CN110532540B

CN110532540B - Method, system, computer system and readable storage medium for determining user preferences

Info

Publication number: CN110532540B
Application number: CN201810513797.3A
Authority: CN
Inventors: 刘继宇; 邵荣防; 郝晖; 谢群群
Original assignee: Beijing Jingdong Century Trading Co Ltd; Beijing Jingdong Shangke Information Technology Co Ltd
Current assignee: Beijing Jingdong Century Trading Co Ltd; Beijing Jingdong Shangke Information Technology Co Ltd
Priority date: 2018-05-25
Filing date: 2018-05-25
Publication date: 2024-04-09
Anticipated expiration: 2038-05-25
Also published as: CN110532540A

Abstract

The present disclosure provides a method of determining user preferences, comprising: acquiring first text information, wherein the first text information comprises search information input by a user and/or description information of an object operated by the user; acquiring second text information, wherein the second text information comprises one or more sub-text information, and different sub-text information comprises description information of each object in different object categories; determining a first similarity of each sub-text information in the first text information and the second text information; and determining a preference of the user according to the first similarity. The present disclosure also provides a system for determining user preferences, a computer system, and a computer-readable storage medium.

Description

Method, system, computer system and readable storage medium for determining user preferences

Technical Field

The present disclosure relates to the field of internet technology, and in particular, to a method, a system, a computer system, and a computer-readable storage medium for determining user preferences.

Background

Currently, existing user interest discrimination models do not provide good service. Particularly, in the aspect of judging the preference of the user to the commodity category, the conventional judging model cannot accurately judge the user interest due to single judging standard, and further cannot accurately adjust the enterprise service by utilizing the judged user interest, so that better support cannot be provided for the enterprise service.

For the above-mentioned problems in the related art, no effective solution has been proposed yet.

Disclosure of Invention

In view of the foregoing, the present disclosure provides a method and system for determining user preferences.

One aspect of the present disclosure provides a method of determining user preferences, comprising: acquiring first text information, wherein the first text information comprises search information input by a user and/or description information of an object operated by the user; obtaining second text information, wherein the second text information comprises one or more sub-text information, and different sub-text information comprises description information of each object in different object categories; determining a first similarity of each sub-text message in the first text message and the second text message; and determining the preference of the user according to the first similarity.

According to an embodiment of the present disclosure, determining a first similarity of each sub-text information in the first text information and the second text information includes: extracting a first feature word from the first text information; extracting corresponding second feature words from each piece of sub-text information; and determining a first similarity between the first text information and each sub-text information according to the first feature word and the corresponding second feature word.

According to an embodiment of the present disclosure, determining a first similarity between the first text information and each of the sub-text information according to the first feature word and the second feature word includes: determining the first same feature words in the first feature words and the corresponding second feature words; counting the number of the first feature words of the first same feature words; determining the number of the second feature words corresponding to the second feature words; and determining a first similarity between the first text information and each sub-text information according to the first feature word number and the second feature word number.

According to an embodiment of the present disclosure, determining a first similarity between the first text information and each of the sub-text information according to the first feature word and the second feature word includes: acquiring a first mapping relation, wherein the first mapping relation comprises at least one mapping relation, and each mapping relation comprises a history first feature word extracted from history first text information, a history second feature word extracted from history second text information and history similarity of the history first feature word and the history second feature word; determining mapping relations corresponding to the first feature words and the second feature words from the at least one mapping relation; determining a second similarity between the first feature word and the second feature word according to the mapping relation; and determining a first similarity between the first text information and each sub-text information according to the second similarity.

According to an embodiment of the present disclosure, determining a first similarity between the first text information and each of the sub-text information according to the first feature word and the second feature word includes: determining a second identical feature word in the first feature word and the corresponding second feature word; counting the number of third feature words of the second same feature words; determining the number of fourth feature words of the corresponding second feature words; and determining a first similarity between the first text information and each sub-text information according to the second similarity, the third feature word number and the fourth feature word number.

According to an embodiment of the present disclosure, the method for determining a user preference further includes: acquiring a first operation frequency of each object in the objects operated by the user; determining object categories to which each object belongs in the objects operated by the user; counting second operation times corresponding to object categories to which the objects belong according to the first operation times; and determining the preference of the user according to the first similarity, the first operation times and the second operation times.

According to an embodiment of the present disclosure, determining the preference of the user according to the first similarity, the first operation number, and the second operation number includes: determining a first preset weight of the first similarity; calculating the first operation times and the second operation times to obtain a first numerical value; determining a second preset weight of the first value; and determining the preference of the user according to the first similarity, the first preset weight, the first numerical value and the second preset weight.

Another aspect of the present disclosure provides a system for determining user preferences, comprising: the first acquisition module is used for acquiring first text information, wherein the first text information comprises search information input by a user and/or description information of an object operated by the user; the second acquisition module is used for acquiring second text information, wherein the second text information comprises one or more pieces of sub-text information, and different pieces of sub-text information comprise description information of each object in different object categories; the first determining module is used for determining a first similarity of each sub-text information in the first text information and the second text information; and a second determining module, configured to determine a preference of the user according to the first similarity.

According to an embodiment of the present disclosure, the first determining module includes: a first extraction unit configured to extract a first feature word from the first text information; a second extraction unit for extracting a corresponding second feature word from each sub-text information; and a first determining unit configured to determine a first similarity between the first text information and each of the sub-text information according to the first feature word and the corresponding second feature word.

