Anti-interference translation mobile phone shell and method for translating by applying mobile phone shell

Abstract

The invention relates to the technical field of mobile phone accessories, in particular to an anti-interference translation mobile phone shell and a translation method using the mobile phone shell, and the anti-interference translation mobile phone shell and the translation method using the mobile phone shell are technically characterized in that a mobile phone is placed in a containing bin and is physically wrapped and protected through the limitation of the containing bin and a protection frame; as the simultaneous translation module is arranged in the cavity of the terminal shell and comprises the wireless communication unit and the central control unit, when the central control unit activates the simultaneous translation module, the wireless communication unit automatically establishes a wireless connection channel with a mobile phone, and real-time voice signal processing is realized through the simultaneous translation module; the simultaneous translation module performs multi-language recognition, semantic analysis and cross-language conversion processing on the acquired voice data, and displays a text subjected to cross-language conversion processing through the mobile phone, so that the purpose of realizing linkage translation between the mobile phone shell and the mobile phone is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of mobile phone accessories, and more specifically, to an anti-interference translation mobile phone case and a translation method using the mobile phone case. Background Art

[0002] Mobile phone cases are one of the important accessories for protecting mobile phones. Due to the diversity of existing mobile phone case styles, they can not only wrap and protect the mobile phone, but also have a recognizable and beautiful appearance, and are therefore very popular in the market.

[0003] Mobile phone cases are often used as one of the mobile phone accessories. It is too monotonous to only serve as a protective cover for the mobile phone. Therefore, there are many optimization and improvements for the functions of mobile phone cases on the market.

[0004] For example, in case 1, patent number 201811243051.1, the Chinese invention patent for an anti-interference translation mobile phone case discloses a terminal shell, which includes a front cover and a rear seat pivotally connected to the front cover. A speaker is provided inside the upper side of the rear seat, and a mobile power supply is provided inside the lower side. A charging connector for inserting a mobile phone is provided at the center of the lower end of the rear seat, and the charging connector is connected to the mobile power supply. An earphone jack for inserting a mobile phone is provided on the top of the rear seat, and the earphone jack is connected to the speaker via a wire. The above-mentioned anti-interference translation mobile phone case can not only charge the mobile phone, but also act as a speaker, providing better sound quality for the mobile phone's external speakers, while also protecting the mobile phone.

[0005] For example, in Case 2, Patent No. 202410168862.9, the Chinese invention patent for a photovoltaic charging mobile phone case discloses that the photovoltaic charging mobile phone case includes a shell, a photovoltaic component, an energy storage module, a switch module, and a control module; the shell is formed with a receiving groove and a receiving cavity, and the receiving groove is used to receive a mobile phone; the photovoltaic component can be received in the receiving cavity, and the photovoltaic component includes a plurality of foldable flexible photovoltaic panels; the energy storage module is arranged in the receiving cavity, and the energy storage module is provided with a charging interface, and the energy storage module is used to store the electrical energy generated by the photovoltaic component; the switch module is arranged in the receiving cavity, and the photovoltaic component, the switch module, and the energy storage module are electrically connected in sequence; the control module is arranged in the receiving cavity, and the control module is electrically connected to the switch module. In the technical solution of the present invention, it is convenient to charge a mobile phone outdoors.

[0006] It can be seen that based on the settings of the mobile phone case, other functions are given to the mobile phone case. This indicates that the mobile phone case industry is breaking through the traditional accessories positioning and continuously creating new consumer value through cross-technological integration. Among them, with the increasing frequency of cross-international cultural exchanges, language barriers in international exchanges have become the most direct obstacle and conflict in communication and trade. For this reason, recognition translators for multiple languages have been born, but the design of translation sections derived from traditional mobile phone cases is still blank. Summary of the Invention

[0007] In view of the above-mentioned deficiencies in the prior art, the first object of the present invention is to provide an anti-interference translation mobile phone case to achieve the purpose of realizing linked translation between the mobile phone case and the mobile phone.

