CN111861670A - Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and storage medium - Google Patents
Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and storage medium Download PDFInfo
- Publication number
- CN111861670A CN111861670A CN202010724869.6A CN202010724869A CN111861670A CN 111861670 A CN111861670 A CN 111861670A CN 202010724869 A CN202010724869 A CN 202010724869A CN 111861670 A CN111861670 A CN 111861670A
- Authority
- CN
- China
- Prior art keywords
- commodity
- historical consumption
- consumption data
- data
- codes
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000000605 extraction Methods 0.000 claims description 28
- 238000004590 computer program Methods 0.000 claims 2
- 230000001815 facial effect Effects 0.000 claims 1
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 3
- 101500011077 Diploptera punctata Allatostatin-9 Proteins 0.000 description 2
- 101500011075 Diploptera punctata Allatostatin-7 Proteins 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the field of artificial intelligence and discloses a commodity recommendation method, a commodity recommendation device, commodity recommendation equipment and a storage medium. The method comprises the following steps: acquiring image data to be analyzed, analyzing the characteristics of the image data based on a preset face recognition algorithm, and acquiring historical consumption data of a target client; judging whether the historical consumption data is empty or not; if the historical consumption data is null, randomly outputting commodity codes in a preset commodity code catalog, and price information and placing position information corresponding to the commodity codes; if the historical consumption data is not null, extracting the commodity codes in the historical consumption data to obtain a commodity code set; and capturing price information and placement position information corresponding to the commodity codes in the commodity code set from the historical consumption data, and outputting the commodity codes, the price information and the placement position information.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a commodity recommendation method, a commodity recommendation device, commodity recommendation equipment and a storage medium.
Background
With the development of economy, the material level of people is continuously improved, and more commodities appear in front of people. With the increase in the variety and brand of commodities, the consumption of people is shifted from the original single commodity to multiple commodities. However, when people select from a plurality of commodities, the selection time is too long due to the fact that too much information of the commodities is too large.
The rapid progress of the internet technology enables people to use computers to screen when facing multi-commodity, and the shopping efficiency of the public in large-scale shopping malls is improved. However, the current screening mode of large shopping malls for commodities is to search on a computer by people themselves actively, and the people are not specific. However, different customers have different consumption habits and preferences, and a system capable of recommending commodities for specific individuals is needed in a large-scale shopping mall at present.
Disclosure of Invention
The invention mainly aims to solve the technical problem that intelligent commodity recommendation cannot be carried out aiming at specific individuals in large shopping malls.
The invention provides a commodity recommendation method in a first aspect, which comprises the following steps:
acquiring image data to be analyzed, analyzing the characteristics of the image data based on a preset face recognition algorithm, and acquiring historical consumption data of a target client;
judging whether the historical consumption data is empty or not;
if the historical consumption data is null, randomly outputting commodity codes in a preset commodity code catalog, and price information and placing position information corresponding to the commodity codes;
if the historical consumption data is not null, extracting the commodity codes in the historical consumption data to obtain a commodity code set;
and capturing price information and placement position information corresponding to the commodity codes in the commodity code set from the historical consumption data, and outputting the commodity codes, the price information and the placement position information.
Optionally, in a first implementation manner of the first aspect of the present invention, the analyzing the features of the image data based on a preset face recognition algorithm to obtain historical consumption data of the target client includes:
judging whether a face image exists in the image data according to a preset face recognition algorithm;
if not, randomly outputting the commodity codes in a preset commodity code catalog, and price information and placing position information corresponding to the commodity codes;
and if so, analyzing the face image to obtain historical consumption data of the target client.
Optionally, in a second implementation manner of the first aspect of the present invention, the analyzing the face image to obtain historical consumption data of the target client includes:
judging whether the number of the faces detected in the face image is unique or not;
if the number of the faces is unique, extracting face data in the face image, and analyzing the face data to obtain historical consumption data of a target client;
and if the number of the human faces is not unique, calculating an area value corresponding to the human face data in the human face image, and analyzing the human face data with the maximum area value to obtain historical consumption data of the target client.
Optionally, in a third implementation manner of the first aspect of the present invention, the extracting the commodity code from the historical consumption data to obtain a commodity code set includes:
counting the frequency of records corresponding to all commodity codes in the historical consumption data;
according to the recorded frequency, arranging commodity codes in the historical consumption data from large to small to obtain a frequency arrangement data set;
and extracting the commodity codes in the frequency arrangement data set according to a preset code extraction threshold value and the arrangement sequence to obtain a commodity code set.