According to an embodiment of the present disclosure, the first determining unit is further configured to: determining the first same feature words in the first feature words and the corresponding second feature words; counting the number of the first feature words of the first same feature words; determining the number of the second feature words corresponding to the second feature words; and determining a first similarity between the first text information and each sub-text information according to the first feature word number and the second feature word number.

According to an embodiment of the present disclosure, the first determining unit is further configured to: acquiring a first mapping relation, wherein the first mapping relation comprises at least one mapping relation, and each mapping relation comprises a history first feature word extracted from history first text information, a history second feature word extracted from history second text information and history similarity of the history first feature word and the history second feature word; determining mapping relations corresponding to the first feature words and the second feature words from the at least one mapping relation; determining a second similarity between the first feature word and the second feature word according to the mapping relation; and determining a first similarity between the first text information and each sub-text information according to the second similarity.

According to an embodiment of the present disclosure, the first determining unit is further configured to: determining a second identical feature word in the first feature word and the corresponding second feature word; determining the number of third feature words of the second same feature word; determining the number of fourth feature words of the corresponding second feature words; and determining a first similarity between the first text information and each sub-text information according to the second similarity, the third feature word number and the fourth feature word number.

According to an embodiment of the present disclosure, the above system for determining user preference further includes: a third obtaining module, configured to obtain a first operation number of each object in the objects operated by the user; a third determining module, configured to determine an object category to which each object belongs in the objects operated by the user; the statistics module is used for counting second operation times corresponding to object categories to which the objects belong according to the first operation times; and a fourth determining module configured to determine a preference of the user according to the first similarity, the first operation number, and the second operation number.

According to an embodiment of the present disclosure, the fourth determination module includes: a second determining unit, configured to determine a first preset weight of the first similarity; the calculating unit is used for calculating the first operation times and the second operation times to obtain a first numerical value; a third determining unit, configured to determine a second preset weight of the first value; and a fourth determining unit configured to determine a preference of the user according to the first similarity, the first preset weight, the first numerical value, and the second preset weight.

Another aspect of the present disclosure provides a computer system comprising: one or more processors; a computer readable storage medium storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of determining user preferences as recited in any of the preceding claims.

Another aspect of the present disclosure provides a computer-readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to implement a method of determining user preferences as described in any of the above.

Drawings

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

FIG. 1 schematically illustrates a system architecture of a method and system for determining user preferences in accordance with an embodiment of the present disclosure;

FIG. 2 schematically illustrates a flow chart of a method of determining user preferences in accordance with an embodiment of the present disclosure;

FIG. 3A schematically illustrates a flowchart of determining a first similarity according to an embodiment of the present disclosure;

FIG. 3B schematically illustrates a flowchart for determining a first similarity according to another embodiment of the present disclosure;

FIG. 3C schematically illustrates a flowchart for determining a first similarity according to another embodiment of the present disclosure;

FIG. 3D schematically illustrates a flowchart for determining a first similarity according to another embodiment of the present disclosure;

FIG. 3E schematically illustrates a flowchart of a method of determining user preferences according to another embodiment of the present disclosure;

FIG. 3F schematically illustrates a flowchart of a method of determining user preferences according to another embodiment of the present disclosure;

FIG. 3G schematically illustrates a system framework for determining user preferences in accordance with an embodiment of the present disclosure;

FIG. 3H schematically illustrates a flowchart for determining a first similarity according to another embodiment of the present disclosure;

FIG. 4 schematically illustrates a block diagram of a system for determining user preferences in accordance with an embodiment of the present disclosure;

FIG. 5A schematically illustrates a block diagram of a first determination module according to an embodiment of the disclosure;

FIG. 5B schematically illustrates a block diagram of a system for determining user preferences in accordance with another embodiment of the present disclosure;

FIG. 5C schematically illustrates a block diagram of a fourth determination module according to an embodiment of the disclosure; and

fig. 6 schematically illustrates a block diagram of a computer system adapted for a method of determining user preferences in accordance with an embodiment of the present disclosure.

Detailed Description

Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is only exemplary and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. In addition, in the following description, descriptions of well-known structures and techniques are omitted so as not to unnecessarily obscure the concepts of the present disclosure.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and/or the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.

All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It should be noted that the terms used herein should be construed to have meanings consistent with the context of the present specification and should not be construed in an idealized or overly formal manner.

Where expressions like at least one of "A, B and C, etc. are used, the expressions should generally be interpreted in accordance with the meaning as commonly understood by those skilled in the art (e.g.," a system having at least one of A, B and C "shall include, but not be limited to, a system having a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.). Where a formulation similar to at least one of "A, B or C, etc." is used, in general such a formulation should be interpreted in accordance with the ordinary understanding of one skilled in the art (e.g. "a system with at least one of A, B or C" would include but not be limited to systems with a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.). It should also be appreciated by those skilled in the art that virtually any disjunctive word and/or phrase presenting two or more alternative items, whether in the description, claims, or drawings, should be understood to contemplate the possibilities of including one of the items, either of the items, or both. For example, the phrase "a or B" should be understood to include the possibility of "a" or "B", or "a and B".

