +a 12 . Then the correlation for this month is a 11 / a 1 Similarly, 12 correlations corresponding to the 12 months can be obtained. The greater the correlation, the closer the feature is to the first category of items.

[0074] According to an embodiment of the present disclosure, the above operation S223 regarding determining multiple evaluation values ​​based on the time, number of occurrences and correlation of each feature includes the following steps (1) to (3).

[0075] (1) Refer to the following formula 1, for N 1 For each of the first features, a first evaluation value u is determined based on a time coefficient associated with the M time periods, the M occurrence times, and the M association degrees.

[0076]

[0077] Wherein, i is a time period, and the value range of i is, for example, 1 to 12; is the time coefficient, f u_i Indicates the number of times each first feature appears in the i-th time period, idf u_i Represents the correlation of each first feature in the i-th time period. For each first feature, multiply the time coefficient, the number of occurrences, and the correlation to obtain the evaluation value of each first feature, and N 1 The evaluation values ​​of the first features are summed and calculated to obtain a first evaluation value u.

[0078] (2) Refer to the following formula 2, for N 2 For each of the second features, a second evaluation value m is determined based on a time coefficient associated with the M time periods, the M occurrence times, and the M degrees of association.

[0079]

[0080] Wherein, i is a time period, and the value range of i is, for example, 1 to 12; is the time coefficient, f m_i Indicates the number of times each second feature appears in the i-th time period, idf m_i Represents the relevance of each second feature in the i-th time period. For each second feature, multiply the time coefficient, the number of occurrences, and the relevance to obtain the evaluation value of each second feature, and N 2 The evaluation values ​​of the second features are summed and calculated to obtain a second evaluation value m.

[0081] (3) Refer to the following formula 3, for N 3 For each of the third features, a third evaluation value p is determined based on a time coefficient associated with the M time periods, the M occurrence times, and the M degrees of association.

[0082]

[0083] Wherein, i is a time period, and the value range of i is, for example, 1 to 12; is the time coefficient, f p_i Indicates the number of times each third feature appears in the i-th time period, idf p_i Represents the relevance of each third feature in the i-th time period. For each third feature, multiply the time coefficient, the number of occurrences, and the relevance to obtain the evaluation value of each third feature, and N 3 The evaluation values ​​of the third features are summed and calculated to obtain a third evaluation value p.

[0084] In the embodiments of the present disclosure, for each first feature, each second feature or each third feature, before using the above formula 1, formula 2 or formula 3 for calculation, the importance, confidence or influence of each feature can be measured, and each feature can be assigned a corresponding weight according to the importance, confidence or influence, and the feature value of each feature is weighted by the weight corresponding to the feature to obtain the weighted feature value, and the weighted feature value is input into formula 1, formula 2 or formula 3 for calculation. For example, each first feature is weighted according to the confidence of user behavior, each second feature is weighted according to the influence of market demand, and each third feature is weighted according to the importance and confidence of item attributes.

[0085] Next, referring to the following formula 4, the overall evaluation value is determined based on the first evaluation value u, the second evaluation value m, the third evaluation value p, the first weight α corresponding to the first evaluation value u, the second weight β corresponding to the second evaluation value m, and the third weight γ corresponding to the third evaluation value p.

[0086]

[0087] As mentioned above, the user behavior data includes, for example: user search data for the first category items and the second category items, user comment data for the first category items and the second category items, and user complaint data for the first category items and the second category items. 1 First features. Among them, N 1The first features include, but are not limited to: item function features, item usage scenario features, user emotion features toward the item, and user emotion degree features toward the item.

[0088] In the embodiments of the present disclosure, the user behavior data can be analyzed using text analysis technology to obtain the functional characteristics of the item, or the user behavior data can be mined using text mining technology to obtain the functional characteristics of the item. The functional characteristics of the item include but are not limited to "battery life" and "screen brightness".

[0089] The entity recognition technology in natural language processing is used to process user behavior data to obtain the usage scenario characteristics of the item. The usage scenario characteristics of the item include but are not limited to "poor battery life for long-distance travel" and "screen glare when used at night".

[0090] The user behavior data is processed using emotion recognition technology to obtain the user's emotional characteristics towards the item. The user's emotional characteristics towards the item include but are not limited to positive emotions "the screen is not dazzling when used at night" and negative emotions "the screen is dazzling when used at night".

