Diet recording system, method, device and equipment based on chat simulation group

Abstract

The invention relates to the technical field of computers, and discloses a diet recording system, method, device and equipment based on a chat simulation group, the system comprises a textbox, an input area, a chat content area and a dialogue area: the textbox is used for obtaining text input content of a user; determining food information corresponding to the character input content based on the character input content; the input area is used for acquiring a to-be-recognized food image, a to-be-recognized voice and food search content of a user; food information corresponding to the to-be-recognized food image, the to-be-recognized voice and the food search content is determined; the chat content area is used for generating chat content replies corresponding to the food information based on the food information by using different virtual characters; and the dialogue area is used for displaying food information and chat content. According to the invention, a user can rapidly and conveniently use various modes in a mixed manner to record own food; and a virtual clock-in group is constructed as an accompanying and supervision for the user in the fat-reducing and weight-reducing process, so that the stickiness and retention of the user are improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a diet record system, method, device and equipment based on a chat simulation group. Background Art

[0002] In the related art, conventional diet record tool apps currently have more and more recording methods, including photo, voice, text, search, etc., which are not user-friendly for first-time users. Moreover, different foods have different most suitable recording methods. For example, simple foods such as bread and milk are suitable for searching, while complex dishes are suitable for photo recording, etc. Users cannot quickly and conveniently mix and use various methods to record their food.

[0003] At the same time, most users of existing conventional diet recording tool apps are for fat loss and weight loss. This process itself is painful and difficult to stick to. A check-in group of friends and nutritionists who can accompany and supervise can effectively help users stick to it. However, existing conventional diet recording tool apps lack the corresponding companionship function and have a poor user experience. Summary of the invention

[0004] In view of this, the present invention provides a diet record system, method, device and equipment based on a chat simulation group to solve the problem of poor user experience of existing diet record tool apps.

[0005] In a first aspect, the present invention provides a diet record system based on a chat simulation group, the system comprising a text box, an input area, a chat content area and a dialogue area:

[0006] The text box is used to obtain the text input content of the user; based on the text input content, determine the food information corresponding to the text input content;

[0007] The input area includes at least one of a photo input area, a voice input area, and a food search area. The photo input area is used to obtain a user's food image to be identified; based on the food image to be identified, determine the food information corresponding to the food image to be identified; the voice input area is used to obtain a user's voice to be identified; based on the voice to be identified, determine the food information corresponding to the voice to be identified; the food search area is used to obtain a user's food search content; based on the food search content, determine the food information corresponding to the food search content;

[0008] A chat content area, used to generate chat content replies corresponding to the food information based on the food information using different virtual characters, wherein the chat content replies include food analysis information corresponding to the food information and / or small talk information corresponding to the text input content;

[0009] Conversation area, used to display food information and chat content.

[0010] In the present invention, a diet record system based on a chat simulation group including a text box, an input area, a chat content area and a dialogue area is constructed. Through the text box and the input area, users can have multiple input methods such as text, photo, voice and search in a form similar to a chat window, which is convenient for users to quickly and conveniently mix various methods to record their own food, thereby improving the food record rate of the diet record tool app; by mixing multiple recording methods for diet recording, since all mobile phone users are very familiar with the operation of the chat group, the button styles and positions of text input, voice, picture transmission and photo taking are very uniform, so in the style of the chat window, users can record their diet in various ways without a teacher, thereby reducing their learning cost of using a new app and improving the efficiency of diet recording. By using different virtual characters to generate chat content corresponding to the recorded food in the chat content area, the professionalism and accuracy of the dialogue characters in diet-related issues are significantly improved, and a virtual punch-in group is constructed for users as companionship and supervision during the process of fat and weight loss, thereby improving the stickiness and retention of users.

[0011] In an optional embodiment, the chat content area is used to generate food cards corresponding to the text input content, food images to be recognized, voices to be recognized, and food search contents based on the text input content, food images to be recognized, voices to be recognized, and food search contents, wherein the food cards are used to represent the detailed information of the food corresponding to the text input content, food images to be recognized, voices to be recognized, and food search contents.

[0012] In this way, a food card corresponding to the user input content is generated, and the detailed information of the food can be further viewed on the food card. The food card ensures the accuracy of the food data and the richness of the data dimension by strictly corresponding to the food items in the food library; by displaying key information directly on the food card and allowing users to click on the card to view other information for further viewing, it helps users filter key information when they do not need to view details, keeping the user interaction simple.

