CN117541355A - Commodity information display method and system - Google Patents
Commodity information display method and system Download PDFInfo
- Publication number
- CN117541355A CN117541355A CN202311629154.2A CN202311629154A CN117541355A CN 117541355 A CN117541355 A CN 117541355A CN 202311629154 A CN202311629154 A CN 202311629154A CN 117541355 A CN117541355 A CN 117541355A
- Authority
- CN
- China
- Prior art keywords
- information
- commodity
- user
- target
- merchandise
- 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 55
- 238000010276 construction Methods 0.000 claims description 13
- 238000012216 screening Methods 0.000 claims description 9
- 238000004883 computer application Methods 0.000 abstract description 2
- 238000003860 storage Methods 0.000 description 15
- 238000012545 processing Methods 0.000 description 9
- 230000006399 behavior Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000012163 sequencing technique Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002787 reinforcement Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 235000002198 Annona diversifolia Nutrition 0.000 description 1
- 241000282842 Lama glama Species 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000001932 seasonal effect Effects 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]
- G06Q30/0641—Shopping interfaces
- G06Q30/0643—Graphical representation of items or shoppers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/90335—Query processing
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a commodity information display method and a commodity information display system, and relates to the technical field of computer application. The commodity information display method comprises the steps of determining requirement information of a user through a LLM model according to information input by the user at the current moment, selecting a target prompt template matched with the requirement information from a preset prompt template library according to the requirement information, acquiring target commodity information from a commodity information library based on the requirement information and the target prompt template, and displaying the target commodity information to the user. According to the method, the LLM model is used for directly interacting with the user to obtain the demand information of the user at the current moment, and then the demand information and the target prompt template matched with the demand information are used for searching the commodity in the commodity information base to obtain the target commodity information.
Description
Technical Field
The invention relates to the technical field of computer application, in particular to a commodity information display method and a commodity information display system.
Background
Commodity information display technology is commonly used in the internet, particularly in the electronic commerce industry. The conventional commodity information display method generally collects data according to implicit feedback behaviors (including historical behaviors and real-time behaviors of a user), and performs a series of processing on the collected data to display commodity information. The commodity information display method cannot interact with the user directly, so that the current requirements of the user are accurately acquired, and the user experience is poor.
Disclosure of Invention
The invention aims to overcome the defect that the current demand of a user is accurately acquired because the commodity information display method in the prior art cannot be directly interacted with the user, so that the user experience is poor.
The invention solves the technical problems by the following technical scheme:
the invention provides a commodity information display method, which comprises the following steps:
determining the demand information of a user through a LLM model according to the information input by the user at the current moment;
selecting a target prompt template matched with the demand information from a preset prompt template library according to the demand information;
acquiring target commodity information from a commodity information base based on the demand information and the target prompt template;
and displaying the target commodity information to the user.
According to the method, the current demand of the user can be accurately obtained, commodity information is provided for the user based on the current demand, and convenience is provided for the user to efficiently search the commodity information and quickly select matched commodities.
Preferably, the obtaining the target commodity information from the commodity information base based on the requirement information and the target prompt template includes:
generating current retrieval information based on the demand information and the target prompt template;
and acquiring the target commodity information from the commodity information base according to the current retrieval information.
In the scheme, the target commodity information is obtained from the commodity information base through the requirement information and the target prompt template matched with the requirement information, and the target commodity information highly matched with the requirement of the user at the current moment can be directly screened out from the commodity information base by the method, so that the commodity information retrieval and selection efficiency of the user is improved.
Preferably, the displaying the target commodity information to the user includes:
sorting the target commodity information through the LLM model according to the correlation degree of the target commodity information and the demand information;
and outputting the ordered target commodity information.
In the scheme, after the target commodity information is ordered according to the correlation degree of the target commodity information and the demand information, commodities with higher correlation degree can be preferentially pushed to the user, and the time for the user to find a proper commodity from the pushed target commodity is saved.