Optionally, in a fourth implementation manner of the first aspect of the present invention, the extracting, according to a preset code extraction threshold, the commodity codes in the frequency permutation data set according to the permutation order to obtain a commodity code set includes:
counting the number of commodity codes in the frequency array data set, and judging whether the number is greater than a preset code extraction threshold value;
if the frequency range data set is not greater than the code extraction threshold, confirming the frequency range data set as a commodity code set;
and if the number of the commodity codes is larger than the code extraction threshold, extracting the commodity codes in the arrangement consumption data set from large to small according to the record frequency to obtain a commodity code set.
Optionally, in a fifth implementation manner of the first aspect of the present invention, the extracting the commodity code from the historical consumption data to obtain a commodity code set further includes:
reading the latest recording date corresponding to all commodity codes in the historical consumption data;
respectively calculating interval duration of the current date and all the latest recorded dates, and arranging the commodity codes in the historical consumption data from small to large according to the interval duration to obtain a date arrangement data set;
and extracting the commodity codes in the date arrangement data set from small to large according to the interval duration according to a preset code limit value to obtain a commodity code set.
Optionally, in a sixth implementation manner of the first aspect of the present invention, after the capturing price information and placement position information corresponding to a product code in the product code set from the historical consumption data, and outputting the product code, the price information, and the placement position information, the method further includes:
acquiring updated image data based on preset refreshing time;
analyzing the characteristics of the updated image data according to the face recognition algorithm to obtain an updated target client corresponding to the updated image data;
judging whether the update target client is consistent with the target client;
and if not, reading the historical consumption data of the update target client, and outputting the data according to the historical consumption data.
A second aspect of the present invention provides a commodity recommending apparatus, including:
the acquisition module is used for acquiring image data to be analyzed and analyzing the characteristics of the image data based on a preset face recognition algorithm to obtain historical consumption data of a target client;
the judging module is used for judging whether the historical consumption data is empty or not;
the output module is used for randomly outputting commodity codes in a preset commodity code catalogue and price information and placing position information corresponding to the commodity codes if the historical consumption data are null;
the extraction module is used for extracting the commodity codes in the historical consumption data to obtain a commodity code set if the historical consumption data is not empty;
and the grabbing module is used for grabbing price information and placing position information corresponding to the commodity codes in the commodity code set from the historical consumption data and outputting the commodity codes, the price information and the placing position information.
A third aspect of the present invention provides a commodity recommending apparatus including: a memory having instructions stored therein and at least one processor, the memory and the at least one processor interconnected by a line; the at least one processor invokes the instructions in the memory to cause the merchandise recommendation device to perform the merchandise recommendation method described above.
A fourth aspect of the present invention provides a computer-readable storage medium having stored therein instructions, which, when run on a computer, cause the computer to execute the above-described article recommendation method.
Drawings
Fig. 1 is a schematic diagram of a first embodiment of a product recommendation method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a second embodiment of a product recommendation method according to an embodiment of the invention;
FIG. 3 is a diagram of a third embodiment of a merchandise recommendation method according to an embodiment of the invention;
FIG. 4 is a schematic diagram of an embodiment of a merchandise recommendation device according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of another embodiment of a merchandise recommendation device according to an embodiment of the present invention;
fig. 6 is a schematic diagram of an embodiment of a product recommendation device in the embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a commodity recommendation method, a commodity recommendation device, commodity recommendation equipment and a storage medium.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
For convenience of understanding, a detailed flow of an embodiment of the present invention is described below, and referring to fig. 1, a first embodiment of a product recommendation method according to an embodiment of the present invention includes:
101. acquiring image data to be analyzed, analyzing the characteristics of the image data based on a preset face recognition algorithm, and obtaining historical consumption data of a target client;
in this embodiment, the built-in camera is used to collect the internal image information of the shopping mall, and when a customer approaches to query the commodity data, the image data changes, and the face of the target customer appears in the image data. And analyzing the face image in the image data according to a built-in face recognition algorithm, and acquiring historical consumption data of the client according to the face image. When the image is analyzed, the CNN model is adopted to analyze the image characteristics, and compared with the traditional CNN model, the function of calculating the face area is added when the image is captured. When the number of the faces is greater than 1, the pixel area size of the faces needs to be compared to judge the distance so that the nearest customer is determined as the target customer.