Embodiments of the present disclosure provide a method of determining user preferences, comprising: acquiring first text information, wherein the first text information comprises search information input by a user and/or description information of an object operated by the user; acquiring second text information, wherein the second text information comprises one or more sub-text information, and different sub-text information comprises description information of each object in different object categories; determining a first similarity of each sub-text information in the first text information and the second text information; and determining a preference of the user according to the first similarity.

Fig. 1 schematically illustrates a system architecture of a method and system of determining user preferences according to an embodiment of the present disclosure. It should be noted that fig. 1 is only an example of a system architecture to which embodiments of the present disclosure may be applied to assist those skilled in the art in understanding the technical content of the present disclosure, but does not mean that embodiments of the present disclosure may not be used in other devices, systems, environments, or scenarios.

As shown in fig. 1, a 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 as a medium to provide 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 fiber optic cables, among others.

The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. Various communication client applications, such as shopping class applications, web browser applications, search class applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only) may be installed on the terminal devices 101, 102, 103.

The terminal devices 101, 102, 103 may be a variety of electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablets, laptop and desktop computers, and the like.

The server 105 may be a server providing various services, such as a background management server (by way of example only) providing support for websites browsed by users using the terminal devices 101, 102, 103. The background management server may analyze and process the received data such as the user request, and feed back the processing result (e.g., the web page, information, or data obtained or generated according to the user request) to the terminal device.

It should be noted that the method for determining user preference provided by the embodiments of the present disclosure may be generally performed by the server 105. Accordingly, the system for determining user preferences provided by embodiments of the present disclosure may be generally disposed in server 105. The method of determining user preferences provided by the embodiments of the present disclosure may also be performed by a server or cluster of servers other than the server 105 and capable of communicating with the terminal devices 101, 102, 103 and/or the server 105. Accordingly, the system for determining user preferences provided by the embodiments of the present disclosure may also be provided in a server or server cluster other than the server 105 and capable of communicating with the terminal devices 101, 102, 103 and/or the server 105.

It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

Fig. 2 schematically illustrates a flow chart of a method of determining user preferences in accordance with an embodiment of the present disclosure.

As shown in fig. 2, the method of determining user preferences may include operations S201 to S204, wherein:

in operation S201, first text information is acquired, wherein the first text information includes search information input by a user and/or description information of an object operated by the user.

In operation S202, second text information is acquired, where the second text information includes one or more sub-text information, and different sub-text information includes description information of each object in different object categories.

In operation S203, a first similarity of each sub-text information in the first text information and the second text information is determined.

In operation S204, a preference of the user is determined according to the first similarity.

In embodiments of the present disclosure, the operations may include, but are not limited to, clicking, dragging, etc., where the operations may include operations through a touch screen, as well as remote sensing operations. The object may include merchandise, goods, etc., and the description information of the object may include the name of the object, for example, red inside booster sports shoes. The user may represent a user account, a user ID, etc. The search information input by the user may be search information input by any person, animal, through a user account, a user ID, or the like. Accordingly, the object operated by the user can also be any object operated by any person or animal through a user account number, a user ID and the like.

According to an embodiment of the present disclosure, the first text information may include search information input by a user and/or description information of an object operated by the user for a certain period of time. The second text information may include one or more sub-text information, different sub-text information including descriptive information for each object in different object categories.

According to the embodiment of the disclosure, the first similarity of each sub-text information in the first text information and the second text information can be determined, and the preference of the user is determined according to the first similarity. For example, the object category corresponding to the first similarity of the maximum value may be determined as the object category that is most preferred by the user, and the object category corresponding to the first similarity of the minimum value may be determined as the object category that is least preferred by the user.

Unlike embodiments of the present disclosure, the prior art only uses a priori knowledge, such as historical clicks, and uses a single rule to determine the user's preferences, it is difficult to mine the interests implied by the user.

According to the embodiment of the disclosure, the first text information and the second text information are obtained, wherein the first text information comprises search information input by a user and/or description information of an object operated by the user, the second text information comprises one or more sub-text information, different sub-text information comprises description information of each object in different object categories, then the first similarity of each sub-text information in the first text information and the second text information is determined, the preference of the user is determined according to the first similarity, the defect that the existing discrimination model cannot accurately discriminate the interest of the user due to single discrimination standard is overcome, the effect of improving the accuracy of determining the preference of the user is achieved, enterprise services can be accurately regulated according to the determined preference of the user, and better support is provided for the enterprise services.

The method illustrated in fig. 2 is further described below with reference to fig. 3A-3H in conjunction with the exemplary embodiment.

Fig. 3A schematically illustrates a flowchart of determining a first similarity according to an embodiment of the present disclosure.

As shown in fig. 3A, determining the first similarity of each sub-text information in the first text information and the second text information may include S301 to S303, where:

in operation S301, a first feature word is extracted from first text information.

In operation S302, a corresponding second feature word is extracted from each sub-text information.

In operation S303, a first similarity between the first text information and each sub-text information is determined according to the first feature word and the corresponding second feature word.

In the embodiment of the disclosure, the acquired first text information may be subjected to word segmentation, for example, the first text information may be subjected to word segmentation by using barker segmentation. After word segmentation, the 'mock' and other auxiliary words can be filtered, and punctuation marks can be filtered. Further, the method of chi-square test can be utilized to select the characteristics of the rest words.

