Method, device, storage medium and program product for assisting shopping

Abstract

The application relates to the field of artificial intelligence, and more particularly to a method for assisting shopping, a computer device for implementing the method, a computer readable storage medium and a computer program product. The method comprises the following steps: receiving a requirement of a user for purchasing a commodity; determining a parameter set of the commodity by carrying out a first negotiation with a merchant based on the requirement; determining a value of a parameter in the parameter set by carrying out a second negotiation with the merchant; and purchasing the commodity according to the value of the parameter.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence, and more specifically to a method for assisting shopping, a computer device for implementing the method, a computer-readable storage medium, and a computer program product. Background Technology

[0002] Traditional e-commerce shopping searches often rely on keyword matching, which cannot support precise product consensus under vague intents. If the user enters non-strictly matching keywords, accurate searches are often unsuccessful. Currently, with the rise of Shopping Agents driven by Large Language Models (LLMs), users can use natural language to delegate cross-platform product price comparisons and purchases to intelligent agents. Furthermore, the Agent Payments Protocol (AP2) proposed by Google and other organizations provides a basic communication framework for agent-driven automated payments. Therefore, users no longer need to search for products, browse stores, filter products, or compare prices across multiple channels; they only need to provide their purchase intent to the intelligent agent and confirm the final purchase to complete the shopping process.

[0003] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this application, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0004] This application provides a method for assisting shopping, a computer device for implementing the method, a computer-readable storage medium, and a computer program product. The method ensures precise alignment between user intent and product parameters through two-phase negotiation, ensuring high fidelity of user intent, executable shopping operations, and minimizing frequent user confirmation requests during the shopping process.

[0005] According to a first aspect of this application, a method for assisting shopping is provided, the method comprising: receiving a user's request to purchase goods; determining a set of parameters for the goods through a first negotiation with a merchant based on the request; determining the values ​​of the parameters in the set of parameters through a second negotiation with the merchant; and purchasing the goods according to the values ​​of the parameters.

[0006] As an alternative to or supplement to the above solutions, in a method according to an embodiment of this application, the requirements are provided in the form of natural language.

[0007] As an alternative or supplement to the above solutions, in a method according to an embodiment of this application, determining the parameter set of the product through a first negotiation with the merchant includes: parsing the requirements to generate an initial parameter set; providing the initial parameter set to the merchant to obtain first feedback; adjusting the initial parameter set based on the first feedback to generate the parameter set; and providing the parameter set to the merchant for confirmation.

[0008] As an alternative or supplement to the above solutions, in a method according to an embodiment of this application, the first feedback includes: additional parameters that are different from the parameters in the initial parameter set, suggestions for retaining or removing parameters in the initial parameter set, and / or standards related to the parameters in the initial parameter set and the additional parameters.

[0009] As an alternative or supplement to the above solutions, in a method according to an embodiment of this application, adjusting the initial parameter set includes: adding the additional parameters to the initial parameter set and / or deleting one or more parameters from the initial parameter set.

[0010] As an alternative or supplement to the above solutions, in a method according to an embodiment of this application, the method further includes: determining the value range of the parameters in the parameter set based on the standard.

[0011] As an alternative or supplement to the above solution, in a method according to an embodiment of this application, in response to the failure to confirm that a certain percentage of merchants among the merchants exceeds a threshold, the parameter set of the goods is redefined.

[0012] As an alternative or supplement to the above solution, in a method according to an embodiment of this application, in response to the number of times the parameter set of the product is redefined exceeding a first threshold number, the user is requested to input a first additional requirement.

[0013] As an alternative or supplement to the above solutions, in a method according to an embodiment of this application, determining the values ​​of parameters in the parameter set through a second negotiation with the merchant includes: generating initial values ​​for the parameters in the parameter set; providing the parameters in the parameter set and their initial values ​​to the merchant to obtain second feedback; adjusting the values ​​of the parameters in the parameter set based on the second feedback; determining the quantity of candidate products based on the adjusted parameter values; and, in response to the quantity of candidate products being greater than a threshold quantity, using the adjusted parameter values ​​as the determined parameter values.

