Automatic purchasing method and device based on intelligent recommendation and electronic equipment

Abstract

The invention provides an automatic purchasing method and device based on intelligent recommendation and electronic equipment, and relates to the technical field of artificial intelligence such as large models, intelligent recommendation and natural language processing. According to the specific implementation scheme, the method comprises the steps of obtaining a shopping list, and analyzing the shopping list to obtain first commodity information; according to the first commodity information, second commodity information fed back by different e-commerce is obtained, and the second commodity information at least comprises commodity prices and promotion information; performing commodity screening among different e-commerce according to the second commodity information to obtain a recommended target commodity combination; and executing payment operation based on the target commodity combination.

Description

Technical Field

[0001] The present disclosure relates to artificial intelligence technology fields such as big models, intelligent recommendations, and natural language processing, and in particular to an automated procurement method, device, and electronic device based on intelligent recommendations. Background Art

[0002] When using a shopping recommendation system to recommend products to users, the existing technology only relies on single product data and simple price detection methods to recommend different products to users. It is unable to compare prices based on product prices on different platforms, and is unable to intelligently calculate the discount strategies of different platforms, resulting in the inability to recommend products with the best price, the most suitable brand and category to users. Summary of the invention

[0003] The present disclosure provides a method, device and electronic device for automated purchasing based on intelligent recommendation.

[0004] According to one aspect of the present disclosure, there is provided an automated purchasing method based on intelligent recommendation, comprising: obtaining a shopping list, and parsing the shopping list to obtain first product information; obtaining second product information fed back by different e-commerce companies based on the first product information, wherein the second product information includes at least product price and promotion information; screening products among different e-commerce companies based on the second product information to obtain a recommended target product combination; and performing a payment operation based on the target product combination.

[0005] According to another aspect of the present disclosure, there is provided an automated purchasing device based on intelligent recommendation, including: a parsing module, used to obtain a shopping list, and parse the shopping list to obtain first product information; an acquisition module, used to obtain second product information fed back by different e-commerce companies based on the first product information, wherein the second product information includes at least product price and promotion information; a screening module, used to screen products among different e-commerce companies based on the second product information, and obtain a recommended target product combination; and a payment module, used to perform a payment operation based on the target product combination.

[0006] According to another aspect of the present disclosure, there is provided an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the automated procurement method based on intelligent recommendation described in the above-mentioned one aspect embodiment.

[0007] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, on which a computer program / instructions are stored, and the computer instructions are used to enable the computer to execute the automated procurement method based on intelligent recommendation described in the above-mentioned embodiment.

[0008] According to another aspect of the present disclosure, a computer program product is provided, including a computer program / instruction, which, when executed by a processor, implements the automated procurement method based on intelligent recommendation described in the above-mentioned embodiment.

[0009] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0011] Figure 1 A flowchart of an automated purchasing method based on intelligent recommendation provided in an embodiment of the present disclosure;

[0012] Figure 2 A flowchart of another automated purchasing method based on intelligent recommendation provided by an embodiment of the present disclosure;

[0013] Figure 3 A schematic diagram of a payment order process for a payment target provided in an embodiment of the present disclosure;

[0014] Figure 4 A flowchart of another automated purchasing method based on intelligent recommendation provided by an embodiment of the present disclosure;

[0015] Figure 5 A schematic diagram of a process for determining a product brand according to third auxiliary information provided in an embodiment of the present disclosure;

[0016] Figure 6 A schematic diagram of a process for determining a product brand based on a user's brand signal information provided by an embodiment of the present disclosure;

[0017] Figure 7 A schematic diagram of a process for determining first product information provided in an embodiment of the present disclosure;

[0018] Figure 8 A flowchart of another automated purchasing method based on intelligent recommendation provided by an embodiment of the present disclosure;

[0019] Fig. 9 A timing diagram of intelligent purchase of goods provided in an embodiment of the present disclosure;

[0020] Fig.10 A schematic diagram of a process for intelligently purchasing goods provided in an embodiment of the present disclosure;

[0021] Fig.11 A schematic diagram of the structure of an automated procurement device based on intelligent recommendation provided in an embodiment of the present disclosure;

[0022] Fig.12 The present invention is a block diagram of an electronic device for implementing the automated purchasing method based on intelligent recommendation according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0023] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0024] The following describes the automated procurement method, device and electronic device based on intelligent recommendation according to the embodiments of the present disclosure with reference to the accompanying drawings.

[0025] Artificial Intelligence (AI) is a discipline that studies how computers can simulate certain thought processes and intelligent behaviors of human beings (such as learning, reasoning, thinking, planning, etc.). It includes both hardware-level technologies and software-level technologies. AI hardware technologies generally include computer vision technology, speech recognition technology, natural language processing technology, as well as learning / deep learning, big data processing technology, knowledge graph technology, and other aspects.

[0026] Figure 1 A flowchart of an automated procurement method based on intelligent recommendation provided in an embodiment of the present disclosure.

[0027] like Figure 1 As shown, the automated procurement method based on intelligent recommendation may include:

[0028] S101, obtaining a shopping list, and parsing the shopping list to obtain first product information.

[0029] It should be noted that the execution subject of the automated procurement method based on intelligent recommendation in the embodiment of the present disclosure may be a hardware device with data processing capabilities and / or the necessary software required to drive the hardware device to work. Optionally, the execution subject may include a server, a user terminal and other intelligent devices. Optionally, the user terminal includes but is not limited to a mobile phone, a computer, an intelligent voice interaction device, etc. Optionally, the server includes but is not limited to a network server, an application server, and may also be a server of a distributed system, or a server combined with a blockchain, etc. The embodiment of the present disclosure is not specifically limited.