Specifically, the words after word segmentation and filtering may be scored and ranked by using a chi-square test method, and a preset number of words after word segmentation and filtering with a higher score are selected as the first feature words, for example, the first 100000 words after word segmentation and filtering with a higher score are used as the first feature words. The formula of chi-square test is as follows:

Wherein f ₀ Represents the observed probability, i.e., the probability that for any word that is segmented and filtered, that word appears in all the segmented and filtered words. f (f) _e The expected probability is represented, i.e., the probability that the word appears in the word that corresponds to all users and that has been segmented and filtered. X is X ² Representing the score of the word.

According to the embodiment of the present disclosure, a corresponding second feature word may be extracted from each sub-text information in the second text information, taking a similar operation to the extraction of the first feature word. The method comprises the steps of carrying out word segmentation and filtering on the sub-text information corresponding to each object category, and further carrying out feature selection on the rest words by using a chi-square test method. For example, the first 1000 words with higher scores can be used as the second feature words corresponding to the sub-text information after word segmentation and filtering.

According to the embodiment of the disclosure, the first similarity between the first text information and each piece of sub-text information is determined according to the extracted first feature words and the corresponding second feature words, so that the effect of determining the accuracy of user preference can be improved, and better support can be provided for enterprise business.

Fig. 3B schematically illustrates a flow chart of determining a first similarity according to another embodiment of the present disclosure.

As shown in fig. 3B, determining the first similarity of the first text information and each sub-text information according to the first feature word and the second feature word may include operations S401 to S404, wherein:

in operation S401, a first identical feature word of the first feature word and the corresponding second feature word is determined.

In operation S402, a first feature word number of first identical feature words is counted.

In operation S403, a second feature word number of the second feature word is determined.

In operation S404, a first similarity between the first text information and each sub-text information is determined according to the first feature word number and the second feature word number.

In an embodiment of the present disclosure, determining the first identical feature words in the first feature words and the corresponding second feature words may include determining the first identical feature words of the first feature words and the second feature words corresponding to the respective object categories, obtaining a plurality of first identical feature words, and counting the number of the first feature words of each first identical feature word.

According to an embodiment of the present disclosure, determining the first similarity between the first text information and each sub-text information according to the first feature word number and the second feature word number may include calculating the first feature word number and the second feature word number to obtain a second value, and determining the first similarity between the first text information and each sub-text information according to the second value.

According to an embodiment of the present disclosure, calculating the first feature word number and the second feature word number may be to calculate a difference or a ratio between the first feature word number and the second feature word number, and determine a first similarity between the first text information and the corresponding sub-text information using the difference or the ratio as the second value.

For example, the keyword represents a first feature word, i.e., the first 100000 words with higher scores, the TOP1000 represents a corresponding second feature word, i.e., the first 1000 words with higher scores, and the first similarity between the first text information and each sub-text information can be determined according to the formula d= (keyword n TOP 1000)/1000. Specifically, the first identical feature words in the first feature words and the corresponding second feature words can be determined, the first feature word number of the first identical feature words is counted, and the ratio of the first feature word number to 1000 (namely, the second feature word number) is calculated, so that the ratio can be used as the first similarity of the first text information and the corresponding sub-text information.

According to the embodiment of the disclosure, the first similarity of the first text information and each piece of sub-text information is determined according to the coincidence ratio of the first feature word and the corresponding second feature word, so that the effect of determining the accuracy of user preference can be improved, and better support can be provided for enterprise business.

Fig. 3C schematically illustrates a flow chart of determining a first similarity according to another embodiment of the present disclosure.

As shown in fig. 3C, determining the first similarity between the first text information and each of the sub-text information according to the first feature word and the second feature word may include operations S501 to S504, wherein:

in operation S501, a first mapping relationship is obtained, where the first mapping relationship includes at least one mapping relationship, and each mapping relationship includes a historical first feature word extracted from the historical first text information, a historical second feature word extracted from the historical second text information, and a historical similarity of the historical first feature word and the historical second feature word.

In operation S502, a mapping relationship corresponding to both the first feature word and the second feature word is determined from at least one mapping relationship.

In operation S503, a second similarity between the first feature word and the second feature word is determined according to the mapping relation.

In operation S504, a first similarity between the first text information and each sub-text information is determined according to the second similarity.

In an embodiment of the present disclosure, the second feature words may include a plurality of sets of second feature words, each set of second feature words corresponding to one of the object categories. For any one group of second feature words, acquiring the first mapping relationship may include: determining an object category corresponding to the second feature word, determining at least one mapping relation corresponding to the object category, and acquiring the at least one mapping relation.

According to an embodiment of the present disclosure, determining, from at least one mapping relationship, a mapping relationship corresponding to both the first feature word and the second feature word may include: determining a historical first feature word and a historical second feature word corresponding to both the first feature word and the second feature word; and taking the mapping relation corresponding to the historical first feature word and the historical second feature word as the mapping relation corresponding to the first feature word and the second feature word.

According to the embodiment of the disclosure, the determined historical similarity included in the mapping relationship corresponding to both the first feature word and the second feature word may be used as the second similarity, and the first similarity may be determined according to the second similarity, for example, the second similarity may be used as the first similarity.

According to embodiments of the present disclosure, a classification model may also be determined from the first mapping relationship, which may be used to determine a second similarity from the first feature word and the second feature word entered therein.