[0014] As an alternative or supplement to the above solution, in a method according to an embodiment of this application, the second feedback includes: the identifier of the alternative product that the merchant can provide, the actual value of the parameter of the alternative product, and the voucher related to the parameter of the alternative product, wherein the actual value of at least one parameter of the alternative product matches the provided initial value.

[0015] As an alternative or supplement to the above solution, in a method according to an embodiment of this application, in response to the quantity of the candidate goods being lower than a threshold, the values ​​of the parameters in the parameter set are re-determined.

[0016] As an alternative or supplement to the above solution, in a method according to an embodiment of this application, in response to the number of times the value of a parameter in the parameter set is redefined exceeding a second threshold number, the user is requested to input a second additional requirement.

[0017] As an alternative or supplement to the above solutions, in a method according to an embodiment of this application, the parameters in the parameter set include a first type of parameters related to product performance and a second type of parameters related to product description.

[0018] As an alternative or supplement to the above solutions, in a method according to an embodiment of this application, for the first type of parameter, the value of the parameter is adjusted based on the actual value of the parameter in the second feedback; and wherein, for the second type of parameter, whether to adjust the value of the parameter to the actual value of the parameter in the second feedback is determined based on the voucher related to the parameter of the candidate product.

[0019] According to a second aspect of this application, a computer device is provided, the device comprising: a memory; a processor; and a computer program stored on the memory and executable on the processor, the execution of the computer program causing the following operations: receiving a user's request to purchase goods; determining a set of parameters for the goods based on the request through a first negotiation with a merchant; determining the values ​​of the parameters in the set of parameters through a second negotiation with the merchant; and purchasing the goods according to the values ​​of the parameters.

[0020] According to a third aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including instructions that, when executed, perform any one of the methods for assisting shopping according to a first aspect of this application.

[0021] According to a fourth aspect of this application, a computer program product is provided, the computer program product comprising a computer program that, when executed by a processor, implements any one of the methods for assisting shopping as described in the first aspect of this application. Attached Figure Description

[0022] The above and / or other aspects and advantages of this application will become clearer and more readily understood from the following description taken in conjunction with the accompanying drawings, in which the same or similar elements are denoted by the same reference numerals. In the drawings: Figure 1 This is a flowchart of a method 100 for assisting shopping according to an embodiment of this application; Figure 2 The illustration shows a flowchart of a first negotiation process 200 according to an embodiment of this application; Figure 3 The illustration shows a flowchart of a second negotiation process 300 according to an embodiment of this application; and Figure 4 This is a schematic block diagram of a computer device 40 according to an embodiment of this application. Detailed Implementation

[0023] The following detailed description is merely exemplary in nature and is not intended to limit the disclosed technology or its application and use. Furthermore, it is not intended to be bound by any express or implied theory presented in the foregoing technical fields, background art, or the following detailed description.

[0024] In the following detailed description of the embodiments, numerous specific details are set forth in order to provide a more thorough understanding of the disclosed technology. However, it will be apparent to those skilled in the art that the disclosed technology can be practiced without these specific details. In other instances, well-known features have not been described in detail to avoid unnecessarily complicating the description.

[0025] Terms such as "possessing" and "comprising" indicate that, in addition to the units (modules) and steps directly and explicitly stated in the specification and claims, the technical solution of this application does not exclude the presence of other units (modules) and steps not directly or explicitly stated. Terms such as "first" and "second" do not indicate the order of the units in terms of time, space, size, etc., but are merely used to distinguish the units. Furthermore, the steps in this document are not limited to being performed in the order they are written; a step written later may be performed simultaneously with or before a step written earlier.

[0026] The AP2 protocol provides a proxy payment function for unattended transactions. Users entrust a payment task (such as shopping) to an AI agent, hoping the agent will make the payment in their absence. The main difference from the attended mode is that no shopping cart authorization is required. The agent must reiterate the user's purchase intention to the user. The user must approve this action and confirm their wish for the agent to continue the purchase in their absence through in-session authentication (such as biometrics).