102. Judging whether the historical consumption data is empty;
in this embodiment, the search obtains historical consumption data of the target client, and the historical consumption data is captured from the consumption database. And the consumption database is searched according to the information of the target client, the information of the target client is possible to be null, when the historical consumption data is { nell }, the historical consumption data is null, and when the historical consumption data is { code: SASA54ss4, type: win, name: ADA, price: 145, location: XXX is not empty.
103. If the historical consumption data is null, randomly outputting commodity codes in a preset commodity code catalog, and price information and placing position information corresponding to the commodity codes;
in this embodiment, when the historical consumption data is returned as { nell }, the commodity code is randomly selected from the commodity code list. For example: four commodity codes, ADAS1, DDDDz1, DDqa554, SSk123, were randomly selected. Then capturing the price and placing position information corresponding to ADAS1, DDDDz1, DDqa554 and SSk12, and finally outputting { code: ADAS1 name EEEprice: 144 location: v, code: DDDDz1 name: QQQ price: 54 location: b, code: DDqa554 name: KKK price: 889 price: c, code: SSk12 name pE price: 4435 location: d, wherein code is data code, name is name, price is price, and location is commodity placing position.
104. If the historical consumption data is not null, extracting the commodity codes in the historical consumption data to obtain a commodity code set;
in this embodiment, when the historical consumption data has data, the commodity codes in the historical consumption data need to be extracted, and the commodity codes may be arranged according to the number of times of appearance of the commodity codes in the historical consumption data, and the commodity codes are extracted from top to bottom. Or extracting from near to far according to the nearest time of the commodity code, setting an extraction threshold value, not extracting when the extraction threshold value is exceeded, and finally obtaining the commodity code set according to the extraction rule.
105. And capturing price information and placing position information corresponding to the commodity codes in the commodity code set from historical consumption data, and outputting the commodity codes, the price information and the placing position information.
In this embodiment, the price information and the placement position information corresponding to the product code in the product code set are captured in the historical consumption data, and then the product code, the price information, and the placement position information are output as { code: SASA54ss4, type: win, name: ADA, price: 145, location: XXX }, where code is a tag indicating a code of the item, type is a tag indicating a type of the item, name is an indication of a name, price is an indication of a price amount, and location is an indication of a location. The output information can be in a preset display screen or can be bound with a mobile phone of a client to send the information to the mobile phone of the client.
In the embodiment of the invention, the identity information of the inquired customer is actively distinguished through the face recognition technology, the historical consumption record of the target customer is captured, and the commodity is recommended according to the historical consumption record, so that the commodity can be recommended and commodity information can be provided in a large-scale market in an individualized and intelligent manner, and the commodity information transmission efficiency is improved.
Referring to fig. 2, a second embodiment of the merchandise recommendation method according to the embodiment of the present invention includes:
201. acquiring image data to be analyzed;
the method embodiment described in this embodiment is similar to the first embodiment, and reference may be made to the corresponding process in the foregoing method embodiment, which is not described herein again.
202. Judging whether a face image exists in the image data according to a preset face recognition algorithm;
in this embodiment, the face recognition algorithm is a trained CNN neural network model, analyzes features in the image data, and determines whether a face of the image data exists based on convolution calculation.
203. If not, randomly outputting price information and placing position information corresponding to the commodity codes in the preset commodity code catalog;
in this embodiment, if there is no face image, the commodity content, price, and placement position information are output at random. Note that there is no face image at this time, and there is no problem in terms of logic because the customer may have a mask, a veil, or the like, and thus the product recommendation is still required.
204. If so, judging whether the number of the detected faces in the face image is unique;
in this embodiment, if a face image is detected, the number of faces is directly determined, and the number of face determinations in the training model is satisfied.
205. If the number of the faces is unique, extracting face data in the face image, and analyzing the face data to obtain historical consumption data of a target client;
in this embodiment, after the number of faces is determined to be unique, the face image is analyzed, the face features are extracted, an analysis matrix is generated, and the consumption data of the target client is obtained through multi-layer convolution judgment of the analysis matrix.
206. If the number of the human faces is not unique, calculating an area value corresponding to human face data in the human face image, and analyzing the human face data with the largest area value to obtain historical consumption data of the target client;
in this embodiment, when calculating the area corresponding to the face data, the face data is first converted into a matrix, and then the corresponding face area value is determined according to the number of elements of the matrix. According to the comparison of the area values, the client closest to the invention is judged, and a mutual comparison method or a transmission comparison method can be used for realizing the comparison of the areas. And finally, extracting the face image with the largest area value for analysis, and calculating the historical consumption data of the target client according to the face image.