Specifically, search information input by a user in history and/or description information (also called history first text information) of an object operated by the user can be obtained, and feature words are extracted to obtain history first feature words; descriptive information (also called historical second text information) of each object in each object category in the history can be extracted, and feature words are extracted to obtain historical second feature words. If the historical first feature word contains the historical second feature word, the matrix element is 1, if the first feature word does not contain the historical second feature word, the matrix element is 0, a binary matrix consisting of 0 and 1 is constructed according to the method, and the binary matrix is used as a training set to train a naive Bayesian model so as to obtain the classification model. Further, the first feature word and the second feature word may be input into the classification model, and then the second similarity Score may be output using the classification model.

According to the embodiment of the disclosure, the second similarity is determined by using the historical similarity, and the first similarity of the first text information and each piece of sub-text information is determined according to the second similarity, so that the operation amount of a system can be reduced, and the operation speed of the system can be increased.

Fig. 3D schematically illustrates a flowchart of determining a first similarity according to another embodiment of the present disclosure.

As shown in fig. 3D, determining the first similarity between the first text information and each of the sub-text information according to the first feature word and the second feature word may include operations S601 to S604, wherein:

in operation S601, a second identical feature word in the first feature word and the corresponding second feature word is determined.

In operation S602, the number of third feature words of the second identical feature words is counted.

In operation S603, a fourth number of feature words of the corresponding second feature words is determined.

In operation S604, a first similarity between the first text information and each sub-text information is determined according to the second similarity, the third feature word number, and the fourth feature word number.

In an embodiment of the present disclosure, determining the first similarity of the first text information and each sub-text information according to the second similarity, the third feature word number, and the fourth feature word number may include: calculating the third characteristic word number and the fourth characteristic word number to obtain a second numerical value; determining a third preset weight of the second numerical value; determining a fourth preset weight of the second similarity; and determining the first similarity between the first text information and each piece of sub-text information according to the second numerical value, the third preset weight, the second similarity and the fourth preset weight.

According to an embodiment of the present disclosure, calculating the third feature word number and the fourth feature word number may be to find a difference or a ratio of the two, and take the difference or the ratio as the second value.

Specifically, the first similarity may be determined according to the following formula:

Score _j ＝0.3×d+0.7×Score

wherein Score _j The first similarity is represented, d represents the coincidence degree with various meshes, score represents the second similarity output by the classification Model, and the third preset weight 0.3 and the fourth preset weight 0.7 are optimal values obtained through experimental judgment and experimental verification.

According to the embodiment of the disclosure, the first similarity between the first text information and each sub-text information is determined by utilizing the coincidence degree of the first feature word and the second feature word and the historical similarity, so that the accuracy of determining the first similarity can be further improved.

Fig. 3E schematically illustrates a flow chart of a method of determining user preferences according to another embodiment of the present disclosure.

As shown in fig. 3E, the method of determining user preferences may further include operations S701 to S704, wherein:

in operation S701, a first number of operations of each of the objects operated by the user is acquired.

In operation S702, an object category to which each object belongs among objects operated by a user is determined.

In operation S703, according to the first operation times, the second operation times corresponding to the object categories to which each object belongs are counted.

In operation S704, a preference of the user is determined according to the first similarity, the first operation number and the second operation number.

In an embodiment of the present disclosure, according to the first operation times, counting the second operation times corresponding to the object categories to which each object belongs includes: and adding the first operation times corresponding to the objects belonging to the same object category in each object to obtain the second operation times.

According to the embodiment of the disclosure, the user preference is determined according to the first similarity, the first operation times and the second operation times, so that the accuracy of determining the user preference can be further improved.

Fig. 3F schematically illustrates a flow chart of a method of determining user preferences according to another embodiment of the present disclosure.

As shown in fig. 3F, determining the preference of the user according to the first similarity, the first operation number, and the second operation number may include operations S801 to S804, wherein:

in operation S801, a first preset weight of the first similarity is determined.

In operation S802, a first number of operations and a second number of operations are calculated to obtain a first value.

In operation S803, a second preset weight of the first value is determined.

In operation S804, the preference of the user is determined according to the first similarity, the first preset weight, the first numerical value, and the second preset weight.

In an embodiment of the present disclosure, the first operation number and the second operation number are calculated, and obtaining the first value may be obtaining a difference or a ratio of the first operation number and the second operation number. For example, the first operation number and the second operation number may be calculated according to the following formula:

wherein, click_times _i For a user operation, e.g. clicking on the number of i-th object category, also called second operation number,score for all user operations, e.g. number of clicks, also called first operation _i Is a first value.

According to an embodiment of the present disclosure, the preference of the user may be determined according to a first similarity, a first preset weight, a first numerical value, and a second preset weight. Specifically, the user's preference may be determined according to the following formula:

S＝0.4×Score _i +0.6×Score _j

where S represents the user' S preference, score _i Score of the first value _j Representing the first similarity, the first preset weight 0.4 and the second preset weight 0.6 are optimal values determined empirically and verified through experiments, although the embodiment of the present disclosure determines the preference of the user and the determined weight is not limited thereto.

According to the embodiment of the disclosure, when the preference of the user category is calculated, not only the similarity between the search information input by the user and/or the description information of the object operated by the user and the description information of each object in the object category is calculated, but also the operation behaviors of the user such as clicking behaviors are considered, so that the accuracy of determining the preference of the user is further improved. Meanwhile, user portraits are enriched, the business of an electronic commerce can be better supported, and in addition, when a user searches an object, the user has a great supporting effect on a recall object candidate set.