[0027] However, given the accuracy and reliability of the intelligent agent's communication, merchants may require user confirmation. For example, when a merchant does not understand the intent expressed by the intelligent agent or is unsure of its ability to meet the user's requirements, the merchant may ask the user to select from a list of available product identifiers or answer additional questions the merchant needs to know. This could result in frequent interruptions to the user, leading to a poor user experience.

[0028] Furthermore, regarding merchants, due to differing naming conventions or customary terminology, intelligent agents may struggle to accurately associate different expressions conveying the same meaning (e.g., Bluetooth version and BT Ver), potentially reducing the richness of available products. On the intelligent agent side, large language models may exhibit biases in understanding user intent (e.g., due to hallucinations), potentially leading to the purchase of unwanted goods and financial losses for the user. On the user side, user expressions may be exaggerated, abbreviated, contradictory, or difficult to quantify (e.g., most comfortable, most suitable, lowest price, and best performance), preventing intelligent agents from generating structured parameters based on these expressions.

[0029] For the reasons mentioned above, current shopping agents may not be able to provide a satisfactory shopping experience and transaction conversion rate.

[0030] In the following, exemplary embodiments according to this application will be described in detail with reference to the accompanying drawings.

[0031] Figure 1This is a flowchart of a method 100 for assisting shopping according to an embodiment of this application. Method 100 can be executed by a smart agent, which can be deployed on a user terminal, in the cloud, or on a merchant terminal, and can be integrated into one module or distributed across multiple modules. Method 100 begins at step 102, receiving a user's request to purchase goods. In some embodiments, the request can be provided in natural language via voice or text. The request can be input to the user terminal via a microphone, or it can be input to an application on the user terminal via an interactive interface. The smart agent can then receive the request. As an example, the user's request to purchase goods might be "to purchase wireless noise-canceling headphones suitable for running."

[0032] In step 104, based on the requirements, a set of parameters for the product is determined through a first negotiation with the merchant. Due to potential illusions and comprehension biases in large language models, intelligent agents may assign natural language requirements to inappropriate or non-existent parameter types. Through the first negotiation with the merchant, a minimum necessary, standard-aligned, and highly consensus-based set of parameters can be dynamically constructed between the user's intent and the merchant's capabilities.

[0033] Next reference Figure 2 , Figure 2 The illustration shows a flowchart of a first negotiation process 200 according to an embodiment of this application. Specifically, determining the parameter set of the product through first negotiation with the merchant includes: in step 202, parsing the request to generate an initial parameter set. Specifically, the intelligent agent can generate the initial parameter set by analyzing and semantically parsing the user's request in natural language form. In the example of purchasing headphones above, for the request of "purchasing wireless noise-canceling headphones suitable for running", the intelligent agent can determine an initial parameter set including the following parameters: weight (to avoid excessive burden during running), waterproof rating (to ensure use when sweating heavily), pairing method (to meet wireless requirements), and anti-fall-off design (to prevent falling off during running).

[0034] In step 204, an initial parameter set is provided to the merchants to obtain first feedback. Specifically, the intelligent agent may provide the generated initial parameter set to the merchants (e.g., via broadcast) to obtain first feedback from the merchants. In some embodiments, the intelligent agent may provide user-provided requests in natural language form along with the initial parameter set to multiple merchants, enabling each of the multiple merchants to analyze the user's requests independently (e.g., through manual analysis or analysis using an artificial intelligence model) and compare the parameters obtained based on the requests with the parameters in the initial parameter set generated by the intelligent agent, thereby providing first feedback regarding the initial parameter set.