[0091] The user behavior data is processed using syntactic analysis technology to obtain the user's emotional level characteristics for the item. The user's emotional level characteristics for the item include but are not limited to "not at all glaring" and "very glaring".

[0092] In the embodiments of the present disclosure, N 1 The first features also reflect the user's satisfaction or dissatisfaction with the first or second category items. The user's dissatisfaction can reflect the improvement points and new demands for the items. Before promoting, producing or selling the first category items, you can 1 The first feature represents the improvement points and new demands for improving the item. In addition, the user behavior data more reflects the user's demand for the item. According to the first feature and the first evaluation value, the market demand for the item can be determined more accurately, thereby bringing greater benefits.

[0093] As mentioned above, the item demand data includes: item production quantity data, item sales data, and item market demand trend data. In the embodiment of the present disclosure, N 2 Second features. Among them, N 2 The second characteristics include but are not limited to: hot item information characteristics, periodic item function characteristics, non-periodic item function characteristics, and item benefit characteristics.

[0094] The anomaly detection technology is used to process the item demand data to obtain the hot item information features, which include but are not limited to "full screen". The hot item information features represent the growth point of market demand.

[0095] The item demand data is processed using time series analysis technology to obtain periodic item functional characteristics and non-periodic item functional characteristics. Periodic item functional characteristics include but are not limited to "short battery life in winter" and "long battery life in summer". Non-periodic item functional characteristics include but are not limited to "comfortable screen touch". Among them, periodic item functional characteristics more reflect the influence of objective factors (such as time factors), while non-periodic functional characteristics more reflect the characteristics of the item itself. When using the above formula 2 to calculate the second evaluation value, the above formula 2 can be used to process non-periodic functional characteristics. When processing periodic item functional characteristics, the time coefficient type in formula 2 can be modified so that the modified time coefficient type is a periodic coefficient type. The item revenue characteristics can be determined by the sales volume and total transaction amount GMV of the item, and the item revenue characteristics can characterize the revenue of promoting, producing, and selling the item.

[0096] In the embodiments of the present disclosure, the item demand data reflects the market demand. Therefore, the item demand data reflects more the trend of the industry market and, to a certain extent, reflects the drift trend of user demand points. Relevant hot items can be customized according to the trend of the trend. These hot spots may be caused by certain people or things in China (such as: the same style as XXX celebrities, etc.), or they may be popular products abroad (such as: the former XX country moisture-proof shoes, etc.). Using trends to customize new items can not only solve user needs but also play a role in promoting the effects of items.

[0097] As mentioned above, the item attribute data includes: item image data, item title data, and item information description data. In the embodiment of the present disclosure, N 3 The third characteristic. Among them, N 3 The third feature includes but is not limited to the feature describing the function of the item.

[0098] Use OCR (Optical Character Recognition) recognition technology to identify text in the image, obtain the functional description features (demand points) of the item based on the recognized text based on text mining and parsing technology, and use statistical learning methods to evaluate the importance of the functional description features (demand points) of the item. Use image matching and image text generation technology to analyze the image, obtain the functional description features (core points) of the item that meet user needs, and use high-order network features to evaluate the importance of the functional description features (core points) of the item. Among them, demand points and core points are both functional description features of the item. Demand points reflect the important selling points of the item, and core points reflect the functional highlights of the item.

[0099] Lexical analysis is used to parse item titles, and item function description features (item core points) that meet user needs are extracted. Feature association analysis technology is used to process item information description data to obtain the confidence of item attributes.

[0100] Among them, the importance and confidence of the item function description features can be used as a reference for assigning weights to each third feature. If the importance or confidence of a third feature is higher, the weight assigned to the third feature is larger.

[0101] In the embodiments of the present disclosure, the item attribute data more reflects the differences between competitors. For the items of competitors (items of the first category), the third feature with higher importance or confidence is compared with the features of the own items to be promoted to customize the competitive products related to the competitor's items, so as to develop or expand the market share of the own items.

[0102] The method for processing item demands in the disclosed embodiment has the advantages of controllable cost, data-based, high efficiency, and wide demand coverage. Among them, cost controllability is reflected in the fact that the evaluation method can be reused after it is developed once, and the subsequent maintenance cost is low. Data-based evaluation results now come from data, and the evaluation suggestions for items are well-founded, reducing dependence on human subjective judgment. High efficiency is reflected in high-concurrency data processing and short output result cycle. Wide demand coverage is reflected in the fact that the evaluation method can be set as a periodic task, the cycle can be adjusted according to demand, and it is automatically triggered and generates results to avoid missing related demands.