207. Judging whether the historical consumption data is empty;
the method embodiment described in this embodiment is similar to the first embodiment, and reference may be made to the corresponding process in the foregoing method embodiment, which is not described herein again.
208. If the historical consumption data is null, randomly outputting commodity codes in a preset commodity code catalog, and price information and placing position information corresponding to the commodity codes;
the method embodiment described in this embodiment is similar to the first embodiment, and reference may be made to the corresponding process in the foregoing method embodiment, which is not described herein again.
209. If the historical consumption data is not null, reading the latest recording date corresponding to all the commodity codes in the historical consumption data;
in the present embodiment, the read product code SDAAS122 corresponds to the latest date of recording 2020.7.10, the product code SDAAS120 corresponds to the latest date of recording 2020.7.12, and the product code SDAAS121 corresponds to the latest date of recording 2020.7.11.
210. Respectively calculating interval duration of the current date and all latest recorded dates, and arranging commodity codes in the historical consumption data from small to large according to the interval duration to obtain a date arrangement data set;
in this embodiment, when the current date and time is 2020.7.14, the interval duration corresponding to the SDAAS122, SDAAS120, SDAAS121 is calculated to be 4 days, 2 days, 3 days, and the commodity codes are ordered as {1SDAAS120, 2SDAAS121, 3SDAAS122} according to the interval duration.
211. According to a preset code extraction threshold value, extracting commodity codes in the data set from small to large according to interval duration to obtain a commodity code set;
in this embodiment, since the code extraction threshold is 2, two commodity codes are extracted from {1SDAAS120, 2SDAAS121, 3SDAAS122} to obtain a commodity code set of { SDAAS120, SDAAS121 }.
212. Capturing price information and placing position information corresponding to the commodity codes in the commodity code set from historical consumption data, and outputting the commodity codes, the price information and the placing position information;
the method embodiment described in this embodiment is similar to the first embodiment, and reference may be made to the corresponding process in the foregoing method embodiment, which is not described herein again.
213. Acquiring updated image data based on preset refreshing time;
in the present embodiment, the refresh time period is 2 seconds, and an image distinguished from the previous image data is acquired again every 2 seconds.
214. Analyzing the characteristics of the updated image data according to a face recognition algorithm to obtain an updated target client corresponding to the updated image data;
in this embodiment, the updated image data is analyzed based on a face recognition algorithm to obtain tag data of an updated target client, and the tag data is compared with the tag data of the target client to determine whether the tag data is consistent with the tag data of the target client.
215. Judging whether the update target client is consistent with the target client;
in this embodiment, the comparison is performed by using a label method, the label of the target client is set as ASA2, and after the data of the update target client is analyzed, the content of the label is interpreted as ASA2, which indicates that the update target client is consistent with the target client. If the label of the update target client is interpreted as ASA1, the update target client is not the same client.
216. And if not, reading the historical consumption data of the updated target client, and outputting the data according to the historical consumption data.
In this embodiment, if the historical consumption data is not consistent with the product recommendation data, the process returns to step 207 to analyze and analyze the historical consumption data again, and finally the product recommendation data is output.
In the embodiment of the invention, the identity information of the inquired customer is actively distinguished through the face recognition technology, the historical consumption record of the target customer is captured, and the commodity is recommended according to the historical consumption record, so that the commodity can be recommended and commodity information can be provided in a large-scale market in an individualized and intelligent manner, and the commodity information transmission efficiency is improved.
Referring to fig. 3, a third embodiment of the product recommendation method according to the embodiment of the present invention includes:
301. acquiring image data to be analyzed, analyzing the characteristics of the image data based on a preset face recognition algorithm, and obtaining historical consumption data of a target client;
the method embodiment described in this embodiment is similar to the first embodiment, and reference may be made to the corresponding process in the foregoing method embodiment, which is not described herein again.
302. Judging whether the historical consumption data is empty;
the method embodiment described in this embodiment is similar to the first embodiment, and reference may be made to the corresponding process in the foregoing method embodiment, which is not described herein again.
303. If the historical consumption data is null, randomly outputting commodity codes in a preset commodity code catalog, and price information and placing position information corresponding to the commodity codes;
the method embodiment described in this embodiment is similar to the first embodiment, and reference may be made to the corresponding process in the foregoing method embodiment, which is not described herein again.