[0035] In some embodiments, the first feedback includes: additional parameters that differ from those in the initial parameter set, suggestions for retaining or removing parameters from the initial parameter set, and / or standards related to the parameters in the initial parameter set and the additional parameters. For example, the merchant may supplement the requirements with additional parameters such as battery life or corrosion resistance. Additionally, the merchant may provide suggestions on retaining or removing parameters from the initial parameter set. Furthermore, the merchant may provide standards (e.g., GS1 standards) related to the parameters in the initial parameter set and the additional parameters. Moreover, the standards may include mandatory and / or non-mandatory standards; international standards, national standards, industry standards, product inspection standards, or the like. The standards may specify value ranges for the parameters in the initial parameter set and / or the additional parameters, and therefore, the intelligent agent can determine the value ranges for the parameters in the final parameter set based on these standards in subsequent steps.

[0036] In step 206, based on the first feedback, the initial parameter set is adjusted to generate a new parameter set. In some embodiments, adjusting the initial parameter set may include adding additional parameters to the initial parameter set and / or deleting one or more parameters from the initial parameter set. For example, when more than a first threshold proportion (e.g., 1 / 3) of merchants suggest removing a parameter from the initial parameter set, it can be determined that the parameter may be inappropriate and can then be removed from the initial parameter set. When more than a second threshold proportion (e.g., 2 / 3) of merchants suggest adding another parameter or a semantically equivalent parameter to the initial parameter set, it can be determined that the parameter may be necessary but previously missing and can then be added to the initial parameter set. In some embodiments, semantically equivalent parameters may include 1) one or more parameters referencing the same criteria, and 2) one or more parameters clustered by similarity after generating embedding vectors using an embedding model (such as all-MiniLM-L6-v2). Furthermore, when less than a third threshold proportion of merchants suggest deleting a specific parameter from the initial parameter set and more than a fourth threshold proportion of merchants suggest retaining the specific parameter, the specific parameter is retained in the parameter set.

[0037] In some embodiments, adjusting the initial parameter set may further include: adjusting the naming of parameters in the initial parameter set based on the standard. As mentioned above, due to different naming rules for various merchants or products, there may be multiple names for a certain parameter (e.g., weight, mass, grams). Therefore, the naming of parameters can be adjusted based on the standards related to the parameters in the initial parameter set and additional parameters in the first feedback, thereby avoiding ambiguity caused by different naming rules. Furthermore, if multiple standards exist simultaneously, priority can be determined according to the hierarchy of the standards' effectiveness; for example, international standards take precedence over national standards, and national standards take precedence over industry standards.

[0038] In step 208, the parameter set is provided to the merchant for confirmation to ensure that the smart agent and the merchant can reach a consensus on the product parameter set. In this step, the merchant can determine its ability to offer products based on the adjusted parameter set. If the merchant can offer products matching the parameter set, confirmation is made; otherwise, no confirmation is made. In some embodiments, in response to a fifth threshold proportion of merchants not confirming, the parameter set of the product is redefined. In this way, it can be ensured that the generated parameter set is usable for filtering products. In some embodiments, to avoid getting stuck in an infinite loop, in response to the number of times the parameter set of the product is redefined exceeding a first threshold number (e.g., twice), the user is requested to input a first additional requirement. The first additional requirement can be a clarification or supplement to the previously provided requirement, and thus, the smart agent or large language model can regenerate the initial parameter set based on the supplementary information. For example, the smart agent can ask the user, "Would you prefer to buy in-ear headphones or bone conduction headphones?" or "Do you need to use headphones for occasions other than running?", to obtain more information for determining the parameters to be included in the parameter set.

[0039] Through the initial negotiation with the merchant, the intelligent agent can determine which parameters of the product need to be considered in this shopping, avoiding the subjective assumptions of the attribute range by the large language model, and ensuring that the generated parameter set can be used to filter products and can serve as a framework for the subsequent second negotiation.

[0040] return Figure 1 In step 106, the values ​​of the parameters in the parameter set are determined through a second negotiation with the merchant. Specifically, in cases such as through... Figure 2 After the first negotiation process 200 determines which parameters of the goods need to be considered in this purchase, the goal of the second negotiation is to reach a precise and executable consensus on the values ​​of each parameter within the confirmed framework (i.e., to determine which conditions these parameters should meet or which values ​​they should match), eliminate ambiguity, and generate a set of parameters that can be verified by machines and are guaranteed to be fulfilled.