[0030] In some implementations, the user may be guided to input a shopping list and the shopping list may be parsed to obtain the first product information, wherein the first product information includes: product category, product quantity, and product brand.

[0031] Optionally, the user may be guided to enter a shopping list through a prompt word. Optionally, the shopping list includes, but is not limited to: goods of a specified brand, goods of an unspecified brand, goods categories, goods quantities, etc.

[0032] That is, the shopping list may be parsed using natural language processing (NLP) technology, and the parsed product information may be structured to obtain the first product information. For example, the shopping list may be parsed using a large model based on NLP. Alternatively, the large model may be used to perform entity extraction on keywords in the shopping list to obtain product information, and the product information may be structured to obtain the first product information. Alternatively, when the shopping list includes products of a specified brand, the product brand may be directly extracted from the shopping list as the first product information.

[0033] In some implementations, if the shopping list includes products of unspecified brands, the product brand can be determined by obtaining the user's historical purchase records and analyzing the user's preferences. Optionally, evaluation information of different brands can be obtained, and different product brands can be sorted according to the evaluation information, and then the product brand with the highest score can be determined as the first product information.

[0034] For example, if the shopping list contains shoes but does not specify a brand, and if the user has purchased shoes from brand A, brand A will be used as the first product information. Alternatively, if brand A, brand B, and brand C shoes are ranked by rating, and the ranking result is that brand B has a higher rating than brand A, and brand A has a higher rating than brand C, brand B will be used as the first product information.

[0035] S102, obtaining second product information fed back by different e-commerce companies based on the first product information, where the second product information at least includes product price and promotion information.

[0036] In some implementations, a query request can be generated based on the first product information, and the product price, inventory, store to which the product belongs, promotion, after-sales and other information of the product included in the first product information can be queried in different e-commerce platforms according to the query request, and used as the second product information. That is, the second product information at least includes the product price and promotion information.

[0037] In some implementations, distributed crawling can be performed on different e-commerce companies based on their respective application programming interfaces (APIs) to obtain the second product information.

[0038] Optionally, identification information of a product brand in the first product information may be determined, and a query request may be generated based on the identification information to query the second product information in the e-commerce platform according to the query request.

[0039] S103: Screen products among different e-commerce platforms according to the second product information to obtain a recommended target product combination.

[0040] In some implementations, the product prices and promotion information of different e-commerce companies can be determined based on the second product information, and multiple preferential rules corresponding to each e-commerce company can be analyzed based on the product prices and promotion information. Further, multiple candidate product combinations corresponding to each e-commerce company are generated based on different preferential rules and the first product information, and candidate prices corresponding to different candidate product combinations are compared to select the candidate product combination with the lowest candidate price as the target product combination.

[0041] In some implementations, multiple candidate product combinations may be generated between different e-commerce platforms based on the first product information according to the discount rules corresponding to different e-commerce platforms. That is, if the user needs to buy 5 pairs of brand A shoes, 3 pairs may be selected from e-commerce platform 1 and 2 pairs may be selected from e-commerce platform 2 to form a candidate product combination. Furthermore, candidate prices corresponding to different candidate product combinations are determined, so that the candidate product combination with the lowest candidate price is used as the target product combination.

[0042] In some implementations, the candidate product combination generated within the e-commerce company can be used as the first candidate product combination, and the candidate product combination generated between different e-commerce companies can be used as the second candidate product combination. Then, the candidate product combination with the lowest candidate price can be selected from the first candidate product combination and the second candidate product combination as the target product combination.

[0043] S104, executing a payment operation based on the target commodity combination.

[0044] In some implementations, the items included in the shopping list can be determined based on the target product combination, and the items can be added to the e-commerce shopping cart. Based on the product prices in the second product information, a payment order for the target product combination can be generated, and then the user can perform a payment operation on the payment order through the payment program to complete the purchase.

[0045] According to the automated purchasing method based on intelligent recommendation provided by the embodiment of the present disclosure, by obtaining the shopping list of the user and determining the first product information from the shopping list, the product price and promotion information can be determined from different e-commerce companies based on the first product information as the second product information. Furthermore, the products are screened from different e-commerce companies based on the second product information to obtain the target product combination, and then the payment operation can be performed on the target product combination. By obtaining the second product information from different e-commerce companies, cross-platform price comparison can be achieved, thereby improving the shopping efficiency of users. By combining the discounts between products on multiple platforms, shopping costs are saved and the shopping experience of users is enhanced.

[0046] Figure 2 A flowchart of an automated procurement method based on intelligent recommendation provided in an embodiment of the present disclosure.

[0047] like Figure 2 As shown, the automated procurement method based on intelligent recommendation may include:

[0048] S201, obtaining a shopping list, and parsing the shopping list to obtain first product information.

[0049] S202: Obtain second product information fed back by different e-commerce companies based on the first product information, where the second product information at least includes product price and promotion information.

[0050] S203: Screen products among different e-commerce platforms according to the second product information to obtain a recommended target product combination.

[0051] The relevant contents of steps S201 - S203 can be found in the above embodiment and will not be repeated here.

[0052] S204: Determine the filtered commodities according to the target commodity combination, where the filtered commodities at least include the target commodities included in the shopping list.

[0053] In some implementations, after obtaining the target product combination, the filtered products can be determined from different e-commerce platforms. If the brand of the product is provided in the shopping list, the filtered products are the target products included in the shopping list. If the shopping list provides the brand of a certain category of products and unspecified brand products of another category, the filtered products include not only the target products, but also products inferred based on user preferences.