Fig. 3G schematically illustrates a system framework for determining user preferences in accordance with an embodiment of the present disclosure.

As shown in fig. 3G, embodiments of the present disclosure relate to main modules of searching, clicking on log data, data cleansing, category preference calculation, and integrating category preferences, where the category preference calculation includes: user click behavior category preference analysis (abbreviated as user click behavior) and text similarity analysis (abbreviated as text similarity). The whole flow adopts a distributed computing framework, so that the mass data processing capacity and the timeliness of data computing are improved. And updating the model in a periodic iterative manner.

According to the embodiment of the disclosure, for the data cleaning portion, data without a user ID may be removed, and/or data from which a source cannot be determined may be removed, and/or blacklist IP data may be removed, so that cleaned data, such as first text information, may be obtained.

Fig. 3H schematically illustrates a flow chart of determining a first similarity according to another embodiment of the present disclosure.

As shown in fig. 3H, the specific operation of the text similarity analysis is to obtain the first text information and the second text information through operation S901, for example, to obtain the first text information as a search term input by the user, and a name of a commodity clicked by the user. The first text information and the second text information are subjected to word segmentation processing and stop word processing (also referred to as filtering) through operation S902, a feature word with higher score is selected to obtain a first feature word and a second feature word through operation S903, then a second similarity of the first feature word and the second feature word is obtained through operation S904 by using a mapping relation, or the coincidence degree (also referred to as a first numerical value) of the first feature word and the second feature word is calculated through operation S905, and then the first similarity, namely the comprehensive category score, is determined through operation S906 according to the first numerical value and the second similarity.

Unlike embodiments of the present disclosure, the prior art determines that user preferences are structured as stand-alone computing schemes, limited by stand-alone performance, limited data volume processing, and unusable in the face of mass data processing. Meanwhile, the prior art lacks support for exclusive business of electronic commerce, such as predicting user intention and determining commodity ordering, and is not suitable for commodity class and order preference of electronic commerce. In addition, the prior art scheme is time-efficient because the iteration cannot be well updated due to the long-time use of fixed data.

The technical scheme provided by the embodiment of the disclosure can be applied to a distributed system architecture and has the capability of processing mass data. For example, the Spark distributed computing framework is used for realizing data computation, so that data above T level can be easily processed, and rapid expansion is supported. In addition, the embodiment of the disclosure can frequently update the user data, and the iteration can be better updated by determining the user preference by using the updated user data.

Fig. 4 schematically illustrates a block diagram of a system for determining user preferences in accordance with an embodiment of the present disclosure.

As shown in fig. 4, a system 400 for determining user preferences may include a first acquisition module 410, a second acquisition module 420, a first determination module 430, and a second determination module 440, wherein:

the first obtaining module 410 is configured to obtain first text information, where the first text information includes search information input by a user and/or description information of an object operated by the user.

The second obtaining module 420 is configured to obtain second text information, where the second text information includes one or more sub-text information, and different sub-text information includes description information of each object in different object categories.

The first determining module 430 is configured to determine a first similarity of each sub-text information in the first text information and the second text information.

The second determining module 440 is configured to determine a preference of the user according to the first similarity.

Fig. 5A schematically illustrates a block diagram of a first determination module according to an embodiment of the disclosure.

As shown in fig. 5A, the first determination module 430 may include a first extraction unit 431, a second extraction unit 432, and a first determination unit 433, wherein:

The first extraction unit 431 is used for extracting a first feature word from the first text information.

The second extraction unit 432 is configured to extract a corresponding second feature word from each of the sub-text information.

The first determining unit 433 is configured to determine a first similarity between the first text information and each sub-text information according to the first feature word and the corresponding second feature word.

By the embodiment of the disclosure, the first similarity between the first text information and each sub-text information is determined according to the extracted first feature words and the corresponding second feature words, the effect of determining the accuracy of the user preference can be improved, so that better support can be provided for enterprise services.

As an alternative embodiment, the first determining unit is further configured to: determining the first same feature words in the first feature words and the corresponding second feature words; counting the number of the first feature words of the first same feature words; determining the number of the second feature words of the corresponding second feature words; and determining a first similarity between the first text information and each piece of sub-text information according to the first feature word number and the second feature word number.

As an alternative embodiment, the first determining unit is further configured to: acquiring a first mapping relation, wherein the first mapping relation comprises at least one mapping relation, and each mapping relation comprises a historical first feature word extracted from historical first text information, a historical second feature word extracted from historical second text information and historical similarity of the historical first feature word and the historical second feature word; determining mapping relations corresponding to the first feature words and the second feature words from the at least one mapping relation; determining a second similarity of the first feature word and the second feature word according to the mapping relation; and determining the first similarity between the first text information and each piece of sub-text information according to the second similarity.

As an alternative embodiment, the first determining unit is further configured to: determining second identical feature words in the first feature words and the corresponding second feature words; determining a third feature word number of the second same feature word; determining the fourth feature word quantity of the corresponding second feature words; and determining the first similarity of the first text information and each piece of sub-text information according to the second similarity, the third feature word number and the fourth feature word number.

Fig. 5B schematically illustrates a block diagram of a system for determining user preferences in accordance with another embodiment of the present disclosure.