[0041] refer to Figure 3 , Figure 3 The illustration shows a flowchart of a second negotiation process 300 according to an embodiment of this application. Figure 3 As illustrated in the diagram, determining the values ​​of parameters in the parameter set through a second negotiation with the merchant includes: in step 302, generating initial values ​​for the parameters in the parameter set. Specifically, the intelligent agent can pre-fill values ​​for each parameter in the parameter set based on experience data or historical data, thereby generating a parameter aggregation with initial values. Continuing with the example of purchasing headphones above, the intelligent agent can determine the initial value for the waterproof rating as IPX7, the maximum weight as 10g, the battery life as 40 minutes, and so on.

[0042] Next, in step 304, the parameters in the parameter set and their initial values ​​can be provided to the merchant to obtain second feedback. In some embodiments, the second feedback may include: the identifier of the alternative product that the merchant can provide, the actual values ​​of the parameters of the alternative product, and the voucher associated with the parameters of the alternative product, wherein the actual value of at least one parameter of the alternative product matches the provided initial value. For example, the identifier of the alternative product may include a StockKeeping Unit (SKU) number, and the voucher associated with the parameters of the alternative product may include the product's instruction manual, test report, physical image, or the like.

[0043] In some embodiments, since the initial values ​​of the parameters are generated by the intelligent agent based on experience and historical data, these values ​​may not be applicable to the current product. Therefore, the merchant needs to provide the actual values ​​of the parameters for the currently available alternative products (as a second feedback) to correct the values ​​of the parameters in the parameter set.

[0044] Then, in step 306, based on the second feedback, the values ​​of the parameters in the parameter set are adjusted. Specifically, if the actual values ​​of the parameters of the candidate products in the second feedback are consistent with the initial values ​​(i.e., consensus is reached), no action is required, and the initial values ​​are directly used as the parameter values. If the actual values ​​of the parameters of the candidate products in the second feedback are inconsistent with the initial values, the values ​​of the parameters need to be adjusted according to the type of the parameter using different fusion strategies (or conflict resolution strategies). In some embodiments, the parameters in the parameter set include first-class parameters related to product performance (e.g., battery life, waterproof rating, weight, etc.) and second-class parameters related to product description (e.g., color, surface finish, etc.). Typically, the first-class parameters can be numerical parameters, which can be directly used for comparison or matching; while the second-class parameters can be textual parameters, which need to be normalized or encoded before they can be used for comparison or matching. In some embodiments, for the first-class parameters, the values ​​of the parameters can be adjusted based on the actual values ​​of the parameters in the second feedback. In the example of purchasing headphones, if the initial value for the weight parameter is 5 grams (i.e., the weight of the product must not exceed 5g), and the actual weight values ​​of the alternative products provided by the merchant in the second feedback are 6.2g, 8.5g, 10g, etc., a conservative strategy can be adopted to ensure the merchant can fulfill their obligations: the lowest valid value among the actual values ​​(i.e., 10g) can be used as the weight parameter value. On the other hand, for the second type of parameter, the decision to adjust the parameter value to the actual value of the parameter in the second feedback is based on the evidence related to the parameter of the alternative products. For example, in the example of purchasing headphones, if the initial value for the surface finish is "baked enamel," and the actual value of the surface finish parameter of the alternative products provided by the merchant in the second feedback is "anti-fingerprint coating," then to avoid false descriptions, an evidence-first strategy can be adopted: the decision to adjust the parameter value to the actual value of the parameter in the second feedback is based on the reputation score of the source merchant and whether evidence can be provided.

[0045] In some embodiments, a set of parameters and their values ​​can be provided to the user for confirmation and end-user authorization can be obtained. For example, a confirmation request can be provided to the user including the following information: purchased product = headphones, waterproof rating = IPX7, weight ≤10g; features include active noise cancellation; battery life greater than 40 minutes. In this way, users only need to provide abstract natural language requirements to obtain options for a detailed set of parameters that can be used to filter products, without having to browse through a lot of products, study relevant parameters, and formulate filtering strategies, which further improves the user's shopping experience.

