CN110827101B - Shop recommending method and device - Google Patents
Shop recommending method and device Download PDFInfo
- Publication number
- CN110827101B CN110827101B CN201810891276.1A CN201810891276A CN110827101B CN 110827101 B CN110827101 B CN 110827101B CN 201810891276 A CN201810891276 A CN 201810891276A CN 110827101 B CN110827101 B CN 110827101B
- Authority
- CN
- China
- Prior art keywords
- store
- compared
- target
- dimension
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 239000013598 vector Substances 0.000 claims description 33
- 238000013507 mapping Methods 0.000 claims description 31
- 101150000446 Tsku gene Proteins 0.000 claims description 30
- 230000007704 transition Effects 0.000 claims description 23
- 238000004590 computer program Methods 0.000 claims description 9
- 230000009191 jumping Effects 0.000 claims 1
- 230000006399 behavior Effects 0.000 abstract description 12
- 238000010586 diagram Methods 0.000 description 13
- 238000004891 communication Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000002860 competitive effect Effects 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 239000012141 concentrate Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0623—Item investigation
- G06Q30/0625—Directed, with specific intent or strategy
- G06Q30/0629—Directed, with specific intent or strategy for generating comparisons
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a shop recommending method and device, and relates to the technical field of computers. One embodiment of the method comprises the following steps: determining a value of a recommended dimension between the target store and the store to be compared; the recommendation dimension includes at least one of: browsing flow dimension, object similarity dimension, volume dimension and trusted identification; and determining the score of the stores to be compared according to the numerical value of the recommended dimension based on a preset scoring model, and recommending the stores to be compared to the target stores according to the sequence from high score to low score. According to the embodiment, the multiple dimensions of the browsing behaviors of the user, the articles in the store, the sales of the store and the like are comprehensively considered, the stores to be compared are scored, and further the bidding is accurately and flexibly recommended for the target store.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a shop recommending method and device.
Background
In order for the store itself to remain competitive, it is necessary to know the competitive stores on the market that are similar to the store itself. The prior art recommendation method for a bid generally includes: searching related articles on the electronic commerce platform, and recommending by taking the store where the article in front in the search result is located as a shop; or recommending a bid according to the off-line sales data; or determining whether to bid for recommendation based on operational experience.
In the process of implementing the present invention, the inventor finds that at least the following problems exist in the prior art:
1) For the method for determining the bidding by searching the articles on the electronic commerce platform, the determined bidding results are inaccurate and incomplete due to the limited articles which can be searched;
2) For the method of recommending the bidding according to the off-line sales data, the off-line sales data cannot replace the on-line sales data as a reference, so that the determined bidding result is inaccurate;
3) With respect to the method for determining a bid to recommend according to operation experience, inaccuracy of the determined bid result is also easily caused due to uncertainty and subjectivity of operation experience.
Disclosure of Invention
In view of the above, the embodiments of the present invention provide a method and an apparatus for recommending stores, which can comprehensively consider multiple dimensions such as user browsing behavior, articles in stores, sales of stores, etc., score stores to be compared, and accurately and flexibly recommend bidding stores for target stores.
To achieve the above object, according to one aspect of the embodiments of the present invention, there is provided a method of store recommendation, including:
Determining a value of a recommended dimension between the target store and the store to be compared; the recommendation dimension includes at least one of: browsing flow dimension, object similarity dimension, volume dimension and trusted identification;
and determining the score of the stores to be compared according to the numerical value of the recommended dimension based on a preset scoring model, and recommending the stores to be compared to the target stores according to the sequence from high score to low score.
Optionally, taking the store containing the target class as the store to be compared; the target class is determined as follows:
mainC＝{Ti|Tsalesi-1＜Tsales·λ≤Tsalesi,i≥2}∪{T1}，0＜λ≤1；
Wherein mainC denotes a set of target categories; t i represents the first i article categories after sorting sales of all article categories from big to small in a preset time period in a target store; tsales i denotes the sum of sales of the first i article categories after sorting sales of all article categories from large to small in a preset time period in the target store; tsales denotes the total sales in the target store for a preset period of time, and λ denotes the category selection threshold.
Optionally, determining the value of the browsing traffic dimension between the target store and the store to be compared includes:
determining the jump probability from the target store to the store to be compared based on the user browsing record;
Taking the jump probability as the numerical value of the browsing flow dimension between the target store and the store to be compared.
Optionally, determining the jump probability of the target store to the store to be compared based on the user browsing record includes:
Determining a user set M to be counted based on user browsing records in a preset historical period or a preset period from the current moment to the current moment, wherein the user to be counted is related to browsing information of the object categories in the object category set mainC on the object shops and the shops to be compared;
Determining a set S mc formed by stores browsed by the mth user to be counted about the c-th target category in mainC according to the browsing information of the user to be counted about the target category to the stores;
Establishing a mapping relation between every two elements in the set S mk, wherein
According to the mapping relation in the set S mc, the transition probability a j from the target store to the j-th store to be compared is determined by adopting the following formula:
Wherein n represents the sum of the numbers of the mapping relations from the target store in the set S mc; n j represents the sum of the numbers of the mapping relations from the target store to the j-th store to be compared in the set S mc; the || symbol represents the number of elements contained in the collection in the || symbol.
Optionally, determining the value of the item similarity dimension between the target store and the store to be compared includes:
determining vectors of all articles in a target store and a store to be compared based on a word frequency-inverse text frequency index algorithm;
According to vectors of all articles in the target store and the stores to be compared, determining articles similar to the articles in the stores to be compared in the target store;
To be used for A value as an item similarity dimension between the target store and the store to be compared; where sim_sku represents a set of items in the target store that are similar to the items in the store to be compared, tsku represents a set of all items in the target store; the || symbol represents the number of elements contained in the collection in the || symbol.