304. If the historical consumption data is not empty, counting the frequency counts corresponding to all commodity codes in the historical consumption data;
in this embodiment, the frequency of recording all the commodities such as the statistical commodity codes AASDF89, WERQ432, fff42s, sss112 is 10 times, 4 times, 5 times, and 66 times.
305. According to the recorded frequency, arranging commodity codes in the historical consumption data from large to small to obtain a frequency arrangement data set;
in this embodiment, the commodity codes are arranged in the order of 66 times, 10 times, 5 times, and 4 times according to the frequency size to generate a set in the arrangement order of sss112, AASDF89, fff42s, and WERQ432, and a frequency arrangement data set of {1ss112, 2AASDF89, 3fff42s, and 4WERQ432} is obtained.
306. Counting the number of commodity codes in the frequency array data set, and judging whether the number is greater than a preset code extraction threshold value;
in this embodiment, the preset code extraction threshold is set to 2, and if the number of commodity codes of { ss112, AASDF89, fff42s, WERQ432} is counted to be 4, it is determined that 4 is greater than 2.
307. If the frequency number array data set is not greater than the code extraction threshold, the frequency number array data set is confirmed to be a commodity code set;
in the present embodiment, the code extraction threshold is set to 9, and the number of commodity codes of { ss112, AASDF89, fff42s, WERQ432} is 4, and { ss112, AASDF89, fff42s, 4WERQ432} is confirmed as the commodity code set.
308. If the number of the commodity codes is larger than the code extraction threshold value, commodity codes in the arrangement consumption data set are extracted from large to small according to the record frequency to obtain a commodity code set;
in this embodiment, the code extraction threshold is set to 2, and 2 commodity codes are extracted according to {1ss112, 2AASDF89, 3fff42s, 4WERQ432} frequency from large to small, resulting in a commodity code set of {1ss112, AASDF89 }.
309. And capturing price information and placing position information corresponding to the commodity codes in the commodity code set from historical consumption data, and outputting the commodity codes, the price information and the placing position information.
The method embodiment described in this embodiment is similar to the first embodiment, and reference may be made to the corresponding process in the foregoing method embodiment, which is not described herein again.
In the embodiment of the invention, the identity information of the inquired customer is actively distinguished through the face recognition technology, the historical consumption record of the target customer is captured, and the commodity is recommended according to the historical consumption record, so that the commodity can be recommended and commodity information can be provided in a large-scale market in an individualized and intelligent manner, and the commodity information transmission efficiency is improved.
In the above description of the method for recommending a commodity according to an embodiment of the present invention, referring to fig. 4, a commodity recommending apparatus according to an embodiment of the present invention is described as follows, where an embodiment of the commodity recommending apparatus according to an embodiment of the present invention includes:
the acquisition module 401 is configured to acquire image data to be analyzed, and analyze features of the image data based on a preset face recognition algorithm to obtain historical consumption data of a target client;
a judging module 402, configured to judge whether the historical consumption data is empty;
an output module 403, configured to randomly output a commodity code in a preset commodity code catalog, and price information and placement position information corresponding to the commodity code if the historical consumption data is null;
an extracting module 404, configured to extract a commodity code from the historical consumption data to obtain a commodity code set if the historical consumption data is not empty;
a capturing module 405, configured to capture price information and placement position information corresponding to the commodity codes in the commodity code set from the historical consumption data, and output the commodity codes, the price information, and the placement position information.
In the embodiment of the invention, the identity information of the inquired customer is actively distinguished through the face recognition technology, the historical consumption record of the target customer is captured, and the commodity is recommended according to the historical consumption record, so that the commodity can be recommended and commodity information can be provided in a large-scale market in an individualized and intelligent manner, and the commodity information transmission efficiency is improved.
Referring to fig. 5, another embodiment of the merchandise recommendation device according to the embodiment of the present invention includes:
the acquisition module 401 is configured to acquire image data to be analyzed, and analyze features of the image data based on a preset face recognition algorithm to obtain historical consumption data of a target client;
a judging module 402, configured to judge whether the historical consumption data is empty;
an output module 403, configured to randomly output a commodity code in a preset commodity code catalog, and price information and placement position information corresponding to the commodity code if the historical consumption data is null;
an extracting module 404, configured to extract a commodity code from the historical consumption data to obtain a commodity code set if the historical consumption data is not empty;
a capturing module 405, configured to capture price information and placement position information corresponding to the commodity codes in the commodity code set from the historical consumption data, and output the commodity codes, the price information, and the placement position information.