Preferably, the demand information includes one or more of the following information: the supply and demand information of the commodity required by the user and the technical information of the commodity required by the user.
Preferably, the commodity information display method further comprises:
screening candidate commodity sequences from the commodity information base through a commodity recall model based on the demand information;
and acquiring the target commodity information from the candidate commodity sequence based on the demand information and the target prompt template.
In the scheme, the commodity recall model is set, so that the power consumption for sequencing the screened target commodity information in the LLM model can be reduced, meanwhile, the interference caused by invalid commodities can be avoided, convenience is brought to a user for quickly screening a plurality of candidate commodities possibly interested in from a commodity information base, commodity primary screening is realized, and the robustness of the LLM model is enhanced.
Preferably, the commodity information display method further comprises:
sending a dialogue request to the user, and if the user accepts the dialogue request, starting the constructed LLM model to carry out dialogue with the user; and if the user refuses the dialogue request, directly displaying any commodity in the commodity information base to the user.
In the scheme, two commodity browsing modes are provided for the user through setting the dialogue request mode, and the user can select according to specific conditions, so that the use experience of the user is further improved.
The invention also provides a commodity information display system, which is used for realizing the commodity information display method, and comprises the following steps:
the user demand information determining module is used for determining the demand information of the user through the LLM model according to the information input by the user at the current moment;
the target prompt template matching module is used for selecting a target prompt template matched with the requirement information from a preset prompt template library according to the requirement information;
the target commodity information acquisition module is used for acquiring target commodity information from a commodity information base based on the demand information and the target prompt template;
and the commodity information display module is used for displaying the target commodity information to the user.
Preferably, the merchandise information display system further comprises:
and the LLM model construction module is used for constructing the LLM model based on the language base model, commodity data and construction dialogue data.
Preferably, the merchandise information display system further comprises:
and the commodity recall module is used for screening candidate commodity sequences from the commodity information base through the commodity recall model based on the demand information.
Preferably, the merchandise information display system further comprises:
a dialogue request display module, configured to send a dialogue request to the user, and if the user accepts the dialogue request, enable the constructed LLM model to perform a dialogue with the user; and if the user refuses the dialogue request, directly displaying any commodity in the commodity information base to the user.
The invention also provides an electronic device comprising a processor and a memory, wherein at least one instruction or at least one section of program is stored in the memory, and the at least one instruction or the at least one section of program is loaded by the processor and executes the commodity information display method.
The present invention also provides a computer storage medium having at least one instruction or at least one program stored therein, the at least one instruction or the at least one program being loaded and executed by a processor to implement the merchandise information display method as described above.
The invention has the positive progress effects that:
according to the method, the LLM model is used for directly interacting with the user to obtain the demand information of the user at the current moment, and then the demand information and the target prompt template matched with the demand information are used for searching the commodity in the commodity information base to obtain the target commodity information.
Drawings
Fig. 1 is a schematic flow chart of a method for displaying merchandise information according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a commodity information data processing flow.
FIG. 3 is a schematic diagram of a preset hint template library construction process.
Fig. 4 is a second flowchart of a method for displaying merchandise information according to an embodiment of the present invention.
Fig. 5 is a schematic diagram of a merchandise information display system according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present application based on the embodiments herein.
In this embodiment, if a directional instruction (such as up, down, left, right, front, and rear … …) is provided, the directional instruction is merely used to explain the relative positional relationship between the components, the movement condition, and the like in a specific posture, and if the specific posture is changed, the directional instruction is changed accordingly.
In addition, if there is a description concerning "first", "second", etc., in this embodiment, the description of "first", "second", etc. is for descriptive purposes only and is not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to base that the technical solutions can be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be regarded as not exist and not within the protection scope of the present application.