Optionally, items in the target store that are similar to the items in the store to be compared are determined as follows:
sim_sku＝
{Tskua|(Tskua∈Tsku)∧(Cskub∈Csku)∧(cos(va,vb)＞β)}；
Wherein Tsku a represents the a-th item in Tsku, csku represents a set of all items in the store to be compared, csku b represents the b-th item in Csku; v a represents the vector of the a-th item in Tsku, v b represents the vector of the b-th item in Csku; cos (v a,vb) represents the cosine similarity of v a and v b and β represents the similarity threshold.
Optionally, determining a value of a volume dimension between the target store and the store to be compared includes:
Obtaining a difference value of total sales of a target store and a store to be compared in a preset time period;
To be used for A value of a dimension of the object volume between the target store and the kth store to be compared;
Wherein D k represents the difference between the total sales of the target store and the kth store to be compared within a preset time period; d max represents the largest value of the difference between the total sales of the target store and all stores to be compared within the preset time period.
Optionally, determining the trusted identification between the target store and the store to be compared includes:
acquiring total sales Tsales of the target shops in a preset time period and total sales Csales of shops to be compared;
When Csales epsilon [ Tdown, tup ], determining that the trusted identification is 1;
When (when) Determining that the trusted identification is 0;
Wherein tup= Tsales ·η up,ηup > 1;
Where η up denotes an upper limit coefficient, η down1 denotes a first lower limit coefficient, η down2 denotes a second lower limit coefficient, and μ denotes a sales threshold.
According to still another aspect of the embodiment of the present invention, there is provided an apparatus for recommending stores, including:
The dimension value determining module is used for determining the value of the recommended dimension between the target store and the store to be compared; the recommendation dimension includes at least one of: browsing flow dimension, object similarity dimension, volume dimension and trusted identification;
and the recommending module is used for determining the score of the stores to be compared according to the numerical value of the recommending dimension based on a preset scoring model, and recommending the stores to be compared to the target stores according to the sequence of the score from high to low.
Optionally, taking the store containing the target class as the store to be compared; the dimension value determining module determines the target category as follows:
mainC＝{Ti|Tsalesi-1＜Tsales·λ≤Tsalesi,i≥2}∪{T1}，0＜λ≤1；
Wherein mainC denotes a set of target categories; t i represents the first i article categories after sorting sales of all article categories from big to small in a preset time period in a target store; tsales i denotes the sum of sales of the first i article categories after sorting sales of all article categories from large to small in a preset time period in the target store; tsales denotes the total sales in the target store for a preset period of time, and λ denotes the category selection threshold.
Optionally, the determining the value of the browsing traffic dimension between the target store and the store to be compared by the dimension value determining module includes:
determining the jump probability from the target store to the store to be compared based on the user browsing record;
Taking the jump probability as the numerical value of the browsing flow dimension between the target store and the store to be compared.
Optionally, the determining the jump probability of the target store to the store to be compared based on the user browsing record includes:
Determining a user set M to be counted based on user browsing records in a preset historical period or a preset period from the current moment to the current moment, wherein the user to be counted is related to browsing information of the object categories in the object category set mainC on the object shops and the shops to be compared;
Determining a set S mc formed by stores browsed by the mth user to be counted about the c-th target category in mainC according to the browsing information of the user to be counted about the target category to the stores;
Establishing a mapping relation between every two elements in the set S mk, wherein
According to the mapping relation in the set S mc, the transition probability a j from the target store to the j-th store to be compared is determined by adopting the following formula:
Wherein n represents the sum of the numbers of the mapping relations from the target store in the set S mc; n j represents the sum of the numbers of the mapping relations from the target store to the j-th store to be compared in the set S mc; the || symbol represents the number of elements contained in the collection in the || symbol.
Optionally, the determining dimension value module determines a value of an item similarity dimension between the target store and the store to be compared, including:
determining vectors of all articles in a target store and a store to be compared based on a word frequency-inverse text frequency index algorithm;
According to vectors of all articles in the target store and the stores to be compared, determining articles similar to the articles in the stores to be compared in the target store;
To be used for A value as an item similarity dimension between the target store and the store to be compared; where sim_sku represents a set of items in the target store that are similar to the items in the store to be compared, tsku represents a set of all items in the target store; the || symbol represents the number of elements contained in the collection in the || symbol.
Optionally, the dimension value determining module determines items in the target store that are similar to the items in the store to be compared according to the following method:
sim_sku＝
{Tskua|(Tskua∈Tsku)∧(Cskub∈Csku)∧(cos(va,vb)＞β)}；
Wherein Tsku a represents the a-th item in Tsku, csku represents a set of all items in the store to be compared, csku b represents the b-th item in Csku; v a represents the vector of the a-th item in Tsku, v b represents the vector of the b-th item in Csku; cos (v a,vb) represents the cosine similarity of v a and v b and β represents the similarity threshold.
Optionally, the dimension determining value module determines a value of a dimension of a volume between the target store and the store to be compared, including:
Obtaining a difference value of total sales of a target store and a store to be compared in a preset time period;
To be used for A value of a dimension of the object volume between the target store and the kth store to be compared;
Wherein D k represents the difference between the total sales of the target store and the kth store to be compared within a preset time period; d max represents the largest value of the difference between the total sales of the target store and all stores to be compared within the preset time period.
Optionally, the dimension value determining module determines a trusted identifier between the target store and the store to be compared, including:
acquiring total sales Tsales of the target shops in a preset time period and total sales Csales of shops to be compared;
When Csales epsilon [ Tdown, tup ], determining that the trusted identification is 1;
When (when) Determining that the trusted identification is 0;
Wherein tup= Tsales ·η up,ηup > 1;
Where η up denotes an upper limit coefficient, η down1 denotes a first lower limit coefficient, η down2 denotes a second lower limit coefficient, and μ denotes a sales threshold.
According to another aspect of an embodiment of the present invention, there is provided an electronic device for store recommendation, including:
One or more processors;
Storage means for storing one or more programs,
The one or more programs, when executed by the one or more processors, cause the one or more processors to implement the store recommended method provided by the present invention.
According to yet another aspect of an embodiment of the present invention, there is provided a computer readable medium having stored thereon a computer program which when executed by a processor implements the method of store recommendation provided by the present invention.