As shown in fig. 5B, the system 400 for determining user preferences may include a third acquisition module 510, a third determination module 520, a statistics module 530, and a fourth determination module 540, wherein:

the third obtaining module 510 is configured to obtain a first operation number of each object in the objects operated by the user.

The third determining module 520 is used for determining user operations object category to which each object belongs.

The statistics module 530 is configured to, and counting the second operation times corresponding to the object categories to which the objects belong.

The fourth determining module 540 is configured to determine a preference of the user according to the first similarity, the first operation number and the second operation number.

FIG. 5C schematically illustrates a process according to the present disclosure a block diagram of a fourth determination module of an embodiment.

As shown in fig. 5C, the fourth determining module 540 may include a second determining unit 541, a calculating unit 542, a third determining unit 543, and a fourth determining unit 544, wherein:

the second determining unit 541 is configured to determine a first preset weight of the first similarity.

The calculating unit 542 is configured to calculate the first operation number and the second operation number to obtain a first value.

The third determining unit 543 is configured to determine a second preset weight of the first value.

The fourth determining unit 544 is configured to determine a preference of the user according to the first similarity, the first preset weight, the first numerical value, and the second preset weight.

Any number of the modules, units, or at least some of the functionality of any number of the modules, units, or units according to embodiments of the present disclosure may be implemented in one module. Any one or more of the modules, units according to embodiments of the present disclosure may be implemented as split into multiple modules. Any one or more of the modules, units according to embodiments of the present disclosure may be implemented at least in part 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 in hardware or firmware in any other reasonable manner of integrating or packaging the circuits, or in any one of or in any suitable combination of three of software, hardware, and firmware. Alternatively, one or more of the modules, units according to embodiments of the disclosure may be at least partially implemented as computer program modules, which when executed, may perform the corresponding functions.

For example, any of the first acquisition module 410, the second acquisition module 420, the first determination module 430, the second determination module 440, the third acquisition module 510, the third determination module 520, the statistics module 530, and the fourth determination module 540 may be combined in one module to be implemented, or any one of the modules may be split into a plurality of modules. Alternatively, at least some of the functionality of one or more of the modules may be combined with at least some of the functionality of other modules and implemented in one module. According to embodiments of the present disclosure, at least one of the first acquisition module 410, the second acquisition module 420, the first determination module 430, the second determination module 440, the third acquisition module 510, the third determination module 520, the statistics module 530, and the fourth determination module 540 may be implemented at least in part as hardware circuitry, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system-on-chip, a system-on-substrate, a system-on-package, an Application Specific Integrated Circuit (ASIC), or may be implemented in hardware or firmware in any other reasonable manner of integrating or packaging circuitry, or in any one of or a suitable combination of three of software, hardware, and firmware implementations. Alternatively, at least one of the first acquisition module 410, the second acquisition module 420, the first determination module 430, the second determination module 440, the third acquisition module 510, the third determination module 520, the statistics module 530, and the fourth determination module 540 may be at least partially implemented as a computer program module, which when executed, may perform the corresponding functions.

Fig. 6 schematically illustrates a block diagram of a computer system suitable for implementing the above-described method according to an embodiment of the present disclosure. The computer system illustrated in fig. 6 is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present disclosure.

As shown in fig. 6, a computer system 600 according to an embodiment of the present disclosure includes a processor 601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. The processor 601 may include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or an associated chipset and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), or the like. Processor 601 may also include on-board memory for caching purposes. The processor 501 may comprise a single processing unit or a plurality of processing units for performing different actions of the method flows according to embodiments of the disclosure.

In the RAM 603, various programs and data required for the operation of the system 600 are stored. The processor 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. The processor 601 performs various operations of the method flow according to the embodiments of the present disclosure by executing programs in the ROM 602 and/or the RAM 603. Note that the program may be stored in one or more memories other than the ROM 602 and the RAM 603. The processor 601 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in the one or more memories.

According to an embodiment of the present disclosure, the system 600 may further include an input/output (I/O) interface 605, the input/output (I/O) interface 605 also being connected to the bus 604. The system 600 may also include one or more of the following components connected to the I/O interface 605: an input portion 606 including a keyboard, mouse, etc.; an output portion 607 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; comprising hard disks or the like a storage section 608; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The drive 610 is also connected to the I/O interface 605 as needed. Removable media 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed as needed on drive 610 so that a computer program read therefrom is installed as needed into storage section 608.

According to embodiments of the present disclosure, the method flow according to embodiments of the present disclosure may be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network through the communication portion 609, and/or installed from the removable medium 611. The above-described functions defined in the system of the embodiments of the present disclosure are performed when the computer program is executed by the processor 601. The systems, devices, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the disclosure.

The present disclosure also provides a computer-readable medium that may be embodied in the apparatus/device/system described in the above embodiments; or may exist alone without being assembled into the apparatus/device/system. The computer readable medium carries one or more programs which, when executed, implement methods in accordance with embodiments of the present disclosure.

According to embodiments of the present disclosure, the computer readable medium may be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, fiber optic cable, radio frequency signals, or the like, or any suitable combination of the foregoing.