[0046] Proceeding to step 308, the number of candidate products is determined based on the adjusted parameter values. Specifically, after obtaining a set of parameters with agreed-upon values ​​through step 306 (and possibly a user confirmation step), this set of parameters is used as the minimum parameter value. All merchant-provided SKUs are then iterated to determine the number of candidate products that match all minimum parameter values. In some embodiments, for numerical parameters (the first type), matching the minimum parameter value means that the actual value of the candidate product's parameter is greater than or equal to the parameter value (e.g., for parameters related to waterproof rating or battery life); or the actual value of the candidate product's parameter is less than or equal to the parameter value (e.g., for weight). For text-based parameters (the second type), matching the minimum parameter value means that the actual value of the candidate product's parameter (after normalization) is completely consistent with the parameter value. For example, the surface finish of headphones, as candidate products, is required to include an anti-fingerprint coating.

[0047] In step 310, it is determined whether the number of candidate items is greater than a threshold number (e.g., greater than 1). If the number of candidate items is greater than the threshold number, it means that there are enough candidate items to match the values ​​of the parameters in the parameter set (i.e., satisfying all the user's requirements). If the number of candidate items is less than the threshold number, it means that there are not enough candidate items to match the values ​​of the parameters in the parameter set (i.e., satisfying all the user's requirements). Therefore, in response to the number of candidate items being greater than the threshold number, in step 312, the adjusted parameter value is used as the determined parameter value; otherwise, the process returns to step 302 and restarts process 300 (i.e., redetermining the parameter values ​​in the parameter set).

[0048] In some embodiments, to prevent entering an infinite loop, in response to the number of times the values ​​of parameters in the parameter set are redefined exceeding a second threshold number (e.g., twice), input of a second additional requirement is requested from the user. The input of the second additional requirement may indicate a compromise acceptable to the user in some aspect. For example, in the absence of a sufficient number of alternative items, the user may be able to make compromises in some aspects to complete the purchase. For instance, the user may be able to slightly relax the weight parameter to obtain a sufficient number of alternative items.

[0049] return Figure 1In step 108, the product is purchased according to the values ​​of all parameters in the parameter set. Specifically, after determining the values ​​of the parameters in the parameter set through step 106 (and process 300), the intelligent agent can use the values ​​of all parameters in the parameter set as filtering conditions to find products. Then, it determines the highest priority product by sorting the products based on various rules (e.g., the user may prefer a certain brand of products, or may seek the product with the lowest price that meets the requirements), and purchases the product for the user or recommends the product to the customer.

[0050] As described above, Method 100 provides an assisted shopping implementation method that accurately aligns user intent with product parameters (and their values) through two-phase negotiation. Because Method 100 treats merchants as a more important source of information and negotiation partner than the shopper, the shopping agent executing Method 100 can obtain information closer to the actual products or market, thereby avoiding comprehension biases caused by relying on large language models and minimizing user disruption. Furthermore, Method 100 can take into account the different naming rules and / or customary names of multiple merchants and accurately map them to appropriate products or parameters. Moreover, Method 100 can correct inappropriate expressions in user descriptions through two-phase negotiation with merchants, avoiding the absence of matching products due to user exaggeration, contradiction, or abbreviation.

[0051] refer to Figure 4 , Figure 4 This is a schematic block diagram of a computer device 40 according to an embodiment of this application. The computer device 40 includes a memory 410, a processor 420, and a computer program 430 stored in the memory 410 and executable on the processor 420, the execution of which causes the method 100 described above to be performed.

[0052] Furthermore, as described above, this application can also be implemented as a computer-readable storage medium storing a program for executing the method 100 described above. Here, various types of computer-readable storage media can be used, such as disks (e.g., magnetic disks, optical disks, etc.), cards (e.g., memory cards, optical cards, etc.), semiconductor memories (e.g., ROM, non-volatile memory, etc.), and tapes (e.g., magnetic tape, cassette tape, etc.).