[0103] The embodiments of the present disclosure consider various types of data, such as user behavior data, item demand data, and item attribute data. User behavior data reflects the user's satisfaction with the item, the improvement points and the degree of desire for the item. Item demand data reflects the drift trend and development trend of market demand, etc. Item attribute data reflects the user's previous needs and the merchant's prediction of the user's current and future needs. The item evaluation value obtained based on user behavior data, item demand data, and item attribute data is more accurate, effective, and objective.

[0104] Figure 5 A block diagram of a device for processing item demand according to an embodiment of the present disclosure is schematically shown.

[0105] like Figure 5 As shown, the device 500 for processing item demand includes, for example, an acquisition module 510 , a processing module 520 , and a determination module 530 .

[0106] The acquisition module 510 may be used to acquire the stored historical data from the data storage platform, wherein the historical data includes user behavior data, item demand data, and item attribute data. The user behavior data characterizes the user's behavior with respect to the first category items and the second category items. The item demand data characterizes the attention paid to the first category items and the second category items. The item attribute data characterizes the attributes of the first category items and the second category items. According to the embodiment of the present disclosure, the acquisition module 510 may, for example, execute the above reference Figure 2 The operation S210 described above will not be described in detail here.

[0107] The processing module 520 can be used to process the historical data to obtain multiple evaluation values ​​for the first category of items, wherein the multiple evaluation values ​​include a first evaluation value corresponding to the user behavior data, a second evaluation value corresponding to the item demand data, and a third evaluation value corresponding to the item attribute data. According to the embodiment of the present disclosure, the processing module 520 can, for example, execute the above reference Figure 2 The operation S220 described above will not be described in detail here.

[0108] The determination module 530 may be used to determine an overall evaluation value based on multiple evaluation values ​​and multiple weight values ​​corresponding to the multiple evaluation values, wherein the overall evaluation value represents the demand for the first category of items. Figure 2 The operation S230 described above will not be described in detail here.

[0109] Figure 6 The block diagram schematically shows a processing module according to an embodiment of the present disclosure.

[0110] like Figure 6 As shown, the processing module 520 includes, for example, a processing submodule 521 , a first determining submodule 522 , and a second determining submodule 523 .

[0111] The processing submodule 521 may be used to process historical data to obtain N features, where N is an integer greater than or equal to 3. According to an embodiment of the present disclosure, the processing submodule 521 may, for example, execute the above reference Figure 4 The operation S221 described above will not be repeated here.

[0112] The first determination submodule 522 may be used to determine the time, number of occurrences, and relevance of each feature in the N features, wherein the relevance represents the association between each feature and the first category item or the second category item. Figure 4 The operation S222 described above will not be repeated here.

[0113] The second determination submodule 523 may be used to determine multiple evaluation values ​​based on the time, number of occurrences, and relevance of each feature. According to an embodiment of the present disclosure, the second determination submodule 523 may, for example, perform the above reference Figure 4 The operation S223 described above will not be repeated here.

[0114] According to an embodiment of the present disclosure, the first determination submodule 522 is also used to: for each feature: determine M occurrence times for the feature, wherein the M occurrence times correspond one-to-one to M time periods, each occurrence time represents the number of times the feature appears in the corresponding time period, and M is an integer greater than or equal to 1; determine M association degrees for the feature, wherein the M association degrees correspond one-to-one to M time periods, each association degree represents the ratio between the number of times the feature is associated with the first category of items and the total number of times, and the total number of times represents the sum of the number of times the feature is associated with the first category of items and the number of times the feature is associated with the second category of items.

[0115] According to an embodiment of the present disclosure, the N features include N 1 The first feature, N 2 The second feature, N 3 The third feature, N 1 、N 2 、N 3 are integers greater than or equal to 1, and N 1 +N 2 +N 3 = N. Based on the time, number of occurrences and relevance of each feature, multiple evaluation values ​​are determined, including: for N 1 For each of the first features, a first evaluation value is determined based on a time coefficient associated with the M time periods, the M occurrence times, and the M associations. 2 For each of the second features, based on the time coefficient associated with the M time periods, the M occurrence times, and the M associations, a second evaluation value is determined. 3 For each third feature among the second features, a third evaluation value is determined based on a time coefficient associated with the M time periods, the M occurrence times, and the M association degrees.