For example, in accordance with an embodiment of the present disclosure, the computer readable medium may include ROM 602 and/or RAM 603 and/or one or more memories other than ROM 602 and RAM 603 described above.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, the modules, segments, or portions of code described above contain one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

Those skilled in the art will appreciate that the features recited in the various embodiments of the disclosure and/or in the claims may be provided in a variety of combinations and/or combinations, even if such combinations or combinations are not explicitly recited in the disclosure. In particular, the features recited in the various embodiments of the present disclosure and/or the claims may be variously combined and/or combined without departing from the spirit and teachings of the present disclosure. All such combinations and/or combinations fall within the scope of the present disclosure.

The embodiments of the present disclosure are described above. However, these examples are for illustrative purposes only 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 embodiments cannot be used advantageously in combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be devised by those skilled in the art without departing from the scope of the disclosure, such alternatives and modifications are intended to fall within the scope of the present disclosure.

Claims

1. A method of determining user preferences, comprising:

acquiring first text information, wherein the first text information comprises search information input by a user and/or description information of an object operated by the user;

Acquiring second text information, wherein the second text information comprises one or more sub-text information, and different sub-text information comprises description information of each object in different object categories;

determining a first similarity of each sub-text information in the first text information and the second text information according to a first feature word and a corresponding second feature word, wherein the first feature word is extracted from the first text information, and the second feature word is extracted from each sub-text information; and

determining a preference of the user according to the first similarity;

wherein determining the first similarity between the first text information and each sub-text information according to the first feature word and the second feature word comprises:

acquiring a first mapping relation, wherein the first mapping relation comprises at least one mapping relation, and each mapping relation comprises a historical first feature word extracted from historical first text information, a historical second feature word extracted from historical second text information and historical similarity of the historical first feature word and the historical second feature word;

determining the mapping relation corresponding to the first feature word and the second feature word from the at least one mapping relation;

Determining a second similarity of the first feature word and the second feature word according to the mapping relation; and

and determining the first similarity between the first text information and each piece of sub-text information according to the second similarity.

2. The method of claim 1, wherein determining a first similarity of the first text information and the respective sub-text information from the first feature word and the second feature word comprises:

determining the first same feature words in the first feature words and the corresponding second feature words;

counting the number of the first feature words of the first same feature words;

determining the number of the second feature words of the corresponding second feature words; and

and determining the first similarity between the first text information and each piece of sub-text information according to the first feature word quantity and the second feature word quantity.

3. The method of claim 1, wherein determining a first similarity of the first text information and the respective sub-text information from the first feature word and the second feature word comprises:

determining second identical feature words in the first feature words and the corresponding second feature words;

Counting the number of third feature words of the second same feature words;

determining the fourth feature word quantity of the corresponding second feature words; and

and determining the first similarity of the first text information and each piece of sub-text information according to the second similarity, the third feature word number and the fourth feature word number.

4. The method of claim 1, wherein the method further comprises:

acquiring a first operation frequency of each object in the objects operated by the user;

determining object categories to which each object belongs in the objects operated by the user;

counting second operation times corresponding to object categories to which the objects belong according to the first operation times; and

and determining the preference of the user according to the first similarity, the first operation times and the second operation times.

5. The method of claim 4, wherein determining the user's preference based on the first similarity, the first number of operations, and the second number of operations comprises:

determining a first preset weight of the first similarity;

calculating the first operation times and the second operation times to obtain a first numerical value;

Determining the first value is a second preset weight of (a); and

and determining the preference of the user according to the first similarity, the first preset weight, the first numerical value and the second preset weight.

6. A system for determining user preferences, comprising:

the first acquisition module is used for acquiring first text information, wherein the first text information comprises search information input by a user and/or description information of an object operated by the user;

the second acquisition module is used for acquiring second text information, wherein the second text information comprises one or more pieces of sub-text information, and different pieces of sub-text information comprise description information of each object in different object categories;

the first determining module is used for determining a first similarity of each piece of sub-text information in the first text information and the second text information according to a first feature word and a corresponding second feature word, wherein the first feature word is extracted from the first text information, and the second feature word is extracted from each piece of sub-text information; and

a second determining module, configured to determine a preference of the user according to the first similarity;

wherein the first determining unit is further configured to:

7. The system according to claim 6, wherein the first determining unit is further configured to:

counting the number of the first feature words of the first same feature words;

8. The system of claim 6, wherein the first determining unit is further configured to:

determining a third feature word number of the second same feature word;

9. The system of claim 6, wherein the system further comprises:

the third acquisition module is used for acquiring the first operation times of each object in the objects operated by the user;

a third determining module, configured to determine an object category to which each object belongs in the objects operated by the user;

the statistics module is used for counting second operation times corresponding to object categories to which the objects belong according to the first operation times; and

and a fourth determining module, configured to determine a preference of the user according to the first similarity, the first operation number and the second operation number.

10. The system of claim 9, wherein the fourth determination module comprises:

A second determining unit, configured to determine a first preset weight of the first similarity;

the calculating unit is used for calculating the first operation times and the second operation times to obtain a first numerical value;

a third determining unit for determining the position of the object, a second preset weight for determining the first value; and

and a fourth determining unit, configured to determine a preference of the user according to the first similarity, the first preset weight, the first numerical value, and the second preset weight.

11. A computer system, comprising:

one or more processors;

a computer readable storage medium storing one or more programs,

wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of determining user preferences of any one of claims 1 to 5.

12. A computer readable storage medium having stored thereon executable instructions which when executed by a processor cause the processor to implement the method of determining user preferences of any one of claims 1 to 5.