One embodiment of the above invention has the following advantages or benefits: the technical means of firstly determining the browsing flow dimension, the object similarity dimension, the body dimension and the numerical value of the credible mark between the target store and the store to be compared, and then scoring the store to be compared according to the dimensions based on the preset scoring model and recommending the store with high score to the target store is adopted, so that the technical problem that the stores cannot be accurately and comprehensively recommended in the prior art is solved, and the technical effect of accurately and flexibly recommending the competing store for the target store is achieved.
Further effects of the above-described non-conventional alternatives are described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
FIG. 1 is a schematic diagram of the main flow of a store recommendation method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a transition probability determination method according to an alternative embodiment of the present invention;
FIG. 3 is a schematic diagram of the main modules of a store recommendation device according to an embodiment of the present invention;
FIG. 4 is an exemplary system architecture diagram in which embodiments of the present invention may be applied;
Fig. 5 is a schematic diagram of a computer system suitable for use in implementing an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, in which various details of the embodiments of the present invention are included to facilitate understanding, and are to be considered merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
FIG. 1 is a schematic diagram of the main flow of a method for store recommendation according to an embodiment of the present invention, as shown in FIG. 1, including:
Step S101, determining a numerical value of a recommended dimension between a target store and a store to be compared; the recommendation dimension includes at least one of: browsing flow dimension, object similarity dimension, volume dimension and trusted identification;
Step S102, determining the score of the stores to be compared according to the numerical value of the recommended dimension based on a preset scoring model, and recommending the stores to be compared to the target stores according to the sequence of the score from high to low.
The scheme of the invention can comprehensively consider a plurality of dimensions such as browsing behaviors of users, articles in stores, sales of stores and the like, score stores to be compared, and accurately and flexibly recommend bidding stores for target stores.
In some embodiments, stores containing the target category are taken as stores to be compared; the target class is determined as follows:
mainC＝{Ti|Tsalesi-1＜Tsales·λ≤Tsalesi,i≥2}∪{T1}，0＜λ≤1；
Wherein mainC denotes a set of target categories; t i represents the first i article categories after sorting sales of all article categories from big to small in a preset time period in a target store; tsales i denotes the sum of sales of the first i article categories after sorting sales of all article categories from large to small in a preset time period in the target store; tsales denotes the total sales in the target store for a preset period of time, and λ denotes the category selection threshold.
The preset time period is adjustable, for example, the time period can be set to be 30 days recently or three months recently;
the category selection threshold λ is adjustable, as may be set to 0.3,0.6,0.8; for the formula, the larger the set lambda value is, the more target categories are determined, and the lambda value can be flexibly adjusted in practical application so as to adapt to various requirements.
The following illustrates a method of determining the target class in the present invention:
For a target store, the sales for all item categories for its last three months are determined as shown in the following table:
table 1 sales of all item categories in three months for the target store
When λ is set to 0.6, i=2 can be determined according to the formula in the present method, so that it can be determined that category 1 and category 2 are target categories of target stores.
When λ is set to 0.3, i=1 can be determined according to the formula in the present method, so that it can be determined that category 1 is the target category of the target store.
When λ is set to 0.9, i=4 can be determined according to the formula in the present method, so that it can be determined that category 1, category 2, category 3, and category 4 are target categories of the target store.
In some embodiments, determining a value of a browse traffic dimension between a target store and a store to be compared includes:
determining the jump probability from the target store to the store to be compared based on the user browsing record;
Taking the jump probability as the numerical value of the browsing flow dimension between the target store and the store to be compared.
The user browsing record can be a record in a preset history period or a preset period from the current moment;
The transition probability matrix of any store can be determined for a plurality of stores by determining the transition probability of any store to another store based on the user browsing record in the preset history period, so that the effect of querying the transition probability of any store to other stores in the plurality of stores according to the transition probability matrix can be achieved;
the browsing flow dimension value is determined based on the user browsing record, and the meaning of the browsing flow dimension value is that the relation of the competing stores is measured by using the behaviors of the user, and the browsing flow dimension value is an important reference basis for recommending the stores.
In some embodiments, determining a probability of a jump of the target store to a store to be compared based on a user browsing record includes:
Determining a user set M to be counted based on user browsing records in a preset historical period or a preset period from the current moment to the current moment, wherein the user to be counted is related to browsing information of the object categories in the object category set mainC on the object shops and the shops to be compared;
Determining a set S mc formed by stores browsed by the mth user to be counted about the c-th target category in mainC according to the browsing information of the user to be counted about the target category to the stores;
Establishing a mapping relation between every two elements in the set S mk, wherein
According to the mapping relation in the set S mc, the transition probability a j from the target store to the j-th store to be compared is determined by adopting the following formula:
Wherein n represents the sum of the numbers of the mapping relations from the target store in the set S mc; n j represents the sum of the numbers of the mapping relations from the target store to the j-th store to be compared in the set S mc; the || symbol represents the number of elements contained in the collection in the || symbol.
The significance of determining the transition probability is that the jump behavior of the user between the target store and the store to be compared can be quantified based on the behavior of the user, so that the jump behavior can be used as a measure of store recommendation according to the quantified result.
For convenience in understanding the method for determining transition probability in the embodiment of the present invention, fig. 2 is a schematic diagram of a method for determining transition probability according to an alternative embodiment of the present invention; in fig. 2, store a is a target store; store B, C, D, E is the store to be compared;
According to the browsing information of the user to be counted about the store where the object class in the target class set is located, five sets are determined, as shown in fig. 2: set 201, set 202, set 203, set 204, set 205; wherein store A, B is in set 201, store A, B, C is in set 202, store A, B, D is in set 203, store A, B, D, E is in set 204, and store A, B, E is in set 205;
as shown in fig. 2, mapping relationships inside the sets are respectively established for the five sets;
Obtaining the number of mapping relations from store A as 10, the sum of the number of mapping relations from store A to store B as 5, the sum of the number of mapping relations from store A to store C as 1, the sum of the number of mapping relations from store A to store D as 2 and the sum of the number of mapping relations from store A to store E as 2 according to the mapping relations;
Further, determining that the transition probability from store A to store B is Store A to store C transition probability ofStore A to store C transition probability is/>Store A to store D transition probability is/>
In some embodiments, determining a value for an item similarity dimension between a target store and a store to be compared comprises:
determining vectors of all articles in a target store and a store to be compared based on a word frequency-inverse text frequency index algorithm;
According to vectors of all articles in the target store and the stores to be compared, determining articles similar to the articles in the stores to be compared in the target store;
To be used for A value as an item similarity dimension between the target store and the store to be compared; where sim_sku represents a set of items in the target store that are similar to the items in the store to be compared, tsku represents a set of all items in the target store; the || symbol represents the number of elements contained in the collection in the || symbol.