[0013] In an optional implementation, the chat content area is further used to: determine whether the text input content contains valid food information based on the text input content;

[0014] When the text input content contains valid food information, the pre-trained model is used to simulate different virtual characters to generate food review information and food prompt information corresponding to the text input content;

[0015] When the text input content does not contain valid food information, the text input content is determined to be a chat task, and a pre-trained model is used to simulate different virtual characters to generate chat information corresponding to the text input content.

[0016] In this method, by identifying whether the input content contains valid food information in the chat content area, when the input content contains valid food information, a pre-trained large model is used to simulate different virtual characters to generate food review information and food prompt information corresponding to the input content; when the input content does not contain valid food information, it is confirmed that the current input content is small talk, and a pre-trained large model is used to simulate different virtual characters to generate small talk chat content corresponding to the input content, thereby realizing the simulation of a virtual check-in group for companionship and supervision, further improving the user experience.

[0017] In a second aspect, the present invention provides a method for recording a diet based on a chat simulation group, which is applied to the method for recording a diet based on a chat simulation group as described in any one of the first aspects, wherein the system includes a text box, an input area, a chat content area, and a dialogue area, and the method includes:

[0018] Using the text box and input area, obtain the user's text input content, food images to be recognized, voice to be recognized, and food search content;

[0019] Based on the text input content, the food image to be recognized, the voice to be recognized and the food search content, determine the food information corresponding to the text input content, the food image to be recognized, the voice to be recognized and the food search content;

[0020] Using different virtual characters, based on the food information, generating chat content replies corresponding to the food information, wherein the chat content replies include food analysis information corresponding to the food information, and / or chat information corresponding to the text input content;

[0021] Use the conversation area to display food information and chat content.

[0022] In the present invention, the information inputted by the text box and the input area is used for natural language text input and search at the same time. The user can have more diverse input methods in a chat window-like form, which is convenient for the user to mix and match multiple recording methods for diet records. Different virtual characters are used. While using the large model dialogue capability, the built-in food database of the app is also used, and professional nutrition expertise is used to construct prompt words. The professionalism and accuracy of diet-related issues are significantly improved, and the user has a virtual check-in group to accompany and supervise during the fat and weight loss process, thereby improving the food recording rate of the diet record tool app and improving user stickiness and retention.

[0023] In an optional implementation, based on the food information, generating a chat content reply corresponding to the food information includes:

[0024] Based on the text input content, food images to be recognized, voices to be recognized and food search content, food cards corresponding to the text input content, food images to be recognized, voices to be recognized and food search content are generated, wherein the food cards are used to represent the detailed food information corresponding to the text input content, food images to be recognized, voices to be recognized and food search content.

[0025] In this way, by generating food cards corresponding to the user input content, users can use the food cards to further view detailed information about the food. Not only is the accuracy of the food data guaranteed, but the dimensions of the data, including the corresponding calories, carbohydrate / fat / protein ratio, vitamin and trace element content of the food, are also richer.

[0026] In an optional implementation, using different virtual characters to generate chat content replies corresponding to the food information based on the food information also includes:

[0027] Based on the text input content, determining whether the text input content contains valid food information;

[0028] When the text input content contains valid food information, the pre-trained model is used to simulate different virtual characters to generate food review information and food prompt information corresponding to the text input content;

[0029] When the text input content does not contain valid food information, the text input content is determined to be a chat task, and a pre-trained model is used to simulate different virtual characters to generate chat information corresponding to the text input content.

[0030] In this method, the virtual characters used for conversation not only use the large model conversation capabilities, but also use the app's built-in food database and professional nutrition expertise to construct prompt words, achieving a significant improvement in professionalism and accuracy when answering diet-related questions; at the same time, users are provided with a virtual check-in group to accompany and supervise them during the fat and weight loss process, further improving the user experience and increasing user stickiness and retention.

[0031] In a third aspect, the present invention provides a diet recording device based on a chat simulation group, the device comprising:

[0032] An input acquisition module is used to obtain the user's text input content, food images to be recognized, voice to be recognized, and food search content using the text box and input area;

[0033] A food recognition module, used to determine food information corresponding to the text input content, the food image to be recognized, the voice to be recognized and the food search content based on the text input content, the food image to be recognized, the voice to be recognized and the food search content;

[0034] A chat reply module, used to generate chat content replies corresponding to the food information by using different virtual characters based on the food information, wherein the chat content replies include a welcome message, food analysis information corresponding to the food information, and small talk information corresponding to the text input content;

[0035] The content display module is used to display food information and chat content in the conversation area.

[0036] In a fourth aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to execute the diet recording method based on a chat simulation group according to the above-mentioned second aspect or any corresponding embodiment thereof.

[0037] In a fifth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the diet recording method based on a chat simulation group according to the second aspect or any corresponding embodiment thereof.