[0008] The first object of the present invention is achieved through the following technical solutions: an anti-interference translation mobile phone case, comprising a terminal shell, a storage compartment provided in the terminal shell, and a protective frame provided around the circumference of the terminal shell; a simultaneous translation module, an induction coil assembly, and a battery are provided inside the terminal shell; the induction coil assembly and the battery are respectively electrically connected to the embedded simultaneous translation module and operate in coordination; the simultaneous translation module further comprises a wireless communication unit and a central control unit;

[0009] When the central control unit activates the simultaneous interpretation module, the wireless communication unit automatically establishes a wireless connection channel with the mobile phone and processes the real-time voice signal through the simultaneous interpretation module;

[0010] The simultaneous interpretation module is equipped with a deep neural network algorithm and collects voice data based on a mobile phone. It can perform multilingual recognition, semantic analysis and cross-language conversion processing on the collected voice data.

[0011] Preferably, the deep neural network algorithm constructs a deep neural network algorithm model by using voiceprint recognition, sound volume and language translation attributes as weights, recognizes the speech texts of multiple speakers through the deep neural network algorithm model, divides the priority levels based on the language texts of multiple speakers according to the deep neural network algorithm model, and manually selects the language text displayed on the mobile phone for real-time translation.

[0012] Preferably, the deep neural network algorithm model includes:

[0013] W=a×W1+b×W2+c×W3;

[0014] W: Final comprehensive weight score; W1: Voiceprint recognition confidence (0-1), W2: Sound source localization stability score (0-1) W3: Language recognition consistency score (0-1), and a, b, c are weight coefficients (a+b+c=1). Based on the final comprehensive weight score, the speech texts of multiple speakers are prioritized and divided.

[0015] Preferably, a comprehensive weight score interference threshold is set, and when the final comprehensive weight score is lower than the comprehensive weight score interference threshold, the language text is judged to be an interference speech.

[0016] Preferably, conference mode and outdoor mode are set according to the usage scenario. The proportion of weight coefficients is dynamically adjusted according to the different modes set. In conference mode, the voiceprint features are significant, and the voiceprint is given a higher weight; in outdoor mode, the sound source positioning excludes background noise, and the weight b of the sound source positioning stability score is increased.

[0017] Preferably, based on the construction of the deep neural network algorithm model, the feature sample set of the identification vector feature obtained by the mobile phone includes:

[0018] Collect multiple audio data;

[0019] Analyze each audio data in sequence, divide each audio data into frames, and obtain multiple audio frames;

[0020] Extracting acoustic features from each of the multiple audio frames to obtain a feature sequence, wherein the feature sequence is used to characterize acoustic features of the multiple audio frames of the audio data;

[0021] Perform identification feature extraction on the feature sequence to obtain identification vector features of the audio data.

[0022] In view of the above-mentioned deficiencies in the prior art, a second object of the present invention is to provide a translation method for realizing network-free portable translation via a mobile phone.

[0023] The following steps are included:

[0024] S1: Automatically establish a wireless connection channel with the mobile phone through the wireless communication unit, completing the wireless connection between the simultaneous interpretation module in the mobile phone case and the mobile phone;

[0025] S2: Based on the voice information data obtained by the mobile phone, the simultaneous interpretation module distinguishes the language recognition type in the voice information data;

[0026] S3: Based on the language recognition type, the voice owner is divided into multiple categories according to the voiceprint and voice distance;

[0027] S4: Based on the sound distance of the sound recorded by the mobile phone, the simultaneous interpretation module is used to distinguish the voiceprint. Relying on the basic acquisition of the language recognition type, the mobile phone compares the language and text and manually selects the text content that needs to be translated in real time.

[0028] In summary, this application has the following beneficial effects:

[0029] The mobile phone is placed in the accommodating compartment, and the mobile phone is physically wrapped and protected by the restrictions of the accommodating compartment and the protective frame. Since the terminal shell is provided with a simultaneous interpretation module, an induction coil assembly and a battery in the cavity, the battery is charged and stored by wireless charging based on the setting of the induction coil assembly. The simultaneous interpretation module includes a wireless communication unit and a central control unit. When the central control unit activates the simultaneous interpretation module, the wireless communication unit automatically establishes a wireless connection channel with the mobile phone, and realizes real-time voice signal processing through the simultaneous interpretation module; the simultaneous interpretation module is equipped with a deep neural network algorithm, and performs voice data acquisition and collection based on the mobile phone. It can perform multilingual recognition, semantic analysis and cross-language conversion processing on the collected voice data, and display the text processed by cross-language conversion through the mobile phone, so as to achieve the purpose of realizing linked translation between the mobile phone case and the mobile phone. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 Schematic diagram of the structure of the terminal housing of the first embodiment of the present application;

[0031] Figure 2 This is a schematic diagram of the circuit connections in the cavity of Example 1 of the present application;

[0032] Figure 3 This is a schematic diagram of the steps of Example 2 of the present application.