Word frequency-inverse text frequency index algorithm (term frequency-inverse document frequency) is a common weighting technique used for information retrieval and data mining;
the names of the articles sold in the target store and all stores to be compared can be acquired first, and word segmentation processing is carried out on all nouns to obtain word sets formed by all words; determining the frequency of each word in the word set in a store by using a word frequency-inverse text frequency index algorithm; and arranging the frequency of each word in the names of the articles according to the word sequence in the word set for each article in each store to obtain the vector of each article in the store.
The following illustrates the method for determining the vector of each item in the target store and the store to be compared using the algorithm in the embodiment of the present invention:
acquiring an article A 1、A1 in the store A and an article B 1、B2 in the store B; after word segmentation, it can be determined that A 1 is composed of a word C 1、C2, A 2 is composed of a word C 1、C3, B 1 is composed of a word C 2、C4, and B 2 is composed of a word C 3、C5;
and then can confirm the word and concentrate the word and have: c 1、C2、C3、C4、C5;
In store a, the word C 1 appears at a frequency of 0.5, C 2 appears at a frequency of 0.25, and C 3 appears at a frequency of 0.25; in order of word set C 1、C2、C3、C4、C5, it can be determined that the vector of item A 1 in store A is (0.5,0.25,0,0,0) and the vector of item A 2 is (0.5,0,0.25,0,0);
In store B, C 2 occurred at a frequency of 0.25, C 3 occurred at a frequency of 0.25, C 4 occurred at a frequency of 0.25, and C 5 occurred at a frequency of 0.25; in the order of word set C 1、C2、C3、C4、C5, the vector of item B 1 in store B may be determined to be (0,0.25,0,0.25,0) and the vector of item B 2 to be (0,0,0.25,0,0.25).
The similarity of articles in stores is measured by using a natural language processing method, so that the similarity between stores is determined, and the relationship of competing stores is measured, so that the method is an important reference basis for recommending stores.
In some embodiments, items in the target store that are similar to items in the store to be compared are determined as follows:
sim_sku＝
{Tskua|(Tskua∈Tsku)∧(Cskub∈Csku)∧(cos(va,vb)＞β)}；
Wherein Tsku a represents the a-th item in Tsku, csku represents a set of all items in the store to be compared, csku b represents the b-th item in Csku; v a represents the vector of the a-th item in Tsku, v b represents the vector of the b-th item in Csku; cos (v a,vb) represents the cosine similarity of v a and v b and β represents the similarity threshold.
The similarity threshold beta can be flexibly adjusted and set according to actual demands, and the similarity between vectors is measured by using a cosine similarity algorithm in the embodiment, so that the articles similar to the articles in the stores to be compared in the target store can be determined, and the method is easy to realize.
In some embodiments, determining a value for a volume dimension between a target store and a store to be compared includes:
Obtaining a difference value of total sales of a target store and a store to be compared in a preset time period;
To be used for A value of a dimension of the object volume between the target store and the kth store to be compared;
Wherein D k represents the difference between the total sales of the target store and the kth store to be compared within a preset time period; d max represents the largest value of the difference between the total sales of the target store and all stores to be compared within the preset time period.
The preset time period can be set in an adjustable way, such as the last three months or the last half year;
The use of logarithmic operation to quantify the actual difference in total sales of the target store and the store to be compared can smooth out the large sales difference in some cases, and is easy to calculate.
In some embodiments, determining a trusted identification between a target store and a store to be compared comprises:
acquiring total sales Tsales of the target shops in a preset time period and total sales Csales of shops to be compared;
When Csales epsilon [ Tdown, tup ], determining that the trusted identification is 1;
When (when) Determining that the trusted identification is 0;
Wherein tup= Tsales ·η up,ηup > 1;
Where η up denotes an upper limit coefficient, η down1 denotes a first lower limit coefficient, η down2 denotes a second lower limit coefficient, and μ denotes a sales threshold.
The upper limit coefficient, the first lower limit coefficient, the second lower limit coefficient and the sales threshold are all adjustably set; the significance of determining a trusted identifier is to mark whether there is a trusted competing relationship between two stores: if the sales difference between the target store and the store to be compared is too large, the target store and the store to be compared can be considered to have no competition relationship;
in the formula in this embodiment, two determination methods under different conditions are set for the lower limit value Tdown in the trusted section [ Tdown, tup ], which is more practical.
For the determined browsing flow dimension, item similarity dimension, volume dimension, credible identification dimension values, the score of the stores to be compared can be determined based on the following preset scoring model:
table 2 preset scoring model
According to the fusion setting of each dimension, a scoring model shown in table 2 can be determined, multiple dimensions can be comprehensively considered to score stores to be compared, and finally, stores with higher scores are recommended to target stores to be used as competing stores.
Fig. 3 is a schematic diagram of main modules of a store recommendation apparatus according to an embodiment of the present invention, and as shown in fig. 3, the store recommendation apparatus 300 includes:
a dimension determining value module 301, configured to determine a value of a recommended dimension between the target store and the store to be compared; the recommendation dimension includes at least one of: browsing flow dimension, object similarity dimension, volume dimension and trusted identification;
And the recommending module 302 is configured to determine a score of the store to be compared according to the numerical value of the recommending dimension based on a preset scoring model, and recommend the store to be compared to the target store according to the order of the scores from high to low.