[0038] In a sixth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the diet recording method based on a chat simulation group according to the second aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 Schematic diagram of the architecture of a diet record system based on a chat simulation group according to an embodiment of the present invention.

[0041] Figure 2 It is a schematic diagram of the interactive process of recording diet in a simulated chat group format according to an embodiment of the present invention.

[0042] Figure 3 It is a flowchart of a diet recording method based on a chat simulation group according to an embodiment of the present invention.

[0043] Figure 4 It is a schematic diagram of the architecture of recording diet by simulating a chat group according to an embodiment of the present invention.

[0044] Figure 54 is a flow chart of another diet recording method based on a chat simulation group according to an embodiment of the present invention.

[0045] Figure 6 4 is a structural block diagram of a diet recording device based on a chat simulation group according to an embodiment of the present invention.

[0046] Figure 7 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0048] In the related art, the current conventional diet recording tool apps have more and more recording methods, including taking photos, voice, text, search, etc., which are not friendly to first-time users. Moreover, different foods have different most suitable recording methods. For example, simple foods such as bread and milk are suitable for searching, and complex dishes are suitable for taking photos and recording. Users cannot quickly and conveniently mix various methods to record their food. At the same time, most users of existing conventional diet recording tool apps are for fat loss and weight loss. This process itself is painful and difficult to stick to. A check-in group of friends and nutritionists who play a role of companionship and supervision can effectively help users to stick to it. However, existing conventional diet recording tool apps lack corresponding companionship functions and have a poor user experience.

[0049] To solve the above problems, a diet recording system based on a chat simulation group is provided in an embodiment of the present invention. The diet recording system based on a chat simulation group in this embodiment is suitable for the use scenario where a user uses a diet recording tool app to record food. The diet recording system based on a chat simulation group is provided by the present invention, and a diet recording system based on a chat simulation group including a text box, an input area, a chat content area and a dialogue area is constructed. Through the text box and the input area, the user can have multiple input methods such as text, photo, voice and search in a form similar to a chat window, which is convenient for users to quickly and conveniently mix various methods to record their own food, thereby improving the food recording rate of the diet recording tool app; by mixing multiple recording methods for diet recording, since all mobile phone users are very familiar with the operation of the chat group, the button styles and positions of text input, voice, picture transmission and photo taking are very uniform, so in the style of the chat window, the user can record diet in various ways without a teacher, thereby reducing his learning cost of using a new app and improving the efficiency of diet recording. By using different virtual characters to generate chat content corresponding to the recorded food in the chat content area, the professionalism and accuracy of the dialogue characters when answering diet-related questions are significantly improved. A virtual check-in group is built for users to accompany and supervise them during the process of fat and weight loss, which improves user stickiness and retention.

[0050] According to an embodiment of the present invention, an embodiment of a diet record system based on a chat simulation group is provided. Figure 1 is a schematic diagram of the architecture of a diet record system based on a chat simulation group according to an embodiment of the present invention. Figure 1 As shown, the diet record system based on the chat simulation group includes: a text box 1, an input area 2, a chat content area 3 and a dialogue area 4: the text box 1 is used to obtain the user's text input content; based on the text input content, determine the food information corresponding to the text input content; the input area 2 includes at least one of a photo input area 21, a voice input area 22 and a food search area 23, the photo input area 21 is used to obtain the user's food image to be identified; based on the food image to be identified, determine the food information corresponding to the food image to be identified; the voice input area 22 is used to obtain the user's voice to be identified; based on the voice to be identified, determine the food information corresponding to the voice to be identified; the food search area 23 is used to obtain the user's food search content; based on the food search content, determine the food information corresponding to the food search content; the chat content area 3 is used to generate a chat content reply corresponding to the food information based on the food information using different virtual characters, wherein the chat content reply includes food analysis information corresponding to the food information, and / or, chat information corresponding to the text input content; the dialogue area 4 is used to display food information and chat content.

[0051] In an optional embodiment, the chat content area 3 is used to generate food cards corresponding to the text input content, the food image to be recognized, the voice to be recognized and the food search content based on the text input content, the food image to be recognized, the voice to be recognized and the food search content, wherein the food cards are used to represent the food detailed information corresponding to the text input content, the food image to be recognized, the voice to be recognized and the food search content.

[0052] In this way, a food card corresponding to the user input content is generated, and the detailed information of the food can be further viewed on the food card. The food card ensures the accuracy of the food data and the richness of the data dimension by strictly corresponding to the food items in the food library; by displaying key information directly on the food card and allowing users to click on the card to view other information for further viewing, it helps users filter key information when they do not need to view details, keeping the user interaction simple.