[0116] According to an embodiment of the present disclosure, the user behavior data includes at least one of the following: user search data for first category items and second category items, user comment data for first category items and second category items, and user complaint data for first category items and second category items. 1 The first feature includes at least one of the following: a functional feature of the item, a feature of a usage scenario of the item, a feature of a user's emotion toward the item, and a feature of a user's emotion degree toward the item.

[0117] According to an embodiment of the present disclosure, the item demand data includes at least one of the following: item production quantity data, item sales data, and item market demand trend data. 2 The second feature includes at least one of the following: a hot item information feature, a periodic item function feature, a non-periodic item function feature, and an item revenue feature.

[0118] According to an embodiment of the present disclosure, the item attribute data includes at least one of the following: item image data, item title data, and item information description data. 3 The third feature includes the item function description feature.

[0119] According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits, or at least part of the functions of any one of them can be implemented in one module. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be split into multiple modules for implementation. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be at least partially implemented as hardware circuits, such as field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), systems on chips, systems on substrates, systems on packages, application specific integrated circuits (ASICs), or can be implemented by hardware or firmware in any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware, and firmware, or in any appropriate combination of any of them. Alternatively, according to the embodiments of the present invention, one or more of the modules, submodules, units, and subunits can be at least partially implemented as computer program modules, and when the computer program modules are run, the corresponding functions can be performed.

[0120] For example, any multiple of the first acquisition module 310, the processing module 320, the second acquisition module 330, and the training module 340 can be combined in one module, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the first acquisition module 310, the processing module 320, the second acquisition module 330, and the training module 340 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware, and firmware, or in a suitable combination of any of them. Alternatively, at least one of the first acquisition module 310 , the processing module 320 , the second acquisition module 330 , and the training module 340 may be at least partially implemented as a computer program module, and when the computer program module is executed, a corresponding function may be performed.

[0121] Figure 7 The block diagram of a computer system suitable for evaluating demand for items according to an embodiment of the present disclosure is schematically shown. Figure 7 The computer system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0122] like Figure 7 As shown, the computer system 700 according to the embodiment of the present disclosure includes a processor 701, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 702 or the program loaded from the storage part 706 to the random access memory (RAM) 703. The processor 701 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (for example, an application-specific integrated circuit (ASIC)), etc. The processor 701 may also include an onboard memory for caching purposes. The processor 701 may include a single processing unit or multiple processing units for performing different actions of the method flow according to the embodiment of the present disclosure.

[0123] In RAM 703, various programs and data required for the operation of system 700 are stored. Processor 701, ROM 702 and RAM 703 are connected to each other through bus 704. Processor 701 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 702 and / or RAM 703. It should be noted that the program can also be stored in one or more memories other than ROM 702 and RAM 703. Processor 701 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in one or more memories.

[0124] According to an embodiment of the present disclosure, the system 700 may further include an input / output (I / O) interface 705, which is also connected to the bus 704. The system 700 may further include one or more of the following components connected to the I / O interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage section 708 as needed.

[0125] According to an embodiment of the present disclosure, the method flow according to an embodiment of the present disclosure can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the removable medium 711. When the computer program is executed by the processor 701, the above-mentioned functions defined in the system of the embodiment of the present disclosure are executed. According to an embodiment of the present disclosure, the system, equipment, device, module, unit, etc. described above can be implemented by a computer program module.

[0126] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0127] According to an embodiment of the present disclosure, a computer-readable storage medium may be a non-volatile computer-readable storage medium, such as, but not limited to, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0128] For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include the ROM 702 and / or the RAM 703 described above and / or one or more memories other than the ROM 702 and the RAM 703 .

[0129] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0130] It will be appreciated by those skilled in the art that the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations and / or combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways without departing from the spirit and teachings of the present disclosure. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0131] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A method for processing item demand executed by a computing device, comprising: Acquire stored historical data from a data storage platform, wherein the historical data includes user behavior data, item demand data, and item attribute data, wherein the user behavior data characterizes user behavior with respect to items of the first category and items of the second category, the item demand data characterizes the attention paid to items of the first category and items of the second category, and the item attribute data characterizes the attributes of items of the first category and items of the second category; Processing the historical data to obtain a plurality of evaluation values ​​for the first category of items, wherein the plurality of evaluation values ​​include a first evaluation value corresponding to the user behavior data, a second evaluation value corresponding to the item demand data, and a third evaluation value corresponding to the item attribute data; and Determine an overall evaluation value based on the multiple evaluation values ​​and multiple weight values ​​corresponding to the multiple evaluation values, wherein the overall evaluation value represents the demand for the first category of items; The processing of the historical data to obtain a plurality of evaluation values ​​for the first category of items includes: Processing the historical data to obtain N features, where N is an integer greater than or equal to 3; Determining the time, number of occurrences, and relevance of each of the N features, wherein the relevance represents the relevance of each feature to the first category of items or the second category of items; and Determine the multiple evaluation values ​​based on the time, number and relevance of each feature; The N features include N1 first features, N2 second features, and N3 third features, N1, N2, and N3 are all integers greater than or equal to 1, and N1+N2+N3=N; The N1 first features include at least one of the following: a functional feature of an item, a feature of a usage scenario of an item, a feature of a user's emotion toward an item, and a feature of a user's degree of emotion toward an item; The N2 second features include at least one of the following: hot item information feature, periodic item function feature, non-periodic item function feature, and item revenue feature; The N3 third features include item function description features.

2. The method according to claim 1, wherein: Determining the time, number of occurrences and relevance of each feature in the N features includes, for each feature: Determine M occurrence counts for the feature, wherein the M occurrence counts correspond to M time periods one by one, each occurrence count represents the number of times the feature appears in the corresponding time period, and M is an integer greater than or equal to 1; and Determine M degrees of association for the feature, wherein the M degrees of association correspond one-to-one to the M time periods, and each degree of association represents a ratio between a number of times the feature is associated with items of the first category and a total number of times, and the total number of times represents a sum of a number of times the feature is associated with items of the first category and a number of times the feature is associated with items of the second category.

3. The method according to claim 2, wherein: Determining the multiple evaluation values ​​based on the time, number of occurrences and relevance of each feature includes: For each of the N1 first features, based on a time coefficient associated with the M time periods, the M occurrence times, and the M association degrees, determining the first evaluation value; For each of the N2 second features, based on a time coefficient associated with the M time periods, the M occurrence times, and the M association degrees, determining the second evaluation value; and For each third feature of the N3 second features, the third evaluation value is determined based on the time coefficient associated with the M time periods, the M occurrence times, and the M association degrees.

4. The method according to claim 3, wherein: The user behavior data includes at least one of the following: user search data for first category items and second category items, user review data for first category items and second category items, and user complaint data for first category items and second category items.

5. The method according to claim 3, wherein: The item demand data includes at least one of the following: item production quantity data, item sales data, and item market demand trend data.

6. The method according to claim 3, wherein: The item attribute data includes at least one of the following: item picture data, item title data, and item information description data.

7. A device for processing item demand, comprising: an acquisition module, configured to acquire stored historical data from a data storage platform, wherein the historical data includes user behavior data, item demand data, and item attribute data, wherein the user behavior data characterizes the user's behavior with respect to items of the first category and items of the second category, the item demand data characterizes the attention paid to items of the first category and items of the second category, and the item attribute data characterizes the attributes of items of the first category and items of the second category; a processing module, configured to process the historical data to obtain a plurality of evaluation values ​​for the first category of items, wherein the plurality of evaluation values ​​include a first evaluation value corresponding to the user behavior data, a second evaluation value corresponding to the item demand data, and a third evaluation value corresponding to the item attribute data; and a determination module, configured to determine an overall evaluation value based on the multiple evaluation values ​​and multiple weight values ​​corresponding to the multiple evaluation values, wherein the overall evaluation value represents the demand for the first category of items; The processing of the historical data to obtain a plurality of evaluation values ​​for the first category of items includes: Processing the historical data to obtain N features, where N is an integer greater than or equal to 3; Determining the time, number of occurrences, and relevance of each of the N features, wherein the relevance represents the relevance of each feature to the first category of items or the second category of items; and Determine the multiple evaluation values ​​based on the time, number and relevance of each feature; The N features include N1 first features, N2 second features, and N3 third features, N1, N2, and N3 are all integers greater than or equal to 1, and N1+N2+N3=N; The N1 first features include at least one of the following: a functional feature of an item, a feature of a usage scenario of an item, a feature of a user's emotion toward an item, and a feature of a user's degree of emotion toward an item; The N2 second features include at least one of the following: hot item information feature, periodic item function feature, non-periodic item function feature, and item revenue feature; The N3 third features include item function description features.

8. A computing device comprising: one or more processors; a memory for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing computer-executable instructions, wherein the instructions are used to implement the method according to any one of claims 1 to 6 when executed.

Images