The scheme of the invention can comprehensively consider a plurality of dimensions such as browsing behaviors of users, articles in stores, sales of stores and the like, score stores to be compared, and accurately and flexibly recommend bidding stores for target stores.
In some embodiments, stores containing the target category are taken as stores to be compared; the dimension value determining module 301 determines the target category as follows:
mainC＝{Ti|Tsalesi-1＜Tsales·λ≤Tsalesi,i≥2}∪{T1}，0＜λ≤1；
Wherein mainC denotes a set of target categories; t i represents the first i article categories after sorting sales of all article categories from big to small in a preset time period in a target store; tsales i denotes the sum of sales of the first i article categories after sorting sales of all article categories from large to small in a preset time period in the target store; tsales denotes the total sales in the target store for a preset period of time, and λ denotes the category selection threshold.
The preset time period is adjustable, for example, the time period can be set to be 30 days recently or three months recently;
the category selection threshold λ is adjustable, as may be set to 0.3,0.6,0.8; for the formula, the larger the set lambda value is, the more target categories are determined, and the lambda value can be flexibly adjusted in practical application so as to adapt to various requirements.
In some embodiments, the determining dimension value module 301 determines a value of a browsing traffic dimension between a target store and a store to be compared, including:
determining the jump probability from the target store to the store to be compared based on the user browsing record;
Taking the jump probability as the numerical value of the browsing flow dimension between the target store and the store to be compared.
The user browsing record can be a record in a preset history period or a preset period from the current moment;
The transition probability matrix of any store can be determined for a plurality of stores by determining the transition probability of any store to another store based on the user browsing record in the preset history period, so that the effect of querying the transition probability of any store to other stores in the plurality of stores according to the transition probability matrix can be achieved;
the browsing flow dimension value is determined based on the user browsing record, and the meaning of the browsing flow dimension value is that the relation of the competing stores is measured by using the behaviors of the user, and the browsing flow dimension value is an important reference basis for recommending the stores.
In some embodiments, the determining dimension value module 301 determines a probability of a jump of the target store to a store to be compared based on a user browsing record, including:
Determining a user set M to be counted based on user browsing records in a preset historical period or a preset period from the current moment to the current moment, wherein the user to be counted is related to browsing information of the object categories in the object category set mainC on the object shops and the shops to be compared;
Determining a set S mc formed by stores browsed by the mth user to be counted about the c-th target category in mainC according to the browsing information of the user to be counted about the target category to the stores;
Establishing a mapping relation between every two elements in the set S mk, wherein
According to the mapping relation in the set S mc, the transition probability a j from the target store to the j-th store to be compared is determined by adopting the following formula:
Wherein n represents the sum of the numbers of the mapping relations from the target store in the set S mc; n j represents the sum of the numbers of the mapping relations from the target store to the j-th store to be compared in the set S mc; the || symbol represents the number of elements contained in the collection in the || symbol.
The significance of determining the transition probability is that the jump behavior of the user between the target store and the store to be compared can be quantified based on the behavior of the user, so that the jump behavior can be used as a measure of store recommendation according to the quantified result.
In some embodiments, the determining dimension value module 301 determines a value of an item similarity dimension between a target store and a store to be compared, including:
determining vectors of all articles in a target store and a store to be compared based on a word frequency-inverse text frequency index algorithm;
According to vectors of all articles in the target store and the stores to be compared, determining articles similar to the articles in the stores to be compared in the target store;
To be used for A value as an item similarity dimension between the target store and the store to be compared; where sim_sku represents a set of items in the target store that are similar to the items in the store to be compared, tsku represents a set of all items in the target store; the || symbol represents the number of elements contained in the collection in the || symbol.
Word frequency-inverse text frequency index algorithm (term frequency-inverse document frequency) is a common weighting technique used for information retrieval and data mining;
The names of the articles sold in the target store and all stores to be compared can be acquired first, and word segmentation processing is carried out on all nouns to obtain word sets formed by all words; determining the frequency of each word in the word set in a store by using a word frequency-inverse text frequency index algorithm; for each article in each store, arranging the frequency of each word in the article name according to the word sequence in the word set to obtain the vector of each article in the store;
The similarity of articles in stores is measured by using a natural language processing method, so that the similarity between stores is determined, and the relationship of competing stores is measured, so that the method is an important reference basis for recommending stores.
In some embodiments, the dimension value determination module 301 determines items in the target store that are similar to items in the store to be compared as follows:
sim_sku＝
{Tskua|(Tskua∈Tsku)∧(Cskub∈Csku)∧(cos(va,vb)＞β)}；
Wherein Tsku a represents the a-th item in Tsku, csku represents a set of all items in the store to be compared, csku b represents the b-th item in Csku; v a represents the vector of the a-th item in Tsku, v b represents the vector of the b-th item in Csku; cos (v a,vb) represents the cosine similarity of v a and v b and β represents the similarity threshold.
The similarity threshold beta can be flexibly adjusted and set according to actual demands, and the similarity between vectors is measured by using a cosine similarity algorithm in the embodiment, so that the articles similar to the articles in the stores to be compared in the target store can be determined, and the method is easy to realize.
In some embodiments, the dimension determination value module 301 determines a value of a volume dimension between a target store and a store to be compared, including:
Obtaining a difference value of total sales of a target store and a store to be compared in a preset time period;
To be used for A value of a dimension of the object volume between the target store and the kth store to be compared;
Wherein D k represents the difference between the total sales of the target store and the kth store to be compared within a preset time period; d max represents the largest value of the difference between the total sales of the target store and all stores to be compared within the preset time period.
The preset time period can be set in an adjustable way, such as the last three months or the last half year;
The use of logarithmic operation to quantify the actual difference in total sales of the target store and the store to be compared can smooth out the large sales difference in some cases, and is easy to calculate.
In some embodiments, the determining dimension value module 301 determines a trusted identification between the target store and the store to be compared, including:
acquiring total sales Tsales of the target shops in a preset time period and total sales Csales of shops to be compared;
When Csales epsilon [ Tdown, tup ], determining that the trusted identification is 1;
When (when) Determining that the trusted identification is 0; /(I)
Wherein tup= Tsales ·η up,ηup > 1;
Where η up denotes an upper limit coefficient, η down1 denotes a first lower limit coefficient, η down2 denotes a second lower limit coefficient, and μ denotes a sales threshold.