[0053] In an optional embodiment, the chat content area 3 is also used to: determine whether the text input content contains valid food information based on the text input content; when the text input content contains valid food information, use a pre-trained model to simulate different virtual characters to generate food review information and food prompt information corresponding to the text input content; when the text input content does not contain valid food information, determine that the text input content is a chat task, use a pre-trained model to simulate different virtual characters, and generate chat information corresponding to the text input content.

[0054] In this method, by identifying whether the input content contains valid food information in the chat content area, when the input content contains valid food information, a pre-trained large model is used to simulate different virtual characters to generate food review information and food prompt information corresponding to the input content; when the input content does not contain valid food information, it is confirmed that the current input content is small talk, and a pre-trained large model is used to simulate different virtual characters to generate small talk chat content corresponding to the input content, thereby realizing the simulation of a virtual check-in group for companionship and supervision, further improving the user experience.

[0055] In one implementation scenario, Figure 2 FIG. 1 is a schematic diagram of an interactive process of recording a diet by simulating a chat group according to an embodiment of the present invention. Figure 2 As shown, recording diet by simulating the chat group can include: first constructing a page shaped like a chat window, which is generated by Html technology and displayed on a mobile phone, and sequentially generating the upper and lower parts, the upper part generated first is the chat area, and then the lower part generated is the input area. The upper part is the conversation area, the left avatar is other people, and the right is yourself. The lower part is the input area, which has three input methods: text input, voice, and photo.

[0056] The functions of each part are as follows: 1. Text box 1: After clicking on text box 1, the input panel of the diet record system based on the chat simulation group is pulled up. After the user enters text, the search list is displayed on the top. Clicking on a food in the search list can record the food on the list. After recording, the dialogue area 4 displays: the text bubble (the content is the food name) on the right, the food card (1 card) and the subsequent text (multiple cards) on the left in sequence; click "OK" on the system input panel to enter the text input.

[0057] After recording, the dialogue area 4 displays: a text bubble (the content is the complete text entered) on the right, and food cards (multiple cards) and subsequent text (multiple items) are displayed in sequence on the left.

[0058] 2. Input area 2: Photo input area 21 button: Click to jump to the original photo record page and take photos to record food. After recording, the dialogue area displays: the right side displays the photo, the left side displays the food cards (multiple cards), and the subsequent text (multiple items).

[0059] Voice input area 22 button: Click to pull up the voice input page, and press the voice input area 22 button to record food. After recording, the dialogue area 4 displays: the text content (the content is the complete text) is displayed on the right, and the food cards (multiple cards) and subsequent texts (multiple items) are displayed in sequence on the left.

[0060] 3. Dialogue Area 4: The dialogue area 4 style includes the following parts:

[0061] 1) Avatar + name: can be set freely.

[0062] 2) Text bubble: The height and width need to adapt to the text length.

[0063] 3) Food Card: Food cards are generated by code in the page of chat content area 3 and displayed in the chat software in the sharing card style. The first line has the food name in large font, and the second line has the unit and calories in small font. Moreover, this food card can be clicked. Clicking on it, you can enter the specific food entry in the food library and further view the detailed information of the food. All food information in the food library is manually pre-produced and imported into the system. Not only is the accuracy of the data guaranteed, but the data dimensions (calorie, carbohydrate / fat / protein ratio, vitamin and trace element content, etc.) are richer. Therefore, displaying the input food information in the form of clickable food cards has two advantages compared to directly giving non-clickable food names in text format: (1) It ensures the accuracy of the data and the richness of the data dimensions by strictly corresponding to the food entries in the food library; (2) It helps users filter key information when they do not need to view details by displaying some key information directly on the food card and other information can be clicked into the card for further viewing, thus keeping the user interaction simple.

[0064] 4) Pictures and emoticon packs: picture styles in chat software.

[0065] 4. Chat content area 3: The chat content area only provides examples and can be expanded and modified arbitrarily based on the capabilities of the big model. The following steps can be implemented directly using the pre-trained version of the big model, or further fine-tuned using chat text or dietary content: If the user has not recorded food, in the prompt word generation phase, the text is directly added with basic information such as the user's age and weight, and then forwarded to the big model for processing. Since the intention at this time is recognized as a chat task, the big model will reply with chat-oriented, unstructured text.

[0066] If there is recorded food in the current dialog box, in addition to adding the user's basic information, the prompt word generation stage will also add "I have eaten a certain weight of a certain food." This information will then be transmitted to the big model. The big model will also reply with chatty, unstructured text, but will answer in combination with the previously recorded food.