Referring to fig. 1 to 5, the present embodiment provides a method for displaying merchandise information, and fig. 1 is a schematic flow chart of a method for displaying merchandise information provided in the embodiment of the present invention, and the present specification provides the method operation steps as an example or a flow chart, but may include more or less operation steps based on conventional or non-creative labor. The order of steps recited in the embodiments is merely one way of performing the order of steps and does not represent a unique order of execution. When implemented in a real system or server product, the methods illustrated in the embodiments or figures may be performed sequentially or in parallel (e.g., in a parallel processor or multithreaded environment). Specifically, as shown in fig. 1, the merchandise information display method includes:
s101: and determining the requirement information of the user through the LLM model according to the information input by the user at the current moment.
In this embodiment, the requirement information of the user is determined through a large-scale language model (Large Language Model, LLM) according to the received information input by the user at the current moment. The LLM model is based on an open-source Llama2 large language model (Llama 2 model), commodity information related data and construction dialogue data are added into the LLM model for fine adjustment, then human feedback reinforcement learning (Reinforcement Learning from Human Feedback, RLHF) training is carried out, and in this stage, sample data are constructed by adopting construction anonymous click and purchase behavior data for training. Based on the method, the LLM model for direct interaction with the user is obtained. The model is capable of completing identification and determination of user demand information through direct dialogue with the user. Specifically, the merchandise information related data includes, but is not limited to: basic characteristics of commodity attributes, such as commodity price, commodity material, commodity production place, commodity production date and quality guarantee period, etc. Construction of dialogue data includes, but is not limited to, obtaining desensitized pre-sales consultation data for the user from customer service, such as the user consulting overall dialogue information for a commodity usage or use case.
In other embodiments, the LLM model can also be built on a GPT-4 based model.
S103: and selecting a target prompt template matched with the demand information from a preset prompt template library according to the demand information.
In this embodiment, diversified prompt templates (i.e., prompt templates) are set in the preset prompt template library, and these templates can be specifically optimized for different needs of the user, and the target prompt template adapted to the needs information is selected from the preset prompt template library through the needs information, so that the content of the outputted commodity information can be more accurately limited, and the specific needs of the user can be better satisfied.
S105: and acquiring target commodity information from a commodity information base based on the demand information and the target prompt template.
In this embodiment, acquiring the target commodity information from the commodity information base based on the demand information and the target prompt template includes generating current search information based on the demand information and the target prompt template, and acquiring the target commodity information from the commodity information base according to the current search information.
Specifically, the template includes a keyword and a filling slot for inserting a specific text element to be extracted and coordinate position information of each text element (coordinate position information of the text element in a text segment). Keywords in the template of the template may include the type of merchandise, the purpose of the merchandise, the price of the merchandise, the specification of the merchandise, etc. And identifying the text elements corresponding to the keywords in the demand information and the coordinate position information of each text element, and filling the identified text elements and the coordinate position information of each text element into a filling groove reserved in the target prompt template to generate current retrieval information. And acquiring target commodity information from the commodity information base according to the generated current retrieval information. By the method, the target commodity information highly matched with the current time requirement of the user can be directly screened out from the commodity information base, and the commodity information retrieval and selection efficiency of the user is improved. The method can reduce the collection of the historical behavior data of the user, avoid the prediction of the current behavior of the user through the historical behavior data, and protect the privacy of the user.
In this embodiment, the LLM model needs to be called according to the demand information and the target prompt template, and the target commodity information is obtained from the commodity information base through the LLM model. Offline commodity information processing and preset Prompt template library construction (Prompt template engineering) are also required before the LLM model is invoked. As shown in fig. 2, fig. 2 is a schematic diagram of a commodity information data processing flow. And the commodity information data processing part is mainly used for processing offline data, starting an offline task and processing the commodity information data, firstly writing the processed data into a Hive data warehouse tool, then writing the data in the Hive into a remote dictionary service (Remote Dictionary Server, redis), and storing the data into the Redis for efficiently reading the data, thereby facilitating the use of the LLM model. As shown in fig. 3, fig. 3 is a schematic diagram of a preset hint template library construction flow. The method comprises the steps of presetting a Prompt template library, namely a template library construction flow, setting a rich and various template library, firstly writing optimized template data into Hive according to different requirements of different users on line, then writing data in Hive into Redis, and storing the data into Redis for efficient reading. When the LLM model is called, target commodity information is required to be obtained from a commodity information base, wherein the commodity information in the commodity information base is the commodity information processed by the offline commodity information.