The upper limit coefficient, the first lower limit coefficient, the second lower limit coefficient and the sales threshold are all adjustably set; the significance of determining a trusted identifier is to mark whether there is a trusted competing relationship between two stores: if the sales difference between the target store and the store to be compared is too large, the target store and the store to be compared can be considered to have no competition relationship;
in the formula in this embodiment, two determination methods under different conditions are set for the lower limit value Tdown in the trusted section [ Tdown, tup ], which is more practical.
FIG. 4 illustrates an exemplary system architecture 400 of a store recommendation method or store recommendation device to which embodiments of the present invention may be applied.
As shown in fig. 4, the system architecture 400 may include terminal devices 401, 402, 403, a network 404, and a server 405. The network 404 is used as a medium to provide communication links between the terminal devices 401, 402, 403 and the server 405. The network 404 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
A user may interact with the server 405 via the network 404 using the terminal devices 401, 402, 403 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., may be installed on the terminal devices 401, 402, 403.
The terminal devices 401, 402, 403 may be various 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 405 may be a server providing various services, such as a background management server (by way of example only) providing support for shopping-type websites browsed by users using the terminal devices 401, 402, 403. The background management server may analyze and process the received data such as the product information query request, and feedback the processing result (e.g., the target push information, the product information—only an example) to the terminal device.
It should be noted that, the method for recommending a store provided in the embodiment of the present invention is generally executed by the server 405, and accordingly, the device for recommending a store is generally disposed in the server 405.
It should be understood that the number of terminal devices, networks and servers in fig. 4 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 5, there is illustrated a schematic diagram of a computer system 500 suitable for use in implementing an embodiment of the present invention. The terminal device shown in fig. 5 is only an example, and should not impose any limitation on the functions and the scope of use of the embodiment of the present invention.
As shown in fig. 5, the computer system 500 includes a Central Processing Unit (CPU) 501, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 502 or a program loaded from a storage section 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the system 500 are also stored. The CPU 501, ROM 502, and RAM 503 are connected to each other through a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
The following components are connected to the I/O interface 505: an input section 506 including a keyboard, a mouse, and the like; an output portion 507 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker, and the like; a storage portion 508 including a hard disk and the like; and a communication section 509 including a network interface card such as a LAN card, a modem, or the like. The communication section 509 performs communication processing via a network such as the internet. The drive 510 is also connected to the I/O interface 505 as needed. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 510 as needed so that a computer program read therefrom is mounted into the storage section 508 as needed.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. 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 flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 509, and/or installed from the removable media 511. The above-described functions defined in the system of the present invention are performed when the computer program is executed by a Central Processing Unit (CPU) 501.
The computer readable medium shown in the present invention 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 document, 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 invention, 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, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
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 invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises 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.
The modules involved in the embodiments of the present invention may be implemented in software or in hardware. The described modules may also be provided in a processor, for example, as: a processor includes a determine dimension values module, a recommendation unit. The names of these modules do not in some cases limit the unit itself, and for example, the module for determining a dimension value may also be described as "a module for sending a picture acquisition request to a connected server".
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be present alone without being fitted into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to include: step S101, determining a numerical value of a recommended dimension between a target store and a store to be compared; the recommendation dimension includes at least one of: browsing flow dimension, object similarity dimension, volume dimension and trusted identification; step S102, determining the score of the stores to be compared according to the numerical value of the recommended dimension based on a preset scoring model, and recommending the stores to be compared to the target stores according to the sequence of the score from high to low.
According to the technical scheme provided by the embodiment of the invention, the technical means that the browsing flow dimension, the object similarity dimension, the body dimension and the numerical value of the credible mark between the target store and the store to be compared are firstly determined, then the store to be compared is scored according to the dimensions based on the preset scoring model, and the store with the high score is further recommended to the target store is adopted, so that the technical problem that the store cannot be accurately and comprehensively recommended in the prior art is solved, and the technical effect of accurately and flexibly recommending the target store for the bidding is achieved.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives can occur depending upon design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (16)
1. A method of store recommendation, comprising:
Determining a value of a recommended dimension between the target store and the store to be compared; the recommendation dimension includes at least one of: browsing flow dimension, object similarity dimension, volume dimension and trusted identification; wherein determining a trusted identification between the target store and the store to be compared comprises: acquiring total sales Tsales of the target shops in a preset time period and total sales Csales of shops to be compared;
When Csales epsilon [ Tdown, tup ], determining that the trusted identification is 1;
When (when) Determining that the trusted identification is 0;
Wherein tup= Tsales ·η up,ηup > 1;
Where η up denotes an upper limit coefficient, η down1 denotes a first lower limit coefficient, η down2 denotes a second lower limit coefficient, μ denotes a sales threshold;
and determining the score of the stores to be compared according to the numerical value of the recommended dimension based on a preset scoring model, and recommending the stores to be compared to the target stores according to the sequence from high score to low score.
2. The method according to claim 1, wherein stores containing the target class are used as stores to be compared; the target class is determined as follows:
mainC＝{Ti|Tsalesi-1＜Tsales·λ≤Tsalesi,i≥2}∪{T1}，0＜λ≤1；
Wherein mainC denotes a set of target categories; t i represents the first i article categories after sorting sales of all article categories from big to small in a preset time period in a target store; tsales i denotes the sum of sales of the first i article categories after sorting sales of all article categories from large to small in a preset time period in the target store; tsales denotes the total sales in the target store for a preset period of time, and λ denotes the category selection threshold.
3. The method of claim 2, wherein determining a value for a browse traffic dimension between the target store and the store to be compared comprises:
determining the jump probability from the target store to the store to be compared based on the user browsing record;
Taking the jump probability as the numerical value of the browsing flow dimension between the target store and the store to be compared.