[0067] Exemplarily, two roles are illustrated in this example, one of which is a nutritionist, who is set to provide professional dietary guidance. The second is a friend, who is set to provide a joking conversation between friends. Among them, the large model used is not limited in the present invention. All mainstream large models include Wenxin Yiyan, Tongyi Qianwen, GPT, etc. There is no strict limit on the model size, which is generally 7B or 14B. The type and size of the model will slightly affect the specific output content, but will not affect the logic, nor will it make a significant difference in the effect. When using large models, you can directly use the original pre-trained models and official interfaces of these large models, or you can use chat text and diet content for further fine-tuning.

[0068] The virtual character outputs the following three types of text: (1) Welcome text, which is triggered when entering the page and is pre-configured by the system.

[0069] (2) Analysis task: The analysis task is triggered after the user records the food.

[0070] Specifically, the nutritionist role can output comments on the food just recorded and give suggestions on what the user should eat for the rest of the day. In the prompt words given to the large model, in addition to the food just recorded, all the food recorded today and the total daily intake target set by the user need to be referred to.

[0071] The friend character can output some humorous daily conversations, which are directly related to the food just recorded, and refer to all the food recorded during the day, as well as the total daily intake goal set by the user.

[0072] (3) Chat task: The chat task is triggered when the user inputs text and no food is recognized. Food is recognized in four cases, and no food is recognized in other cases, including: the user inputs text in the text box and selects a specific food in the search list; the user inputs text in the text box and a valid food is recognized in the subsequent text input; the user takes a photo and recognizes a valid food; the user speaks and recognizes a valid food in the voice record.

[0073] The diet record system based on chat simulation group provided in this embodiment is constructed to include a text box, an input area, a chat content area and a dialogue area. Through the text box and the input area, users can have multiple input methods such as text, photo, voice and search in a form similar to a chat window, which is convenient for users to quickly and conveniently mix various methods to record their food, thereby improving the food record rate of the diet record tool app; by mixing multiple recording methods for diet recording, since all mobile phone users are very familiar with the operation of the chat group, the button styles and positions of text input, voice, picture transmission and photo taking are very uniform, so in the style of the chat window, users can record their diet in various ways without a teacher, thereby reducing their learning cost of using a new app and improving the efficiency of diet recording. By using different virtual characters to generate chat content corresponding to the recorded food in the chat content area, the professionalism and accuracy of the dialogue characters in diet-related issues are significantly improved, and a virtual punch-in group is constructed for users as a companion and urge in the process of fat and weight loss, thereby improving the stickiness and retention of users.

[0074] According to an embodiment of the present invention, an embodiment of a diet record method based on a chat simulation group is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0075] In this embodiment, a method for recording diet based on a chat simulation group is provided, which can be used for the diet recording based on the chat simulation group mentioned above. The system includes a text box, an input area, a chat content area and a dialogue area. Figure 3 is a flow chart of a method for recording diet based on a chat simulation group according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0076] Step S301, using the text box and input area, obtain the user's text input content, food images to be recognized, voice to be recognized and food search content.

[0077] Step S302, based on the text input content, the food image to be recognized, the voice to be recognized and the food search content, determine the food information corresponding to the text input content, the food image to be recognized, the voice to be recognized and the food search content.

[0078] Step S303, using different virtual characters to generate chat content replies corresponding to the food information based on the food information.

[0079] In an embodiment of the present invention, the chat content reply includes a welcome message, food analysis information corresponding to the food information, and chat information corresponding to the text input content.

[0080] Step S304, using the conversation area to display food information and chat content.

[0081] In one implementation scenario, Figure 4 is a schematic diagram of an architecture for recording diet by simulating a chat group according to an embodiment of the present invention. Figure 4 As shown, the overall process of diet recording by simulating a chat group is divided into three parts.

[0082] The first part is user input, and the user will first use various methods to input.

[0083] The second part is to confirm the intention and display it. Among the four user input methods, taking photos, voice, and searching are all necessary to record food and display food cards. Finally, the characters in the group enter the food analysis task. The detailed process is shown in the figure. However, text input may be recording food or other content such as chatting, so the text input must first enter the intention recognition module. When the intention is judged to be food recording, the keyword extraction, matching food library, and displaying food cards are executed, and the characters in the group enter the food analysis task; when the intention is judged to be other, the characters in the group enter the chatting task.

[0084] The third part is the role reply in the group, indicating Figure 4 In the example, there are two roles A and B in the group, which can be expanded arbitrarily, and all role replies are executed in parallel. The module order of each role's reply process is the same, including user information acquisition (this time's recorded food, today's recorded food, today's expected total calories and expected proportions of the three major nutrients, user gender, height, weight, age, etc.), prompt word generation, large model reply, text post-processing, and display in the chat group. However, the prompt word generation and text post-processing links in the character analysis and chat tasks are different, and the prompt words and text post-processing links of different roles are also different. For example: In the analysis task, the nutritionist's prompt word requires a reply to the comments on the current recorded food and today's subsequent dietary recommendations. In the chat task, it mainly provides professional suggestions and replies to user questions.