S107: and displaying the target commodity information to the user.
In this embodiment, displaying target commodity information to a user includes: and sequencing the target commodity information through the LLM model according to the correlation degree of the target commodity information and the demand information, and outputting the sequenced target commodity information. The demand information includes one or more of the following: supply and demand information of commodities required by users and technical information of commodities required by users. After the target commodity information is ordered according to the correlation degree of the target commodity information and the demand information, commodities with higher correlation degree can be preferentially pushed to the user, and the time for the user to find a proper commodity from the pushed target commodity is saved.
Specifically, the supply and demand information of the commodity required by the user included in the demand information is the sum of commodity supply information, price information, flow channel information and commodity demand information, and the commodity supply information includes commodity quality, variety, specification, style, flower color, quantity and service mode, new technology, new material and application condition of new technology, current technical state and development trend of new commodity, package, trademark and use instruction of commodity; consumer impressions and ratings of goods; commercial advertisements, and the like. The commodity price information comprises factory, wholesale and retail prices of the commodity; commodity pricing standards; price ratios, regional differences and seasonal differences between commodities; consumer reactions to commodity price changes, and the like. The distribution channel information comprises commodity packaging, storage and transportation conditions; the distribution channel and mode of the commodity; sales of wholesalers and retailers; consumer or user impressions to retailers, sponsors; promotion and after-sales services, etc. Technical information of commodities required by users comprises new invention and patent technology; designing a new structure or a new formula of the commodity; advanced process flow; new equipment, new technology and new materials, and the like.
Sequencing the target commodity information through the LLM model based on the correlation degree of the target commodity information and the demand information, and outputting the sequenced target commodity information, wherein the correlation degree of the target commodity information and the demand information can be obtained through calculating similarity and other modes, and the main similarity calculation method comprises cosine similarity, pearson correlation coefficient, euclidean distance, jacquard distance and the like. For example, the demand information input by the user has the properties of price, purpose, variety, specification, color and the like of a certain commodity, and the target commodity information with the largest number of the properties which are the same as or similar to the price, purpose, variety, specification, color of the certain commodity input by the user is recommended to the user by the LLM model. In other words, the LLM model is used for arranging the target commodity information with higher correlation degree with the requirement information of the user at a front position for the user to browse, namely, the target commodity information is ordered from high to low according to the correlation degree with the requirement information of the user, and the ordered target commodity information is output.
In this embodiment, the commodity information display method further includes screening candidate commodity sequences from the commodity information base through a commodity recall model based on the demand information, and obtaining target commodity information from the candidate commodity sequences based on the demand information and the target prompt template.
Specifically, candidate commodity sequences are screened out from a commodity information base through a commodity recall model based on the demand information, the commodity recall model can search and recall commodities based on the demand information, M commodities possibly interested by a user are screened out of millions of commodities for each user rapidly (M is a specific number, for higher performance of a sequencing stage, a number within 1000 is generally adopted), the screened M commodities interested form the candidate commodity sequences, target commodity information is acquired from the candidate commodity sequences based on the demand information and a target prompt template, and the process of acquiring the target commodity information is consistent with the process of acquiring the target commodity information from the commodity information base based on the demand information and the target prompt template. By setting the commodity recall model, the power consumption of sequencing the screened target commodity information in the LLM model can be reduced, meanwhile, the interference caused by invalid commodities can be avoided, convenience is brought to a user to rapidly screen a plurality of candidate commodities possibly interested from a commodity information base, commodity preliminary screening is realized, and the robustness of the LLM model is enhanced.
In this embodiment, the method for displaying merchandise information further includes sending a dialogue request to the user, if the user accepts the dialogue request, enabling the constructed LLM model to perform dialogue with the user, and if the user refuses the dialogue request, directly displaying any merchandise in the merchandise information library to the user.
Specifically, when the user browses commodity information on a website or an Application (APP), a dialogue request interface is sent to the user, and if the user accepts a dialogue request, a dialogue box is displayed, so that the user can conveniently input the current requirement. If the user refuses the dialogue request, the common commodity information display page is displayed, namely, any commodity in the commodity information base is directly displayed to the user.
If the dialogue request presented to the user is refused when the user enters the website or the application program, any commodity in the commodity information base is normally presented to the user.
The above-mentioned method for displaying merchandise information is described fully below by way of a specific embodiment, as shown in fig. 4, and fig. 4 is a schematic flow chart of a method for displaying merchandise information in an embodiment of the present invention. Firstly, when a user enters a website or an application program, a dialogue module is displayed for the user, if the user accepts browsing commodity information in a dialogue mode, based on information input by the user at the current moment, the demand information of the user is determined through a LLM model, a commodity recall model searches and recalls from a commodity information base based on the demand information of the user, candidate commodity sequences meeting the demand information of the user are screened out, then current search information is generated based on the demand information and a target prompt template matched with the demand information, and target commodity information is obtained from the candidate commodity sequences according to the current search information. And sequencing the target commodity information from high to low according to the correlation degree of the target commodity information and the demand information through the LLM model, and outputting the sequenced target commodity information for browsing or purchasing by a user. If the dialogue module is displayed to the user, the user refuses to display any commodity directly.
The embodiment of the invention also provides a commodity information display system, as shown in fig. 5, fig. 5 is a schematic diagram of the commodity information display system provided in the embodiment of the invention, where the commodity information display system is used for implementing the commodity information display method, and the commodity information display system includes: the system comprises a user demand information determining module 1, a target prompt template matching module 2, a target commodity information acquisition module 3 and a commodity information display module 4.
The user demand information determining module 1 is configured to determine demand information of a user according to information input at a current moment of the user through a LLM model.
The target prompt template matching module 2 is used for selecting a target prompt template matched with the requirement information from a preset prompt template library according to the requirement information.
And the target commodity information acquisition module 3 is used for acquiring target commodity information from the commodity information base based on the demand information and the target prompt template.
And the commodity information display module 4 is used for displaying the target commodity information to the user.
In this embodiment, the target commodity information acquisition module includes: the system comprises a current retrieval information generation sub-module and a target commodity information acquisition sub-module.
And the current search information generation sub-module is used for generating current search information based on the demand information and the target prompt template.
And the target commodity information acquisition sub-module is used for acquiring target commodity information from the commodity information base according to the current retrieval information.
In this embodiment, the merchandise information display module includes: a target commodity ordering sub-module and a target commodity outputting sub-module.
And the target commodity ordering sub-module is used for ordering the target commodity information through the LLM model according to the correlation degree of the target commodity information and the demand information.
And the target commodity output sub-module is used for outputting the ordered target commodity information.
In this embodiment, the merchandise information display system further includes:
and the LLM model construction module is used for constructing the LLM model based on the language base model, commodity data and construction dialogue data.
In this embodiment, the merchandise information display system further includes:
and the commodity recall module is used for screening candidate commodity sequences from the commodity information base through the commodity recall model based on the demand information.
In this embodiment, the merchandise information display system further includes:
the dialogue request display module is used for sending dialogue requests to users, and if the users accept the dialogue requests, the constructed LLM model is started to carry out dialogue with the users; if the user refuses the dialogue request, any commodity in the commodity information base is directly displayed to the user.
The system and method embodiments in the embodiments of the present application are based on the same application concept.
The method embodiments provided by the present embodiments may be performed to a user in a computer terminal, server, or similar computing device. Taking the example of running on a server, the server may vary considerably in configuration or performance and may include one or more central processing units (Central Processing Units, CPU) (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA or the like), memory for storing data, one or more storage mediums (e.g., one or more mass storage devices) for storing applications or data. The memory and storage medium may be transitory or persistent. The program stored on the storage medium may include one or more modules, each of which may include a series of instruction operations on the server. Still further, the central processor may be configured to communicate with a storage medium and execute a series of instruction operations on the storage medium on a server. The server may also include one or more power supplies, one or more wired or wireless network interfaces, one or more input/output interfaces, and/or one or more operating systems, such as Windows Server, mac OS XTM, unixTM, linuxTM, freeBSDTM, etc.
The input-output interface may be used to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of a server. In one example, the input-output interface includes a network adapter (Network Interface Controller, NIC) that can connect to other network devices through the base station to communicate with the internet. In one example, the input-output interface may be a Radio Frequency (RF) module for communicating with the internet wirelessly.
The embodiment of the invention also provides electronic equipment, which comprises a processor and a memory, wherein at least one instruction or at least one section of program is stored in the memory, and the at least one instruction or the at least one section of program is loaded and executed by the processor to realize the commodity information display method.
The embodiment of the invention provides a computer readable storage medium, wherein at least one instruction or at least one section of program is stored in the computer readable storage medium, and the at least one instruction or the at least one section of program is loaded and executed by a processor to realize the commodity information display method.
Alternatively, in this embodiment, the storage medium may be located in at least one network server among a plurality of network servers of the computer network. Alternatively, in the present embodiment, the storage medium may include, but is not limited to: a U-disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, there is also provided in the present embodiment a computer program product including a computer program stored in a readable storage medium, from which at least one processor of a computer device reads and executes the computer program, so that the computer device performs the merchandise information display method of the embodiment of the present disclosure.
It should be noted that: the sequence of the embodiment is only for description, and does not represent the advantages and disadvantages of the embodiment. And the foregoing description has been directed to specific embodiments of this specification. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for the apparatus embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments in part.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program for instructing relevant hardware, where the program may be stored in a computer readable storage medium, and the storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The foregoing description of the preferred embodiments of the present application is not intended to limit the invention to the particular embodiments of the present application, but to limit the scope of the invention to the particular embodiments of the present application.
Claims (10)
1. A merchandise information display method, characterized in that the merchandise information display method comprises:
determining the demand information of a user through a LLM model according to the information input by the user at the current moment;
selecting a target prompt template matched with the demand information from a preset prompt template library according to the demand information;
acquiring target commodity information from a commodity information base based on the demand information and the target prompt template;
and displaying the target commodity information to the user.
2. The merchandise information display method according to claim 1, wherein the obtaining target merchandise information from a merchandise information base based on the demand information and the target cue template comprises:
generating current retrieval information based on the demand information and the target prompt template;
and acquiring the target commodity information from the commodity information base according to the current retrieval information.
3. The merchandise information display method according to claim 1, wherein said displaying said target merchandise information to said user comprises:
sorting the target commodity information through the LLM model according to the correlation degree of the target commodity information and the demand information;
and outputting the ordered target commodity information.
4. A merchandise information display method according to claim 3, wherein said demand information includes one or more of the following information: the supply and demand information of the commodity required by the user and the technical information of the commodity required by the user.
5. The merchandise information display method according to claim 1, wherein the merchandise information display method further comprises:
screening candidate commodity sequences from the commodity information base through a commodity recall model based on the demand information;
and acquiring the target commodity information from the candidate commodity sequence based on the demand information and the target prompt template.
6. The merchandise information display method according to claim 1, wherein the merchandise information display method further comprises:
sending a dialogue request to the user, and if the user accepts the dialogue request, starting the constructed LLM model to carry out dialogue with the user; and if the user refuses the dialogue request, directly displaying any commodity in the commodity information base to the user.
7. A merchandise information display system, the merchandise information display system comprising:
the user demand information determining module is used for determining the demand information of the user through the LLM model according to the information input by the user at the current moment;
the target prompt template matching module is used for selecting a target prompt template matched with the requirement information from a preset prompt template library according to the requirement information;
the target commodity information acquisition module is used for acquiring target commodity information from a commodity information base based on the demand information and the target prompt template;
and the commodity information display module is used for displaying the target commodity information to the user.
8. The merchandise information display system of claim 7, wherein the merchandise information display system further comprises:
and the LLM model construction module is used for constructing the LLM model based on the language base model, commodity data and construction dialogue data.
9. The merchandise information display system of claim 7, wherein the merchandise information display system further comprises:
and the commodity recall module is used for screening candidate commodity sequences from the commodity information base through the commodity recall model based on the demand information.
10. The merchandise information display system of claim 7, wherein the merchandise information display system further comprises:
a dialogue request display module, configured to send a dialogue request to the user, and if the user accepts the dialogue request, enable the constructed LLM model to perform a dialogue with the user; and if the user refuses the dialogue request, directly displaying any commodity in the commodity information base to the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311629154.2A CN117541355A (en) | 2023-11-30 | 2023-11-30 | Commodity information display method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311629154.2A CN117541355A (en) | 2023-11-30 | 2023-11-30 | Commodity information display method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117541355A true CN117541355A (en) | 2024-02-09 |
Family
ID=89782132
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311629154.2A Pending CN117541355A (en) | 2023-11-30 | 2023-11-30 | Commodity information display method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117541355A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118035387A (en) * | 2024-04-03 | 2024-05-14 | 浙江口碑网络技术有限公司 | Data selecting and outputting method and device based on large language model |
-
2023
- 2023-11-30 CN CN202311629154.2A patent/CN117541355A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118035387A (en) * | 2024-04-03 | 2024-05-14 | 浙江口碑网络技术有限公司 | Data selecting and outputting method and device based on large language model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108205768B (en) | Database establishing method, data recommending device, equipment and storage medium | |
| US11727459B2 (en) | Search query-based replacement part interface | |
| US20180165745A1 (en) | Intelligent Recommendation Method and System | |
| CN106708821A (en) | User personalized shopping behavior-based commodity recommendation method | |
| CN106372961A (en) | Commodity recommendation method and device | |
| CN112837118A (en) | Commodity recommendation method and device for enterprise users | |
| CN111027895A (en) | Stock prediction and behavior data collection method, apparatus, device and medium for commodity | |
| CN111695960A (en) | Object recommendation system, method, electronic device and storage medium | |
| CN117541355A (en) | Commodity information display method and system | |
| CN102314654A (en) | Information push method and information push server | |
| CN112528153A (en) | Content recommendation method, device, equipment, storage medium and program product | |
| CN112132660B (en) | Commodity recommendation method, system, equipment and storage medium | |
| CN113689259A (en) | Commodity personalized recommendation method and system based on user behaviors | |
| CN113781149A (en) | Information recommendation method and device, computer-readable storage medium and electronic equipment | |
| CN114820123A (en) | Group purchase commodity recommendation method, device, equipment and storage medium | |
| CN115392947A (en) | Demand prediction method and device | |
| CN117421355A (en) | Search recall method, device and equipment | |
| CN112258272A (en) | Transaction content management method and system based on website page and readable storage medium | |
| CN110717095B (en) | Service item pushing method and device | |
| CN116664222A (en) | Data processing method and device | |
| CN111639274B (en) | Online commodity intelligent sorting method, device, computer equipment and storage medium | |
| CN115187330A (en) | Product recommendation method, device, equipment and medium based on user label | |
| CN115225921A (en) | Live broadcast interaction control method, device, equipment and storage medium based on big data | |
| KR102270381B1 (en) | Method for providing shopping interface based on consumer data and apparatus thereof | |
| CN113781171A (en) | Information pushing method, device, equipment and storage medium |
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 |