[0033] Reference numerals: 1. terminal housing; 11. storage compartment; 12. protective frame; 13. induction coil assembly; 14. battery; 2. simultaneous interpretation module. DETAILED DESCRIPTION

[0034] In order to make the technical problems, technical solutions and beneficial effects to be solved by this application more clearly understood, this application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0035] It should be noted that when a component is referred to as being “fixed to” or “disposed on” another component, it can be directly on the other component or indirectly on the other component. When a component is referred to as being “connected to” another component, it can be directly or indirectly connected to the other component.

[0036] It should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on this application.

[0037] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. Throughout the description of this application, "plurality" means two or more, unless otherwise specifically defined.

[0038] Example 1: An anti-interference translation mobile phone case, see Figure 1-Figure 2 , comprising a terminal housing 1, a accommodating compartment 11 provided in the terminal housing 1, and a accommodating compartment 12 arranged circumferentially around the terminal housing 1, wherein a simultaneous interpretation module 2, an accommodating compartment 13, and an accommodating compartment 14 are provided inside the terminal housing 1, wherein the accommodating compartment 13 and the accommodating compartment 14 are respectively electrically connected to the embedded simultaneous interpretation module 2 and realize coordinated operation, and the simultaneous interpretation module 2 further comprises a wireless communication unit and a central control unit;

[0039] When the central control unit activates the simultaneous interpretation module 2, the wireless communication unit automatically establishes a wireless connection channel with the mobile phone, and processes the real-time voice signal through the simultaneous interpretation module 2;

[0040] The simultaneous interpretation module 2 is equipped with a deep neural network algorithm and collects voice data based on a mobile phone. It can perform multilingual recognition, semantic analysis and cross-language conversion processing on the collected voice data.

[0041] In this embodiment, a mobile phone is placed in a storage compartment 11, and the mobile phone is physically wrapped and protected by the restrictions of the storage compartment 11 and the storage compartment 12. Since the terminal housing 1 is provided with a simultaneous translation module 2, a storage compartment 13 and a storage compartment 14 in the cavity, the storage compartment 14 is charged and stored by wireless charging based on the setting of the storage compartment 13. The simultaneous translation module 2 includes a wireless communication unit and a central control unit. When the central control unit activates the simultaneous translation module 2, the wireless communication unit automatically establishes a wireless connection channel with the mobile phone, and the simultaneous translation module 2 realizes real-time voice signal processing; the simultaneous translation module 2 is equipped with a deep neural network algorithm, and performs multilingual recognition, semantic analysis and cross-language conversion processing on the collected voice data based on the mobile phone, and the text of the cross-language conversion processing is displayed by the mobile phone, thereby achieving the purpose of realizing the linkage translation between the mobile phone case and the mobile phone. The mobile phone case and mobile phone of this embodiment can be selected according to actual conditions. For example, if a tablet is selected, the terminal housing 1 is a tablet protective cover.

[0042] Specifically, the deep neural network algorithm constructs a deep neural network algorithm model by using voiceprint recognition, sound volume and language translation attributes as weights, recognizes the speech texts of multiple speakers through the deep neural network algorithm model, prioritizes the language texts of multiple speakers according to the deep neural network algorithm model, and manually selects the language text displayed on the mobile phone for real-time translation.

[0043] By building a deep neural network algorithm model, the order of language texts of multiple speakers is identified, and the deep neural network algorithm model is rebuilt based on voiceprint recognition, sound volume, and language translation attributes as weights. Finally, humans manually select the language text displayed on the mobile phone for real-time translation. Users can independently choose the translation language text, which is real-time and efficient.

[0044] In addition, based on the hardware structure support of the mobile phone case: the terminal shell 1 + the storage compartment 12 design, the built-in translation module, the induction coil and the storage compartment 14;

[0045] Then through the algorithm architecture: a dynamic weight model based on deep neural network, which involves voiceprint, sound source positioning, language consistency, etc.

[0046] Utilize mode switching: that is, dynamically adjust the weights of conference mode and outdoor mode to achieve translation of language texts in multiple modes.

[0047] In essence, it establishes a multi-scenario, multi-person anti-interference translation mechanism, which filters out noise through a comprehensive weight score threshold. In this way, when recognizing the speech of multiple people, the speech content of each speaker can be filtered out through the set comprehensive weight score threshold. A part of the text content of the background speaker can be filtered out, and then manual translation can be performed based on the filtered text.

[0048] In addition, there are conference mode and outdoor mode according to the usage scenario. The proportion of weight coefficients is dynamically adjusted according to the different modes set. In conference mode, the voiceprint features are significant, and the voiceprint is given a higher weight; in outdoor mode, the sound source positioning excludes background noise and increases the weight b of the sound source positioning stability score.

[0049] The deep neural network algorithm model of this embodiment includes:

[0050] W=a×W1+b×W2+c×W3;

[0051] W: Final comprehensive weight score; W1: Voiceprint recognition confidence (0-1), W2: Sound source localization stability score (0-1) W3: Language recognition consistency score (0-1), and a, b, c are weight coefficients (a+b+c=1). Based on the final comprehensive weight score, the speech texts of multiple speakers are prioritized and divided.

[0052] By comprehensively weighting the scores, the speech texts of multiple speakers are prioritized in order to reduce the speech texts to be recognized and translated, thus reducing interference.

[0053] Example Scenario 1: Conference Mode

[0054] Input data:

[0055] W1=0.92, voiceprint recognition confidence; W2=0.85, sound source localization stability score; W3=0.95, language recognition consistency score;

[0056] Set the conference mode to α = 0.6, b = 0.25, c = 0.15;

[0057] W=0.6×0.92+0.25×0.85+0.15×0.95=0.914.

[0058] Scenario 2: Outdoor Mode

[0059] Input data:

[0060] W1=0.65, voiceprint recognition confidence; W2=0.90, sound source localization stability score; W3=0.80, language recognition consistency score;

[0061] Set outdoor mode, α = 0.4, b = 0.5, c = 0.1;

[0062] W=0.4×0.65+0.5×0.90+0.1×0.80=0.79.

[0063] The voiceprint recognition confidence is used to identify the owner of the language text. The voiceprint recognition confidence method is based on the construction of the deep neural network algorithm model. The feature sample set of the recognition vector feature obtained by the mobile phone includes:

[0064] Collect multiple audio data;

[0065] Analyze each audio data in sequence, divide each audio data into frames, and obtain multiple audio frames;

[0066] Extracting acoustic features from each of the multiple audio frames to obtain a feature sequence, wherein the feature sequence is used to characterize acoustic features of the multiple audio frames of the audio data;

[0067] Perform identification feature extraction on the feature sequence to obtain identification vector features of the audio data.

[0068] In this embodiment, the simultaneous interpretation module 2, the storage compartment 13 and the storage compartment 14 are embedded in the mobile phone case. This is based on the convenience of carrying mobile phones and the current universality of carrying mobile phones. The mobile phone case with a translation function can achieve a fast response through a wireless connection of Bluetooth or a local area network, without having to consider the problem of poor mobile phone network or mobile phone signal. Face-to-face instant translation is achieved directly through the multilingual recognition, semantic analysis and cross-language conversion processing of the simultaneous interpretation module 2 in the mobile phone case.

[0069] Example 2: A translation method based on the above-mentioned setting of the anti-interference translation mobile phone case for translation, see Figure 3 , including the following steps,

[0070] S1: Automatically establish a wireless connection channel with the mobile phone through the wireless communication unit, completing the wireless connection between the simultaneous interpretation module 2 in the mobile phone case and the mobile phone;

[0071] S2: Based on the voice information data obtained by the mobile phone, the simultaneous interpretation module 2 distinguishes the language recognition type in the voice information data;

[0072] S3: Based on the language recognition type, the voice owner is divided into multiple categories according to the voiceprint and voice distance;

[0073] S4: Based on the sound distance of the sound recorded by the mobile phone, the simultaneous interpretation module 2 is used to distinguish the voiceprint. Relying on the basic acquisition of the language recognition type, the mobile phone compares the language and text and manually selects the text content that needs to be translated in real time.

[0074] Based on the above steps, a wireless connection is established between the mobile phone and the mobile phone case, thereby achieving the purpose of realizing network-free portable translation through the mobile phone.

[0075] The rest of this embodiment is the same as that of the first embodiment. The features not explained in this embodiment are all based on the explanations of the first embodiment and will not be described in detail here.

[0076] The above embodiments are merely explanations of the present application and are not limitations of the present application. After reading this specification, those skilled in the art may make modifications to the embodiments without any creative contribution as needed. However, as long as they are within the scope of the claims of the present application, they are protected by the patent law.

Claims

1. An anti-interference translation mobile phone case, characterized by: The device comprises a terminal housing, a storage compartment disposed within the terminal housing, and a protective frame disposed circumferentially around the terminal housing. A simultaneous interpretation module, an induction coil assembly, and a battery are disposed within the terminal housing. The induction coil assembly and the battery are electrically connected to the embedded simultaneous interpretation module and operate in coordination therewith. The simultaneous interpretation module further comprises a wireless communication unit and a central control unit. When the central control unit activates the simultaneous interpretation module, the wireless communication unit automatically establishes a wireless connection channel with the mobile phone and processes the real-time voice signal through the simultaneous interpretation module; The simultaneous interpretation module is equipped with a deep neural network algorithm and collects voice data based on a mobile phone. It can perform multilingual recognition, semantic analysis and cross-language conversion processing on the collected voice data.

2. The anti-interference translation mobile phone case according to claim 1, characterized in that: The deep neural network algorithm uses voiceprint recognition, sound volume and language translation attributes as weights to construct a deep neural network algorithm model, recognizes the speech texts of multiple speakers through the deep neural network algorithm model, prioritizes the language texts of multiple speakers based on the deep neural network algorithm model, and manually selects the language text displayed on the mobile phone for real-time translation.

3. The anti-interference translation mobile phone case according to claim 2, characterized in that: The deep neural network algorithm model includes: W=a×W1+b×W2+c×W3; W: Final comprehensive weight score; W1: Voiceprint recognition confidence (0-1), W2: Sound source localization stability score (0-1) W3: Language recognition consistency score (0-1), and a, b, c are weight coefficients (a+b+c=1). Based on the final comprehensive weight score, the speech texts of multiple speakers are prioritized and divided.

4. The anti-interference translation mobile phone case according to claim 3, characterized in that: A comprehensive weight score interference threshold is set. When the final comprehensive weight score is lower than the comprehensive weight score interference threshold, the language text is judged to be interference speech.

5. The anti-interference translation mobile phone case according to claim 3 is characterized by: There are conference mode and outdoor mode according to the usage scenario. The weight coefficient ratio is dynamically adjusted according to the different modes set. In conference mode, the voiceprint characteristics are significant, and the voiceprint is given a higher weight; in outdoor mode, the sound source positioning excludes background noise, which increases the weight b of the sound source positioning stability score.

6. The anti-interference translation mobile phone case according to claim 4, characterized in that: Based on the construction of the deep neural network algorithm model, the feature sample set of the identification vector feature obtained by the mobile phone includes: Collect multiple audio data; Analyze each audio data in sequence, divide each audio data into frames, and obtain multiple audio frames; Extracting acoustic features from each of the multiple audio frames to obtain a feature sequence, wherein the feature sequence is used to characterize acoustic features of the multiple audio frames of the audio data; Perform identification feature extraction on the feature sequence to obtain identification vector features of the audio data.

7. A translation method, characterized by: Including the following step, S1: Automatically establish a wireless connection channel with the mobile phone through the wireless communication unit, completing the wireless connection between the simultaneous interpretation module in the mobile phone case and the mobile phone; S2: Based on the voice information data obtained by the mobile phone, the simultaneous interpretation module distinguishes the language recognition type in the voice information data; S3: Based on the language recognition type, the voice owner is divided into multiple categories according to the voiceprint and voice distance; S4: Based on the sound distance of the sound recorded by the mobile phone, the simultaneous interpretation module is used to distinguish the voiceprint. Relying on the basic acquisition of the language recognition type, the mobile phone compares the language and text and manually selects the text content that needs to be translated in real time.

Images