[0085] The dialog flow in the page can continue until the user exits the page.

[0086] The diet recording method based on the chat simulation group provided in this embodiment uses the information input in the text box and the input area for natural language text input and search at the same time. The user can have more diverse input methods in a form similar to a chat window, which is convenient for the user to mix and use multiple recording methods to record diets; different virtual characters are used, while using the large model dialogue capability, the built-in food database of the app is also used, and professional nutrition expertise is used to construct prompt words, which significantly improves the professionalism and accuracy in diet-related issues, and enables users to have a virtual check-in group to accompany and supervise during the process of fat and weight loss, thereby improving the food recording rate of the diet recording tool app and improving user stickiness and retention.

[0087] In this embodiment, a method for recording diet based on a chat simulation group is provided, which can be used for the diet recording based on the chat simulation group mentioned above. The system includes a text box, an input area, a chat content area and a dialogue area. Figure 5 is a flow chart of another diet recording method based on a chat simulation group according to an embodiment of the present invention. Figure 5 As shown, the process includes the following steps:

[0088] Step S501: Use the text box and input area to obtain the user's text input content, food images to be recognized, voice to be recognized, and food search content. Figure 3 Step S301 of the illustrated embodiment will not be described in detail here.

[0089] Step S502: based on the text input content, the food image to be recognized, the voice to be recognized and the food search content, determine the food information corresponding to the text input content, the food image to be recognized, the voice to be recognized and the food search content. Figure 3 Step S302 of the illustrated embodiment will not be described in detail here.

[0090] Step S503, using different virtual characters to generate chat content replies corresponding to the food information based on the food information.

[0091] Specifically, the above step S503 includes:

[0092] Step S5031, based on the text input content, the food image to be recognized, the voice to be recognized and the food search content, generate food cards corresponding to the text input content, the food image to be recognized, the voice to be recognized and the food search content.

[0093] In the embodiment of the present invention, the food card is used to represent the food detailed information corresponding to the text input content, the food image to be recognized, the voice to be recognized, and the food search content.

[0094] In one example, a food card is generated by code in the page of chat content area 3 and displayed in the chat software in the sharing card style, with the food name in large font on the first line and the unit and calories in small font on the second line. Moreover, this food card can be clicked, and by clicking on it, the specific food entry in the food library can be further viewed for detailed information of the food. All food information in the food library is manually pre-produced and imported into the system, which not only guarantees the accuracy of the data, but also enriches the data dimensions (calorie, carbon water / fat / protein ratio, vitamin and trace element content, etc.). Therefore, displaying the input food information in the form of clickable food cards has two advantages compared to directly giving the non-clickable food name in text form: (1) It ensures the accuracy of the data and the richness of the data dimension by strictly corresponding to the food entry in the food library; (2) It helps users filter out key information when they do not need to view details by displaying some key information directly on the food card and other information can be clicked into the card for further viewing, thus keeping the user interaction simple.

[0095] In this way, by generating food cards corresponding to the user input content, users can use the food cards to further view detailed information about the food. Not only is the accuracy of the food data guaranteed, but the dimensions of the data, including the corresponding calories, carbohydrate / fat / protein ratio, vitamin and trace element content of the food, are also richer.

[0096] Step S5032: Based on the text input content, determine whether the text input content contains valid food information.

[0097] Step S5033, when the text input content contains valid food information, a pre-trained model is used to simulate different virtual characters to generate food review information and food prompt information corresponding to the text input content.

[0098] Step S5034, when the text input content does not contain valid food information, the text input content is determined to be a chat task, and a pre-trained model is used to simulate different virtual characters to generate chat information corresponding to the text input content.

[0099] In one example, the chat content area only provides examples, which can be expanded and modified arbitrarily based on the capabilities of the big model. The following steps can be implemented directly using the pre-trained version of the big model, or further fine-tuned using chat text or dietary content: If the user has not recorded food, the text is directly expanded by adding basic information such as the user's age and weight during the prompt word generation phase and then forwarded to the big model for processing. Since the intention at this time is recognized as a chat task, the big model will reply with chat-oriented, unstructured text.

[0100] If there is recorded food in the current dialog box, in addition to adding the user's basic information, the prompt word generation stage will also add "I have eaten a certain weight of a certain food." This information will then be transmitted to the big model. The big model will also reply with chatty, unstructured text, but will answer in combination with the previously recorded food.

[0101] Exemplarily, two roles are illustrated in this example, one of which is a nutritionist, who is set to provide professional dietary guidance. The second is a friend, who is set to provide a joking conversation between friends. Among them, the large model used is not limited in the present invention. All mainstream large models include Wenxin Yiyan, Tongyi Qianwen, GPT, etc. There is no strict limit on the model size, which is generally 7B or 14B. The type and size of the model will slightly affect the specific output content, but will not affect the logic, nor will it make a significant difference in the effect. When using large models, you can directly use the original pre-trained models and official interfaces of these large models, or you can use chat text and diet content for further fine-tuning.

[0102] The virtual character outputs the following three types of text: (1) Welcome text, which is triggered when entering the page and is pre-configured by the system.

[0103] (2) Analysis task: The analysis task is triggered after the user records the food.

[0104] Specifically, the nutritionist role can output comments on the food just recorded and give suggestions on what the user should eat for the rest of the day. In the prompt words given to the large model, in addition to the food just recorded, all the food recorded today and the total daily intake target set by the user need to be referred to.

[0105] The friend character can output some humorous daily conversations, which are directly related to the food just recorded, and refer to all the food recorded during the day, as well as the total daily intake goal set by the user.

[0106] (3) Chat task: The chat task is triggered when the user inputs text and no food is recognized. Food is recognized in four cases, and no food is recognized in other cases, including: the user inputs text in the text box and selects a specific food in the search list; the user inputs text in the text box and a valid food is recognized in the subsequent text input; the user takes a photo and recognizes a valid food; the user speaks and recognizes a valid food in the voice record.

[0107] In this method, the virtual characters used for conversation not only use the large model conversation capabilities, but also use the app's built-in food database and professional nutrition expertise to construct prompt words, achieving a significant improvement in professionalism and accuracy when answering diet-related questions; at the same time, users are provided with a virtual check-in group to accompany and supervise them during the fat and weight loss process, further improving the user experience and increasing user stickiness and retention.

[0108] Step S504: Use the conversation area to display food information and chat content. Figure 3 Step S304 of the illustrated embodiment will not be described in detail here.

[0109] The diet recording method based on the chat simulation group provided in this embodiment generates food cards corresponding to the user input content. The user can use the food cards to further view the detailed information of the food. Not only is the accuracy of the food data guaranteed, but the dimensions of the data, including the corresponding calories, carbon water / fat / protein ratio, vitamin and trace element content of the food, are richer. The virtual character used for dialogue not only uses the large model dialogue capability, but also uses the food database built into the app, and uses professional nutrition expertise to construct prompt words, which significantly improves the professionalism and accuracy of diet-related issues; at the same time, it provides users with a virtual check-in group as a companion and urge in the process of fat and weight loss, further improving the user experience and improving user stickiness and retention.

[0110] In this embodiment, a diet recording device based on a chat simulation group is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware is also possible and conceived.

[0111] This embodiment provides a diet recording device based on a chat simulation group, such as Figure 6 As shown, including:

[0112] The input acquisition module 601 is used to obtain the user's text input content, food images to be recognized, voice to be recognized and food search content using the text box and input area. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0113] The food recognition module 602 is used to determine the food information corresponding to the text input content, the food image to be recognized, the voice to be recognized and the food search content based on the text input content, the food image to be recognized, the voice to be recognized and the food search content. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0114] The chat reply module 603 is used to generate chat content replies corresponding to the food information by using different virtual characters based on the food information, wherein the chat content replies include welcome words, food analysis information corresponding to the food information, and chat information corresponding to the text input content. Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0115] Content display module 604 is used to display food information and chat content in the conversation area. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0116] In some optional implementations, the chat reply module 603 includes:

[0117] A food card generation unit is used to generate food cards corresponding to text input content, food images to be recognized, voices to be recognized and food search content based on text input content, food images to be recognized, voices to be recognized and food search content, wherein the food cards are used to represent detailed food information corresponding to the text input content, food images to be recognized, voices to be recognized and food search content.

[0118] In some optional implementations, the chat reply module 603 includes:

[0119] The valid food identification unit is used to determine whether the text input content contains valid food information based on the text input content.

[0120] The food review generation unit is used to simulate different virtual characters using a pre-trained model to generate food review information and food prompt information corresponding to the text input content when the text input content contains valid food information.

[0121] The chat information generating unit is used to determine that the text input content is a chat task when the text input content does not contain valid food information, and use a pre-trained model to simulate different virtual characters to generate chat information corresponding to the text input content.