[0054] For example, if the shopping list is: buy 5 pairs of shoes of brand A, obtain the second product information from different e-commerce platforms, and filter out the target product combination according to the second product information, so as to determine that the filtered product from the target product combination is the shoes of brand A. The target product is the shoes of brand A.

[0055] If the shopping list is: buy a hat of brand B and 5 pairs of shoes, by obtaining the second product information from different e-commerce platforms and filtering out the target product combination according to the second product information, it can be determined from the target product combination that the filtered products are hats of brand B and shoes of brand A. Among them, the target product is a hat of brand B.

[0056] S205, adding the filtered commodities to the shopping cart, and generating a payment order for the target shopping combination according to the second commodity information of the filtered commodities.

[0057] S206, calling the payment program to pay the target payment order.

[0058] In some implementations, the filtered items can be added to the shopping cart of each e-commerce company based on the e-commerce company corresponding to the filtered items, and a payment order for the target shopping combination can be generated based on the second product information such as the product price, promotional information, etc.

[0059] Optionally, after the payment order of the target shopping combination is generated, the order can be sent to the user for confirmation. If the user confirms that it is correct, the target payment order can be paid by calling the payment program. Optionally, the payment program can be called based on the API of the payment program.

[0060] In some implementations, the user's payment results can also be monitored. If the user's payment is successful, the user will be informed that the payment is completed. If the user's payment fails, the information is returned to the user for re-payment, or the user will be informed that the payment failed.

[0061] According to the automated purchasing method based on intelligent recommendation provided by the embodiment of the present disclosure, by obtaining the shopping list of the user and determining the first product information from the shopping list, the product price and promotional information can be determined from different e-commerce companies as the second product information based on the first product information. Furthermore, the products are screened from different e-commerce companies based on the second product information to obtain a target product combination, and then the screened products can be determined from the target product combination, and the target payment order is determined based on the second product information of the screened products, and the payment operation is performed on the target payment order. By automatically generating a payment order based on the shopping list for payment, the process of manual cross-platform price comparison is simplified, and the shopping efficiency of users is improved. By combining the discounts between products on multiple platforms, shopping costs are saved and the shopping experience of users is enhanced.

[0062] like Figure 3 The process diagram of the target payment order is shown. By generating a target product combination corresponding to the user's shopping list, and adding the filtered products in the target product combination to the shopping cart of the e-commerce service, and confirming the promotion information of the filtered products. After confirmation, a target payment order for the target shopping combination is generated, and the target payment order is paid based on the API call payment program, and then the payment result is monitored. If the user payment is successful, the user payment is fed back to complete. If the user payment fails, it is returned to the user for re-payment, or the user payment failure is fed back.

[0063] Figure 4 A flowchart of an automated procurement method based on intelligent recommendation provided in an embodiment of the present disclosure.

[0064] like Figure 4 As shown, the automated procurement method based on intelligent recommendation may include:

[0065] S401, obtaining a shopping list.

[0066] The relevant contents of step S401 can be found in the above embodiment and will not be described again here.

[0067] S402, calling a natural language model to extract key entity information from the shopping list.

[0068] In some implementations, the shopping list of the user is unstructured text, and key entity information can be extracted from the shopping list by calling a natural language model. Alternatively, key entity information can be extracted from the shopping list based on keywords.

[0069] For example, you can use the categories of different products as keywords, such as tops, hats, mobile phones, etc. You can also use the quantity of products as keywords, such as 5, 3 pairs, etc. You can also use the brand of the product as a keyword, such as brand A, brand B, etc.

[0070] In other words, key entity information such as product category, product brand, and product quantity can be extracted from the shopping list.

[0071] S403: Generate structured data based on key entity information.

[0072] S404: Analyze and identify the intent of the structured data, and output the first product information.

[0073] In some implementations, structured data may be obtained by structuring key entity information. Further, by analyzing and identifying the intent of the information contained in the structured data, the product category, product quantity, and product brand may be accurately determined as the first product information and output.

[0074] Optionally, by analyzing and identifying the intent of the structured data, the product category is obtained, and whether the structured data contains the product quantity and product brand is further identified. In response to identifying the product quantity and product brand from the structured data, the first product information is generated according to the product category, product quantity and product brand.

[0075] In some implementations, if the quantity or brand of goods is not identified from the structured data, historical sales data, user reviews, product prices and other information of different brands under the product category can be used as auxiliary information, and the product brand and quantity can be determined based on the auxiliary information as the first product information.

[0076] That is to say, in response to at least one information item of the quantity and brand of goods not being identified from the structured data, auxiliary information matching the unidentified information item is obtained, and the information item is determined based on the auxiliary information, and combined with the product category, the first product information is generated, so as to realize comparative analysis of product brands and achieve personalized product recommendations.

[0077] In some implementations, in response to not identifying the information item as the quantity of goods, the second product information is determined to be the first auxiliary information, and a quantity decision is made based on the price of the goods and the promotion information to obtain the quantity of the goods. In other words, if the first product information does not include the quantity of the goods, an appropriate quantity of the goods can be recommended to the user based on the price information of the goods, so as to enhance the shopping experience of the user and reduce the cost and time of the user's decision-making.

[0078] In some implementations, in response to the unidentified information item being a product brand, historical behavior data of the user is obtained as second auxiliary information, and quality association information and product price information of the candidate product brand are obtained as third auxiliary information.

[0079] Furthermore, the product brand can be determined from the candidate product brands according to at least one of the second auxiliary information and the third auxiliary information. In other words, product brands can be recommended to users according to the user's historical behavior data and the brand's quality information and price information to improve the user's shopping experience and satisfaction.

[0080] Optionally, brands with product categories may be determined as candidate product brands. Based on at least one of the second auxiliary information and the third auxiliary information, the candidate product brands may be comprehensively evaluated to obtain an evaluation value of each candidate product brand, and the candidate product brand with the highest evaluation value may be used as the product brand.

[0081] For example, Figure 5 A flow chart of determining a product brand based on the third auxiliary information is shown. When it is determined that the unidentified information item is a product brand, multiple candidate product brands can be determined based on the brand library corresponding to the product category, and the quality-related information and product price information of the candidate product brands can be obtained. Further, based on the quality-related information and product price information of the candidate product brands, a comprehensive evaluation is performed on the candidate product brands to obtain an evaluation value of each candidate product brand, and the candidate product brands are sorted according to the evaluation value, and product brands are recommended based on the sorting result, for example, the candidate product brand with the highest evaluation value is determined as the product brand.

[0082] In some implementations, in response to the information item not being identified as a product brand, the user's brand preference information may be determined based on historical behavior data, and the product brand may be determined from candidate product brands based on the brand preference information. The candidate product brands may also be sorted based on quality association information and product price information to determine the product brand from the candidate product brands, thereby achieving personalized intelligent recommendations and recommending high-quality product brands to users, thereby improving the user's shopping experience.

[0083] Example description, such as Figure 6 The flowchart of determining the brand of a product based on the brand signal information of the user is shown in FIG. By obtaining the historical behavior data of the user and extracting the characteristics of the preference behavior from the historical behavior data, the brand preference information is obtained. Therefore, the purchase behavior can be clustered according to the brand preference information to generate a preference model, and then the preference model can be used to determine the product brand from the candidate product brands.

[0084] Figure 7The flowchart for determining the first product information is shown. The shopping list of the user is obtained and the shopping list is parsed using the NPL model. By extracting key entities from the shopping list and generating structured data based on the key entity information, the product category can be obtained by performing intent recognition on the structured data, and it can be determined whether the structured data contains the product brand. If the product brand is included, the product brand can be identified, and it can be further determined whether the structured data contains the product quantity. If the product quantity is included, the first product information can be generated based on the product category, product quantity and product brand.

[0085] If the structured data does not contain the product brand, the product brand can be inferred based on the user's historical behavior data, quality-related information of the product brand, and product price information, and then further determine whether the structured data contains the product quantity. If it does not contain the product quantity, the product quantity can be calculated based on the product price and promotional information to generate the first product information based on the product category, product quantity and product brand.

[0086] S405: Obtain second product information fed back by different e-commerce companies based on the first product information, where the second product information at least includes product price and promotion information.

[0087] S406: Screen products among different e-commerce platforms according to the second product information to obtain a recommended target product combination.

[0088] S407, executing a payment operation based on the target commodity combination.

[0089] The relevant contents of steps S405-S407 can be found in the above embodiment and will not be repeated here.

[0090] According to the automated purchasing method based on intelligent recommendation provided by the embodiment of the present disclosure, by obtaining the shopping list of the user and parsing the shopping list to determine the structured data corresponding to the shopping list, and determining the first product information from the structured data, the product price and promotion information can be determined from different e-commerce companies based on the first product information as the second product information. Furthermore, the products are screened from different e-commerce companies based on the second product information to obtain the target product combination, and then the payment operation can be performed on the target product combination. When the shopping list does not contain the product brand, the different brands are evaluated and analyzed based on the price-performance ratio of different brands, the user's preferences and other information, so as to recommend the product brand to the user, which can realize personalized intelligent recommendation, reduce the user's shopping decision-making cost, and improve the user's shopping experience.

[0091] Figure 8 A flowchart of an automated procurement method based on intelligent recommendation provided in an embodiment of the present disclosure.

[0092] like Figure 8 As shown, the automated procurement method based on intelligent recommendation may include:

[0093] S801, obtaining a shopping list, and parsing the shopping list to obtain first product information.

[0094] The relevant contents of step S801 can be found in the above embodiment and will not be described again here.

[0095] S802, calling an application program interface API to send a query request to different e-commerce companies, where the query request is related to the first product information, and receiving the second product information fed back by different e-commerce companies.

[0096] In some implementations, distributed crawling can be performed on different e-commerce companies based on their respective application programming interfaces (APIs) to obtain the second product information, thereby obtaining product prices and promotional information from multiple different e-commerce companies, which helps to obtain the best promotion and save users' shopping costs.

[0097] Optionally, the identification information of the product brand in the first product information can be determined, and a query request can be generated based on the identification information to query the product price and promotion information in the e-commerce according to the query request as the second product information, and then the second product information fed back by different e-commerce companies can be received.

[0098] S803, combining products in different e-commerce companies according to product prices and promotion information, and obtaining a first candidate product combination for each e-commerce company.

[0099] In some implementations, the preferential rules of each e-commerce company can be determined based on the promotion information of each e-commerce company, and different products can be selected and combined within the e-commerce company based on the product prices to meet the preferential rules of the e-commerce company, thereby obtaining a first candidate product combination. The products in the first candidate product combination at least include the target product in the shopping list.

[0100] As an example, take e-commerce 1 as an example. The discount rule determined according to the promotional information is 200 off for purchases over 1000. The target products in the shopping list are handbags, shoes, and hats. The first product information determined according to the shopping list is handbags of brand A, shoes of brand B, and hats of brand C. By obtaining the price of each product in e-commerce 1 and determining the total price of the products according to the quantity of the products, if the total price of the products meets the discount rule, the first candidate product combination is handbags of brand A, shoes of brand B, and hats of brand C; if the total price of the products does not meet the discount rule, other products can be selected to be added to the first candidate product combination so that the total price of the products meets the discount rule, thereby obtaining the first candidate product combination.

[0101] S804: Combining products among different e-commerce companies based on product prices and promotion information to obtain at least one second candidate product combination.

[0102] In some implementations, the preferential rules of each e-commerce company can be determined based on the promotion information of each e-commerce company, and the commodity combination strategies among different e-commerce companies can be analyzed based on the preferential rules and commodity prices, so as to select different commodities for combination according to the commodity combination strategy to obtain the second candidate commodity combination. The commodities in the second candidate commodity combination at least include the target commodity in the shopping list.

[0103] For example, take e-commerce 1 and e-commerce 2 as examples. If the shopping list indicates that the user needs to buy 5 pairs of brand A shoes, by determining the discount rules of e-commerce 1 and e-commerce 2, and based on the discount rules, analyze the product combination strategy between e-commerce 1 and e-commerce 2. Buying 2 pairs of brand A shoes on e-commerce 1 and 3 pairs of brand A shoes on e-commerce 2 can achieve the greatest discount. The second candidate product combination is 2 pairs of brand A shoes from e-commerce 1 and 3 pairs of brand A shoes from e-commerce 2.

[0104] S805: Determine a target commodity combination from the first candidate commodity combination and the second candidate commodity combination.

[0105] In some implementations, the first candidate product combination and the second candidate product combination can be screened according to the product quantity and optimal price required by the user to determine the target product combination, which can save shopping costs and improve shopping experience.

[0106] In some implementations, the second product information also includes at least product auxiliary information of the target product on different e-commerce platforms, and the product auxiliary information includes at least the product inventory quantity. That is to say, by determining the product quantity and product inventory quantity required for the target product, and based on the product quantity and product inventory quantity of the target product, a third candidate product combination is determined from the first candidate product combination and the second candidate product combination.

[0107] Further, the commodity payment information of the third candidate commodity combination is obtained, and the target commodity combination is determined from the third candidate commodity combination according to the commodity payment information. Optionally, the third candidate commodity combinations can be sorted according to the commodity payment information to determine the third candidate commodity combination with the smallest commodity payment information from the third candidate commodity combinations as the target commodity combination.

[0108] In some implementations, the product auxiliary information also includes at least: sales volume of the target product, the store to which the target product belongs, and the service information of the store. That is to say, the score of the third candidate product combination can also be obtained based on the sales volume of the target product, the store to which the target product belongs, and the service information of the store, and the third candidate product combination can be combined and screened based on the score to obtain the final third candidate product combination.

[0109] Optionally, by scoring the third candidate product combinations according to the product auxiliary information, a score value for each third candidate product combination is obtained, and the third candidate product combination with the largest score value is used as the final third candidate product combination. This can ensure that the products in the final third candidate product combination have more reliable after-sales service to enhance the user's shopping experience.

[0110] In some implementations, after obtaining the target product combination, the user's target product combination can also be adjusted to make shopping more satisfying to the user's needs. That is, the target product combination can be displayed, and the product combination adjustment operation can be monitored. In response to monitoring the product combination adjustment operation, the target product combination is adjusted according to the product combination adjustment operation to generate the final target product combination.

[0111] S806, executing a payment operation based on the target commodity combination.

[0112] The relevant contents of step S806 can be found in the above embodiment and will not be repeated here.

[0113] According to the automated purchasing method based on intelligent recommendation provided by the embodiment of the present disclosure, by obtaining the shopping list of the user and determining the first commodity information from the shopping list, the commodity price and promotion information can be determined from different e-commerce companies based on the first commodity information as the second commodity information. Furthermore, the commodities are screened in different e-commerce companies based on the second commodity information to obtain the first candidate commodity combination and the second candidate commodity combination, and the target commodity combination is determined from the first candidate commodity combination and the second candidate commodity combination based on the quantity and price of the commodities, and then the payment operation can be performed on the target commodity combination. By obtaining the second commodity information from different e-commerce companies, cross-platform price comparison can be achieved, thereby improving the shopping efficiency of users. By combining the discounts between commodities on multiple platforms, shopping costs are saved and the shopping experience of users is enhanced.

[0114] like Fig. 9 The timing diagram of intelligent procurement of goods is shown. Fig. 9 It includes list parsing module, product information acquisition and processing module, brand and category recommendation module, user preference analysis module, automatic ordering and payment module, product API, shopping cart API, and payment system API.

[0115] The list parsing module obtains the shopping list input by the user and parses the shopping list to obtain the product category, product quantity and product brand as the first product information, and sends the parsed first product information to the product information acquisition and processing module. Furthermore, based on the product API, the product price and promotion information are obtained from different e-commerce companies as the second product information, and then products can be filtered based on the second product information, and price comparison results or discount recommendations and other information are returned to determine the target product combination based on the price comparison results or discount recommendations.

[0116] When the shopping list does not contain a product brand, the brand and category recommendation module can recommend the product brand, and the product brand can be determined by analyzing and suggesting the brand. Optionally, the user preference analysis module can also analyze user preferences and recommend products.

[0117] After the target product combination is determined, the target product combination can be fed back to the user, and the user can adjust the target product combination to obtain the final target product combination, and further send the final target product combination to the automatic ordering and payment module, which adds the products in the final target product combination to the shopping cart based on the shopping cart API, obtains the target payment order, and calls the payment system based on the payment system API to pay for the target payment order and complete the shopping.

[0118] like Fig.10 The flowchart of intelligent purchasing of goods is shown in FIG. Fig.10 It includes list parsing module, product information acquisition and processing module, brand and category recommendation module, user preference analysis module, and automatic ordering and payment module.

[0119] The user inputs a shopping list, and the list parsing module parses the shopping list. By determining whether the shopping list contains the product brand, if so, a complete list containing the product brand can be generated. If not, the brand and category recommendation module can generate a recommended list of product brands, and the user preference analysis module can generate a personalized recommended list as the first product information based on the complete list or the recommended list.

[0120] Furthermore, the product information acquisition and processing module acquires product prices and promotion information corresponding to the first product information from different e-commerce platforms as second product information, and a target product combination can be screened out based on the second product information. Optionally, the user can adjust the target product combination to obtain a final target product combination.

[0121] Furthermore, the automatic ordering and payment module generates a target payment order according to the target product combination, and performs a payment operation on the target payment order to complete the shopping and end the shopping process. If the payment fails, the target payment order can be re-initiated to guide the user to make a new payment.

[0122] Corresponding to the automated procurement methods based on intelligent recommendation provided in the above-mentioned embodiments, an embodiment of the present disclosure further provides an automated procurement device based on intelligent recommendation. Since the automated procurement device based on intelligent recommendation provided in the embodiment of the present disclosure corresponds to the automated procurement methods based on intelligent recommendation provided in the above-mentioned embodiments, the implementation methods of the above-mentioned automated procurement methods based on intelligent recommendation are also applicable to the automated procurement device based on intelligent recommendation provided in the embodiment of the present disclosure, and will not be described in detail in the following embodiments.

[0123] Fig.11 A schematic diagram of the structure of an automated procurement device based on intelligent recommendation provided in an embodiment of the present disclosure.

[0124] like Fig.11 As shown, the automatic procurement device 1100 based on intelligent recommendation according to an embodiment of the present disclosure includes a parsing module 1101 , an acquisition module 1102 , a screening module 1103 and a payment module 1104 .

[0125] The parsing module 1101 is used to obtain a shopping list and parse the shopping list to obtain first product information;

[0126] An acquisition module 1102 is configured to acquire second product information fed back by different e-commerce companies based on the first product information, where the second product information at least includes product price and promotion information;

[0127] A screening module 1103 is used to screen products among different e-commerce platforms according to the second product information to obtain a recommended target product combination;

[0128] The payment module 1104 is used to perform a payment operation based on the target commodity combination.

[0129] In one embodiment of the present disclosure, the payment module 1104 is further used to: determine the filtered commodities according to the target commodity combination, wherein the filtered commodities at least include the target commodities included in the shopping list; add the filtered commodities to the shopping cart, and generate a payment order for the target shopping combination according to the second commodity information of the filtered commodities; and call the payment program to pay for the target payment order.

[0130] In one embodiment of the present disclosure, the parsing module 1101 is further used to: call a natural language model to extract key entity information from the shopping list; generate structured data based on the key entity information; analyze and identify intent of the structured data, and output the first product information.

[0131] In one embodiment of the present disclosure, the parsing module 1101 is further used to: analyze and identify the intent of the structured data to obtain the product category; in response to identifying the product quantity and product brand from the structured data, generate the first product information according to the product category, product quantity and product brand.

[0132] In one embodiment of the present disclosure, the parsing module 1101 is further used to: in response to at least one information item of the quantity and brand of the goods not being identified from the structured data, obtain auxiliary information matching the unidentified information item; determine the information item based on the auxiliary information, and generate the first product information in combination with the product category.

[0133] In one embodiment of the present disclosure, the parsing module 1101 is further used to: in response to the unidentified information item being the commodity quantity, determine that the second commodity information is the first auxiliary information, and make a quantity decision based on the commodity price and promotion information to obtain the commodity quantity.

[0134] In one embodiment of the present disclosure, the parsing module 1101 is further used to: in response to the unidentified information item being the product brand, obtain the user's historical behavior data as second auxiliary information; obtain quality-related information and product price information of the candidate product brand as third auxiliary information; and determine the product brand from the candidate product brands based on at least one of the second auxiliary information and the third auxiliary information.

[0135] In one embodiment of the present disclosure, the analysis module 1101 is also used to: determine the user's brand preference information based on the historical behavior data, and determine the product brand from the candidate product brands based on the brand preference information; and / or sort the candidate product brands according to the quality association information and product price information to determine the product brand from the candidate product brands.

[0136] In one embodiment of the present disclosure, the acquisition module 1102 is further used to: call an application program interface API to send query requests to different e-commerce companies, where the query requests are related to the first product information, and receive second product information fed back by different e-commerce companies.

[0137] In one embodiment of the present disclosure, the screening module 1103 is further used to: combine commodities within different e-commerce companies based on the commodity prices and promotional information to obtain a first candidate commodity combination for each e-commerce company; combine commodities between different e-commerce companies based on the commodity prices and promotional information to obtain at least one second candidate commodity combination; and determine the target commodity combination from the first candidate commodity combination and the second candidate commodity combination.

[0138] In one embodiment of the present disclosure, the screening module 1103 is further used to: determine the quantity of goods required for the target goods and the inventory quantity of the goods; determine a third candidate product combination from the first candidate product combination and the second candidate product combination based on the quantity of goods and the inventory quantity of the target goods; obtain product payment information of the third candidate product combination; and determine the target product combination from the third candidate product combination based on the product payment information.

[0139] In one embodiment of the present disclosure, the screening module 1103 is further used to: obtain the score of the third candidate product combination based on the sales volume of the target product, the store to which the target product belongs and the service information of the store; and perform combination screening on the third candidate product combination based on the score to obtain a final third candidate product combination.

[0140] In one embodiment of the present disclosure, the screening module 1103 is further used to: display the target product combination and monitor the product combination adjustment operation; in response to monitoring the product combination adjustment operation, adjust the target product combination according to the product combination adjustment operation to generate a final target product combination.

[0141] According to the automated purchasing method based on intelligent recommendation provided by the embodiment of the present disclosure, by obtaining the shopping list of the user and determining the first product information from the shopping list, the product price and promotion information can be determined from different e-commerce companies based on the first product information as the second product information. Furthermore, the products are screened from different e-commerce companies based on the second product information to obtain the target product combination, and then the payment operation can be performed on the target product combination. By obtaining the second product information from different e-commerce companies, cross-platform price comparison can be achieved, thereby improving the shopping efficiency of users. By combining the discounts between products on multiple platforms, shopping costs are saved and the shopping experience of users is enhanced.

[0142] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0143] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0144] Fig.12 A schematic block diagram of an example electronic device 1200 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0145] like Fig.12 As shown, the device 1200 includes a computing unit 1201, which can perform various appropriate actions and processes according to a computer program / instruction stored in a read-only memory (ROM) 1202 or a computer program / instruction loaded from a storage unit 1206 to a random access memory (RAM) 1203. In the RAM 1203, various programs and data required for the operation of the device 1200 can also be stored. The computing unit 1201, the ROM 1202, and the RAM 1203 are connected to each other via a bus 1204. An input / output (I / O) interface 1205 is also connected to the bus 1204.

[0146] A number of components in the device 1200 are connected to the I / O interface 1205, including: an input unit 1206 such as a keyboard, a mouse, etc.; an output unit 1207 such as various types of displays, speakers, etc.; a storage unit 1208 such as a disk, an optical disk, etc.; and a communication unit 1209 such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1209 allows the device 1200 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0147] The computing unit 1201 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1201 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 1201 performs the various methods and processes described above, such as an automated procurement method based on intelligent recommendation. For example, in some embodiments, the automated procurement method based on intelligent recommendation may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 1206. In some embodiments, part or all of the computer program / instructions may be loaded and / or installed on the device 1200 via the ROM 1202 and / or the communication unit 1209. When the computer program / instructions are loaded into the RAM 1203 and executed by the computing unit 1201, one or more steps of the automated procurement method based on intelligent recommendation described above may be performed. Alternatively, in other embodiments, the computing unit 1201 may be configured to execute an automated purchasing method based on intelligent recommendation in any other appropriate manner (eg, by means of firmware).

[0148] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs / instructions that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0149] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0150] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0151] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0152] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0153] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs / instructions running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0154] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in the disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in the disclosure can be achieved, and this document does not limit them here.

[0155] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. An automated procurement method based on intelligent recommendation, wherein: The method comprises: Obtaining a shopping list, and parsing the shopping list to obtain first product information; According to the first product information, second product information fed back by different e-commerce companies is obtained, where the second product information at least includes product price and promotion information; Screening products among different e-commerce platforms based on the second product information to obtain a recommended target product combination; A payment operation is performed based on the target commodity combination.

2. The method according to claim 1, wherein: The performing a payment operation based on the target commodity combination includes: Determining filtered commodities according to the target commodity combination, wherein the filtered commodities at least include the target commodities included in the shopping list; Adding the screened commodities to the shopping cart, and generating a payment order for the target shopping combination according to the second commodity information of the screened commodities; The payment program is called to pay the target payment order.

3. The method according to claim 1, wherein: The parsing the shopping list to obtain the first product information includes: Calling a natural language model to extract key entity information from the shopping list; Generate structured data according to the key entity information; The structured data is analyzed and the intent is identified, and the first product information is output.

4. The method according to claim 3, wherein: The analyzing and identifying the intent of the structured data and outputting the first product information includes: Analyze and identify the intent of the structured data to obtain product categories; In response to identifying the commodity quantity and commodity brand from the structured data, the first commodity information is generated according to the commodity category, commodity quantity and commodity brand.

5. The method according to claim 4, wherein: The method further comprises: In response to not identifying at least one of the information items of the quantity of goods and the brand of goods from the structured data, acquiring auxiliary information matching the unidentified information item; The information item is determined according to the auxiliary information, and combined with the commodity category to generate the first commodity information.

6. The method according to claim 5, wherein: The method further comprises: In response to the unrecognized information item being the commodity quantity, the second commodity information is determined to be the first auxiliary information, and a quantity decision is made based on the commodity price and promotion information to obtain the commodity quantity.

7. The method according to claim 5, wherein: The method further comprises: In response to the unidentified information item being the product brand, acquiring historical behavior data of the user as second auxiliary information; Acquire quality-related information and product price information of candidate product brands as third auxiliary information; The product brand is determined from the candidate product brands according to at least one of the second auxiliary information and the third auxiliary information.

8. The method according to claim 7, wherein: The method further comprises: Determining the user's brand preference information according to the historical behavior data, and determining the product brand from candidate product brands based on the brand preference information; and / or, The candidate product brands are sorted according to the quality-related information and product price information to determine the product brand from the candidate product brands.

9. The method according to any one of claims 1 to 8, wherein: The obtaining, according to the first product information, second product information fed back by different e-commerce companies includes: An application programming interface (API) is called to send query requests to different e-commerce companies, where the query requests are related to the first product information, and second product information fed back by different e-commerce companies is received.

10. The method according to any one of claims 1 to 8, wherein: The filtering of products among different e-commerce platforms according to the second product information to obtain a recommended target product combination includes: Combining products among different e-commerce companies based on the product prices and promotion information to obtain a first candidate product combination for each e-commerce company; Combining products among different e-commerce companies according to the product prices and promotion information to obtain at least one second candidate product combination; The target commodity combination is determined from the first candidate commodity combination and the second candidate commodity combination.

11. The method according to claim 10, wherein: The second product information at least further includes product auxiliary information of the target product on different e-commerce platforms, and the product auxiliary information at least includes product inventory quantity. Determining the target product combination from the first candidate product combination and the second candidate product combination includes: Determine the quantity of the target product required and the inventory quantity of the target product; Determine a third candidate product combination from the first candidate product combination and the second candidate product combination according to the product quantity of the target product and the product inventory quantity; Acquiring commodity payment information of the third candidate commodity combination; The target commodity combination is determined from the third candidate commodity combination according to the commodity payment information.

12. The method according to claim 10, wherein: The commodity auxiliary information at least includes: the sales volume of the target commodity, the store to which the target commodity belongs and the service information of the store, and the method further includes: Obtaining a score for the third candidate product combination according to the sales volume of the target product, the store to which the target product belongs, and the service information of the store; The third candidate product combination is screened according to the score to obtain a final third candidate product combination.

13. The method according to any one of claims 1 to 8, wherein: After filtering products among different e-commerce platforms according to the second product information and obtaining a recommended target product combination, the method further includes: Displaying the target product combination and monitoring the product combination adjustment operation; In response to monitoring the commodity combination adjustment operation, the target commodity combination is adjusted according to the commodity combination adjustment operation to generate a final target commodity combination.

14. An automated purchasing device based on intelligent recommendation, wherein: The device comprises: A parsing module, used to obtain a shopping list and parse the shopping list to obtain first product information; An acquisition module, configured to acquire second product information fed back by different e-commerce companies based on the first product information, wherein the second product information at least includes product price and promotion information; A screening module, configured to screen products among different e-commerce platforms according to the second product information, and obtain a recommended target product combination; A payment module is used to perform a payment operation based on the target commodity combination.

15. The device according to claim 14, wherein: The payment module is also used for: Determining filtered commodities according to the target commodity combination, wherein the filtered commodities at least include the target commodities included in the shopping list; Adding the screened commodities to the shopping cart, and generating a payment order for the target shopping combination according to the second commodity information of the screened commodities; The payment program is called to pay the target payment order.

16. The device according to claim 14, wherein: The parsing module is also used for: Calling a natural language model to extract key entity information from the shopping list; Generate structured data according to the key entity information; The structured data is analyzed and the intent is identified, and the first product information is output.

17. The device according to claim 16, wherein: The parsing module is also used for: Analyze and identify the intent of the structured data to obtain product categories; In response to identifying the commodity quantity and commodity brand from the structured data, the first commodity information is generated according to the commodity category, commodity quantity and commodity brand.

18. The device according to claim 17, wherein: The parsing module is also used for: In response to not identifying at least one of the information items of the quantity of goods and the brand of goods from the structured data, acquiring auxiliary information matching the unidentified information item; The information item is determined according to the auxiliary information, and combined with the commodity category to generate the first commodity information.

19. The device according to claim 18, wherein: The parsing module is also used for: In response to the unrecognized information item being the commodity quantity, the second commodity information is determined to be the first auxiliary information, and a quantity decision is made based on the commodity price and promotion information to obtain the commodity quantity.

20. The device according to claim 18, wherein The parsing module is also used for: In response to the unidentified information item being the product brand, acquiring historical behavior data of the user as second auxiliary information; Acquire quality-related information and product price information of candidate product brands as third auxiliary information; The product brand is determined from the candidate product brands according to at least one of the second auxiliary information and the third auxiliary information.

21. The device according to claim 20, wherein: The parsing module is also used for: Determining the user's brand preference information according to the historical behavior data, and determining the product brand from candidate product brands based on the brand preference information; and / or, The candidate product brands are sorted according to the quality-related information and product price information to determine the product brand from the candidate product brands.

22. The device according to any one of claims 14 to 21, wherein: The acquisition module is further used for: An application programming interface (API) is called to send query requests to different e-commerce companies, where the query requests are related to the first product information, and second product information fed back by different e-commerce companies is received.

23. The device according to any one of claims 14 to 21, wherein: The screening module is further used for: Combining products among different e-commerce companies based on the product prices and promotion information to obtain a first candidate product combination for each e-commerce company; Combining products among different e-commerce companies according to the product prices and promotion information to obtain at least one second candidate product combination; The target commodity combination is determined from the first candidate commodity combination and the second candidate commodity combination.

24. The device according to claim 23, wherein: The screening module is further used for: Determine the quantity of the target product required and the inventory quantity of the target product; Determine a third candidate product combination from the first candidate product combination and the second candidate product combination according to the product quantity of the target product and the product inventory quantity; Acquiring commodity payment information of the third candidate commodity combination; The target commodity combination is determined from the third candidate commodity combination according to the commodity payment information.

25. The method according to claim 24, wherein: The screening module is further used for: Obtaining a score for the third candidate product combination according to the sales volume of the target product, the store to which the target product belongs, and the service information of the store; The third candidate product combination is screened according to the score to obtain a final third candidate product combination.

26. The device according to any one of claims 14 to 21, wherein: The screening module is further used for: Displaying the target product combination and monitoring the product combination adjustment operation; In response to monitoring the commodity combination adjustment operation, the target commodity combination is adjusted according to the commodity combination adjustment operation to generate a final target commodity combination.

27. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 13.

28. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-13.

29. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the method according to any one of claims 1 to 13 is implemented.

Images