Wherein the obtaining module 401 includes:
the judging unit 4011 is configured to judge whether a face image exists in the image data according to a preset face recognition algorithm;
the output unit 4012 is configured to randomly output the commodity codes in the preset commodity code catalog, and the price information and the placement position information corresponding to the commodity codes if the commodity codes do not exist;
and the analyzing unit 4013 is configured to analyze the face image if the face image exists, so as to obtain historical consumption data of the target customer.
The analysis unit 4013 is specifically configured to:
judging whether the number of the faces detected in the face image is unique or not;
if the number of the faces is unique, extracting face data in the face image, and analyzing the face data to obtain historical consumption data of a target client;
and if the number of the human faces is not unique, calculating an area value corresponding to the human face data in the human face image, and analyzing the human face data with the maximum area value to obtain historical consumption data of the target client.
Wherein the extraction module 404 comprises:
the counting unit 4041 is configured to count the record frequency numbers corresponding to all the commodity codes in the historical consumption data;
the arranging unit 4042 is configured to arrange the commodity codes in the historical consumption data from large to small according to the record frequency to obtain a frequency arrangement data set;
the extracting unit 4043 is configured to extract the commodity codes in the frequency array data set according to an array sequence according to a preset code extraction threshold, so as to obtain a commodity code set.
Wherein, the arrangement unit 4042 is specifically configured to:
counting the number of commodity codes in the frequency array data set, and judging whether the number is greater than a preset code extraction threshold value;
if the frequency range data set is not greater than the code extraction threshold, confirming the frequency range data set as a commodity code set;
and if the number of the commodity codes is larger than the code extraction threshold, extracting the commodity codes in the arrangement consumption data set from large to small according to the record frequency to obtain a commodity code set.
Wherein, the extracting module 404 may be further specifically configured to:
reading the latest recording date corresponding to all commodity codes in the historical consumption data;
respectively calculating interval duration of the current date and all the latest recorded dates, and arranging the commodity codes in the historical consumption data from small to large according to the interval duration to obtain a date arrangement data set;
and extracting the commodity codes in the date arrangement data set from small to large according to the interval duration according to a preset code limit value to obtain a commodity code set.
The commodity recommending device further includes an updating module 406, where the updating module 406 is specifically configured to:
acquiring updated image data based on preset refreshing time;
analyzing the characteristics of the updated image data according to the face recognition algorithm to obtain an updated target client corresponding to the updated image data;
judging whether the update target client is consistent with the target client;
and if not, reading the historical consumption data of the update target client, and outputting the data according to the historical consumption data.
In the embodiment of the invention, the identity information of the inquired customer is actively distinguished through the face recognition technology, the historical consumption record of the target customer is captured, and the commodity is recommended according to the historical consumption record, so that the commodity can be recommended and commodity information can be provided in a large-scale market in an individualized and intelligent manner, and the commodity information transmission efficiency is improved.
Fig. 4 and 5 describe the commodity recommending apparatus in the embodiment of the present invention in detail from the perspective of the modular functional entity, and the commodity recommending apparatus in the embodiment of the present invention is described in detail from the perspective of hardware processing.
Fig. 6 is a schematic structural diagram of an article recommendation device 600 according to an embodiment of the present invention, where the article recommendation device 600 may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 610 (e.g., one or more processors) and a memory 620, and one or more storage media 630 (e.g., one or more mass storage devices) storing applications 633 or data 632. Memory 620 and storage medium 630 may be, among other things, transient or persistent storage. The program stored in the storage medium 630 may include one or more modules (not shown), each of which may include a series of instruction operations for the article recommendation device 600. Still further, the processor 610 may be configured to communicate with the storage medium 630 to execute a series of instruction operations in the storage medium 630 on the merchandise recommendation device 600.
The merchandise-based recommendation device 600 may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input-output interfaces 660, and/or one or more operating systems 631, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, and the like. Those skilled in the art will appreciate that the configuration of the merchandise recommendation device illustrated in FIG. 6 does not constitute a limitation of the merchandise recommendation device based thereon, and may include more or less components than those illustrated, or some components in combination, or a different arrangement of components.
The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium, and which may also be a volatile computer-readable storage medium, having stored therein instructions, which, when executed on a computer, cause the computer to perform the steps of the merchandise recommendation method.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses, and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for recommending a commodity, comprising the steps of:
acquiring image data to be analyzed, analyzing the characteristics of the image data based on a preset face recognition algorithm, and acquiring historical consumption data of a target client;
judging whether the historical consumption data is empty or not;
if the historical consumption data is null, randomly outputting commodity codes in a preset commodity code catalog, and price information and placing position information corresponding to the commodity codes;
if the historical consumption data is not null, extracting the commodity codes in the historical consumption data to obtain a commodity code set;
and capturing price information and placement position information corresponding to the commodity codes in the commodity code set from the historical consumption data, and outputting the commodity codes, the price information and the placement position information.
2. The commodity recommendation method according to claim 1, wherein the analyzing the characteristics of the image data based on a preset face recognition algorithm to obtain historical consumption data of the target customer comprises:
judging whether a face image exists in the image data according to a preset face recognition algorithm;
if not, randomly outputting the commodity codes in a preset commodity code catalog, and price information and placing position information corresponding to the commodity codes;
and if so, analyzing the face image to obtain historical consumption data of the target client.
3. The commodity recommendation method according to claim 2, wherein the analyzing the facial image to obtain historical consumption data of the target customer comprises:
judging whether the number of the faces detected in the face image is unique or not;
if the number of the faces is unique, extracting face data in the face image, and analyzing the face data to obtain historical consumption data of a target client;
and if the number of the human faces is not unique, calculating an area value corresponding to the human face data in the human face image, and analyzing the human face data with the maximum area value to obtain historical consumption data of the target client.
4. The method for recommending merchandise according to claim 1, wherein said extracting the merchandise codes from the historical consumption data to obtain a set of merchandise codes comprises:
counting the frequency of records corresponding to all commodity codes in the historical consumption data;
according to the recorded frequency, arranging commodity codes in the historical consumption data from large to small to obtain a frequency arrangement data set;
and extracting the commodity codes in the frequency arrangement data set according to a preset code extraction threshold value and the arrangement sequence to obtain a commodity code set.
5. The method of claim 4, wherein the extracting the product codes in the frequency arrangement data set according to the arrangement order according to the preset code extraction threshold to obtain the product code set comprises:
counting the number of commodity codes in the frequency array data set, and judging whether the number is greater than a preset code extraction threshold value;
if the frequency range data set is not greater than the code extraction threshold, confirming the frequency range data set as a commodity code set;
and if the number of the commodity codes is larger than the code extraction threshold, extracting the commodity codes in the arrangement consumption data set from large to small according to the record frequency to obtain a commodity code set.
6. The method for recommending merchandise according to claim 1, wherein said extracting the merchandise codes from the historical consumption data to obtain a set of merchandise codes further comprises:
reading the latest recording date corresponding to all commodity codes in the historical consumption data;
respectively calculating interval duration of the current date and all the latest recorded dates, and arranging the commodity codes in the historical consumption data from small to large according to the interval duration to obtain a date arrangement data set;
and extracting the commodity codes in the date arrangement data set from small to large according to the interval duration according to a preset code limit value to obtain a commodity code set.
7. The commodity recommendation method according to any one of claims 1 to 6, wherein after said capturing price information and placement position information corresponding to commodity codes in said commodity code set from said historical consumption data and outputting said commodity codes, said price information and said placement position information, further comprising:
acquiring updated image data based on preset refreshing time;
analyzing the characteristics of the updated image data according to the face recognition algorithm to obtain an updated target client corresponding to the updated image data;
judging whether the update target client is consistent with the target client;
and if not, reading the historical consumption data of the update target client, and outputting the data according to the historical consumption data.
8. An article recommendation device, characterized by comprising:
the acquisition module is used for acquiring image data to be analyzed and analyzing the characteristics of the image data based on a preset face recognition algorithm to obtain historical consumption data of a target client;
the judging module is used for judging whether the historical consumption data is empty or not;
the output module is used for randomly outputting commodity codes in a preset commodity code catalogue and price information and placing position information corresponding to the commodity codes if the historical consumption data are null;
the extraction module is used for extracting the commodity codes in the historical consumption data to obtain a commodity code set if the historical consumption data is not empty;
and the grabbing module is used for grabbing price information and placing position information corresponding to the commodity codes in the commodity code set from the historical consumption data and outputting the commodity codes, the price information and the placing position information.
9. An article recommendation apparatus characterized by comprising: a memory having instructions stored therein and at least one processor, the memory and the at least one processor interconnected by a line;
the at least one processor invokes the instructions in the memory to cause the item recommendation device to perform the item recommendation method of any of claims 1-7.