[0122] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0123] The diet recording device based on the chat simulation group in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0124] The embodiment of the present invention also provides a computer device having the above Figure 6 The diet record device based on the chat simulation group is shown.

[0125] See also Figure 7 , Figure 7 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 7 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 7 A processor 10 is taken as an example.

[0126] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0127] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0128] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0129] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0130] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 7 The example of connecting through bus is taken in the following.

[0131] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0132] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0133] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0134] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A diet record system based on chat simulation group, characterized in that: The system includes a text box, an input area, a chat content area, and a dialogue area: The text box is used to obtain text input content from the user; based on the text input content, determine the food information corresponding to the text input content; The input area includes at least one of a photo input area, a voice input area, and a food search area, wherein the photo input area is used to obtain a user's food image to be identified; based on the food image to be identified, food information corresponding to the food image to be identified is determined; The voice input area is used to obtain the user's voice to be recognized; based on the voice to be recognized, determine the food information corresponding to the voice to be recognized; The food search area is used to obtain the user's food search content; Based on the food search content, determining food information corresponding to the food search content; The chat content area is used to generate chat content replies corresponding to the food information based on the food information using different virtual characters, wherein the chat content replies include food analysis information corresponding to the food information and / or small talk information corresponding to the text input content; The conversation area is used to display the food information and the chat content.

2. The system according to claim 1, characterized in that The chat content area is used to generate food cards corresponding to the text input content, the food image to be recognized, the voice to be recognized and the food search content based on the text input content, the food image to be recognized, the voice to be recognized and the food search content, wherein the food card is used to represent the food detailed information corresponding to the text input content, the food image to be recognized, the voice to be recognized and the food search content.

3. The system according to claim 1, characterized in that The chat content area is also used to: determine whether the text input content contains valid food information based on the text input content; When the text input content contains valid food information, a pre-trained model is used to simulate different virtual characters to generate food review information and food prompt information corresponding to the text input content; When the text input content does not contain valid food information, the text input content is determined to be a chat task, and the pre-trained model is used to simulate different virtual characters to generate chat information corresponding to the text input content.

4. A diet recording method based on a chat simulation group, characterized in that: Applied to the diet record based on chat simulation group as claimed in any one of claims 1 to 3, the system comprises a text box, an input area, a chat content area and a dialogue area, and the method comprises: Utilizing the text box and the input area, obtaining the user's text input content, the food image to be recognized, the voice to be recognized, and the food search content; Based on the text input content, the food image to be recognized, the voice to be recognized and the food search content, determine the food information corresponding to the text input content, the food image to be recognized, the voice to be recognized and the food search content; Using different virtual characters, based on the food information, generating chat content replies corresponding to the food information, wherein the chat content replies include food analysis information corresponding to the food information, and / or small talk information corresponding to the text input content; The conversation area is used to display the food information and the chat content.

5. The method according to claim 4, characterized in that The generating a chat content reply corresponding to the food information based on the food information includes: Based on the text input content, the food image to be recognized, the voice to be recognized and the food search content, food cards corresponding to the text input content, the food image to be recognized, the voice to be recognized and the food search content are generated, wherein the food cards are used to represent the food detailed information corresponding to the text input content, the food image to be recognized, the voice to be recognized and the food search content.

6. The method according to claim 4, characterized in that The method of using different virtual characters to generate chat content replies corresponding to the food information based on the food information further includes: Based on the text input content, determining whether the text input content contains valid food information; When the text input content contains valid food information, a pre-trained model is used to simulate different virtual characters to generate food review information and food prompt information corresponding to the text input content; When the text input content does not contain valid food information, the text input content is determined to be a chat task, and the pre-trained model is used to simulate different virtual characters to generate chat information corresponding to the text input content.

7. A diet recording device based on a chat simulation group, characterized in that: The device comprises: An input acquisition module is used to obtain the user's text input content, food images to be recognized, voice to be recognized, and food search content using the text box and input area; A food recognition module, configured to determine food information corresponding to the text input content, the food image to be recognized, the voice to be recognized and the food search content based on the text input content, the food image to be recognized, the voice to be recognized and the food search content; A chat reply module, used to generate chat content replies corresponding to the food information based on the food information by using different virtual characters, wherein the chat content replies include a welcome message, food analysis information corresponding to the food information, and chat information corresponding to the text input content; The content display module is used to display the food information and the chat content in the conversation area.

8. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the diet recording method based on a chat simulation group as described in any one of claims 4 to 6 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the diet recording method based on a chat simulation group according to any one of claims 4 to 6.

10. A computer program product, characterized in that It comprises computer instructions, and the computer instructions are used to make a computer execute the diet recording method based on a chat simulation group as described in any one of claims 4 to 6.

Images