[0053] This application can also be implemented as a computer program product comprising a computer program that, when executed by a processor, implements the method 100 described above.

[0054] Where applicable, the various embodiments provided in this application may be implemented using hardware, software, or a combination of hardware and software. Furthermore, where applicable, without departing from the scope of this application, the various hardware and / or software components described herein may be combined into composite components comprising software, hardware, and / or both. Where applicable, without departing from the scope of this application, the various hardware and / or software components described herein may be divided into sub-components comprising software, hardware, or both. Additionally, where applicable, it is contemplated that software components may be implemented as hardware components, and vice versa.

[0055] The software (such as program code and / or data) according to this application can be stored on one or more computer storage media. It is also contemplated that the software identified herein can be implemented using one or more networked and / or otherwise general-purpose or special-purpose computers and / or computer systems. Where applicable, the order of the various steps described herein can be changed, combined into compound steps, and / or divided into sub-steps to provide the features described herein.

[0056] The embodiments and examples presented herein are provided to best illustrate embodiments of this application and its particular applications, thereby enabling those skilled in the art to implement and use this application. However, those skilled in the art will understand that the above description and examples are provided for ease of illustration and example only. The descriptions presented are not intended to cover all aspects of this application or to limit this application to the precise forms disclosed.

Claims

1. A method for assisting in shopping, the method comprising: Receive user requests for purchasing goods; Based on the aforementioned requirements, the set of parameters for the product is determined through a first negotiation with the merchant; The values ​​of the parameters in the parameter set are determined through a second negotiation with the merchant; as well as Purchase goods according to the values ​​of the parameters mentioned.

2. The method as described in claim 1, wherein, The requirements are provided in natural language.

3. The method as described in claim 1, wherein, The set of parameters for the product, determined through initial negotiation with the merchant, includes: The requirements are parsed to generate an initial parameter set; The initial parameter set is provided to the merchant to obtain initial feedback; Based on the first feedback, the initial parameter set is adjusted to generate the parameter set; and The parameter set is provided to the merchant for confirmation.

4. The method of claim 3, wherein, The first feedback includes: additional parameters that are different from those in the initial parameter set, suggestions for retaining or removing parameters in the initial parameter set, and / or criteria related to the parameters in the initial parameter set and the additional parameters.

5. The method of claim 4, wherein, Adjusting the initial parameter set includes: adding the additional parameters to the initial parameter set and / or deleting one or more parameters from the initial parameter set.

6. The method of claim 4, wherein, The method further includes: determining the value range of the parameters in the parameter set based on the standard.

7. The method of claim 3, wherein, In response to the fact that a certain percentage of merchants among the merchants have not confirmed their purchases, the parameter set for the product is redefined.

8. The method of claim 7, wherein, In response to the number of times the parameter set of the product is redefined exceeding a first threshold number, the user is requested to input a first additional requirement.

9. The method of claim 1, wherein, The values ​​of the parameters in the parameter set are determined through a second negotiation with the merchant, including: Generate initial values ​​for the parameters in the parameter set; The parameters in the parameter set and their initial values ​​are provided to the merchant to obtain a second feedback. Based on the second feedback, the values ​​of the parameters in the parameter set are adjusted; Based on the adjusted parameter values, determine the quantity of candidate products; and In response to the number of candidate products exceeding a threshold number, the adjusted parameter value is used as the determined parameter value.

10. The method of claim 9, wherein, The second feedback includes: the identifier of the alternative product that the merchant can provide, the actual value of the parameter of the alternative product, and the voucher related to the parameter of the alternative product, wherein the actual value of at least one parameter of the alternative product matches the provided initial value.

11. The method of claim 9, wherein, In response to the quantity of the candidate products falling below a threshold, the values ​​of the parameters in the parameter set are redefined.

12. The method of claim 11, wherein, In response to the number of times the values ​​of the parameters in the parameter set are redefined exceeding a second threshold number, the user is requested to input a second additional requirement.