4. A method according to claim 3, wherein determining the probability of jumping of the target store to the store to be compared based on the user browsing records comprises:
Determining a user set M to be counted based on user browsing records in a preset historical period or a preset period from the current moment to the current moment, wherein the user to be counted is related to browsing information of the object categories in the object category set mainC on the object shops and the shops to be compared;
Determining a set S mc formed by stores browsed by the mth user to be counted about the c-th target category in mainC according to the browsing information of the user to be counted about the target category to the stores;
Establishing a mapping relation between every two elements in the set S mk, wherein
According to the mapping relation in the set S mc, the transition probability a j from the target store to the j-th store to be compared is determined by adopting the following formula:
Wherein n represents the sum of the numbers of the mapping relations from the target store in the set S mc; n j represents the sum of the numbers of the mapping relations from the target store to the j-th store to be compared in the set S mc; the || symbol represents the number of elements contained in the collection in the || symbol.
5. The method of claim 2, wherein determining a value for an item similarity dimension between the target store and the store to be compared comprises:
determining vectors of all articles in a target store and a store to be compared based on a word frequency-inverse text frequency index algorithm;
According to vectors of all articles in the target store and the stores to be compared, determining articles similar to the articles in the stores to be compared in the target store;
To be used for A value as an item similarity dimension between the target store and the store to be compared; where sim_sku represents a set of items in the target store that are similar to the items in the store to be compared, tsku represents a set of all items in the target store; the || symbol represents the number of elements contained in the collection in the || symbol.
6. The method of claim 5, wherein the items in the target store that are similar to the items in the store to be compared are determined as follows:
sim_sku＝
{Tskua|(Tskua∈Tsku)∧(Cskub∈Csku)∧(cos(va,vb)＞β)}；
Wherein Tsku a represents the a-th item in Tsku, csku represents a set of all items in the store to be compared, csku b represents the b-th item in Csku; v a represents the vector of the a-th item in Tsku, v b represents the vector of the b-th item in Csku; cos (v a,vb) represents the cosine similarity of v a and v b and β represents the similarity threshold.
7. The method of claim 2, wherein determining a value for a volume dimension between the target store and the store to be compared comprises:
Obtaining a difference value of total sales of a target store and a store to be compared in a preset time period;
To be used for A value of a dimension of the object volume between the target store and the kth store to be compared;
Wherein D k represents the difference between the total sales of the target store and the kth store to be compared within a preset time period; d max represents the largest value of the difference between the total sales of the target store and all stores to be compared within the preset time period.
8. A store recommendation device, comprising:
The dimension value determining module is used for determining the value of the recommended dimension between the target store and the store to be compared; the recommendation dimension includes at least one of: browsing flow dimension, object similarity dimension, volume dimension and trusted identification; wherein determining a trusted identification between the target store and the store to be compared comprises: acquiring total sales Tsales of the target shops in a preset time period and total sales Csales of shops to be compared;
When Csales epsilon [ Tdown, tup ], determining that the trusted identification is 1;
When (when) Determining that the trusted identification is 0;
Wherein tup= Tsales ·η up,ηup > 1;
Where η up denotes an upper limit coefficient, η down1 denotes a first lower limit coefficient, η down2 denotes a second lower limit coefficient, μ denotes a sales threshold;
and the recommending module is used for determining the score of the stores to be compared according to the numerical value of the recommending dimension based on a preset scoring model, and recommending the stores to be compared to the target stores according to the sequence of the score from high to low.
9. The device according to claim 8, wherein stores containing the target class are used as stores to be compared; the dimension value determining module determines the target category as follows:
mainC＝{Ti|Tsalesi-1＜Tsales·λ≤Tsalesi,i≥2}∪{T1}，0＜λ≤1；
Wherein mainC denotes a set of target categories; t i represents the first i article categories after sorting sales of all article categories from big to small in a preset time period in a target store; tsales i denotes the sum of sales of the first i article categories after sorting sales of all article categories from large to small in a preset time period in the target store; tsales denotes the total sales in the target store for a preset period of time, and λ denotes the category selection threshold.
10. The apparatus of claim 9, wherein the dimension determination module determines a value of a browse traffic dimension between a target store and a store to be compared, comprising:
determining the jump probability from the target store to the store to be compared based on the user browsing record;
Taking the jump probability as the numerical value of the browsing flow dimension between the target store and the store to be compared.
11. The apparatus of claim 10, wherein the determining dimension value module determines a probability of a jump of the target store to a store to be compared based on a user browsing record, comprising:
Determining a user set M to be counted based on user browsing records in a preset historical period or a preset period from the current moment to the current moment, wherein the user to be counted is related to browsing information of the object categories in the object category set mainC on the object shops and the shops to be compared;
Determining a set S mc formed by stores browsed by the mth user to be counted about the c-th target category in mainC according to the browsing information of the user to be counted about the target category to the stores;
Establishing a mapping relation between every two elements in the set S mk, wherein
According to the mapping relation in the set S mc, the transition probability a j from the target store to the j-th store to be compared is determined by adopting the following formula:
Wherein n represents the sum of the numbers of the mapping relations from the target store in the set S mc; n j represents the sum of the numbers of the mapping relations from the target store to the j-th store to be compared in the set S mc; the || symbol represents the number of elements contained in the collection in the || symbol.
12. The apparatus of claim 9, wherein the dimension determination module determines a value of an item similarity dimension between a target store and a store to be compared, comprising:
determining vectors of all articles in a target store and a store to be compared based on a word frequency-inverse text frequency index algorithm;
According to vectors of all articles in the target store and the stores to be compared, determining articles similar to the articles in the stores to be compared in the target store;
To be used for A value as an item similarity dimension between the target store and the store to be compared; where sim_sku represents a set of items in the target store that are similar to the items in the store to be compared, tsku represents a set of all items in the target store; the || symbol represents the number of elements contained in the collection in the || symbol.