10. A computer-readable storage medium, having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the item recommendation method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010724869.6A CN111861670A (en) | 2020-07-24 | 2020-07-24 | Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010724869.6A CN111861670A (en) | 2020-07-24 | 2020-07-24 | Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111861670A true CN111861670A (en) | 2020-10-30 |
Family
ID=72950486
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010724869.6A Pending CN111861670A (en) | 2020-07-24 | 2020-07-24 | Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111861670A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106709776A (en) * | 2015-11-17 | 2017-05-24 | 腾讯科技（深圳）有限公司 | Commodity pushing method and apparatus thereof |
| CN109214893A (en) * | 2018-08-31 | 2019-01-15 | 深圳春沐源控股有限公司 | Method of Commodity Recommendation, recommender system and computer installation |
| CN109284413A (en) * | 2018-09-07 | 2019-01-29 | 平安科技（深圳）有限公司 | Method of Commodity Recommendation, device, equipment and storage medium based on recognition of face |
| WO2020056980A1 (en) * | 2018-09-19 | 2020-03-26 | 平安科技（深圳）有限公司 | Service guiding method and apparatus based on human facial recognition, and storage medium |
| WO2020073524A1 (en) * | 2018-10-10 | 2020-04-16 | 深圳云天励飞技术有限公司 | Method and apparatus for recommending a product offline, and electronic device |
-
2020
- 2020-07-24 CN CN202010724869.6A patent/CN111861670A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106709776A (en) * | 2015-11-17 | 2017-05-24 | 腾讯科技（深圳）有限公司 | Commodity pushing method and apparatus thereof |
| CN109214893A (en) * | 2018-08-31 | 2019-01-15 | 深圳春沐源控股有限公司 | Method of Commodity Recommendation, recommender system and computer installation |
| CN109284413A (en) * | 2018-09-07 | 2019-01-29 | 平安科技（深圳）有限公司 | Method of Commodity Recommendation, device, equipment and storage medium based on recognition of face |
| WO2020056980A1 (en) * | 2018-09-19 | 2020-03-26 | 平安科技（深圳）有限公司 | Service guiding method and apparatus based on human facial recognition, and storage medium |
| WO2020073524A1 (en) * | 2018-10-10 | 2020-04-16 | 深圳云天励飞技术有限公司 | Method and apparatus for recommending a product offline, and electronic device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109697629B (en) | Product data pushing method and device, storage medium and computer equipment | |
| CN112035742A (en) | User portrait generation method, device, equipment and storage medium | |
| CN109190586B (en) | Customer's visiting analysis method, device and storage medium | |
| CN108229314B (en) | Target person searching method and device and electronic equipment | |
| US20130300729A1 (en) | Comparing Virtual and Real Images in a Shopping Experience | |
| CN106856015B (en) | A kind of Work attendance method and device | |
| CN107909443A (en) | Information-pushing method, apparatus and system | |
| CN103765457A (en) | Digital advertising system | |
| JP2011253344A (en) | Purchase behavior analysis device, purchase behavior analysis method and program | |
| CA3014365C (en) | System and method for gathering data related to quality of service in a customer service environment | |
| CN103207888A (en) | Product search device and product search method | |
| US20120296776A1 (en) | Adaptive interactive search | |
| CN108335317A (en) | Shopping guide method and device under a kind of line | |
| CN108537166A (en) | The method and apparatus for determining shelf pageview and analyzing pageview | |
| CN111191523A (en) | Information display method and device, storage medium and electronic device | |
| CN113191845A (en) | Online live shopping platform data analysis processing method, system, equipment and computer storage medium | |
| CN116739836B (en) | Restaurant data analysis method and system based on knowledge graph | |
| CN111914163A (en) | Medicine combination recommendation method and device, electronic equipment and storage medium | |
| JP2023507043A (en) | DATA PROCESSING METHOD, DEVICE, DEVICE, STORAGE MEDIUM AND COMPUTER PROGRAM | |
| CN113888254A (en) | Shelf commodity management method and electronic equipment | |
| CN103597485A (en) | Pattern extraction device and method | |
| KR102077630B1 (en) | System and method for analyzing commercial based on pos and video | |
| JP6314071B2 (en) | Information processing apparatus, information processing method, and program | |
| CN111861670A (en) | Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and storage medium | |
| CN112445985A (en) | Similar population acquisition method based on browsing behavior optimization |
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 |