13. The method of claim 9, wherein, The parameters in the parameter set include a first category of parameters related to product performance and a second category of parameters related to product description.

14. The method of claim 13, wherein, For the first type of parameter, the value of the parameter is adjusted based on the actual value of the parameter in the second feedback; and wherein, for the second type of parameter, whether to adjust the value of the parameter to the actual value of the parameter in the second feedback is determined based on the voucher related to the parameter of the candidate product.

15. A computer device, the device comprising: Memory; processor; and a computer program stored on the memory and executable on the processor, the execution of which causes the following operations: Receive user requests for purchasing goods; Based on the aforementioned requirements, the set of parameters for the product is determined through a first negotiation with the merchant; The values ​​of the parameters in the parameter set are determined through a second negotiation with the merchant; as well as Purchase goods according to the values ​​of the parameters mentioned.

16. The computer device as claimed in claim 15, wherein, The requirements are provided in natural language.

17. The computer device as claimed in claim 15, wherein, The set of parameters for the product, determined through initial negotiation with the merchant, includes: The requirements are parsed to generate an initial parameter set; The initial parameter set is provided to the merchant to obtain initial feedback; Based on the first feedback, the initial parameter set is adjusted to generate the parameter set; and The parameter set is provided to the merchant for confirmation.

18. The computer device as claimed in claim 17, wherein, The first feedback includes: additional parameters that are different from those in the initial parameter set, suggestions for retaining or removing parameters in the initial parameter set, and / or criteria related to the parameters in the initial parameter set and the additional parameters.

19. The computer device as claimed in claim 18, wherein, Adjusting the initial parameter set includes: adding the additional parameters to the initial parameter set and / or deleting one or more parameters from the initial parameter set.

20. The computer device of claim 18, wherein, The execution of the computer program also results in the following operation: determining the range of values ​​for the parameters in the parameter set based on the standard.

21. The computer device as claimed in claim 17, wherein, In response to the fact that a certain percentage of merchants among the merchants have not confirmed their purchases, the parameter set for the product is redefined.

22. The computer device as claimed in claim 21, wherein, In response to the number of times the parameter set of the product is redefined exceeding a first threshold number, the user is requested to input a first additional requirement.

23. The computer device as claimed in claim 15, wherein, The values ​​of the parameters in the parameter set are determined through a second negotiation with the merchant, including: Generate initial values ​​for the parameters in the parameter set; The parameters in the parameter set and their initial values ​​are provided to the merchant to obtain a second feedback. Based on the second feedback, the values ​​of the parameters in the parameter set are adjusted; Based on the adjusted parameter values, determine the quantity of candidate products; and In response to the number of candidate products exceeding a threshold number, the adjusted parameter value is used as the determined parameter value.

24. The computer device as claimed in claim 23, wherein, The second feedback includes: the identifier of the alternative product that the merchant can provide, the actual value of the parameter of the alternative product, and the voucher related to the parameter of the alternative product, wherein the actual value of at least one parameter of the alternative product matches the provided initial value.

25. The computer device as claimed in claim 23, wherein, In response to the quantity of the candidate products falling below a threshold, the values ​​of the parameters in the parameter set are redefined.

26. The computer device as claimed in claim 25, wherein, In response to the number of times the values ​​of the parameters in the parameter set are redefined exceeding a second threshold number, the user is requested to input a second additional requirement.

27. The computer device as claimed in claim 23, wherein, The parameters in the parameter set include a first category of parameters related to product performance and a second category of parameters related to product description.

28. The computer device as claimed in claim 27, wherein, For the first type of parameter, the value of the parameter is adjusted based on the actual value of the parameter in the second feedback; and wherein, for the second type of parameter, whether to adjust the value of the parameter to the actual value of the parameter in the second feedback is determined based on the voucher related to the parameter of the candidate product.

29. A computer-readable storage medium comprising instructions that, when executed, perform a shopping assistance method according to any one of claims 1-14.

30. A computer program product comprising a computer program that, when executed by a processor, implements the assisted shopping method according to any one of claims 1-14.

Images