13. The apparatus of claim 12, wherein the dimension value determination module determines items in the target store that are similar to items in the store to be compared by:
sim_sku＝
{Tskua|(Tskua∈Tsku)∧(Cskub∈Csku)∧(cos(va,vb)＞β)}；
Wherein Tsku a represents the a-th item in Tsku, csku represents a set of all items in the store to be compared, csku b represents the b-th item in Csku; v a represents the vector of the a-th item in Tsku, v b represents the vector of the b-th item in Csku; cos (v a,vb) represents the cosine similarity of v a and v b and β represents the similarity threshold.
14. The apparatus of claim 9, wherein the dimension determination module determines a value of a volume dimension between a target store and a store to be compared, comprising:
Obtaining a difference value of total sales of a target store and a store to be compared in a preset time period;
To be used for A value of a dimension of the object volume between the target store and the kth store to be compared;
Wherein D k represents the difference between the total sales of the target store and the kth store to be compared within a preset time period; d max represents the largest value of the difference between the total sales of the target store and all stores to be compared within the preset time period.
15. A store-recommended electronic device, comprising:
One or more processors;
Storage means for storing one or more programs,
When executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-7.
16. A computer readable medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810891276.1A CN110827101B (en) | 2018-08-07 | 2018-08-07 | Shop recommending method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810891276.1A CN110827101B (en) | 2018-08-07 | 2018-08-07 | Shop recommending method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110827101A CN110827101A (en) | 2020-02-21 |
| CN110827101B true CN110827101B (en) | 2024-05-24 |
Family
ID=69533642
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810891276.1A Active CN110827101B (en) | 2018-08-07 | 2018-08-07 | Shop recommending method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110827101B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113763080A (en) * | 2020-08-26 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Method and device for determining recommended article, electronic equipment and storage medium |
| CN113129053B (en) * | 2021-03-29 | 2024-05-21 | 北京沃东天骏信息技术有限公司 | Information recommendation model training method, information recommendation method and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4960526B1 (en) * | 2011-09-29 | 2012-06-27 | 株式会社ぐるなび | Store information provision system |
| CN105005579A (en) * | 2015-05-28 | 2015-10-28 | 携程计算机技术（上海）有限公司 | Personalized sorting method and system of hotel room types in OTA (Online Travel Agent) website |
| CN105631717A (en) * | 2016-02-07 | 2016-06-01 | 徐璇炫 | Cost performance real-time bidding method and device |
| CN107247786A (en) * | 2017-06-15 | 2017-10-13 | 北京小度信息科技有限公司 | Method, device and server for determining similar users |
| CN107291939A (en) * | 2017-07-06 | 2017-10-24 | 携程计算机技术（上海）有限公司 | The clustering match method and system of hotel information |
| CN107464037A (en) * | 2017-07-05 | 2017-12-12 | 九次方大数据信息集团有限公司 | Enterprise's portrait method and system based on multi objective dimensional model |
| CN107730313A (en) * | 2017-09-30 | 2018-02-23 | 口碑(上海)信息技术有限公司 | Recommend method and device in shop based on rationale for the recommendation |
| CN107851268A (en) * | 2015-07-24 | 2018-03-27 | 万事达卡国际股份有限公司 | For carrying out the method and system of ranking to businessman |
-
2018
- 2018-08-07 CN CN201810891276.1A patent/CN110827101B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4960526B1 (en) * | 2011-09-29 | 2012-06-27 | 株式会社ぐるなび | Store information provision system |
| CN105005579A (en) * | 2015-05-28 | 2015-10-28 | 携程计算机技术（上海）有限公司 | Personalized sorting method and system of hotel room types in OTA (Online Travel Agent) website |
| CN107851268A (en) * | 2015-07-24 | 2018-03-27 | 万事达卡国际股份有限公司 | For carrying out the method and system of ranking to businessman |
| CN105631717A (en) * | 2016-02-07 | 2016-06-01 | 徐璇炫 | Cost performance real-time bidding method and device |
| CN107247786A (en) * | 2017-06-15 | 2017-10-13 | 北京小度信息科技有限公司 | Method, device and server for determining similar users |
| CN107464037A (en) * | 2017-07-05 | 2017-12-12 | 九次方大数据信息集团有限公司 | Enterprise's portrait method and system based on multi objective dimensional model |
| CN107291939A (en) * | 2017-07-06 | 2017-10-24 | 携程计算机技术（上海）有限公司 | The clustering match method and system of hotel information |
| CN107730313A (en) * | 2017-09-30 | 2018-02-23 | 口碑(上海)信息技术有限公司 | Recommend method and device in shop based on rationale for the recommendation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110827101A (en) | 2020-02-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108153901B (en) | Knowledge graph-based information pushing method and device | |
| CN107679211B (en) | Method and device for pushing information | |
| CN109145280B (en) | Information pushing method and device | |
| US11836778B2 (en) | Product and content association | |
| CN110020162B (en) | User identification method and device | |
| CN107832338B (en) | Method and system for recognizing core product words | |
| CN110766486A (en) | Method and device for determining item category | |
| CN107291835B (en) | Search term recommendation method and device | |
| CN110827101B (en) | Shop recommending method and device | |
| CN110992127A (en) | Article recommendation method and device | |
| CN111160410A (en) | Object detection method and device | |
| CN107291923B (en) | Information processing method and device | |
| CN113450172A (en) | Commodity recommendation method and device | |
| CN112862553A (en) | Commodity recommendation method and device | |
| CN107357847B (en) | Data processing method and device | |
| CN114036397B (en) | Data recommendation method, device, electronic equipment and medium | |
| CN110766431A (en) | Method and device for judging whether user is sensitive to coupon | |
| CN110544140A (en) | method and device for processing browsing data | |
| CN111125514B (en) | Method, device, electronic equipment and storage medium for analyzing user behaviors | |
| CN113722593A (en) | Event data processing method and device, electronic equipment and medium | |
| CN110738538B (en) | Method and device for identifying similar objects | |
| CN111339434B (en) | Information recommendation method and device, electronic equipment and computer storage medium | |
| CN113327145A (en) | Article recommendation method and device | |
| CN110110199B (en) | Information output method and device | |
| CN111833085A (en) | Method and device for calculating price of article |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |