Commodity supply information processing method, medium and electronic equipment
Patent Information
- Application Number
- CN202410955097.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-16
- Publication Date
- 2024-11-08
Smart Images

Figure CN118917899A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the fields of Internet technology and data processing technology, and in particular to a commodity supply information processing method, medium and electronic device. Background Art
[0002] The commodity supplier (supplier) refers to the enterprise and its branches that provide commodities and corresponding services. With the development of Internet technology, the types of Internet business are also increasing, and various business fields, such as home decoration business and equipment leasing business, have the need to find suppliers.
[0003] In the related art, when the need to source suppliers arises, purchasing personnel source suppliers offline. For example, when a customer needs to purchase a toilet in a home improvement business, purchasing personnel can visit offline toilet sales stores to conduct investigations and consultations, and recommend toilet suppliers that meet the user's needs. However, the efficiency and accuracy of offline supplier sourcing are low, and in scenarios with a large number of customers, the workload of purchasing personnel in offline supplier sourcing is heavy. Summary of the invention
[0004] In order to solve the above technical problems, a commodity supply information processing method, medium and electronic device are proposed.
[0005] According to a first aspect of an embodiment of the present disclosure, there is provided a method for processing commodity supply information, comprising:
[0006] Performing multimedia analysis on at least one set of customer communication information to obtain text information to be processed corresponding to the at least one set of customer communication information;
[0007] Perform semantic analysis on each text information to be processed to obtain related information of at least one commodity supplier;
[0008] Based on the association information of the at least one commodity supplier, acquiring attribute information of the at least one commodity supplier;
[0009] The attribute information of the at least one commodity supplier is input into a pre-trained first text model, and the recommendation score of the at least one commodity supplier is output through the first text model.
[0010] In some embodiments of the present disclosure, after generating the recommendation score of the at least one commodity supplier, the method further includes:
[0011] Classify the at least one commodity supplier according to the category of the commodity supplier to obtain at least one commodity supplier list;
[0012] Sort the commodity suppliers in each commodity supplier list according to the recommendation score;
[0013] The sorted list of suppliers of each product is pushed to the matching business parties respectively.
[0014] In some embodiments of the present disclosure, the semantic analysis of each text information to be processed to obtain the associated information of at least one commodity supplier includes:
[0015] The pre-trained first text model is used to generate the associated information of the at least one commodity supplier based on each piece of text information to be processed.
[0016] In some embodiments of the present disclosure, the acquiring, based on the association information of the at least one commodity supplier, the attribute information of the at least one commodity supplier includes:
[0017] Based on the association information of the at least one commodity supplier, the attribute information of the at least one commodity supplier is acquired from a network server using a web crawler algorithm.
[0018] In some embodiments of the present disclosure, the performing multimedia analysis on at least one set of customer communication information to obtain the to-be-processed text information corresponding to the at least one set of customer communication information includes:
[0019] In response to at least one group of customer communication information being audio information, performing voice enhancement processing on the audio information, and recognizing text in the audio information after voice enhancement processing by a voice recognition algorithm, to obtain text information to be processed corresponding to at least one group of customer communication information;
[0020] In response to at least one group of customer source communication information being text information, filtering the text information to obtain to-be-processed text information corresponding to at least one group of customer source communication information;
[0021] In response to at least one group of customer communication information being image information, the image is subjected to noise reduction preprocessing, and text in the image information after noise reduction preprocessing is recognized by a text recognition algorithm to obtain text information to be processed corresponding to at least one group of customer communication information.
[0022] In some embodiments of the present disclosure, the step of inputting the attribute information of the at least one commodity supplier into a pre-trained first text model, and outputting a recommendation score of the at least one commodity supplier via the first text model, comprises:
[0023] Determine, by using the first text model, a single score corresponding to each attribute information in the attribute information of the at least one commodity supplier;
[0024] Based on the individual scores corresponding to the attribute information of the at least one commodity supplier, a recommendation score of the at least one commodity supplier is determined.
[0025] In some embodiments of the present disclosure, before performing multimedia analysis on at least one set of customer communication information, the method further includes:
[0026] Acquire the customer source communication information from the customer source information database of each business party according to a set period; or,
[0027] Receive customer communication information uploaded by users through the client.
[0028] According to a second aspect of an embodiment of the present disclosure, there is provided a commodity supply information processing device, including:
[0029] A first parsing module is used to perform multimedia parsing processing on at least one group of customer communication information to obtain text information to be processed corresponding to the at least one group of customer communication information;
[0030] A second parsing module is used to perform semantic parsing on each text information to be processed to obtain associated information of at least one commodity supplier;
[0031] A first acquisition module, configured to acquire attribute information of the at least one commodity supplier based on the association information of the at least one commodity supplier;
[0032] The generating module is used to input the attribute information of the at least one commodity supplier into a pre-trained first text model, and output the recommendation score of the at least one commodity supplier through the first text model.
[0033] In some embodiments of the present disclosure, the device further comprises:
[0034] A classification module, used to classify the at least one commodity supplier according to the category of the commodity supplier to obtain at least one commodity supplier list;
[0035] A sorting module, used to sort the commodity suppliers in each commodity supplier list according to the recommendation score;
[0036] The push module is used to push the sorted list of commodity suppliers to the matching business parties respectively.
[0037] In some embodiments of the present disclosure, the second parsing module is specifically configured to generate the associated information of the at least one commodity supplier based on each piece of text information to be processed, using a pre-trained first text model.
[0038] In some embodiments of the present disclosure, the first acquisition module is specifically configured to acquire attribute information of the at least one commodity supplier from a network server using a web crawler algorithm based on the association information of the at least one commodity supplier.
[0039] In some embodiments of the present disclosure, the first parsing module includes:
[0040] The audio analysis submodule is used for performing speech enhancement processing on the audio information in response to at least one group of customer communication information being audio information, and recognizing text in the audio information after speech enhancement processing by a speech recognition algorithm to obtain text information to be processed corresponding to at least one group of customer communication information;
[0041] A text parsing submodule, configured to filter the text information in response to at least one group of customer communication information being text information, and obtain text information to be processed corresponding to at least one group of customer communication information;
[0042] The image analysis submodule is used to perform noise reduction preprocessing on the image in response to at least one group of customer communication information being image information, and to recognize text in the image information after noise reduction preprocessing through a text recognition algorithm to obtain text information to be processed corresponding to at least one group of customer communication information.
[0043] In some embodiments of the present disclosure, the generating module includes:
[0044] A first determination submodule, configured to determine, by using the first text model, a single score corresponding to each attribute information in the attribute information of the at least one commodity supplier;
[0045] The second determination submodule is used to determine the recommendation score of at least one commodity supplier based on the single score corresponding to each attribute information of the at least one commodity supplier.
[0046] In some embodiments of the present disclosure, the device further comprises:
[0047] The customer source information acquisition module is used to acquire the customer source communication information from the customer source information database of each business party according to a set period; or, receive the customer source communication information uploaded by the user through the client.
[0048] According to a third aspect of an embodiment of the present disclosure, there is provided a computer-readable storage medium, wherein the storage medium stores computer program instructions, and when the computer program instructions are executed, the above-mentioned commodity supply information processing method is implemented.
[0049] According to a fourth aspect of an embodiment of the present disclosure, an electronic device is provided, the electronic device comprising:
[0050] A memory for storing a computer program product;
[0051] The processor is used to execute the computer program product stored in the memory, and when the computer program product is executed, the above-mentioned commodity supply information processing method is implemented.
[0052] According to a fifth aspect of an embodiment of the present disclosure, there is provided a computer program product, comprising computer program instructions, which implement the above-mentioned commodity supply information processing method when executed by a processor.
[0053] Based on the above embodiments of the present disclosure, the attribute information of the corresponding commodity supplier can be automatically obtained based on the acquired customer source communication information, and the recommendation score of the commodity supplier can be automatically calculated based on the attribute information of the commodity supplier. Therefore, the technical solution of the present disclosure can automatically obtain the attribute information of the commodity supplier based on the customer source communication information, and determine the recommendation score of the commodity supplier based on the attribute information of the commodity supplier, thereby realizing the automation and intelligence of commodity supplier sourcing, and improving the efficiency and accuracy of commodity supplier sourcing.
[0054] The technical solution of the present disclosure is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS
[0055] By describing the embodiments of the present disclosure in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present disclosure will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present disclosure and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the present disclosure and do not constitute a limitation of the present disclosure. In the drawings, the same reference numerals generally represent the same components or steps.
[0056] Figure 1 A flowchart of an embodiment of a method for processing commodity supply information disclosed in the present invention;
[0057] Figure 2 A flowchart of another embodiment of the commodity supply information processing method disclosed in the present invention;
[0058] Figure 3 A flowchart of another embodiment of the commodity supply information processing method disclosed in the present invention;
[0059] Figure 4 It is a structural schematic diagram of an embodiment of a commodity supply information processing device disclosed in the present invention;
[0060] Figure 5 It is a structural schematic diagram of another embodiment of the commodity supply information processing device disclosed in the present invention;
[0061] Figure 6It is a structural diagram of an electronic device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION
[0062] The exemplary embodiments according to the present disclosure will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments of the present disclosure, and it should be understood that the present disclosure is not limited to the exemplary embodiments described here.
[0063] It should be noted that the relative arrangement of components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise.
[0064] Those skilled in the art can understand that the terms "first" and "second" in the embodiments of the present disclosure are only used to distinguish different steps, devices or modules, etc., and neither represent any specific technical meaning nor indicate the necessary logical order between them.
[0065] It should also be understood that in the embodiments of the present disclosure, “plurality” may refer to two or more than two, and “at least one” may refer to one, two, or more than two.
[0066] It should also be understood that any component, data or structure mentioned in the embodiments of the present disclosure can generally be understood as one or more, unless explicitly limited or otherwise indicated in the context.
[0067] In addition, the term "and / or" in this disclosure is only a description of the association relationship of associated objects, indicating that there may be three relationships, such as A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this disclosure generally indicates that the associated objects before and after are in an "or" relationship.
[0068] It should also be understood that the description of the various embodiments in the present disclosure focuses on the differences between the various embodiments, and the same or similar aspects thereof can be referenced to each other, and for the sake of brevity, they will not be described one by one.
[0069] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.
[0070] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or uses.
[0071] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.
[0072] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.
[0073] The embodiments of the present disclosure can be applied to electronic devices such as terminal devices, computer systems, servers, etc., which can operate with many other general or special computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments and / or configurations suitable for use with electronic devices such as terminal devices, computer systems or servers include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, small computer systems, large computer systems, and distributed cloud computing technology environments including any of the above systems, etc.
[0074] Electronic devices such as terminal devices, computer systems, servers, etc. can be described in the general context of computer system executable instructions (such as program modules) executed by computer systems. Generally, program modules can include routines, programs, target programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in a distributed cloud computing environment. In a distributed cloud computing environment, tasks can be performed by remote processing devices linked through a communication network. In a distributed cloud computing environment, program modules can be located on local or remote computing system storage media including storage devices.
[0075] Exemplary Methods
[0076] Figure 1 FIG. 1 is a flow chart of an embodiment of the method for processing commodity supply information disclosed in the present invention. Figure 1 The method shown is applied in an electronic device (such as a computer or a server), and includes steps 101 to 104. Each step is described below.
[0077] In step 101, multimedia analysis is performed on at least one group of customer communication information to obtain text information to be processed corresponding to at least one group of customer communication information.
[0078] The customer communication information may include information about communication between the service provider and the customer, which can help the service provider understand the interests and needs of the user. The text information to be processed may be stored in a database or a data table so that it can be read at any time when needed.
[0079] Among them, the types of customer communication information are not unique. For example, customer communication information can be audio information, such as the recording information of a voice call between a service provider and a customer; customer communication information can also be text information, such as the text information generated by the service provider and the customer communicating through an instant communication program; customer communication information can also be image information, such as during the communication between the service provider and the customer, the customer sends an image to the service provider, and the image can contain the customer's demand information, such as a picture of a promotional leaflet for a certain product.
[0080] In some optional implementations, there is no unique way to obtain customer communication information. The electronic device may obtain customer communication information from the customer information database of each business party according to a set period; or, the electronic device may receive customer communication information actively uploaded by the user through the client.
[0081] The set period may be a pre-set periodic time interval for obtaining customer communication. For example, the set period may be 12 hours. The electronic device may request customer communication information from various business parties, such as the customer system and the order system, every 12 hours. Each business party may return the customer communication information recorded in the customer information database to the electronic device. The customer communication information may also be offline communication data. For example, when a user visits a store to learn about relevant information, the service provider may record the communication information and upload it to the electronic device.
[0082] In some optional implementations, in order to automatically identify and perform multimedia analysis on customer communication information, an optical character recognition (OCR) component, an automatic speech recognition (ASR) component, etc. may be embedded in the electronic device to automatically analyze customer communication information (text, images, audio, etc.) and obtain corresponding text information to be processed.
[0083] In specific implementation, if at least one group of customer communication information is audio information, the audio information may be first subjected to voice enhancement processing, and the text in the audio information subjected to voice enhancement processing may be recognized by a voice recognition algorithm to obtain the to-be-processed text information corresponding to at least one group of customer communication information. The voice enhancement processing may include removing noise from the audio, thereby improving the voice quality, which is helpful to subsequently improve the efficiency and accuracy of text recognition through audio.
[0084] If at least one set of customer communication information is text information, the text information may be filtered to obtain the to-be-processed text information corresponding to at least one set of customer communication information. The filtering process may include filtering irrelevant information in the text information. For example, a service provider and a customer may talk about a lot of things during the communication process, and the text content irrelevant to the product or service may be filtered out.
[0085] If at least one set of customer communication information is image information, the image is subjected to noise reduction preprocessing, and the text in the image information subjected to noise reduction preprocessing is recognized by a text recognition algorithm to obtain the to-be-processed text information corresponding to at least one set of customer communication information. The noise reduction preprocessing may include removing noise and interference in the image by an image filtering algorithm to achieve noise reduction preprocessing, and the image may also be corrected to arrange the text horizontally or vertically, and then the text is recognized from the image.
[0086] Among them, the text information to be processed can be text containing customer needs identified from customer communication information, for example, the text information to be processed "I understand that you currently need two sets of toilets, so what are your requirements for the brand of toilets? I want a Jian brand toilet. I understand that you currently need a Jian brand toilet, and we have some. Do you have any product suppliers in mind? We may have cooperated with them, or can give you more information. Well, we went to Lazy Cat Wooden Balcony Decoration Engineering Co., Ltd. a few days ago to see it, and it feels okay..."
[0087] In step 102, semantic analysis is performed on each text message to be processed to obtain associated information of at least one commodity supplier.
[0088] Semantic parsing refers to converting natural language text into structured semantic representation. Through semantic parsing, it is possible to obtain effective information from a large amount of data. The associated information of the commodity supplier can be information related to the commodity supplier, such as the company name of the commodity supplier, the category of the commodity supplier, the brand of the commodity supplier, etc. The associated information of the commodity supplier can be stored in a database or data table so that it can be read at any time when needed.
[0089] In some optional implementations, a pre-trained first text model may be used to generate associated information of at least one commodity supplier based on each piece of text information to be processed.
[0090] The first text model may be ChatGPT (Generative Pre-Trained Transformer). The first text model may be pre-trained based on a large number of training samples, and the trained first text model may output product supplier related information for the input text information to be processed.
[0091] In some optional implementations, a large number of training samples may be collected in advance, each of which may include a text sample and carry a sample label of the commodity supplier-associated information corresponding to the text information. The initial model is trained using a large number of training samples, that is, by inputting a large number of training samples into the chat generative pre-trained conversion model, the chat generative pre-trained conversion model learns the text of these training samples for semantic analysis to obtain the corresponding commodity supplier-associated information prediction label. In the process of the chat generative pre-trained conversion model learning these training samples, the hyperparameters of the initialization model (parameters include learning rate, batch size, and number of training rounds) may be fine-tuned so that the commodity supplier-associated information prediction label obtained by the model based on the text sample is as consistent as possible with the commodity supplier-associated information sample label. After the training is completed, the first text model is obtained by the chat generative pre-trained conversion model.
[0092] Exemplarily, based on the above example of text information to be processed, the associated information of the product supplier can be obtained as "Company: Lazy Cat Wooden Balcony Decoration Engineering Co., Ltd.; Category: Toilet; Brand: Jianpai".
[0093] In step 103, attribute information of at least one commodity supplier is obtained based on the association information of at least one commodity supplier.
[0094] Among them, the attribute information of the commodity supplier can be used to indicate the industry attribute information of the commodity supplier, which is publicly available information of the commodity supplier and does not involve private information. For example, the attribute information of the commodity supplier may include registered capital, registration years, enterprise scale, enterprise profile, national standard industry, etc. The attribute information of the commodity supplier can be stored in a database or data table so that it can be read at any time when needed.
[0095] In some optional implementations, a web crawler algorithm may be used to obtain corresponding attribute information of at least one commodity supplier from a network server based on association information of each commodity supplier.
[0096] The network server may be a network platform for querying the attribute information of the commodity supplier.
[0097] In step 104, attribute information of at least one commodity supplier is input into a pre-trained first text model, and a recommendation score of at least one commodity supplier is output via the first text model.
[0098] Among them, the recommendation score of the commodity supplier is used to indicate an evaluation of the commodity supplier. The higher the recommendation score of the commodity supplier, the more worthy of recommendation the commodity supplier is, and the lower the recommendation score of the commodity supplier, the less worthy of recommendation the commodity supplier is.
[0099] The first text model may be a chat generation pre-trained conversion model. The first text model may be pre-trained based on a large number of training samples, and the trained first text model may output commodity supplier association information for the input text information to be processed.
[0100] In some optional implementations, a large number of training samples may be collected in advance, each of which may include a sample of attribute information of a commodity supplier and carry a sample label of a commodity supply information processing score corresponding to the sample of attribute information of the commodity supplier. The initial model is trained using a large number of training samples, that is, by inputting a large number of training samples into the chat generative pre-trained conversion model, the chat generative pre-trained conversion model learns the text of these training samples for semantic analysis to obtain the corresponding commodity supply information processing score prediction label. In the process of the chat generative pre-trained conversion model learning these training samples, the hyperparameters of the initialization model (the parameters include the learning rate, the batch size, and the number of training rounds) may be fine-tuned so that the commodity supply information processing score prediction label obtained by the model based on the text sample is as consistent as possible with the commodity supply information processing score sample label. After the training is completed, the first text model is obtained by the chat generative pre-trained conversion model.
[0101] Through the above steps 101 to 104, the attribute information of the corresponding commodity supplier can be automatically obtained based on the obtained customer source communication information, and the recommendation score of the commodity supplier can be automatically calculated based on the attribute information of the commodity supplier. Therefore, the technical solution disclosed in the present invention can automatically obtain the attribute information of the commodity supplier and obtain the recommendation score of the commodity supplier based on the customer source communication information, realize the automation and intelligence of commodity supplier sourcing, and improve the efficiency and accuracy of commodity supplier sourcing.
[0102] Figure 2 The flowchart is another embodiment of the commodity supply information processing method disclosed in the present invention. Figure 2 Taking the example of making recommendations based on the recommendation scores of the commodity suppliers, the method includes steps 201 to 203. Each step is described below.
[0103] In step 201, at least one commodity supplier is classified according to the category of the commodity supplier to obtain at least one commodity supplier list.
[0104] The category of the goods supplied by the commodity supplier may indicate the category of the goods supplied by the commodity supplier, for example, the category of the goods supplied by the commodity supplier may be household goods, building materials, tiles, etc. The category of the goods supplied by the commodity supplier may be obtained according to the company profile, business scope, etc. in the attribute information of the commodity supplier. Some commodity suppliers with the same category of goods supplied by the commodity supplier may be recorded in each commodity supplier list.
[0105] In step 202, the commodity suppliers in each commodity supplier list are sorted according to the recommendation score.
[0106] In order to better recommend product suppliers to users, product suppliers can be sorted from high to low according to the recommendation score, which helps customers to give priority to product suppliers with high recommendation scores and improve the recommendation effect.
[0107] In step 203, the sorted lists of commodity suppliers are pushed to matching business parties respectively.
[0108] The business parties may be associated business systems, for example, business system 1 that specializes in providing home hard decoration services, and business system 2 that specializes in providing soft decoration services.
[0109] In some optional implementations, after sorting the commodity suppliers in each commodity supplier list, the corresponding commodity supplier list can be pushed to the corresponding business party according to the category of the commodity suppliers in each commodity supplier list, such as recommending the tile commodity supplier list to the business system 1 that specializes in providing home hard decoration services, and recommending the home commodity supplier list to the business system 2 that specializes in providing home soft decoration services.
[0110] In some optional implementations, before pushing the commodity supplier list to the matching business party, the commodity suppliers in the commodity supplier list may also be filtered according to the recommendation score of each commodity supplier. For example, commodity suppliers with a recommendation score lower than a set threshold are filtered out, and only commodity suppliers with a recommendation score not lower than the set threshold are retained in the commodity supplier list.
[0111] Through the above steps 201 to 203, by classifying and sorting the commodity suppliers according to the categories of the commodity suppliers, and pushing the sorted commodity supplier lists to the matching business parties respectively, accurate recommendations can be achieved, thereby improving the efficiency and accuracy of the commodity supplier sourcing operations of each business party.
[0112] Figure 3The flowchart is another embodiment of the commodity supply information processing method disclosed in the present invention. Figure 3 Taking how to obtain a recommendation score as an example for exemplary description, step 104 includes steps 141 - 142. Each step is described below.
[0113] In step 141, a first text model is used to determine a single score corresponding to each attribute information in the attribute information of at least one commodity supplier.
[0114] Among them, the single score refers to the score corresponding to each attribute information. For example, for the registered capital attribute, the score can be given according to the size of the registered capital. The larger the registered capital, the higher the score. For the establishment time attribute, the score can be given according to the early or late establishment time of the enterprise. The earlier the establishment time, the higher the score. For the number of employees in the enterprise, the score can be given according to the size of the enterprise. The more people, the higher the score.
[0115] In some optional implementations, the corresponding score can be determined according to the specific attribute values of each attribute information of the commodity supplier. For example, the score weight range of registered capital is 0 to 10 points, with a maximum of 10 points. The registered capital is more than 100 million. Assuming that the registered capital of the company is 10 million RMB, the registered capital score is: 10*(1000 / 10000)=1 point. The score weight range of establishment time is 0 to 10 points, with a maximum of 10 points. The establishment time is more than 20 years. Assuming that the company was established for 6 years, min(10,(6 / 20)*10)≈min(10,0.3*10)≈min(10,3)≈3 points.
[0116] In step 142, based on the individual scores corresponding to the respective attribute information of the at least one commodity supplier, a recommendation score of the at least one commodity supplier is determined.
[0117] In some optional implementations, the individual scores corresponding to the attribute information of the product supplier may be directly summed up to obtain the corresponding recommendation score.
[0118] After obtaining the attribute information of the commodity supplier through the above steps 141 to 142, the technical solution disclosed in the present invention can automatically calculate the recommendation score of each commodity supplier. Since the recommendation score of the commodity supplier is obtained by comprehensive calculation based on the attribute information of the commodity supplier, it has high accuracy and is conducive to improving the effect of commodity supply information processing.
[0119] Exemplary Devices
[0120] Figure 4 FIG. 1 is a schematic diagram of a structure of an embodiment of a commodity supply information processing device disclosed in the present invention. Figure 4 As shown, including:
[0121] The first parsing module 41 is used to perform multimedia parsing processing on at least one group of customer communication information to obtain text information to be processed corresponding to at least one group of customer communication information;
[0122] The second parsing module 42 is used to perform semantic parsing on each text information to be processed to obtain the associated information of at least one commodity supplier;
[0123] A first acquisition module 43, configured to acquire attribute information of at least one commodity supplier based on association information of at least one commodity supplier;
[0124] The generating module 44 is used to input the attribute information of at least one commodity supplier into the pre-trained first text model, and output the recommendation score of at least one commodity supplier through the first text model.
[0125] Figure 5 A schematic diagram of the structure of another embodiment of the commodity supply information processing device disclosed in the present invention. Figure 5 As shown, in Figure 4 Based on the illustrated embodiment, in some embodiments of the present disclosure, the device further includes:
[0126] A classification module 45, configured to classify at least one commodity supplier according to the category of the commodity supplier to obtain at least one commodity supplier list;
[0127] A sorting module 46, used to sort the commodity suppliers in each commodity supplier list according to the recommendation score;
[0128] The push module 47 is used to push the sorted commodity supplier lists to the matching business parties respectively.
[0129] In some embodiments of the present disclosure, the second parsing module 42 is specifically configured to generate associated information of at least one commodity supplier based on each piece of text information to be processed, using a pre-trained first text model.
[0130] In some embodiments of the present disclosure, the first acquisition module 43 is specifically configured to acquire attribute information of at least one commodity supplier from a network server by using a web crawler algorithm based on association information of at least one commodity supplier.
[0131] In some embodiments of the present disclosure, the first parsing module 41 includes:
[0132] The audio analysis submodule 411 is used for performing voice enhancement processing on the audio information in response to at least one group of customer communication information being audio information, and recognizing text in the audio information after voice enhancement processing by a voice recognition algorithm to obtain text information to be processed corresponding to at least one group of customer communication information;
[0133] The text parsing submodule 412 is used for filtering the text information in response to at least one group of customer communication information being text information, and obtaining the to-be-processed text information corresponding to the at least one group of customer communication information;
[0134] The image analysis submodule 413 is used to perform noise reduction preprocessing on the image in response to at least one group of customer communication information being image information, and recognize text in the image information after noise reduction preprocessing through a text recognition algorithm to obtain the to-be-processed text information corresponding to at least one group of customer communication information.
[0135] In some embodiments of the present disclosure, the generation module 44 includes:
[0136] A first determination submodule 441 is used to determine, by using a first text model, a single score corresponding to each attribute information in the attribute information of at least one commodity supplier;
[0137] The second determination submodule 442 is configured to determine a recommendation score of at least one commodity supplier based on the individual scores corresponding to each attribute information of the at least one commodity supplier.
[0138] In some embodiments of the present disclosure, the device further comprises:
[0139] The customer source information acquisition module 48 is used to acquire customer source communication information from the customer source information database of each business party according to a set period; or, receive customer source communication information uploaded by the user through the client.
[0140] The device of the embodiment of the present disclosure can be used to implement the methods of the above-mentioned embodiments of the present disclosure. The two correspond to each other in specific implementation, and the specific implementations of related parts are referenced to each other, which will not be repeated here.
[0141] Exemplary electronic devices, computer program products, computer-readable storage media, and systems
[0142] An embodiment of the present disclosure further provides an electronic device, comprising: a memory for storing a computer program; a processor for executing the computer program stored in the memory, and when the computer program is executed, the commodity supply information processing method of any of the above embodiments of the present disclosure is implemented.
[0143] Below, reference Figure 6 An electronic device according to an embodiment of the present disclosure is described, in which a device for implementing the method according to an embodiment of the present disclosure may be integrated. Figure 6 A structural diagram of an electronic device provided in an exemplary embodiment of the present disclosure, such as Figure 6As shown, the electronic device includes one or more processors 61, one or more computer-readable storage media memory 62, and a computer program stored in the memory and executable on the processor. When executing the program in the memory 62, the above-mentioned commodity supply information processing method can be implemented.
[0144] Specifically, in practical applications, the electronic device may further include components such as an input device 63 and an output device 64, and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown). Those skilled in the art will appreciate that Figure 6 The structure of the electronic device shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or certain components, or different component arrangements.
[0145] The processor 61 can be a central processing unit (CPU) or other forms of processing units with commodity supply information processing capabilities and / or instruction execution capabilities. It performs various functions and processes data by running or executing software programs and / or modules stored in the memory 62, and calling data stored in the memory 62, thereby monitoring the electronic device as a whole.
[0146] The memory 62 may store one or more computer program products, and the memory may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The above-mentioned volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The above-mentioned non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program products may be stored on the computer-readable storage medium, and the processor 61 may run the computer program products to implement the commodity supply information processing method of each embodiment of the present disclosure and / or other desired functions.
[0147] The input device 63 can be used to receive input digital or character information. The input device 63 can include a keyboard, a mouse, a joystick, etc. related to user settings and function control.
[0148] The output device 64 can output various information to the outside, including the determined distance information, direction information, etc. The output device 64 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.
[0149] The electronic device may also include a power supply for supplying power to various components, which may be logically connected to the processor 61 through a power management system, so as to manage charging, discharging, power consumption and other functions through the power management system. The power supply may also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators and other arbitrary components.
[0150] Of course, to simplify, Figure 6 Only some of the components related to the present disclosure in the electronic device are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device may further include any other appropriate components.
[0151] In addition to the above-mentioned methods and devices, an embodiment of the present disclosure may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the commodity supply information processing method according to various embodiments of the present disclosure described in the above-mentioned "Exemplary Method" section of this specification.
[0152] The computer program product may be written in any combination of one or more programming languages to write program code for performing the operations of the disclosed embodiments, including object-oriented programming languages such as Java, C++, etc., and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.
[0153] In addition, an embodiment of the present disclosure may also be a computer-readable storage medium having computer program instructions stored thereon. When the computer program instructions are executed by a processor, the processor executes the steps of the commodity supply information processing method according to various embodiments of the present disclosure described in the above “Exemplary Method” section of this specification.
[0154] Computer readable storage media can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable 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 above.
[0155] The basic principles of the present disclosure are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present disclosure. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, and are not limitations. The above details do not limit the present disclosure to the necessity of adopting the above specific details to be implemented.
[0156] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0157] A person of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk, etc., various media that can store program codes.
[0158] The method and apparatus of the present disclosure may be implemented in many ways. For example, the method and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above, unless otherwise specifically stated. In addition, in some embodiments, the present disclosure may also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present disclosure. Therefore, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.
[0159] The description of the present disclosure is given for the purpose of illustration and description, and is not intended to be exhaustive or to limit the present disclosure to the disclosed form. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present disclosure, and to enable those of ordinary skill in the art to understand the present disclosure and thereby design various embodiments with various modifications suitable for specific uses.
Claims
1. A commodity supply information processing method, characterized in that: include: Performing multimedia analysis on at least one set of customer communication information to obtain text information to be processed corresponding to the at least one set of customer communication information; Perform semantic analysis on each text information to be processed to obtain related information of at least one commodity supplier; Based on the association information of the at least one commodity supplier, acquiring attribute information of the at least one commodity supplier; The attribute information of the at least one commodity supplier is input into a pre-trained first text model, and the recommendation score of the at least one commodity supplier is output through the first text model.
2. The method according to claim 1, characterized in that After generating the recommendation score of the at least one commodity supplier, the method further includes: Classify the at least one commodity supplier according to the category of the commodity supplier to obtain at least one commodity supplier list; Sort the commodity suppliers in each commodity supplier list according to the recommendation score; The sorted list of suppliers of each product is pushed to the matching business parties respectively.
3. The method according to any one of claims 1-2, characterized in that: The semantic analysis of each text information to be processed to obtain the associated information of at least one commodity supplier includes: The pre-trained first text model is used to generate the associated information of the at least one commodity supplier based on each piece of text information to be processed.
4. The method according to any one of claims 1 to 3, characterized in that: The acquiring, based on the association information of the at least one commodity supplier, the attribute information of the at least one commodity supplier comprises: Based on the association information of the at least one commodity supplier, the attribute information of the at least one commodity supplier is acquired from a network server using a web crawler algorithm.
5. The method according to any one of claims 1 to 4, characterized in that: The performing multimedia analysis processing on at least one group of customer source communication information to obtain the to-be-processed text information corresponding to the at least one group of customer source communication information includes: In response to at least one group of customer communication information being audio information, performing voice enhancement processing on the audio information, and recognizing text in the audio information after voice enhancement processing by a voice recognition algorithm, to obtain text information to be processed corresponding to at least one group of customer communication information; In response to at least one group of customer source communication information being text information, filtering the text information to obtain to-be-processed text information corresponding to at least one group of customer source communication information; In response to at least one group of customer communication information being image information, the image is subjected to noise reduction preprocessing, and text in the image information after noise reduction preprocessing is recognized by a text recognition algorithm to obtain text information to be processed corresponding to at least one group of customer communication information.
6. The method according to any one of claims 1 to 5, characterized in that: The step of inputting the attribute information of the at least one commodity supplier into a pre-trained first text model, and outputting a recommendation score of the at least one commodity supplier through the first text model, comprises: Determine, by using the first text model, a single score corresponding to each attribute information in the attribute information of the at least one commodity supplier; Based on the individual scores corresponding to the attribute information of the at least one commodity supplier, a recommendation score of the at least one commodity supplier is determined.
7. The method according to any one of claims 1 to 6, characterized in that: Before performing multimedia analysis on at least one set of customer communication information, the method further includes: Acquire the customer source communication information from the customer source information database of each business party according to a set period; or, Receive customer communication information uploaded by users through the client.
8. A computer-readable storage medium, wherein the storage medium stores computer program instructions, and when the computer program instructions are executed, the method according to any one of claims 1 to 7 is implemented.
9. An electronic device, comprising: a memory for storing a computer program product; A processor is used to execute the computer program product stored in the memory, and when the computer program product is executed, it implements the method described in any one of claims 1 to 7.
10. A computer program product comprising computer program instructions, characterized in that When the computer program instructions are executed by a processor, the method described in any one of claims 1 to 7 is implemented.
